技术领域technical field
本发明涉及起重装备结构健康监测领域、设备故障预测领域、设备运行效率评估领域、设备维修决策领域，特别涉及一种基于起重装备工作状态的预测性维修决策方法及系统。The invention relates to the field of structural health monitoring of lifting equipment, the field of equipment failure prediction, the field of equipment operation efficiency evaluation, and the field of equipment maintenance decision-making, and particularly relates to a predictive maintenance decision-making method and system based on the working state of lifting equipment.
背景技术Background technique
起重装备的故障检测与诊断经历了从停机维护、定期维护到预测性维护的发展过程。早期的停机维护或者无计划维护并不能真正规避安全事故和经济损失。定期维护或者计划维护又会过度维护造成不必要的资源浪费。预测性维护，又称为基于状态的维护或视情维护，能够在生产运作的同时对设备进行实时或定期的状态监测，提前预知安全隐患并做出防范，是当前最重要的发展方向。The fault detection and diagnosis of lifting equipment has experienced the development process from downtime maintenance, regular maintenance to predictive maintenance. Early downtime maintenance or unplanned maintenance cannot really avoid safety accidents and economic losses. Regular maintenance or planned maintenance will cause unnecessary waste of resources due to excessive maintenance. Predictive maintenance, also known as condition-based maintenance or condition-based maintenance, is the most important development direction at present.
目前，故障预测分析方法可分为三类：基于分析模型、基于定性经验和基于数据驱动。基于模型的方法较为依赖过程机理研究，工程实际中也不容易得到精确解析解。基于经验的方法可以提供直观的分析，避免复杂的数学建模，但对专家知识的要求较高且不便于定量计算。基于数据的方法对系统机理和先验知识的要求低，但是对数据积累要求高且缺少直观的物理意义。Currently, fault prediction analysis methods can be divided into three categories: analytical model-based, qualitative experience-based, and data-driven. Model-based methods rely more on process mechanism research, and it is not easy to obtain accurate analytical solutions in engineering practice. Experience-based methods can provide intuitive analysis and avoid complex mathematical modeling, but require high expert knowledge and are not convenient for quantitative calculations. Data-based methods have low requirements for system mechanism and prior knowledge, but high requirements for data accumulation and lack of intuitive physical meaning.
维修决策模型以剩余寿命、故障概率等参数描述设备的系统特性或劣化过程，并根据生产需求建立决策优化目标，提高生产设备可靠性并减少资源损耗。常见的定期维护策略包括年龄更换策略和成批更换策略，设定一定的年限到期更换。故障限制策略则以系统可靠性、失效率等指标作为维修决策标准。维修费用限制策略和维修时间限制策略均以维修维护的成本作为决策依据。现有维修决策研究大多只考虑其中一种标准和策略，而不能进行综合性决策考量。The maintenance decision-making model describes the system characteristics or deterioration process of equipment with parameters such as remaining life and failure probability, and establishes decision-making optimization goals according to production requirements to improve the reliability of production equipment and reduce resource consumption. Common regular maintenance strategies include age replacement strategy and batch replacement strategy, setting a certain number of years for replacement. The failure limitation strategy takes system reliability, failure rate and other indicators as maintenance decision criteria. Both the maintenance cost limitation strategy and the maintenance time limitation strategy take the maintenance cost as the decision basis. Most of the existing research on maintenance decision-making only considers one of the standards and strategies, but cannot carry out comprehensive decision-making considerations.
因此需要发明一种基于起重装备工作状态的预测性维修决策方法，能够基于设备工作状态提供必要的故障预测预警，进而综合考虑系统可靠性、维修成本、潜在运行效率等指标，给出设备当前运行状态下是否需要立即维修的决策建议，减少设备安全隐患，提升企业生产效益。Therefore, it is necessary to invent a predictive maintenance decision-making method based on the working state of the lifting equipment, which can provide the necessary fault prediction and early warning based on the working state of the equipment, and then comprehensively consider the system reliability, maintenance cost, potential operating efficiency and other indicators, and give the current state of the equipment. Decision-making suggestions on whether immediate maintenance is required in the running state can reduce equipment safety hazards and improve enterprise production efficiency.
发明内容Contents of the invention
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。The present invention aims to solve one of the technical problems in the related art at least to a certain extent.
为此，本发明的一个目的在于提出一种基于起重装备工作状态的预测性维修决策方法，该方法可以提供预测性维修维护，并且提高维修决策水平和设备运行效率。Therefore, an object of the present invention is to propose a predictive maintenance decision-making method based on the working state of lifting equipment, which can provide predictive maintenance and improve maintenance decision-making level and equipment operation efficiency.
本发明的另一个目的在于提出一种基于起重装备工作状态的预测性维修决策系统。Another object of the present invention is to propose a predictive maintenance decision system based on the working state of the lifting equipment.
为达到上述目的，本发明一方面实施例提出了一种基于起重装备工作状态的预测性维修决策方法，包括以下步骤：获取起重装备的历史运行数据；根据所述故障树专家知识和所述历史运行数据建立贝叶斯网络预测模型，以预测起重装备的潜在故障和安全隐患；获取起重装备的当前运行状态，以根据所述当前运行状态和贝叶斯网络预测模型，实现起重机整体可靠性预测和潜在故障原因的快速定位；以起重机整体故障概率和潜在故障原因概率作为权重，建立潜在运行效率的预测维修决策模型，得到起重装备潜在运行效率、潜在维修成本和潜在生产损失；根据所述预测结果得到所述测维修决策模型的决策建议。In order to achieve the above object, an embodiment of the present invention proposes a predictive maintenance decision method based on the working state of the lifting equipment, which includes the following steps: acquiring historical operating data of the lifting equipment; Establish a Bayesian network prediction model based on the historical operating data to predict potential failures and potential safety hazards of the lifting equipment; obtain the current operating state of the lifting equipment, and realize the crane based on the current operating state and the Bayesian network prediction model. Overall reliability prediction and rapid location of potential failure causes; with the crane's overall failure probability and potential failure cause probability as weights, a predictive maintenance decision model for potential operating efficiency is established to obtain the potential operating efficiency, potential maintenance costs, and potential production losses of lifting equipment ; According to the prediction result, the decision-making suggestion of the maintenance decision-making model is obtained.
本发明实施例的基于起重装备工作状态的预测性维修决策方法，可以结合故障树专家知识和设备历史运行记录进行贝叶斯网络预测模型建模，并且基于系统状态快速定位潜在的故障原因并预测系统可靠性，根据贝叶斯后验概率和当前系统状态，给出系统潜在运行效率的预测模型，综合系统可靠性、运行效率、维护成本等标准实现起重装备的预测性健康管理和维修决策，能够根据起重装备实时工作状态预测潜在故障和安全隐患，并提供维修决策建议，有效加强起重装备生产过程的监控管理，提供预测性维修维护，提高维修决策水平和设备运行效率，减少安全隐患和国民经济损失。The predictive maintenance decision-making method based on the working state of the lifting equipment in the embodiment of the present invention can combine the expert knowledge of the fault tree and the historical operation records of the equipment to carry out the Bayesian network prediction model modeling, and quickly locate the potential cause of the fault based on the system state and Predict system reliability. According to the Bayesian posterior probability and current system status, a prediction model for potential operating efficiency of the system is given, and comprehensive system reliability, operating efficiency, maintenance costs and other criteria are used to realize predictive health management and maintenance of lifting equipment. Decision-making can predict potential failures and potential safety hazards according to the real-time working status of lifting equipment, and provide maintenance decision-making suggestions, effectively strengthen the monitoring and management of the production process of lifting equipment, provide predictive maintenance, improve maintenance decision-making level and equipment operation efficiency, reduce Potential safety hazards and national economic losses.
另外，根据本发明上述实施例的基于起重装备工作状态的预测性维修决策方法还可以具有以下附加的技术特征：In addition, the predictive maintenance decision-making method based on the working state of the lifting equipment according to the above-mentioned embodiments of the present invention may also have the following additional technical features:
进一步地，在本发明的一个实施例中，所述建立贝叶斯网络预测模型具体包括：基于故障树的贝叶斯网络结构设计充分运用专家知识，且基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，并且基于故障逻辑为贝叶斯网络参数提供合理初值；基于最大期望算法的贝叶斯网络参数修正方法，以充分利用系统运行记录，从可能含有缺失样本的历史数据中挖掘起重装备的运行特性，并根据系统随时间产生的变化修正模型，改善所述贝叶斯网络预测模型的参数。Further, in one embodiment of the present invention, the establishment of the Bayesian network prediction model specifically includes: the Bayesian network structure design based on the fault tree fully uses expert knowledge, and the fault tree structure based on the lifting equipment is Bayesian Provide a reference for the structure design of the Yasian network, and provide a reasonable initial value for the Bayesian network parameters based on fault logic; the Bayesian network parameter correction method based on the maximum expectation algorithm to make full use of the system operation records, from the history that may contain missing samples The operating characteristics of the lifting equipment are mined from the data, and the model is corrected according to the changes of the system over time, so as to improve the parameters of the Bayesian network prediction model.
进一步地，在本发明的一个实施例中，所述建立潜在运行效率的预测维修决策模型具体包括：基于贝叶斯后验概率的系统可靠性预测，从而根据所述起重装备实时监测到的局部异常预测系统整体失效率；基于起重装备潜在运行效率预测模型，从而基于所述贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对所述起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；基于系统可靠性和潜在运行效率的预测性维修决策，从而综合考虑系统可靠性、维修成本、潜在运行效率和潜在生产损失，进而得到起重装备发现局部异常时是否立即停机维修的决策建议。Further, in an embodiment of the present invention, the establishment of the predictive maintenance decision model of potential operating efficiency specifically includes: system reliability prediction based on Bayesian posterior probability, so that according to the real-time monitoring of the lifting equipment Local anomalies predict the overall failure rate of the system; based on the prediction model of the potential operating efficiency of the lifting equipment, the reliability of the system and the cause of potential failures are predicted and estimated based on the Bayesian network prediction model, and the impact of local anomalies on the lifting equipment is comprehensively considered. The potential downtime loss and performance loss caused by the system, and predict the potential operating efficiency of the equipment; predictive maintenance decisions based on system reliability and potential operating efficiency, so as to comprehensively consider system reliability, maintenance costs, potential operating efficiency and potential production loss, and then Get decision-making suggestions on whether to shut down the lifting equipment immediately for maintenance when local abnormalities are found.
进一步地，在本发明的一个实施例中，计算内容包括时间稼动率、性能稼动率和潜在运行效率，其中，时间稼动率用于反映设备维修维护引起的非计划停机对运行效率的影响，性能稼动率用于反映设备的性能发挥情况，潜在运行效率用于综合考量节点异常对系统造成的潜在停机损失和性能损失，预测起重装备的潜在运行效率。Further, in one embodiment of the present invention, the calculation content includes time utilization rate, performance utilization rate and potential operating efficiency, wherein the time utilization rate is used to reflect the impact of unplanned downtime caused by equipment maintenance on operating efficiency Impact, the performance utilization rate is used to reflect the performance of the equipment, and the potential operating efficiency is used to comprehensively consider the potential downtime loss and performance loss caused by node abnormalities to the system, and predict the potential operating efficiency of the lifting equipment.
进一步地，在本发明的一个实施例中，其中，Further, in one embodiment of the present invention, wherein,
其中，TAll为完整负荷时间为，TStop为潜在停机时间的期望；Among them, TAll is the full load time, and TStop is the expectation of potential downtime;
其中，Vcost为局部异常对系统整体运作速度的影响；Among them, Vcost is the impact of local abnormalities on the overall operating speed of the system;
PCE＝时间稼动率×性能稼动率PCE = time utilization rate × performance utilization rate
其中，PCE为潜在运行效率。Among them, PCE is the potential operating efficiency.
为达到上述目的，本发明另一方面实施例提出了一种基于起重装备工作状态的预测性维修决策系统，包括：获取模块，用于获取起重装备的历史运行数据；第一模型建立模块，用于根据所述故障树专家知识和所述历史运行数据建立贝叶斯网络预测模型，以预测起重装备的潜在故障和安全隐患；预测模块，用于获取起重装备的当前运行状态，以根据所述当前运行状态和贝叶斯网络预测模型，实现起重机整体可靠性预测和潜在故障原因的快速定位；第二模型建立模块，以起重机整体故障概率和潜在故障原因概率作为权重，建立潜在运行效率的预测维修决策模型，得到起重装备潜在运行效率、潜在维修成本和潜在生产损失；决策模块，用于根据所述预测结果得到所述测维修决策模型的决策建议。In order to achieve the above purpose, another embodiment of the present invention proposes a predictive maintenance decision system based on the working state of the lifting equipment, including: an acquisition module for acquiring historical operating data of the lifting equipment; a first model building module , for establishing a Bayesian network prediction model according to the expert knowledge of the fault tree and the historical operation data, to predict potential failures and potential safety hazards of the lifting equipment; a prediction module, for obtaining the current operating state of the lifting equipment, According to the current operating state and the Bayesian network prediction model, the overall reliability prediction of the crane and the rapid location of potential failure causes are realized; the second model building module uses the overall failure probability of the crane and the potential failure cause probability as weights to establish potential failures. The predictive maintenance decision model of operating efficiency obtains the potential operating efficiency, potential maintenance cost and potential production loss of the lifting equipment; the decision module is used to obtain the decision suggestion of the predictive maintenance decision model according to the prediction result.
本发明实施例的基于起重装备工作状态的预测性维修决策系统，可以结合故障树专家知识和设备历史运行记录进行贝叶斯网络预测模型建模，并且基于系统状态快速定位潜在的故障原因并预测系统可靠性，根据贝叶斯后验概率和当前系统状态，给出系统潜在运行效率的预测模型，综合系统可靠性、运行效率、维护成本等标准实现起重装备的预测性健康管理和维修决策，能够根据起重装备实时工作状态预测潜在故障和安全隐患，并提供维修决策建议，有效加强起重装备生产过程的监控管理，提供预测性维修维护，提高维修决策水平和设备运行效率，减少安全隐患和国民经济损失。The predictive maintenance decision system based on the working state of the lifting equipment in the embodiment of the present invention can combine the expert knowledge of the fault tree and the historical operation records of the equipment to carry out Bayesian network prediction model modeling, and quickly locate the potential cause of the fault based on the system state and Predict system reliability. According to the Bayesian posterior probability and current system status, a prediction model for potential operating efficiency of the system is given, and comprehensive system reliability, operating efficiency, maintenance costs and other criteria are used to realize predictive health management and maintenance of lifting equipment. Decision-making can predict potential failures and potential safety hazards according to the real-time working status of lifting equipment, and provide maintenance decision-making suggestions, effectively strengthen the monitoring and management of the production process of lifting equipment, provide predictive maintenance, improve maintenance decision-making level and equipment operation efficiency, reduce Potential safety hazards and national economic losses.
另外，根据本发明上述实施例的基于起重装备工作状态的预测性维修决策系统还可以具有以下附加的技术特征：In addition, the predictive maintenance decision system based on the working state of the lifting equipment according to the above embodiments of the present invention may also have the following additional technical features:
进一步地，在本发明的一个实施例中，所述第一模型建立模块具体用于：基于故障树的贝叶斯网络结构设计充分运用专家知识，且基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，并且基于故障逻辑为贝叶斯网络参数提供合理初值；基于最大期望算法的贝叶斯网络参数修正方法，以充分利用系统运行记录，从可能含有缺失样本的历史数据中挖掘起重装备的运行特性，并根据系统随时间产生的变化修正模型，改善所述贝叶斯网络预测模型的参数。Further, in one embodiment of the present invention, the first model building module is specifically used for: Bayesian network structure design based on fault tree fully utilizes expert knowledge, and the fault tree structure based on lifting equipment is Bayesian It provides a reference for the design of the network structure, and provides a reasonable initial value for the parameters of the Bayesian network based on the fault logic; the correction method of the parameters of the Bayesian network based on the maximum expectation algorithm, in order to make full use of the system operation records, from the historical data that may contain missing samples The operating characteristics of the lifting equipment are excavated, and the model is corrected according to the changes of the system over time, and the parameters of the Bayesian network prediction model are improved.
进一步地，在本发明的一个实施例中，所述第二模型建立模块具体用于：基于贝叶斯后验概率的系统可靠性预测，从而根据所述起重装备实时监测到的局部异常预测系统整体失效率；基于起重装备潜在运行效率预测模型，从而基于所述贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对所述起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；基于系统可靠性和潜在运行效率的预测性维修决策，从而综合考虑系统可靠性、维修成本、潜在运行效率和潜在生产损失，进而得到起重装备发现局部异常时是否立即停机维修的决策建议。Further, in an embodiment of the present invention, the second model building module is specifically used for: predicting system reliability based on Bayesian posterior probability, so as to predict local abnormalities detected in real time by the lifting equipment The overall failure rate of the system; based on the prediction model of the potential operating efficiency of the lifting equipment, the prediction and estimation of the reliability of the system and the cause of potential failures based on the Bayesian network prediction model, comprehensively considering the potential impact of local abnormalities on the lifting equipment Downtime loss and performance loss, and predict the potential operating efficiency of equipment; predictive maintenance decisions based on system reliability and potential operating efficiency, so as to comprehensively consider system reliability, maintenance costs, potential operating efficiency and potential production loss, and then get lifting A decision-making suggestion on whether to shut down the equipment immediately for maintenance when a local abnormality is found.
进一步地，在本发明的一个实施例中，计算内容包括时间稼动率、性能稼动率和潜在运行效率，其中，时间稼动率用于反映设备维修维护引起的非计划停机对运行效率的影响，性能稼动率用于反映设备的性能发挥情况，潜在运行效率用于综合考量节点异常对系统造成的潜在停机损失和性能损失，预测起重装备的潜在运行效率。Further, in one embodiment of the present invention, the calculation content includes time utilization rate, performance utilization rate and potential operating efficiency, wherein the time utilization rate is used to reflect the impact of unplanned downtime caused by equipment maintenance on operating efficiency Impact, the performance utilization rate is used to reflect the performance of the equipment, and the potential operating efficiency is used to comprehensively consider the potential downtime loss and performance loss caused by node abnormalities to the system, and predict the potential operating efficiency of the lifting equipment.
进一步地，在本发明的一个实施例中，其中，Further, in one embodiment of the present invention, wherein,
其中，TAll为完整负荷时间为，TStop为潜在停机时间的期望；Among them, TAll is the full load time, and TStop is the expectation of potential downtime;
其中，Vcost为局部异常对系统整体运作速度的影响；Among them, Vcost is the impact of local abnormalities on the overall operating speed of the system;
PCE＝时间稼动率×性能稼动率PCE = time utilization rate × performance utilization rate
其中，PCE为潜在运行效率。Among them, PCE is the potential operating efficiency.
本发明附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
附图说明Description of drawings
本发明上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：The above and/or additional aspects and advantages of the present invention will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:
图1为根据本发明实施例的基于起重装备工作状态的预测性维修决策方法的流程图；Fig. 1 is a flowchart of a predictive maintenance decision-making method based on the working state of lifting equipment according to an embodiment of the present invention;
图2为根据本发明一个实施例的基于专家知识和系统运行记录的贝叶斯网络构造的流程图；Fig. 2 is the flow chart of the Bayesian network construction based on expert knowledge and system operation records according to one embodiment of the present invention;
图3为根据本发明一个实施例的故障树示意图；3 is a schematic diagram of a fault tree according to an embodiment of the present invention;
图4为根据本发明一个实施例的故障树逻辑门向贝叶斯参数的转换关系示意图；Fig. 4 is a schematic diagram of the conversion relationship from fault tree logic gates to Bayesian parameters according to an embodiment of the present invention;
图5为根据本发明一个实施例的基于最大期望算法的贝叶斯网络参数修正的流程图；Fig. 5 is the flowchart of the Bayesian network parameter correction based on the maximum expectation algorithm according to one embodiment of the present invention;
图6为根据本发明一个具体实施例的构造贝叶斯网络的流程图；Fig. 6 is the flowchart of constructing Bayesian network according to a specific embodiment of the present invention;
图7为根据本发明一个具体实施例的基于起重装备工作状态的预测性维修决策方法的流程图；Fig. 7 is a flowchart of a predictive maintenance decision-making method based on the working state of lifting equipment according to a specific embodiment of the present invention;
图8为根据本发明一个实施例的起重装备潜在运行效率预测模型的原理示意图；以及Fig. 8 is a schematic diagram of the principle of a prediction model for potential operating efficiency of lifting equipment according to an embodiment of the present invention; and
图9为根据本发明一个实施例的基于起重装备工作状态的预测性维修决策系统的结构示意图。Fig. 9 is a schematic structural diagram of a predictive maintenance decision system based on the working state of lifting equipment according to an embodiment of the present invention.
具体实施方式detailed description
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本发明，而不能理解为对本发明的限制。Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.
下面参照附图描述根据本发明实施例提出的基于起重装备工作状态的预测性维修决策方法及系统，首先将参照附图描述根据本发明实施例提出的基于起重装备工作状态的预测性维修决策方法。The following describes the predictive maintenance decision-making method and system based on the working state of the lifting equipment according to the embodiments of the present invention with reference to the accompanying drawings. First, the predictive maintenance based on the working state of the lifting equipment according to the embodiments of the present invention will be described with reference to the accompanying drawings decision making method.
图1是本发明实施例的基于起重装备工作状态的预测性维修决策方法的流程图。Fig. 1 is a flowchart of a predictive maintenance decision-making method based on the working state of lifting equipment according to an embodiment of the present invention.
如图1所示，该基于起重装备工作状态的预测性维修决策方法包括以下步骤：As shown in Figure 1, the predictive maintenance decision method based on the working state of lifting equipment includes the following steps:
在步骤S101中，获取起重装备的历史运行数据。In step S101, historical operation data of lifting equipment is obtained.
在步骤S102中，根据故障树专家知识和历史运行数据建立贝叶斯网络预测模型，以预测起重装备的潜在故障和安全隐患。In step S102, a Bayesian network prediction model is established according to expert knowledge of the fault tree and historical operating data to predict potential faults and potential safety hazards of the lifting equipment.
也就是说，首先基于专家知识和系统运行记录的贝叶斯网络预测模型构造方法，用于结合专家经验和起重装备历史运行数据，针对研究对象快速有效地建立贝叶斯网络模型，从而预测起重装备的潜在故障和安全隐患。That is to say, firstly, the Bayesian network prediction model construction method based on expert knowledge and system operation records is used to quickly and effectively establish a Bayesian network model for the research object by combining expert experience and historical operating data of lifting equipment, so as to predict Potential failure and safety hazards of lifting equipment.
其中，在本发明的一个实施例中，建立贝叶斯网络预测模型具体包括：基于故障树的贝叶斯网络结构设计充分运用专家知识，且基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，并且基于故障逻辑为贝叶斯网络参数提供合理初值；基于最大期望算法的贝叶斯网络参数修正方法，以充分利用系统运行记录，从可能含有缺失样本的历史数据中挖掘起重装备的运行特性，并根据系统随时间产生的变化修正模型，改善贝叶斯网络预测模型的参数。Wherein, in one embodiment of the present invention, establishing the Bayesian network prediction model specifically includes: the Bayesian network structure design based on the fault tree fully utilizes expert knowledge, and the fault tree structure based on the lifting equipment is a Bayesian network Provide reference for structural design, and provide reasonable initial values for Bayesian network parameters based on fault logic; Bayesian network parameter correction method based on maximum expectation algorithm to make full use of system operation records and mine from historical data that may contain missing samples The operating characteristics of the lifting equipment, and modify the model according to the changes of the system over time, and improve the parameters of the Bayesian network prediction model.
可以理解的是，具体建模方法包括：基于故障树的贝叶斯网络结构设计方法，用于充分运用专家知识，基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，基于故障逻辑为贝叶斯网络参数提供合理初值；基于最大期望算法的贝叶斯网络参数修正方法，用于充分利用系统运行记录，从可能含有缺失样本的历史数据中充分挖掘起重装备的运行特性，引入专家经验无法考虑到的因素，并及时根据系统随时间产生的变化修正模型，进一步改善贝叶斯网络模型的参数，减少建模过程对专家知识和系统机理的依赖；结合故障树和最大期望算法的完整构造流程，用于结合所述基于故障树的贝叶斯网络结构设计方法和所述基于最大期望算法的贝叶斯网络参数修正方法，完整实现贝叶斯网络的建模过程。It can be understood that the specific modeling methods include: Bayesian network structure design method based on fault tree, which is used to make full use of expert knowledge; the fault tree structure based on lifting equipment provides a reference for Bayesian network structure design; The logic provides reasonable initial values for Bayesian network parameters; the Bayesian network parameter correction method based on the maximum expectation algorithm is used to make full use of system operation records and fully mine the operating characteristics of lifting equipment from historical data that may contain missing samples , introduce factors that cannot be considered by expert experience, and timely correct the model according to the changes of the system over time, further improve the parameters of the Bayesian network model, and reduce the dependence of the modeling process on expert knowledge and system mechanism; combined with fault tree and maximum The complete construction process of the expectation algorithm is used to combine the Bayesian network structure design method based on the fault tree and the Bayesian network parameter correction method based on the maximum expectation algorithm to completely realize the modeling process of the Bayesian network.
在步骤S103中，获取起重装备的当前运行状态，以根据当前运行状态和贝叶斯网络预测模型，实现起重机整体可靠性预测和潜在故障原因的快速定位。In step S103, the current operating state of the lifting equipment is obtained, so as to realize the overall reliability prediction of the crane and the rapid location of potential failure causes according to the current operating state and the Bayesian network prediction model.
在步骤S104中，以起重机整体故障概率和潜在故障原因概率作为权重，建立潜在运行效率的预测维修决策模型，得到起重装备潜在运行效率、潜在维修成本和潜在生产损失。In step S104, the overall failure probability of the crane and the potential failure cause probability are used as weights to establish a predictive maintenance decision model for potential operating efficiency to obtain the potential operating efficiency, potential maintenance cost and potential production loss of the lifting equipment.
也就是说，其次，基于潜在运行效率的预测性维修决策模型，用于根据设备运行状态实现潜在故障原因的快速定位和可靠性预测，并以故障概率和可靠性作为权重建立模型，预测起重装备的潜在运行效率，最后给出预测性维修决策方法，综合考虑系统可靠性、维修成本、潜在运行效率等指标，给出设备当前运行状态下是否需要立即维修的决策建议。That is to say, secondly, the predictive maintenance decision-making model based on potential operating efficiency is used to realize the rapid location and reliability prediction of potential failure causes according to the equipment operating status, and establish a model with failure probability and reliability as weights to predict lifting The potential operating efficiency of the equipment, and finally a predictive maintenance decision-making method is given, which comprehensively considers system reliability, maintenance costs, potential operating efficiency and other indicators, and gives a decision-making suggestion on whether the equipment needs to be repaired immediately under the current operating state.
其中，在本发明的一个实施例中，建立潜在运行效率的预测维修决策模型具体包括：基于贝叶斯后验概率的系统可靠性预测，从而根据起重装备实时监测到的局部异常预测系统整体失效率；基于起重装备潜在运行效率预测模型，从而基于贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；基于系统可靠性和潜在运行效率的预测性维修决策，从而综合考虑系统可靠性、维修成本、潜在运行效率和潜在生产损失，进而得到起重装备发现局部异常时是否立即停机维修的决策建议。Among them, in one embodiment of the present invention, the establishment of a predictive maintenance decision model for potential operating efficiency specifically includes: system reliability prediction based on Bayesian posterior probability, so as to predict the overall Failure rate: Based on the prediction model of the potential operating efficiency of the lifting equipment, the Bayesian network prediction model is used to predict the reliability of the system and the cause of potential failures, and comprehensively consider the potential downtime loss and performance loss of the lifting equipment caused by local abnormalities. And predict the potential operating efficiency of the equipment; predictive maintenance decisions based on system reliability and potential operating efficiency, so as to comprehensively consider system reliability, maintenance costs, potential operating efficiency and potential production loss, and then obtain whether the lifting equipment finds local abnormalities Decision-making recommendations for immediate downtime for maintenance.
可以理解的是，具体决策模型包括：基于贝叶斯后验概率的系统可靠性预测方法，用于根据起重装备实时监测到的局部异常预测系统整体失效率；起重装备潜在运行效率预测模型，用于基于贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；基于系统可靠性和潜在运行效率的预测性维修决策方法，用于综合考虑系统可靠性、维修成本、潜在运行效率、潜在生产损失等指标，给出起重装备发现局部异常时是否立即停机维修的决策建议。It can be understood that the specific decision-making model includes: a system reliability prediction method based on Bayesian posterior probability, which is used to predict the overall failure rate of the system according to the local abnormalities detected in real time by the lifting equipment; the potential operating efficiency prediction model of the lifting equipment , used for predicting and estimating system reliability and potential failure causes based on the Bayesian network prediction model, comprehensively considering the potential downtime loss and performance loss caused by local abnormalities to lifting equipment, and predicting the potential operating efficiency of the equipment; based on system reliability The predictive maintenance decision-making method based on the characteristics and potential operating efficiency is used to comprehensively consider the system reliability, maintenance cost, potential operating efficiency, potential production loss and other indicators, and give a decision-making suggestion on whether to immediately shut down the lifting equipment for maintenance when local abnormalities are found.
进一步地，在本发明的一个实施例中，计算内容包括时间稼动率、性能稼动率和潜在运行效率，其中，时间稼动率用于反映设备维修维护引起的非计划停机对运行效率的影响，性能稼动率用于反映设备的性能发挥情况，潜在运行效率用于综合考量节点异常对系统造成的潜在停机损失和性能损失，预测起重装备的潜在运行效率。Further, in one embodiment of the present invention, the calculation content includes time utilization rate, performance utilization rate and potential operating efficiency, wherein the time utilization rate is used to reflect the impact of unplanned downtime caused by equipment maintenance on operating efficiency Impact, the performance utilization rate is used to reflect the performance of the equipment, and the potential operating efficiency is used to comprehensively consider the potential downtime loss and performance loss caused by node abnormalities to the system, and predict the potential operating efficiency of the lifting equipment.
另外，在本发明的一个实施例中，其中，In addition, in an embodiment of the present invention, wherein,
其中，TAll为完整负荷时间为，TStop为潜在停机时间的期望；Among them, TAll is the full load time, and TStop is the expectation of potential downtime;
其中，Vcost为局部异常对系统整体运作速度的影响；Among them, Vcost is the impact of local abnormalities on the overall operating speed of the system;
PCE＝时间稼动率×性能稼动率PCE = time utilization rate × performance utilization rate
其中，PCE为潜在运行效率。Among them, PCE is the potential operating efficiency.
在步骤S105中，根据预测结果得到测维修决策模型的决策建议。In step S105, a decision suggestion of the maintenance decision model is obtained according to the prediction result.
简言之，在本发明的实施例中，本发明实施例的决策方法可以基于故障树专家知识和设备历史运行记录，建立贝叶斯网络预测模型，根据贝叶斯后验概率和当前系统状态，提供系统潜在运行效率的预测模型，并综合系统可靠性、运行效率、维护成本等标准实现起重装备的预测性健康管理和维修决策。In short, in the embodiment of the present invention, the decision-making method of the embodiment of the present invention can establish a Bayesian network prediction model based on the expert knowledge of the fault tree and the historical operation records of the equipment, and according to the Bayesian posterior probability and the current system state , provide a predictive model of the potential operating efficiency of the system, and integrate system reliability, operating efficiency, maintenance costs and other criteria to achieve predictive health management and maintenance decisions for lifting equipment.
在本发明的一个实施例中，本发明实施例的决策方法包括：In one embodiment of the present invention, the decision-making method of the embodiment of the present invention includes:
步骤S1：基于专家知识和系统运行记录的贝叶斯网络预测模型构造方法，用于结合专家经验和起重装备历史运行数据，针对研究对象快速有效地建立贝叶斯网络模型，从而预测起重装备的潜在故障和安全隐患；该方法具体包括：Step S1: The Bayesian network prediction model construction method based on expert knowledge and system operation records is used to quickly and effectively establish a Bayesian network model for the research object by combining expert experience and historical operating data of lifting equipment, so as to predict lifting Potential failures and safety hazards of equipment; the method specifically includes:
步骤S101，基于故障树的贝叶斯网络结构设计方法，用于充分运用专家知识，基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，基于故障逻辑为贝叶斯网络参数提供合理初值；Step S101, the Bayesian network structure design method based on the fault tree is used to make full use of expert knowledge, the fault tree structure based on the lifting equipment provides a reference for the Bayesian network structure design, and the Bayesian network parameters are provided based on the fault logic. reasonable initial value;
步骤S102，基于最大期望算法的贝叶斯网络参数修正方法，用于充分利用系统运行记录，从可能含有缺失样本的历史数据中充分挖掘起重装备的运行特性，引入专家经验无法考虑到的因素，并及时根据系统随时间产生的变化修正模型，进一步改善贝叶斯网络模型的参数，减少建模过程对专家知识和系统机理的依赖；Step S102, the Bayesian network parameter correction method based on the maximum expectation algorithm is used to make full use of the system operation records, fully mine the operation characteristics of the lifting equipment from the historical data that may contain missing samples, and introduce factors that cannot be considered by expert experience , and timely correct the model according to the changes of the system over time, further improve the parameters of the Bayesian network model, and reduce the dependence of the modeling process on expert knowledge and system mechanism;
具体地，结合故障树和最大期望算法的贝叶斯网络完整构造流程，用于结合所述基于故障树的贝叶斯网络结构设计方法和所述基于最大期望算法的贝叶斯网络参数修正方法，完整实现贝叶斯网络的建模过程。Specifically, the complete construction process of the Bayesian network combined with the fault tree and the maximum expectation algorithm is used to combine the Bayesian network structure design method based on the fault tree and the Bayesian network parameter correction method based on the maximum expectation algorithm , fully realize the modeling process of Bayesian network.
步骤S2，基于潜在运行效率的预测性维修决策模型，用于根据设备运行状态实现潜在故障原因的快速定位和可靠性预测，并以故障概率和可靠性作为权重建立模型，预测起重装备的潜在运行效率，最后给出预测性维修决策方法，综合考虑系统可靠性、维修成本、潜在运行效率等指标，给出设备当前运行状态下是否需要立即维修的决策建议；该模型具体包括：Step S2, the predictive maintenance decision model based on potential operating efficiency is used to quickly locate potential failure causes and predict reliability according to equipment operating status, and establish a model with failure probability and reliability as weights to predict the potential of lifting equipment. Operational efficiency. Finally, a predictive maintenance decision-making method is given, which comprehensively considers system reliability, maintenance costs, potential operating efficiency and other indicators, and gives decision-making suggestions on whether immediate maintenance is required under the current operating state of the equipment; the model specifically includes:
步骤S201，基于贝叶斯后验概率的系统可靠性预测方法，用于根据起重装备实时监测到的局部异常预测系统整体失效率；Step S201, a system reliability prediction method based on Bayesian posterior probability, which is used to predict the overall failure rate of the system according to the local abnormality detected in real time by the lifting equipment;
步骤S202，起重装备潜在运行效率预测模型，用于基于贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；其中的运算主要包含两个指标：时间稼动率和性能稼动率。其中，时间稼动率用于反映设备维修维护引起的非计划停机对运行效率的影响，而性能稼动率，用于反映设备的性能发挥情况。Step S202, the potential operating efficiency prediction model of the lifting equipment is used to predict and estimate the system reliability and potential failure causes based on the Bayesian network prediction model, and comprehensively consider the potential shutdown loss and performance loss of the lifting equipment caused by local abnormalities, And predict the potential operating efficiency of the equipment; the calculation mainly includes two indicators: time utilization rate and performance utilization rate. Among them, the time utilization rate is used to reflect the impact of unplanned downtime caused by equipment maintenance on operating efficiency, and the performance utilization rate is used to reflect the performance of the equipment.
步骤S3，基于系统可靠性和潜在运行效率的预测性维修决策方法，用于综合考虑系统可靠性、维修成本、潜在运行效率、潜在生产损失等指标，给出起重装备发现局部异常时是否立即停机维修的决策建议。Step S3, the predictive maintenance decision-making method based on system reliability and potential operating efficiency is used to comprehensively consider the system reliability, maintenance cost, potential operating efficiency, potential production loss and other indicators, and give whether the lifting equipment finds local abnormalities immediately. Decision-making recommendations for downtime maintenance.
本发明实施例的决策方法具有以下有益效果：The decision-making method in the embodiment of the present invention has the following beneficial effects:
(1)能够根据起重装备实时工作状态预测潜在故障和安全隐患，并提供维修决策建议；(1) Be able to predict potential failures and safety hazards according to the real-time working status of lifting equipment, and provide maintenance decision-making suggestions;
(2)能够根据系统监测到的局部异常，预测可能发生的整体故障，提前预知安全隐患，供生产人员做出防范；(2) According to the local abnormality detected by the system, it can predict the overall failure that may occur, and predict the safety hazard in advance, so that the production personnel can take precautions;
(3)能够结合故障树专家知识和设备历史运行记录，进行贝叶斯网络预测模型建模；能够运用故障树简化建模过程，同时充分利用系统运行记录，引入专家经验无法考虑到的因素，根据系统随时间产生的变化修正模型，减少建模过程对专家知识和系统机理的依赖；(3) Be able to combine fault tree expert knowledge and equipment historical operation records to carry out Bayesian network prediction model modeling; be able to use fault trees to simplify the modeling process, and at the same time make full use of system operation records to introduce factors that cannot be considered by expert experience, Correct the model according to the changes of the system over time, reducing the dependence of the modeling process on expert knowledge and system mechanism;
(4)能够综合考虑系统可靠性、维修成本、潜在运行效率等多项指标，给出设备当前运行状态下是否需要立即维修的决策建议。(4) It can comprehensively consider multiple indicators such as system reliability, maintenance cost, and potential operating efficiency, and give decision-making suggestions on whether immediate maintenance is required under the current operating state of the equipment.
下面以一个具体实施例对本发明实施例的决策方法进行详细描述。The decision-making method of the embodiment of the present invention will be described in detail below with a specific embodiment.
1.基于专家知识和系统运行记录的贝叶斯网络预测模型构造方法。1. A Bayesian network prediction model construction method based on expert knowledge and system operation records.
本发明实施例的建模方法可以充分结合专家知识和系统运行记录，针对研究对象快速有效地建立贝叶斯网络预测模型。首先以故障树知识为贝叶斯网络结构设计提供参考，由逻辑门转化而得的条件概率表为贝叶斯网络参数训练提供了合理初值；然后从历史数据中充分挖掘对象设备的运行特性，引入专家经验无法考虑到的因素，进一步完善贝叶斯网络参数。上述过程如图2所示。The modeling method of the embodiment of the present invention can fully combine expert knowledge and system operation records, and quickly and effectively establish a Bayesian network prediction model for the research object. First, the fault tree knowledge is used as a reference for Bayesian network structure design, and the conditional probability table converted from logic gates provides a reasonable initial value for Bayesian network parameter training; then, the operating characteristics of the target equipment are fully excavated from historical data , introduce factors that cannot be considered by expert experience, and further improve the parameters of the Bayesian network. The above process is shown in Figure 2.
1.1基于故障树的贝叶斯网络结构设计方法。1.1 Bayesian network structure design method based on fault tree.
图3给出了简单的故障树示例。在故障树中，事件(节点)状态可以用正常/异常的二值逻辑表达，对应贝叶斯网络中节点变量Xi的布尔取值。不妨假设节点正常时Xi＝0，节点异常时Xi＝1。Figure 3 shows a simple fault tree example. In the fault tree, the event (node) state can be expressed by normal/abnormal binary logic, which corresponds to the Boolean value of the node variable Xi in theBayesian network. It may be assumed thatXi = 0 when the node is normal, andXi = 1 when the node is abnormal.
故障树节点之间以逻辑门连接，对应贝叶斯网络的参数；统计故障树底事件的发生概率可以赋值为相应贝叶斯网络节点的先验概率。图4给出了由故障树向贝叶斯网络的逻辑转换关系The nodes of the fault tree are connected by logic gates, which correspond to the parameters of the Bayesian network; the probability of occurrence of events at the bottom of the statistical fault tree can be assigned as the prior probability of the corresponding Bayesian network node. Figure 4 shows the logical conversion relationship from fault tree to Bayesian network
1.2基于最大期望算法的贝叶斯网络参数修正方法。1.2 The Bayesian network parameter correction method based on the maximum expectation algorithm.
最大期望算法(Expectation Maximization Algorithm，EM算法)可以从数据缺失的样本中对目标参数进行迭代的最大似然估计，其中缺失的样本视为隐变量。算法可分为期望步(Expectation Step)和最大似然步(Maximum Likelihood Step)，由目标参数的适当初值开始迭代，首先根据目标参数的估计值计算隐变量的分布，再以该分布下隐变量的期望作为隐变量的估计值，考虑目标参数对该分布的最大似然估计，重复上述步骤直至迭代收敛。隐变量的分布可以用后验概率密度(或对数似然函数)表示。The Expectation Maximization Algorithm (EM algorithm) can iteratively estimate the target parameters from the samples with missing data, and the missing samples are regarded as hidden variables. The algorithm can be divided into Expectation Step and Maximum Likelihood Step. The iteration starts from the appropriate initial value of the target parameter. First, the distribution of hidden variables is calculated according to the estimated value of the target parameter. The expectation of the variable is used as the estimated value of the hidden variable, and the maximum likelihood estimation of the distribution is considered for the target parameter, and the above steps are repeated until the iteration converges. The distribution of hidden variables can be represented by the posterior probability density (or log-likelihood function).
其中，当应用到贝叶斯网络参数训练时，样本数据Xi(x1,x2,…,xn)对应系统运行记录，缺失值Yi(y1,y2,…,ym)对应其中未记录或记录丢失的部分，目标参数θ对应贝叶斯网络的完整参数列表CPT，由此即可参照所述方法得到贝叶斯网络参数的估计值(如图5所示)，过程如下：Among them, when applied to Bayesian network parameter training, the sample data Xi (x1 ,x2 ,…,xn ) corresponds to the system operation record, and the missing value Yi( y1 ,y2 ,…,ym ) Corresponding to the part that is not recorded or the record is lost, the target parameter θ corresponds to the complete parameter list CPT of the Bayesian network, so that the estimated value of the Bayesian network parameters can be obtained by referring to the method (as shown in Figure 5), the process as follows:
初始条件：选定合适的CPT初值开始迭代；Initial conditions: Select an appropriate initial value of CPT to start iteration;
期望步：根据CPT估计值和已知的运行记录，估计缺失样本的可能取值并填充到系统运行记录中，构成完整的训练样本；Expectation step: According to the estimated value of CPT and known operating records, estimate the possible values of the missing samples and fill them into the system operating records to form a complete training sample;
最大似然步：根据填充得到的样本，对CPT列表做最大似然估计。Maximum likelihood step: Based on the filled samples, perform maximum likelihood estimation on the CPT list.
1.3结合故障树和最大期望算法的贝叶斯网络完整构造流程。1.3 The complete construction process of Bayesian network combined with fault tree and maximum expectation algorithm.
完整的构造方法以故障树引入专家知识，提供贝叶斯网络的参考结构和参数初值；在系统运行记录的基础上，基于最大期望算法进一步调节参数完善贝叶斯网络建模，完整流程如图6所示。The complete construction method uses the fault tree to introduce expert knowledge, and provides the reference structure and initial parameters of the Bayesian network; on the basis of the system operation records, further adjusts the parameters based on the maximum expectation algorithm to improve the Bayesian network modeling. The complete process is as follows: Figure 6 shows.
2.基于潜在运行效率的预测性维修决策模型。2. A predictive maintenance decision model based on potential operational efficiency.
本发明实施例以基于前文所述方法建立的贝叶斯网络预测模型为基础，根据设备运行状态实现潜在故障原因的快速定位和可靠性预测，并以故障概率和可靠性作为权重建立模型，预测起重装备的潜在运行效率。最后给出预测性维修决策方法，综合考虑系统可靠性、维修成本、潜在运行效率等指标，给出设备当前运行状态下是否需要立即维修的决策建议。决策过程如图7所示。The embodiment of the present invention is based on the Bayesian network prediction model established based on the method described above, and realizes the rapid location and reliability prediction of potential failure causes according to the equipment operating status, and establishes a model with the failure probability and reliability as weights to predict Potential operating efficiency of lifting equipment. Finally, a predictive maintenance decision-making method is given, which comprehensively considers system reliability, maintenance cost, potential operating efficiency and other indicators, and gives a decision-making suggestion on whether the equipment needs to be repaired immediately under the current operating state. The decision-making process is shown in Figure 7.
2.1基于贝叶斯后验概率的系统可靠性预测方法。2.1 System reliability prediction method based on Bayesian posterior probability.
参考图3所示简单的贝叶斯网络模型，包含顶事件T，以及系统症状节点Xi(x1,x2,…,xn)。系统运行过程中，实时监测症状节点X的变化，记观察到异常的节点集合为XE，其中Referring to the simple Bayesian network model shown in Figure 3, it includes a top event T and system symptom nodes Xi (x1 , x2 ,...,x n) . During the operation of the system, monitor the changes of the symptom node X in real time, record the set of observed abnormal nodes as XE , where
根据不确定性假设，系统出现局部异常时，可能发生整体故障，也可能保持正常运作，表现为一定概率的故障风险。经贝叶斯网络推理，可以根据当前工作状态预测系统整体失效率PT＝Pr(T＝1|XE)，其中PR＝1-PT可用于衡量系统可靠性。According to the uncertainty assumption, when a local abnormality occurs in the system, the overall failure may occur, or it may maintain normal operation, which is expressed as a failure risk with a certain probability. Through Bayesian network reasoning, the overall failure rate of the system can be predicted according to the current working state PT =Pr(T =1|XE ), where PR =1-PT can be used to measure system reliability.
进一步讨论系统在未来发生故障的情况，此时导致故障的原因可能只有Xi∈XE，也可能是先前未监测到的节点引起的。因此估计潜在维修代价时，应考虑当前监测状态下各症状节点在未来作为原因引起故障的后验概率PC(Xi)＝Pr(Xi＝1|T,XE)。显然当Xi∈XE时，有PC(Xi)＝1。Further discuss the situation that the system will fail in the future. At this time, the cause of the failure may only be Xi ∈ XE , or it may be caused by a node that has not been monitored before. Therefore, when estimating the potential maintenance cost, the posterior probability PC (Xi )=Pr(Xi =1|T,XE ) of each symptomatic node in the current monitoring state as the cause of failure in the future should be considered. Obviously when Xi ∈ XE , there is PC (Xi )=1.
2.2起重装备潜在运行效率预测模型。2.2 Prediction model of potential operating efficiency of lifting equipment.
2.2.1时间稼动率2.2.1 Time utilization rate
时间稼动率反映设备维修维护引起的非计划停机对运行效率的影响。定义完整负荷时间为TAll，潜在停机时间的期望TStop应为各部位维修时间的加权和，权重为各症状节点作为故障原因的后验概率PC(Xi)和系统故障率PT之积，因为：The time utilization rate reflects the impact of unplanned downtime caused by equipment maintenance on operating efficiency. Define the complete load time as TAll , and the expectedTStop of the potentialdowntime should be the weighted sum of the maintenance time of each part. accumulate because:
此外应根据专家经验建立单个节点维修时间的知识库T(t1,t2,…,tn)，其中ti为单独维修Xi节点所需的时间。建立如下关系：In addition, the knowledge base T(t1 ,t2 ,…,tn ) of the maintenance time of a single node should be established based on expert experience, where ti is the time required to maintain the Xi node alone. Create the following relationship:
2.2.2性能稼动率2.2.2 Performance Utilization Rate
性能稼动率反映设备的性能发挥情况，一般以实际生产速度和理论生产速度的比率表征。在预测性效率评估中，需要凭经验估计局部异常对系统整体运作速度的影响Vcost，故仿照时间稼动率建立节点对性能影响的专家知识库V(v1,v2,…,vn)，其中vi为Xi节点异常时对系统整体性能影响的占比估计，且应满足∑vi≤100％。建立如下关系：The performance utilization rate reflects the performance of the equipment, and is generally characterized by the ratio of the actual production speed to the theoretical production speed. In predictive efficiency evaluation, it is necessary to estimate the influence Vcost of local anomalies on the overall operating speed of the system based on experience, so the expert knowledge base V(v1 ,v2 ,…,vn ), where vi is the estimated proportion of the impact on the overall system performance when the Xi node is abnormal, and it should satisfy ∑vi ≤100%. Create the following relationship:
2.2.3潜在运行效率2.2.3 Potential operating efficiency
如图8所示，可以给出预测起重装备潜在运行效率的PCE模型(PredictiveCraneEffectiveness，PCE)。该模型基于贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量了节点异常对系统造成的潜在停机损失和性能损失：As shown in Figure 8, a PCE model (Predictive Crane Effectiveness, PCE) for predicting the potential operating efficiency of the lifting equipment can be given. This model is based on the prediction and estimation of system reliability and potential failure causes based on the Bayesian network prediction model, and comprehensively considers the potential downtime loss and performance loss caused by node abnormalities to the system:
PCE＝时间稼动率×性能稼动率。PCE = time utilization rate × performance utilization rate.
2.3基于系统可靠性和潜在运行效率的预测性维修决策方法。2.3 Predictive maintenance decision-making method based on system reliability and potential operating efficiency.
预测性维修决策的主要目标是给出系统发现局部异常时是否立即停机维修的建议。当系统潜在故障风险较小，或故障造成的损失较小而维修成本较高时，应暂缓维修；当系统故障风险较大、故障损失较大且维修成本较低时，应建议立即停机维修。以上决策应综合考虑故障发生故障的概率、引起的生产损失以及所需付出的成本。本发明实施例比较暂不维修可能产生的潜在损失CPOT和立即维修所需的成本CNow作为决策依据，前者基于贝叶斯后验概率估计，后者严格按当前监测状态计算。The main goal of predictive maintenance decision-making is to give suggestions on whether to shut down the system immediately for maintenance when local abnormalities are found. When the potential failure risk of the system is small, or the loss caused by the failure is small and the maintenance cost is high, the maintenance should be postponed; when the system failure risk is high, the failure loss is large and the maintenance cost is low, it should be recommended to shut down immediately for maintenance. The above decision should comprehensively consider the probability of failure, the production loss caused and the cost to be paid. The embodiment of the present invention compares the potential loss CPOT that may be caused by not maintaining temporarily and the cost CNow required for immediate maintenance as a decision basis. The former is based on Bayesian posterior probability estimation, and the latter is calculated strictly according to the current monitoring status.
在不考虑安全事故的情况下，系统故障引发的经济损失可抽象为生产损失CPrd和维修成本CRpr。CPrd来自系统故障和异常带来的生产效率损失，可以用PCE衡量；CRpr来自修理异常节点、消除故障隐患所需的费用。假设理想状态下系统在TAll时间内的产值为CAll,各节点的维修费用为C(c1,c2,…,cn)，其中ci为维修Xi节点时所需的费用。建立如下关系：Without considering safety accidents, the economic loss caused by system failure can be abstracted as production loss CPrd and maintenance cost CRpr . CPrd comes from the loss of production efficiency caused by system failures and abnormalities, which can be measured by PCE; CRpr comes from the cost of repairing abnormal nodes and eliminating hidden troubles. Assume that in an ideal state, the output value of the system within TAll time is CAll , and the maintenance cost of each node is C(c1 ,c2 ,…,cn ), whereci is the cost of maintaining X inodes . Create the following relationship:
1)暂不维修的潜在经济损失：CPOT＝(1-PCE)×CAll；1) Potential economic loss if not repaired temporarily: CPOT = (1-PCE) × CAll ;
2)立即维修的经济损失：CNow＝C'Prd+C'Rpr；2) Economic loss of immediate maintenance: CNow = C'Prd + C'Rpr;
3)决策标准(损失比)：3) Decision criteria (loss ratio):
上述结果损失比Eval可作为依据比较维修与否带来的损失，在合理设置TAll和CAll的情况下，可以得到下表所示的维修建议，具体决策标准应以实际生产场景为准，如表1所示。The above result loss ratio Eval can be used as a basis to compare the loss caused by maintenance or not. In the case of reasonable setting of TAll and CAll , the maintenance suggestions shown in the table below can be obtained. The specific decision-making criteria should be based on the actual production scene. As shown in Table 1.
表1Table 1
根据本发明实施例的基于起重装备工作状态的预测性维修决策方法，可以结合故障树专家知识和设备历史运行记录进行贝叶斯网络预测模型建模，并且基于系统状态快速定位潜在的故障原因并预测系统可靠性，根据贝叶斯后验概率和当前系统状态，给出系统潜在运行效率的预测模型，综合系统可靠性、运行效率、维护成本等标准实现起重装备的预测性健康管理和维修决策，能够根据起重装备实时工作状态预测潜在故障和安全隐患，并提供维修决策建议，有效加强起重装备生产过程的监控管理，提供预测性维修维护，提高维修决策水平和设备运行效率，减少安全隐患和国民经济损失。According to the predictive maintenance decision-making method based on the working state of the lifting equipment according to the embodiment of the present invention, the Bayesian network prediction model modeling can be carried out by combining the expert knowledge of the fault tree and the historical operation records of the equipment, and the potential cause of the fault can be quickly located based on the system state And predict the reliability of the system. According to the Bayesian posterior probability and the current system state, the prediction model of the potential operating efficiency of the system is given, and the comprehensive system reliability, operating efficiency, maintenance cost and other standards realize the predictive health management and maintenance of lifting equipment. Maintenance decision-making can predict potential failures and potential safety hazards based on the real-time working status of lifting equipment, and provide maintenance decision-making suggestions, effectively strengthen the monitoring and management of the production process of lifting equipment, provide predictive maintenance, improve maintenance decision-making level and equipment operation efficiency, Reduce potential safety hazards and national economic losses.
其次参照附图描述根据本发明实施例提出的基于起重装备工作状态的预测性维修决策系统。Next, the predictive maintenance decision system based on the working state of the lifting equipment proposed according to the embodiment of the present invention will be described with reference to the accompanying drawings.
图9是本发明实施例的基于起重装备工作状态的预测性维修决策系统的结构示意图。Fig. 9 is a schematic structural diagram of a predictive maintenance decision system based on the working state of lifting equipment according to an embodiment of the present invention.
如图9所示，该基于起重装备工作状态的预测性维修决策系统10包括：获取模块100、第一模型建立模块200、预测模块300、第二模型建立模块400和决策模块500。As shown in FIG. 9 , the predictive maintenance decision system 10 based on the working state of lifting equipment includes: an acquisition module 100 , a first model building module 200 , a prediction module 300 , a second model building module 400 and a decision module 500 .
其中，获取模块100用于获取起重装备的历史运行数据。第一模型建立模块200用于根据所述故障树专家知识和所述历史运行数据建立贝叶斯网络预测模型，以预测起重装备的潜在故障和安全隐患。预测模块300用于获取起重装备的当前运行状态，以根据所述当前运行状态和贝叶斯网络预测模型，实现起重机整体可靠性预测和潜在故障原因的快速定位。第二模型建立模块400用于以起重机整体故障概率和潜在故障原因概率作为权重，建立潜在运行效率的预测维修决策模型，得到起重装备潜在运行效率、潜在维修成本和潜在生产损失。决策模块500用于根据所述预测结果得到所述测维修决策模型的决策建议。本发明实施例的决策系统10可以有效加强起重装备生产过程的监控管理，提供预测性维修维护，提高维修决策水平和设备运行效率，减少安全隐患和国民经济损失。Wherein, the obtaining module 100 is used for obtaining historical operation data of the lifting equipment. The first model building module 200 is used for building a Bayesian network prediction model according to the expert knowledge of the fault tree and the historical operation data, so as to predict potential failures and potential safety hazards of the lifting equipment. The prediction module 300 is used to obtain the current operating state of the lifting equipment, so as to realize the overall reliability prediction of the crane and the rapid location of potential failure causes according to the current operating state and the Bayesian network prediction model. The second model building module 400 is used to establish a predictive maintenance decision model for potential operating efficiency by taking the overall failure probability of the crane and the potential failure cause probability as weights to obtain the potential operating efficiency, potential maintenance cost and potential production loss of the lifting equipment. The decision-making module 500 is configured to obtain a decision-making suggestion of the maintenance decision-making model according to the prediction result. The decision-making system 10 of the embodiment of the present invention can effectively strengthen the monitoring and management of the production process of lifting equipment, provide predictive maintenance, improve maintenance decision-making level and equipment operation efficiency, and reduce potential safety hazards and national economic losses.
进一步地，在本发明的一个实施例中，第一模型建立模块200具体用于：基于故障树的贝叶斯网络结构设计充分运用专家知识，且基于起重装备的故障树结构为贝叶斯网络结构设计提供参考，并且基于故障逻辑为贝叶斯网络参数提供合理初值；基于最大期望算法的贝叶斯网络参数修正方法，以充分利用系统运行记录，从可能含有缺失样本的历史数据中挖掘起重装备的运行特性，并根据系统随时间产生的变化修正模型，改善贝叶斯网络预测模型的参数。Further, in one embodiment of the present invention, the first model building module 200 is specifically used for: Bayesian network structure design based on fault tree fully utilizes expert knowledge, and the fault tree structure based on lifting equipment is Bayesian Provide reference for network structure design, and provide reasonable initial values for Bayesian network parameters based on fault logic; Bayesian network parameter correction method based on maximum expectation algorithm to make full use of system operation records, from historical data that may contain missing samples Excavate the operating characteristics of lifting equipment, and modify the model according to the changes of the system over time, and improve the parameters of the Bayesian network prediction model.
进一步地，在本发明的一个实施例中，第二模型建立模块400具体用于：基于贝叶斯后验概率的系统可靠性预测，从而根据起重装备实时监测到的局部异常预测系统整体失效率；基于起重装备潜在运行效率预测模型，从而基于贝叶斯网络预测模型对系统可靠性和潜在故障原因的预测估计，综合考量局部异常对起重装备造成的潜在停机损失和性能损失，并预测设备的潜在运行效率；基于系统可靠性和潜在运行效率的预测性维修决策，从而综合考虑系统可靠性、维修成本、潜在运行效率和潜在生产损失，进而得到起重装备发现局部异常时是否立即停机维修的决策建议。Further, in one embodiment of the present invention, the second model building module 400 is specifically used for: system reliability prediction based on Bayesian posterior probability, so as to predict the overall failure of the system according to the local abnormality detected in real time by the lifting equipment rate; based on the prediction model of the potential operating efficiency of the lifting equipment, the Bayesian network prediction model is used to predict the reliability of the system and the cause of potential failures, comprehensively consider the potential downtime loss and performance loss of the lifting equipment caused by local abnormalities, and Predict the potential operating efficiency of equipment; predictive maintenance decisions based on system reliability and potential operating efficiency, so as to comprehensively consider system reliability, maintenance costs, potential operating efficiency and potential production loss, and then obtain whether the lifting equipment detects local abnormalities immediately Decision-making recommendations for downtime maintenance.
进一步地，在本发明的一个实施例中，计算内容包括时间稼动率、性能稼动率和潜在运行效率，其中，时间稼动率用于反映设备维修维护引起的非计划停机对运行效率的影响，性能稼动率用于反映设备的性能发挥情况，潜在运行效率用于综合考量节点异常对系统造成的潜在停机损失和性能损失，预测起重装备的潜在运行效率。Further, in one embodiment of the present invention, the calculation content includes time utilization rate, performance utilization rate and potential operating efficiency, wherein the time utilization rate is used to reflect the impact of unplanned downtime caused by equipment maintenance on operating efficiency Impact, the performance utilization rate is used to reflect the performance of the equipment, and the potential operating efficiency is used to comprehensively consider the potential downtime loss and performance loss caused by node abnormalities to the system, and predict the potential operating efficiency of the lifting equipment.
进一步地，在本发明的一个实施例中，其中，Further, in one embodiment of the present invention, wherein,
其中，TAll为完整负荷时间为，TStop为潜在停机时间的期望；Among them, TAll is the full load time, and TStop is the expectation of potential downtime;
其中，Vcost为局部异常对系统整体运作速度的影响；Among them, Vcost is the impact of local abnormalities on the overall operating speed of the system;
PCE＝时间稼动率×性能稼动率PCE = time utilization rate × performance utilization rate
其中，PCE为潜在运行效率。Among them, PCE is the potential operating efficiency.
需要说明的是，前述对基于起重装备工作状态的预测性维修决策方法实施例的解释说明也适用于该实施例的基于起重装备工作状态的预测性维修决策系统，此处不再赘述。It should be noted that the foregoing explanations of the embodiment of the predictive maintenance decision method based on the working state of the lifting equipment are also applicable to the predictive maintenance decision system based on the working state of the lifting equipment in this embodiment, and will not be repeated here.
根据本发明实施例的基于起重装备工作状态的预测性维修决策系统，可以结合故障树专家知识和设备历史运行记录进行贝叶斯网络预测模型建模，并且基于系统状态快速定位潜在的故障原因并预测系统可靠性，根据贝叶斯后验概率和当前系统状态，给出系统潜在运行效率的预测模型，综合系统可靠性、运行效率、维护成本等标准实现起重装备的预测性健康管理和维修决策，能够根据起重装备实时工作状态预测潜在故障和安全隐患，并提供维修决策建议，有效加强起重装备生产过程的监控管理，提供预测性维修维护，提高维修决策水平和设备运行效率，减少安全隐患和国民经济损失。According to the predictive maintenance decision system based on the working state of the lifting equipment according to the embodiment of the present invention, the Bayesian network predictive model modeling can be carried out in combination with the expert knowledge of the fault tree and the historical operation records of the equipment, and the potential cause of the fault can be quickly located based on the system state And predict the reliability of the system. According to the Bayesian posterior probability and the current system state, the prediction model of the potential operating efficiency of the system is given, and the comprehensive system reliability, operating efficiency, maintenance cost and other standards realize the predictive health management and maintenance of lifting equipment. Maintenance decision-making can predict potential failures and potential safety hazards based on the real-time working status of lifting equipment, and provide maintenance decision-making suggestions, effectively strengthen the monitoring and management of the production process of lifting equipment, provide predictive maintenance, improve maintenance decision-making level and equipment operation efficiency, Reduce potential safety hazards and national economic losses.
在本发明中，除非另有明确的规定和限定，第一特征在第二特征“上”或“下”可以是第一和第二特征直接接触，或第一和第二特征通过中间媒介间接接触。而且，第一特征在第二特征“之上”、“上方”和“上面”可是第一特征在第二特征正上方或斜上方，或仅仅表示第一特征水平高度高于第二特征。第一特征在第二特征“之下”、“下方”和“下面”可以是第一特征在第二特征正下方或斜下方，或仅仅表示第一特征水平高度小于第二特征。In the present invention, unless otherwise clearly specified and limited, the first feature may be in direct contact with the first feature or the first and second feature may be in direct contact with the second feature through an intermediary. touch. Moreover, "above", "above" and "above" the first feature on the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. "Below", "beneath" and "beneath" the first feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is less horizontally than the second feature.
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.
尽管上面已经示出和描述了本发明的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention, those skilled in the art can make the above-mentioned The embodiments are subject to changes, modifications, substitutions and variations.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610958285.9ACN106503813A (en) | 2016-10-27 | 2016-10-27 | Prospective maintenance decision-making technique and system based on hoisting equipment working condition |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610958285.9ACN106503813A (en) | 2016-10-27 | 2016-10-27 | Prospective maintenance decision-making technique and system based on hoisting equipment working condition |
| Publication Number | Publication Date |
|---|---|
| CN106503813Atrue CN106503813A (en) | 2017-03-15 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610958285.9APendingCN106503813A (en) | 2016-10-27 | 2016-10-27 | Prospective maintenance decision-making technique and system based on hoisting equipment working condition |
| Country | Link |
|---|---|
| CN (1) | CN106503813A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107315396A (en)* | 2017-05-27 | 2017-11-03 | 中国电子科技集团公司第三十六研究所 | A kind of state monitor maintenance and predictive maintenance Combined maintenance method and system for planning |
| CN107909161A (en)* | 2017-11-24 | 2018-04-13 | 西南交通大学 | A kind of traction power supply maintenance of equipment method based on risk cost prediction |
| CN109214544A (en)* | 2018-06-28 | 2019-01-15 | 广东工业大学 | Life prediction and maintenance measures method and apparatus and storage medium, computer |
| CN109635997A (en)* | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN109697455A (en)* | 2018-11-14 | 2019-04-30 | 清华大学 | The method for diagnosing faults and device of distribution switchgear |
| CN109886485A (en)* | 2019-02-13 | 2019-06-14 | 上海大学 | An optimization method of traffic infrastructure maintenance strategy |
| EP3537352A1 (en)* | 2018-03-08 | 2019-09-11 | General Electric Company | Analytics |
| CN110362939A (en)* | 2019-07-19 | 2019-10-22 | 北京计算机技术及应用研究所 | Network target range equipment architecture Reliability modeling system and method based on Monte carlo |
| CN111176234A (en)* | 2019-12-30 | 2020-05-19 | 四川九合智能科技有限公司 | Cement production equipment life cycle predictive maintenance system |
| CN111310948A (en)* | 2020-03-31 | 2020-06-19 | 北京交通大学 | Obtaining method of optimal maintenance strategy for rail transit on-board signal system |
| CN111311059A (en)* | 2020-01-16 | 2020-06-19 | 成都大汇物联科技有限公司 | Knowledge graph-based water mill room fault diagnosis method |
| CN111563606A (en)* | 2020-04-30 | 2020-08-21 | 新智数字科技有限公司 | Equipment predictive maintenance method and device |
| CN111563612A (en)* | 2020-04-13 | 2020-08-21 | 深圳达实智能股份有限公司 | Predictive operation and maintenance management method and system for air conditioner of subway station |
| CN111627189A (en)* | 2019-02-12 | 2020-09-04 | 珠海格力电器股份有限公司 | Equipment exception handling method, system and storage medium |
| CN111768113A (en)* | 2020-07-03 | 2020-10-13 | 许艳杰 | Public cloud-based hydraulic engineering management system and method |
| CN111143752B (en)* | 2019-05-17 | 2021-01-08 | 深圳市德塔防爆电动汽车有限公司 | Method for calculating safety importance of electric vehicle and electric vehicle |
| CN113374543A (en)* | 2021-06-04 | 2021-09-10 | 西安交通大学 | Aeroengine part maintenance method based on time-varying fault rate model |
| CN113689042A (en)* | 2021-08-25 | 2021-11-23 | 华自科技股份有限公司 | Fault source prediction method for monitoring node |
| CN114063588A (en)* | 2020-07-29 | 2022-02-18 | 中车株洲电力机车研究所有限公司 | Method, device and equipment for selecting test speed of transmission control unit |
| CN114580679A (en)* | 2022-03-11 | 2022-06-03 | 国能黄骅港务有限责任公司 | Method and device for determining equipment stability and production operation system |
| CN114604768A (en)* | 2022-01-24 | 2022-06-10 | 杭州大杰智能传动科技有限公司 | Intelligent tower crane maintenance management method and system based on fault identification model |
| CN114626559A (en)* | 2022-03-12 | 2022-06-14 | 军事科学院系统工程研究院军需工程技术研究所 | Diet equipment maintainability assessment method and device |
| CN114780732A (en)* | 2022-06-22 | 2022-07-22 | 天津市天锻压力机有限公司 | Forging hydraulic press predictive maintenance method and system based on Bayes classification model |
| CN115511136A (en)* | 2022-11-01 | 2022-12-23 | 北京磁浮有限公司 | Equipment fault auxiliary diagnosis method and system based on hierarchical analysis and fault tree |
| CN115936679A (en)* | 2023-01-13 | 2023-04-07 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Method and device for digitizing forecast maintenance decision of complex system |
| CN117102950A (en)* | 2023-10-17 | 2023-11-24 | 上海诺倬力机电科技有限公司 | Fault analysis method, device, electronic equipment and computer readable storage medium |
| CN118333600A (en)* | 2024-03-14 | 2024-07-12 | 中国电建集团华东勘测设计研究院有限公司 | Power station equipment maintenance quality evaluation method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en)* | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN102495549A (en)* | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system and method for engineering machinery |
| CN102645595A (en)* | 2012-04-10 | 2012-08-22 | 明玮机械(东莞)有限公司 | Equipment overall efficiency detecting method |
| KR20140078000A (en)* | 2012-12-13 | 2014-06-25 | 한국건설기술연구원 | Management strategy generation method for each bridge and bridge group considering life cycle of bridge, and bridge management system using the same |
| CN104915730A (en)* | 2015-06-09 | 2015-09-16 | 西北工业大学 | Device multi-attribute maintenance decision method based on weight |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en)* | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN102495549A (en)* | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system and method for engineering machinery |
| CN102645595A (en)* | 2012-04-10 | 2012-08-22 | 明玮机械(东莞)有限公司 | Equipment overall efficiency detecting method |
| KR20140078000A (en)* | 2012-12-13 | 2014-06-25 | 한국건설기술연구원 | Management strategy generation method for each bridge and bridge group considering life cycle of bridge, and bridge management system using the same |
| CN104915730A (en)* | 2015-06-09 | 2015-09-16 | 西北工业大学 | Device multi-attribute maintenance decision method based on weight |
| Title |
|---|
| 钟虞全: ""贝叶斯网络在起重机故障诊断中的应用"", 《中国优秀硕士学位论文全文数据库》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107315396B (en)* | 2017-05-27 | 2019-06-11 | 中国电子科技集团公司第三十六研究所 | A hybrid maintenance planning method and system for condition monitoring maintenance and predictive maintenance |
| CN107315396A (en)* | 2017-05-27 | 2017-11-03 | 中国电子科技集团公司第三十六研究所 | A kind of state monitor maintenance and predictive maintenance Combined maintenance method and system for planning |
| CN107909161A (en)* | 2017-11-24 | 2018-04-13 | 西南交通大学 | A kind of traction power supply maintenance of equipment method based on risk cost prediction |
| CN107909161B (en)* | 2017-11-24 | 2023-07-25 | 西南交通大学 | Traction power supply equipment maintenance method based on risk cost prediction |
| EP3537352A1 (en)* | 2018-03-08 | 2019-09-11 | General Electric Company | Analytics |
| CN109214544A (en)* | 2018-06-28 | 2019-01-15 | 广东工业大学 | Life prediction and maintenance measures method and apparatus and storage medium, computer |
| CN109214544B (en)* | 2018-06-28 | 2021-03-09 | 广东工业大学 | Life prediction and maintenance decision method and device, storage medium and computer |
| CN109635997A (en)* | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN109697455A (en)* | 2018-11-14 | 2019-04-30 | 清华大学 | The method for diagnosing faults and device of distribution switchgear |
| CN111627189A (en)* | 2019-02-12 | 2020-09-04 | 珠海格力电器股份有限公司 | Equipment exception handling method, system and storage medium |
| CN109886485A (en)* | 2019-02-13 | 2019-06-14 | 上海大学 | An optimization method of traffic infrastructure maintenance strategy |
| CN111143752B (en)* | 2019-05-17 | 2021-01-08 | 深圳市德塔防爆电动汽车有限公司 | Method for calculating safety importance of electric vehicle and electric vehicle |
| CN110362939A (en)* | 2019-07-19 | 2019-10-22 | 北京计算机技术及应用研究所 | Network target range equipment architecture Reliability modeling system and method based on Monte carlo |
| CN111176234A (en)* | 2019-12-30 | 2020-05-19 | 四川九合智能科技有限公司 | Cement production equipment life cycle predictive maintenance system |
| CN111311059B (en)* | 2020-01-16 | 2023-08-29 | 成都大汇物联科技有限公司 | Waterwheel house fault diagnosis method based on knowledge graph |
| CN111311059A (en)* | 2020-01-16 | 2020-06-19 | 成都大汇物联科技有限公司 | Knowledge graph-based water mill room fault diagnosis method |
| CN111310948A (en)* | 2020-03-31 | 2020-06-19 | 北京交通大学 | Obtaining method of optimal maintenance strategy for rail transit on-board signal system |
| CN111310948B (en)* | 2020-03-31 | 2024-04-30 | 北京交通大学 | Method for acquiring optimized maintenance strategy of rail transit vehicle-mounted signal system |
| CN111563612A (en)* | 2020-04-13 | 2020-08-21 | 深圳达实智能股份有限公司 | Predictive operation and maintenance management method and system for air conditioner of subway station |
| CN111563612B (en)* | 2020-04-13 | 2024-03-22 | 深圳达实智能股份有限公司 | Method and system for managing predictive operation and maintenance of air conditioner of subway station |
| CN111563606A (en)* | 2020-04-30 | 2020-08-21 | 新智数字科技有限公司 | Equipment predictive maintenance method and device |
| CN111768113A (en)* | 2020-07-03 | 2020-10-13 | 许艳杰 | Public cloud-based hydraulic engineering management system and method |
| CN114063588A (en)* | 2020-07-29 | 2022-02-18 | 中车株洲电力机车研究所有限公司 | Method, device and equipment for selecting test speed of transmission control unit |
| CN114063588B (en)* | 2020-07-29 | 2023-10-31 | 中车株洲电力机车研究所有限公司 | Transmission control unit test speed selection method, device and equipment |
| CN113374543A (en)* | 2021-06-04 | 2021-09-10 | 西安交通大学 | Aeroengine part maintenance method based on time-varying fault rate model |
| CN113689042A (en)* | 2021-08-25 | 2021-11-23 | 华自科技股份有限公司 | Fault source prediction method for monitoring node |
| CN114604768A (en)* | 2022-01-24 | 2022-06-10 | 杭州大杰智能传动科技有限公司 | Intelligent tower crane maintenance management method and system based on fault identification model |
| CN114580679A (en)* | 2022-03-11 | 2022-06-03 | 国能黄骅港务有限责任公司 | Method and device for determining equipment stability and production operation system |
| CN114626559A (en)* | 2022-03-12 | 2022-06-14 | 军事科学院系统工程研究院军需工程技术研究所 | Diet equipment maintainability assessment method and device |
| CN114780732B (en)* | 2022-06-22 | 2022-09-13 | 天津市天锻压力机有限公司 | Forging hydraulic press predictive maintenance method and system based on Bayes classification model |
| CN114780732A (en)* | 2022-06-22 | 2022-07-22 | 天津市天锻压力机有限公司 | Forging hydraulic press predictive maintenance method and system based on Bayes classification model |
| CN115511136A (en)* | 2022-11-01 | 2022-12-23 | 北京磁浮有限公司 | Equipment fault auxiliary diagnosis method and system based on hierarchical analysis and fault tree |
| CN115936679A (en)* | 2023-01-13 | 2023-04-07 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Method and device for digitizing forecast maintenance decision of complex system |
| CN115936679B (en)* | 2023-01-13 | 2023-06-16 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | A digital method and device for predictive maintenance decision-making of complex systems |
| CN117102950A (en)* | 2023-10-17 | 2023-11-24 | 上海诺倬力机电科技有限公司 | Fault analysis method, device, electronic equipment and computer readable storage medium |
| CN117102950B (en)* | 2023-10-17 | 2023-12-22 | 上海诺倬力机电科技有限公司 | Fault analysis method, device, electronic equipment and computer readable storage medium |
| CN118333600A (en)* | 2024-03-14 | 2024-07-12 | 中国电建集团华东勘测设计研究院有限公司 | Power station equipment maintenance quality evaluation method |
| Publication | Publication Date | Title |
|---|---|---|
| CN106503813A (en) | Prospective maintenance decision-making technique and system based on hoisting equipment working condition | |
| CN102262690B (en) | Modeling method of early warning model of mixed failures and early warning model of mixed failures | |
| CN116341919B (en) | Data and model combined driving safety risk assessment and early warning method | |
| WO2025001516A1 (en) | Refrigeration system operation method and apparatus, device, and storage medium | |
| CN119142750A (en) | Intelligent mine ore conveying management system | |
| CN117592975A (en) | Cloud computing-based highway electromechanical equipment operation and maintenance decision-making processing method and system | |
| CN105825279A (en) | Multi-component system group maintenance decision method and multi-component system group maintenance decision device based on prediction | |
| CN110009144A (en) | A method and system for determining an equipment replacement strategy | |
| CN117994076A (en) | Natural gas pipe network scheduling energy-saving assessment method based on big data | |
| CN105574604A (en) | Power network operation event-oriented monitoring, pre-judging and analyzing system | |
| CN111428356A (en) | Maintenance method and system for newly developed degraded equipment | |
| Hao et al. | Deep reinforce learning for joint optimization of condition-based maintenance and spare ordering | |
| CN118095086A (en) | Intelligent decision method for bridge full life cycle maintenance based on reinforcement learning | |
| Wang et al. | Condition-based maintenance method for multicomponent system considering maintenance delay based on remaining useful life prediction: Subsea tree system as a case | |
| CN117638938A (en) | Control methods, devices and electronic equipment for power systems | |
| Cai et al. | A novel RUL prognosis methodology of multilevel system with cascading failure: Subsea oil and gas transportation systems as a case study | |
| CN118675781A (en) | Intelligent monitoring and optimizing method and system for production business process of nuclear power plant | |
| CN117611128A (en) | A health management system and method considering single spare parts guarantee | |
| Marugán et al. | A reinforcement learning agent for maintenance of deteriorating systems with increasingly imperfect repairs | |
| CN119559013B (en) | A new energy operation system intelligent monitoring and management method | |
| CN116755964A (en) | Fault prediction and health management system for reinforcement server | |
| CN120123313A (en) | A method for life cycle assessment and dynamic update of distributed resources | |
| Veerappan | Digital Twin Modeling for Predictive Maintenance in Large-Scale Power Transformers | |
| CN116351545B (en) | LSTM-based coal mill fault early warning method | |
| CN118778529A (en) | Intelligent control method and system for construction electricity |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20170315 | |
| RJ01 | Rejection of invention patent application after publication |