CN113515560A - Analysis method, device, electronic device and storage medium for vehicle failure - Google Patents
Analysis method, device, electronic device and storage medium for vehicle failureDownload PDFInfo
- Publication number
- CN113515560A CN113515560ACN202110815025.7ACN202110815025ACN113515560ACN 113515560 ACN113515560 ACN 113515560ACN 202110815025 ACN202110815025 ACN 202110815025ACN 113515560 ACN113515560 ACN 113515560A
- Authority
- CN
- China
- Prior art keywords
- fault
- vehicle
- data
- period
- confidence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本公开涉及车辆大数据技术领域，尤其涉及一种车辆故障的分析方法、装置、电子设备及存储介质。The present disclosure relates to the technical field of vehicle big data, and in particular, to an analysis method, device, electronic device and storage medium for vehicle faults.
背景技术Background technique
随着汽车行业的创新发展，越来越多的智能化汽车行驶在大街小巷。车联网平台可以实时获得智能化汽车的行车信号、故障信号等海量数据，并在后台利用这些数据分析驾驶行为，以达到提高行车安全的目的。With the innovation and development of the automobile industry, more and more intelligent vehicles are driving on the streets. The Internet of Vehicles platform can obtain massive data such as driving signals and fault signals of intelligent vehicles in real time, and use these data to analyze driving behavior in the background to achieve the purpose of improving driving safety.
现有技术包括基于专家系统的故障数据分析。该方法虽然直观、解释能力强，但是难以获取完备的知识库，无学习能力，容错能力较差，分析效率低。在此基础上，发展出了利用人工神经网络构建数据的关联规则，但是此方法对分析样本的要求较高，要求基于完备的样本集进行神经网络的训练，而现实中形成完备的样本集是及其困难的，因而训练出的神经网络存在诊断不准的情况。综上，现有技术中并不存在一种深度、高效且稳定的车辆故障分析方法。The prior art includes expert system-based analysis of fault data. Although this method is intuitive and has strong explanatory ability, it is difficult to obtain a complete knowledge base, has no learning ability, poor fault tolerance and low analysis efficiency. On this basis, an association rule using artificial neural network to construct data is developed. However, this method has high requirements for analyzing samples, and requires training of neural network based on a complete sample set. In reality, a complete sample set is formed by It is extremely difficult, so the trained neural network has inaccurate diagnosis. To sum up, there is no in-depth, efficient and stable vehicle fault analysis method in the prior art.
发明内容SUMMARY OF THE INVENTION
本公开提供了一种车辆故障的分析方法、装置、电子设备以及存储介质。The present disclosure provides an analysis method, device, electronic device and storage medium for vehicle failure.
根据本公开的一方面，提供了一种车辆故障的分析方法，包括：According to an aspect of the present disclosure, a method for analyzing vehicle faults is provided, including:
根据车辆的故障数据确定故障时段；Determine the fault period according to the fault data of the vehicle;
获取该故障时段内车辆的运行数据及车辆状态；Obtain the operating data and vehicle status of the vehicle during the fault period;
分析该故障时段内的故障数据、运行数据和车辆状态，获得对应于车辆状态的故障特征数据集；Analyze the fault data, operation data and vehicle state within the fault period to obtain a fault feature data set corresponding to the vehicle state;
利用频繁模式增长法挖掘该故障特征数据集，得到车辆故障及相关特征的关联结果。The fault feature dataset was mined by the frequent pattern growth method, and the correlation results of vehicle faults and related features were obtained.
根据本公开的另一方面，提供了一种车辆故障的分析装置，包括：According to another aspect of the present disclosure, an apparatus for analyzing vehicle failures is provided, including:
确定模块，用于根据车辆的故障数据确定故障时段；a determining module, used for determining the fault period according to the fault data of the vehicle;
获取模块，用于获取该故障时段内车辆的运行数据及车辆状态；The acquisition module is used to acquire the running data and vehicle status of the vehicle during the fault period;
分析模块，用于分析该故障时段内的故障数据、运行数据和车辆状态，获得对应于车辆状态的故障特征数据集；The analysis module is used to analyze the fault data, operation data and vehicle state in the fault period, and obtain the fault feature data set corresponding to the vehicle state;
挖掘模块，用于利用频繁模式增长法挖掘该故障特征数据集，得到车辆故障及相关特征的关联结果。The mining module is used to mine the fault feature data set by using the frequent pattern growth method to obtain the correlation results of vehicle faults and related features.
根据本公开的另一方面，提供了一种电子设备，包括：According to another aspect of the present disclosure, there is provided an electronic device, comprising:
至少一个处理器；以及at least one processor; and
与该至少一个处理器通信连接的存储器；其中，a memory communicatively coupled to the at least one processor; wherein,
该存储器存储有可被该至少一个处理器执行的指令，该指令被该至少一个处理器执行，以使该至少一个处理器能够执行本公开任一实施例中的方法。The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method in any of the embodiments of the present disclosure.
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，该计算机指令用于使计算机执行本公开任一实施例中的方法。According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method in any of the embodiments of the present disclosure.
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现本公开任一实施例中的方法。According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program that, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
根据本公开的技术，可以从海量故障数据中挖掘出车辆故障的内在规律，充分展示各运行数据对故障数据产生的影响程度，分析各故障的主要诱因，为车辆安全行驶及合理安排检修提供支撑。According to the technology of the present disclosure, the inherent law of vehicle failures can be mined from massive failure data, the degree of influence of each operation data on the failure data can be fully displayed, the main causes of each failure can be analyzed, and support for safe driving of vehicles and reasonable maintenance arrangements can be provided. .
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.
附图说明Description of drawings
附图用于更好地理解本方案，不构成对本公开的限定。其中：The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:
图1是根据本公开一实施例的车辆故障的分析方法的流程示意图；FIG. 1 is a schematic flowchart of a method for analyzing vehicle faults according to an embodiment of the present disclosure;
图2是根据本公开一实施例的挖掘方法流程示意图；2 is a schematic flowchart of a mining method according to an embodiment of the present disclosure;
图3是根据本公开另一实施例的车辆故障的分析方法的流程示意图；3 is a schematic flowchart of a method for analyzing vehicle faults according to another embodiment of the present disclosure;
图4是根据本公开再一实施例的车辆故障的分析方法的流程示意图；4 is a schematic flowchart of a method for analyzing vehicle faults according to still another embodiment of the present disclosure;
图5是根据本公开一实施例的车辆故障的分析装置结构框图；5 is a structural block diagram of an apparatus for analyzing vehicle faults according to an embodiment of the present disclosure;
图6是根据本公开一实施例的挖掘模块结构框图；6 is a structural block diagram of a mining module according to an embodiment of the present disclosure;
图7是根据本公开另一实施例的车辆故障的分析装置结构框图；7 is a structural block diagram of an apparatus for analyzing vehicle faults according to another embodiment of the present disclosure;
图8是用来实现本公开实施例的车辆故障的分析方法的电子设备的框图。8 is a block diagram of an electronic device used to implement the method for analyzing vehicle faults according to an embodiment of the present disclosure.
具体实施方式Detailed ways
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。本文中术语“第一”、“第二”表示指代多个类似的技术用语并对其进行区分，并不是限定顺序的意思，或者限定只有两个的意思，例如，第一特征和第二特征，是指代有两类/两个特征，第一特征可以为一个或多个，第二特征也可以为一个或多个。The term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, and A and B exist independently B these three cases. The term "at least one" herein refers to any combination of any one of a plurality or at least two of a plurality, for example, including at least one of A, B, and C, and may mean including from A, B, and Any one or more elements selected from the set of C. The terms "first" and "second" herein refer to and distinguish between a plurality of similar technical terms, and do not mean to limit the order, or to limit only two meanings, for example, the first feature and the second Feature means that there are two types/two features, the first feature can be one or more, and the second feature can also be one or more.
另外，为了更好的说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following detailed description. It will be understood by those skilled in the art that the present disclosure may be practiced without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art have not been described in detail so as not to obscure the subject matter of the present disclosure.
车联网行业的快速发展带来了海量车辆行驶数据以及故障数据可以通过高速传输上传至后台，进行精准快速数据运算，使得基于大数据的汽车故障关联分析预测成为落地的可能。相关技术人员做了很多相关工作，希望通过挖掘分析海量数据得到各行驶数据与故障数据之间的关联关系，挖掘出一些人工无法直接得到的内在规律，用来反馈给车辆的设计、研发、升级以及反馈用户的故障预警推送等场景。The rapid development of the Internet of Vehicles industry has brought a large amount of vehicle driving data and fault data that can be uploaded to the background through high-speed transmission for accurate and fast data calculation, making it possible to analyze and predict vehicle faults based on big data. Relevant technicians have done a lot of related work, hoping to obtain the correlation between each driving data and fault data by mining and analyzing massive data, and dig out some inherent laws that cannot be directly obtained manually, which can be used to feed back to vehicle design, research and development, and upgrades. And feedback user's failure warning push and other scenarios.
根据本公开的实施例，提供了一种车辆故障的分析方法，图1是根据本公开一实施例的车辆故障的分析方法的流程示意图，该方法可用于车辆故障的分析装置，实现车辆故障及相关特征分析以及故障预警。如图1所示，该方法包括：According to an embodiment of the present disclosure, a method for analyzing vehicle faults is provided. FIG. 1 is a schematic flowchart of a method for analyzing vehicle faults according to an embodiment of the present disclosure. Relevant feature analysis and fault warning. As shown in Figure 1, the method includes:
S101、根据车辆的故障数据确定故障时段；S101. Determine the fault period according to the fault data of the vehicle;
一示例中，可以从车辆大数据监控平台上获取车辆故障数据，该车辆故障数据可包括故障时间、故障地点、故障类别、行车状态基础数据等，本公开不对数据的获取来源和具体内容做限制；然后从车辆的故障数据中提取出故障发生的时刻，将包含该时刻的固定长度的时间段确定为故障时段，如，某辆车在09:15发生了A故障，在09:15前后各推15分钟，将09:00-09:30划分为故障A对应的故障时段。一示例中，一个故障时段中可能包含多个故障，比如例如某辆车在09:15发生了A故障，09:20发生了B故障，也可以将09:00-09:30划分为故障A和B两个故障组合成的群组对应的故障时段。In one example, vehicle fault data can be obtained from a vehicle big data monitoring platform, and the vehicle fault data can include fault time, fault location, fault category, basic data of driving status, etc. The present disclosure does not limit the source and specific content of the data acquisition ; Then extract the moment when the fault occurs from the fault data of the vehicle, and determine the time period of fixed length including the moment as the fault period. For example, if a vehicle has A fault at 09:15, the Push for 15 minutes, and divide 09:00-09:30 into the fault period corresponding to fault A. In an example, a fault period may contain multiple faults. For example, a vehicle has fault A at 09:15 and fault B at 09:20. 09:00-09:30 can also be divided into fault A. The fault period corresponding to the group formed by the two faults of B.
需要强调的是，本公开中不限制故障时段的数量，可能存在一至多个故障时段。比如，车辆大数据监控平台上可能汇集了10万余辆新能源汽车，历时近6个月的车辆故障数据，包括故障时间、故障地点、故障类别、行车状态基础数据等海量数据。其中，针对车辆运行中常见的电机和电池故障，平台可以将CAN总线与车载T-BOX连接，通过CAN网络采集数据，获取不同工况下不同故障的发生时刻故障类型与表现特征。这些庞大的数据，对应着很多个故障时段，本步骤中，可以将海量的故障时段都确定下来。It should be emphasized that the number of failure periods is not limited in the present disclosure, and there may be one or more failure periods. For example, the vehicle big data monitoring platform may have collected more than 100,000 new energy vehicles and vehicle failure data that lasted for nearly 6 months, including massive data such as failure time, failure location, failure category, and basic driving status data. Among them, for the common motor and battery faults in vehicle operation, the platform can connect the CAN bus to the vehicle T-BOX, collect data through the CAN network, and obtain the fault types and performance characteristics at the time of occurrence of different faults under different working conditions. These huge data correspond to many fault periods. In this step, a large number of fault periods can be determined.
S102、获取该故障时段内车辆的运行数据及车辆状态；S102, acquiring the running data and vehicle status of the vehicle within the fault period;
一示例中，在得到多个故障时段的基础上，分别获取每个故障时段内对应的车辆运行数据及车辆状态，其中，车辆运行数据包括车辆运行过程中车辆自身或环境相关的所有数据。本公开车辆故障的分析方法中使用到的所有数据的原始数据可以从车辆大数据监控平台上获取，也可以从第三方提供的数据平台上获取，所有数据包括但不限于车辆故障数据、车辆运行数据、车辆状态等，本公开不做限制。In an example, on the basis of obtaining multiple fault periods, corresponding vehicle operation data and vehicle status in each fault period are obtained respectively, wherein the vehicle operation data includes all data related to the vehicle itself or the environment during vehicle operation. The original data of all data used in the analysis method of vehicle failure of the present disclosure can be obtained from the vehicle big data monitoring platform, or from the data platform provided by a third party. All data include but are not limited to vehicle failure data, vehicle operation Data, vehicle status, etc., are not limited in this disclosure.
一示例中，可以获取该故障时段内按预设时间间隔采集的车辆的运行数据及车辆状态，该运行数据包括车辆的信号数据与环境数据。其中，车辆状态也可以称作车辆工况或典型工况，具体可以是车辆行驶状态、车辆充电状态或车辆静置状态，也可以是其余的用以进行分类的车辆状况或状态，比如新能源车的行驶状态、油电混合车的加油状态等等。另，运行数据中的信号数据可以是车辆速度、电池温度或最低单体电压等车辆各个部件的运行数据；运行数据中的环境数据可以是环境温度或湿度等；具体可参考表1，但不限于表1列出的运行数据类型。还需说明的是，上述车辆运行数据是按照预设时间间隔获得的，每种数据的预设时间间隔可以相同，也可以不同。比如，可以设定每隔1分钟采集一次实施车速，同时，设定每隔5分钟采集一次电池电压。In one example, the operation data and vehicle status of the vehicle collected at preset time intervals during the fault period may be acquired, where the operation data includes signal data and environmental data of the vehicle. Among them, the vehicle state may also be called a vehicle operating condition or a typical operating condition, which may specifically be a vehicle driving state, a vehicle charging state, or a vehicle stationary state, or other vehicle conditions or states used for classification, such as new energy The driving state of the car, the fueling state of the hybrid vehicle, and so on. In addition, the signal data in the operating data can be the operating data of various parts of the vehicle such as vehicle speed, battery temperature or minimum cell voltage; the environmental data in the operating data can be the ambient temperature or humidity, etc. For details, please refer to Table 1, but not Limited to the operational data types listed in Table 1. It should also be noted that the above-mentioned vehicle operation data are obtained according to preset time intervals, and the preset time intervals of each type of data may be the same or different. For example, it can be set to collect the actual vehicle speed every 1 minute, and at the same time, it can be set to collect the battery voltage every 5 minutes.
上述示例中，为了进行更深层次的故障关联挖掘，不但收集了车辆各部件的信号数据，还收集了环境数据，通过全面收集与车辆相关的所有数据，为之后进行关联分析打下了较好的数据基础。In the above example, in order to carry out deeper fault correlation mining, not only the signal data of each component of the vehicle, but also the environmental data are collected. By comprehensively collecting all the data related to the vehicle, good data is laid for the subsequent correlation analysis. Base.
表1车辆运行数据示例Table 1 Example of vehicle operation data
S103、分析该故障时段内的故障数据、运行数据和车辆状态，获得对应于车辆状态的故障特征数据集；S103, analyzing the fault data, operation data and vehicle state within the fault period to obtain a fault feature data set corresponding to the vehicle state;
一示例中，分别分析多个故障时段内的故障数据、运行数据和车辆状态，依据不同阈值将运行数据划分为不同的离散状态并进行归一处理，最后提取出对应同样车辆状态的数据分析结果，整理后获得故障特征数据集。比如，提取出某一特定车型车辆行驶状态下对应的多个故障时段，分析后得到该故障时段故障数据及其对应的离散化、归一化后的运行数据，组成故障特征数据集，如表2所示：In an example, the fault data, operating data and vehicle status in multiple fault periods are analyzed separately, the operating data is divided into different discrete states according to different thresholds and normalized, and finally the data analysis results corresponding to the same vehicle status are extracted. , and the fault feature dataset is obtained after sorting. For example, multiple fault periods corresponding to the driving state of a certain vehicle type are extracted, and after analysis, the fault data of the fault period and the corresponding discretized and normalized operating data are obtained to form a fault feature data set, as shown in Table 1. 2 shows:
表2故障特征数据集示例Table 2 Examples of fault feature datasets
一示例中，对某一故障时段内的故障数据进行分析，即是对该时段内的故障进行分类统计，得到一个统计结果。比如，在09:00-09:30这一故障时段内，故障A于{[09:15:10-09:15:15],[09:16:10-19:16:15]…}持续出现，则经过分析后的统计结果为：A故障时间间隔为55s，持续时间为5s，周期性频率为1min/次。In an example, the analysis of the fault data in a certain fault period is to classify and count the faults in the period to obtain a statistical result. For example, during the fault period of 09:00-09:30, fault A continues at {[09:15:10-09:15:15], [09:16:10-19:16:15]…} If it occurs, the statistical result after analysis is: A failure time interval is 55s, duration is 5s, and periodic frequency is 1min/time.
一示例中，可以根据预设的一个或多个阈值对该故障时段内的运行数据进行离散化和归一化处理，并与该故障时段内的故障数据组合后，按照该车辆状态分类，得到对应于车辆状态的故障特征数据集。具体地，以表征速度的运行数据为例，首先，因为在故障时段内，会采集到多个车辆速度的实时值，所以需要先对这些速度数据进行规范化处理，包括剔除异常数据，统一单位；然后根据预设的阈值对规范后的速度数据进行多区间的离散化处理，比如预设三个阈值区间：速度小于40千米/小时属于低速，速度大于40千米/小时但小于80千米/小时属于中速，速度大于80千米/小时属于高速，速度大于140千米/小时属于极端超速状态，计算落入预设区间的速度的比率，最终得到离散化的统计结果，如：在故障时段，低速占20％，中速占5％，高速占70％，出现极端超速状态；又如，通过平台大数据统计分析已知，车辆起步期发动机转速正常范围在在1000-2000转/分钟，则故障期内符合起步阶段的工况下发动机转速超过了3000转/分钟，则视为故障潜在特征数据之一，即得到了归一化的统计结果。之后，将上述经离散、归一化处理后的数据与其对应的车辆状态和故障数据结合，得到如表2所示的故障特征数据集。In one example, the operating data within the fault period may be discretized and normalized according to one or more preset thresholds, and after being combined with the fault data within the fault period, the vehicle state can be classified according to the vehicle state to obtain A dataset of fault features corresponding to vehicle states. Specifically, taking the running data representing the speed as an example, first of all, because multiple real-time values of vehicle speed will be collected during the fault period, it is necessary to normalize these speed data, including removing abnormal data and unifying the unit; Then, the standardized speed data is discretized in multiple intervals according to the preset threshold. For example, three preset threshold intervals are preset: the speed is less than 40 km/h, which is a low speed, and the speed is greater than 40 km/h but less than 80 km. /hour belongs to medium speed, speed greater than 80km/h belongs to high speed, and speed greater than 140km/h belongs to extreme overspeed state. During the fault period, the low speed accounts for 20%, the medium speed accounts for 5%, and the high speed accounts for 70%, and an extreme overspeed state occurs; for another example, it is known from the statistical analysis of the platform's big data that the normal range of the engine speed at the starting stage of the vehicle is 1000-2000 rpm/ minutes, then the engine speed exceeds 3000 rpm under the working conditions in the starting stage during the fault period, which is regarded as one of the potential characteristic data of the fault, that is, the normalized statistical results are obtained. After that, the above-mentioned discrete and normalized data are combined with the corresponding vehicle state and fault data to obtain the fault feature data set shown in Table 2.
需要强调的是，进行离散化的阈值可以结合人工经验来设定，也可以在分析的过程中根据分析的结果不断改进。比如，在经过几次车辆故障分析之后，发觉某一故障与车辆高速行驶强关联，为了进一步挖掘二者的关系，可以将速度重新划分阈值，比如大于80千米/小时小于100千米/小时属于微高速，大于100千米/小时但小于120千米/小时属于一般高速，大于150千米/小时属于超级高速，然后根据重新划分的阈值挖掘故障和特征之间的关联。总之，通过灵活划分阈值，并与对应的故障和车辆状态相结合得到故障特征数据集，可以更加精确地为故障溯源；基于经验不断改进更加合理的划分阈值，也可以控制频繁模式增长法，加快算法运行速度。显而易见，本公开中对故障时段内的所有数据进行了细致、完备的处理，处理后的数据更加具备分析价值，在后续的实操过程中使用方便。It should be emphasized that the threshold for discretization can be set in combination with human experience, and can also be continuously improved according to the results of the analysis during the analysis process. For example, after several vehicle failure analysis, it is found that a certain failure is strongly related to the high-speed driving of the vehicle. In order to further explore the relationship between the two, the speed can be re-divided into the threshold, such as greater than 80 km/h and less than 100 km/h It is a micro-high speed, more than 100 km/h but less than 120 km/h is a general high-speed, and more than 150 km/h is a super-high speed, and then the correlation between the fault and the feature is mined according to the re-divided threshold. In short, by flexibly dividing the thresholds and combining them with the corresponding faults and vehicle states to obtain the fault feature data set, the fault source can be traced more accurately; based on experience, the more reasonable dividing thresholds can be continuously improved, and the frequent pattern growth method can also be controlled to speed up Algorithm running speed. Obviously, in this disclosure, all data in the fault period is processed meticulously and completely, and the processed data has more analytical value and is convenient to use in subsequent practical operations.
S104、利用频繁模式增长法挖掘该故障特征数据集，得到车辆故障及相关特征的关联结果。S104, using the frequent pattern growth method to mine the fault feature data set, and obtain the correlation result of the vehicle fault and related features.
一示例中，利用频繁模式增长法挖掘故障特征数据集，可以得到车辆故障与车辆运行数据的关联数值，以数值的大小表征车辆故障与车辆运行数据的关联强度，从而找到隐含强关联关系的相关数据。In an example, the frequent pattern growth method is used to mine the fault feature data set, and the correlation value between the vehicle fault and the vehicle operation data can be obtained, and the correlation strength between the vehicle fault and the vehicle operation data can be represented by the magnitude of the value, so as to find the implicit strong correlation relationship. related data.
本公开将数据挖掘关联分析理论应用到车辆故障样本分析中，从海量故障数据中挖掘有效知识，并通过灵活设置阈值条件，控制规则树生长算法，加快算法运行速度。根据车辆不同驾驶工况对故障划分，以不同故障时间划分故障阶段，通过对故障阶段内各类驾驶状态和电信号数值离散化，构建故障特征数据集，最后对故障数据事务集进行关联规则挖掘，测试表明，利用关联规则挖掘车辆故障数据，扩展了有效的故障发生模式，取得了较好效果，对车辆的技术工程研发和用户预警应用具有一定的积极意义。The present disclosure applies the data mining correlation analysis theory to the analysis of vehicle fault samples, mines effective knowledge from massive fault data, and controls the rule tree growth algorithm by flexibly setting threshold conditions to speed up the running speed of the algorithm. The faults are divided according to different driving conditions of the vehicle, and the fault stages are divided according to different fault times. By discretizing various driving states and electrical signal values in the fault stage, the fault feature data set is constructed, and finally the association rules are mined for the fault data transaction set. , the test shows that the use of association rules to mine vehicle fault data expands the effective fault occurrence mode and achieves good results, which has a certain positive significance for the technical engineering research and development of vehicles and user early warning applications.
图2是根据本公开一实施例的挖掘方法流程示意图，如图2所示，在一种实施方式中，步骤S104可以具体包括以下步骤：FIG. 2 is a schematic flowchart of a mining method according to an embodiment of the present disclosure. As shown in FIG. 2 , in one embodiment, step S104 may specifically include the following steps:
S201、利用频繁模式增长法的支持度计算，挖掘该故障特征数据集，得到符合预设支持度阈值的频繁项集；S201. Use the support degree calculation of the frequent pattern growth method to mine the fault feature data set to obtain frequent itemsets that meet a preset support degree threshold;
S202、对该频繁项集内的所有项进行任意组合并计算每个组合的置信度；S202. Arbitrarily combine all items in the frequent itemset and calculate the confidence level of each combination;
S203、根据该置信度筛选出符合预设置信度阈值的组合作为车辆故障及相关特征的关联结果。S203 , according to the confidence, filter out a combination that meets a preset confidence threshold as the correlation result between the vehicle fault and related features.
一示例中，利用支持度计算公式挖掘故障特征数据集，筛选出符合预设支持度阈值的频繁项集。具体地，在获得故障特征数据集后，对每一类特征数据和每一类故障数据进行唯一编码，比如电池电压低于3.4v编码对应着XH001，电压欠压故障的编码对应着GZ001。然后利用支持度计算公式(1)和(2)对每一类故障进行支持度计算，支持度是指某事件同时出现的频率，公式中的X，Y为两个事件代号，number(X)为该单一事件X发生的次数，number(XY)为两个事件同时发生的次数，num(AllSamples)为所有样本总数，support(X,Y)是指XY同时出现的概率，support(X)是指X单一事件出现的概率；具体地，计算单一事件时用公式(1)，计算两个事件或是扩展至多个事件的情况下用公式(2)。实际实施过程中，先通过公式(1)计算出单一特征的支持度记录C1，其中，C代表支持度的计算结果，下角标1代表只有一个事件(此处的事件也被称作特征)即单一特征，结果如表3所示。In an example, the fault feature data set is mined by using the support degree calculation formula, and frequent itemsets that meet the preset support degree threshold are screened out. Specifically, after obtaining the fault characteristic data set, uniquely encode each type of characteristic data and each type of fault data. For example, the code of battery voltage below 3.4v corresponds to XH001, and the code of voltage undervoltage fault corresponds to GZ001. Then use the support calculation formulas (1) and (2) to calculate the support for each type of fault. The support refers to the frequency of an event occurring at the same time. X and Y in the formula are the two event codes, number(X) is the number of occurrences of the single event X, number(XY) is the number of simultaneous occurrences of two events, num(AllSamples) is the total number of all samples, support(X,Y) is the probability that XY occurs at the same time, and support(X) is Refers to the probability of occurrence of a single event of X; specifically, formula (1) is used when calculating a single event, and formula (2) is used when calculating two events or extending to multiple events. In the actual implementation process, the support record C1 of a single feature is first calculated by formula (1), where C represents the calculation result of the support degree, and the
表3单一特征的支持度记录Table 3 Support record of a single feature
提前设定好一个预设支持度阈值，计算出特征的支持度后，筛选出支持度高于阈值的特征，比如本示例中设定预设支持度阈值Smin为0.02，从单一特征的支持度记录C1中筛选出支持度大于0.02的特征，记入为单项频繁项集L1，其中，L代表频繁项集，下角标1代表单个特征，如表4所示：A preset support threshold is set in advance, and after calculating the support of the feature, the features whose support is higher than the threshold are screened out. For example, in this example, the preset support threshold Smin is set to 0.02. The features with a support degree greater than 0.02 are screened out from the degree record C1 and recorded as a single frequent itemset L1 , where L represents the frequent itemset, and the
表4单项频繁项集Table 4 Single frequent itemsets
从单项频繁项集L1中选取特征进行两两组合，即对支持度高于阈值的特征进行两两组合，舍弃重复项后，利用公式(2)计算得到双项的支持度记录C2，其中，C代表支持度的计算结果，下角标2代表双项特征，得到结果如表5所示：Select features from the single frequent itemset L1 to perform pairwise combination, that is, perform pairwise combination of features whose support degree is higher than the threshold. After discarding the duplicate items, formula (2) is used to calculate the double-item support degree record C2 , Among them, C represents the calculation result of the support degree, and the
表5双项特征的支持度记录Table 5 Support records of two-item features
同样，从中挑选出高于预设支持度阈值的项，得到双项频繁项集L2，如表6所示：Similarly, items higher than the preset support threshold are selected from them, and the double-item frequent itemset L2 is obtained, as shown in Table 6:
表6双项频繁项集Table 6 Two-item frequent itemsets
不断进行迭代搜索，当计算出K项的频繁项集Lk之后，利用公式(2)计算K+1项的支持度，直至K+1项的频繁项集与K项的频繁项集相同为止，记录下计算过程中所有支持度记录和频繁项集。Continue to iteratively search, after calculating the frequent itemset Lk of K items, use formula (2) to calculate the support of K+1 items, until the frequent itemsets of K+1 items are the same as the frequent itemsets of K items , record all support records and frequent itemsets in the calculation process.
接下来，利用置信度公式对该频繁项集内的所有项进行任意组合并计算每个组合的置信度，根据该置信度筛选出符合预设置信度阈值的组合。具体地，置信度公式(3)中，conf(X→Y)(也可表示为P(Y|X))表示由前项X(也叫规则左部)推导后项Y(也叫规则右部)的这条规则的置信度，P(X)为前项X事件发生的概率，P(XY)为XY两事件同时发生的概率。Next, use the confidence formula to arbitrarily combine all items in the frequent itemset, calculate the confidence of each combination, and screen out the combination that meets the preset confidence threshold according to the confidence. Specifically, in the confidence formula (3), conf(X→Y) (which can also be expressed as P(Y|X)) means that the latter item Y (also called the right side of the rule) is derived from the former item X (also called the left part of the rule). Part) of the confidence of this rule, P(X) is the probability of occurrence of the previous X event, and P(XY) is the probability of the simultaneous occurrence of XY two events.
Conf(X→Y)＝P(Y|X)＝P(XY)/P(X) (3)Conf(X→Y)=P(Y|X)=P(XY)/P(X) (3)
具体地，首先，遍历每个双项频繁项集L2中的所有特征项，逐一取单一特征项作为规则右部的元素，针对每一个规则右部元素，选择其他元素作为规则左部的元素；利用置信度公式算出左部推导右部的置信度，然后用规则左部和右部作为特征组合的支持度除以置信度，得到对应的规则置信度。将计算得出的置信度与预先设置好的最小置信度Fmin进行比较，筛选出大于最小置信度的规则左部和规则右部，作为筛选出的组合纳入强关联规则池中，如表7所示：Specifically, first, traverse all the feature items in each double-item frequent itemset L2 , take a single feature item one by one as the element in the right part of the rule, and for each element in the right part of the rule, select other elements as the elements in the left part of the rule ; Use the confidence formula to calculate the confidence of the left part to derive the right part, and then divide the support degree of the left part and the right part of the rule as the feature combination by the confidence degree to obtain the corresponding rule confidence degree. Compare the calculated confidence level with the preset minimum confidence level Fmin , and filter out the left and right parts of the rule that are greater than the minimum confidence level. shown:
表7双项组合规则置信度Table 7 Confidence of two-item combination rule
利用前述方法，计算出多个特征项的规则置信度。以计算三项特征的规则置信度为例，遍历三项频繁项集L3中的所有特征项，逐一取单一特征项作为规则右部的元素，针对每一个规则右部元素，选择其他元素作为规则左部的元素；然后选取两个特征作为规则右部的元素，再选择出匹配的左部的元素。遍历所有可能的规则左部和规则右部后，进行规则置信度的计算和比较。最后通过前述方法筛选出大于最小置信度Fmin阈值的组合纳入强规则池中，结果如表8所示：Using the aforementioned method, the rule confidences of multiple feature items are calculated. Taking the calculation of the rule confidence of three features as an example, traverse all the feature items in thethree -item frequent item set L3, take a single feature item one by one as the element in the right part of the rule, and select other elements as the element in the right part of each rule. The elements on the left side of the rule; then two features are selected as the elements on the right side of the rule, and then the matching elements on the left side are selected. After traversing all possible rule left parts and rule right parts, calculate and compare the rule confidence. Finally, the combination that is greater than the minimum confidence Fmin threshold is screened out into the strong rule pool by the aforementioned method. The results are shown in Table 8:
表8三项组合规则置信度Table 8 Confidence Levels of Three Combination Rules
不断迭代遍历K项频繁项集Lk中的所有特征项，并从中生成各K项集可能存在的所有全部规则，依据最小置信度Fmin阈值不断筛选符合条件的强规则入池。Iteratively traverses all the feature items in theK frequent itemsets Lk, and generates all the possible rules of each K itemsets from them, and continuously filters the qualified strong rules into the pool according to the minimum confidence Fmin threshold.
分析强规则池中的组合，作为车辆故障及相关特征的关联结果。具体地，根据置信度将强规则池中所有组合进行排序，如表9所示：The combinations in the pool of strong rules are analyzed as the result of the association of vehicle faults and related features. Specifically, all combinations in the strong rule pool are sorted according to the confidence, as shown in Table 9:
表9置信度排序Table 9 Confidence ranking
一示例中，可以将得到的多个该关联结果按照置信度从高到低进行排序，选出排序在前的指定个数的关联结果推送给车载终端或用户终端。基于规则置信度的值进行排序后，获取规则置信度较高的组合，通过分析其中包含的具体特征得到车辆故障的有效相关信息，以规则置信度为0.944的组合为例，该组合涉及的特征包括电压欠压故障(GZ001)、电池电压低于3.4V(XH001)、车速较高(XH002)，可知，在检测到电池电压较低的情况下，如果还保持着较高的车速，极易出现电池欠压故障。通过此方法对车辆行驶相关的所有数据进行深入挖掘，能够挖掘出部分隐含知识，对发现部分车辆运行故障机理具有重要的指导作用。In an example, a plurality of the obtained association results may be sorted in descending order of confidence, and a specified number of association results that are ranked first may be selected and pushed to the vehicle-mounted terminal or the user terminal. After sorting based on the value of the rule confidence, the combination with a higher rule confidence is obtained, and the effective relevant information of the vehicle fault is obtained by analyzing the specific features contained in it. Taking the combination with a rule confidence of 0.944 as an example, the features involved Including voltage undervoltage fault (GZ001), battery voltage lower than 3.4V (XH001), and high vehicle speed (XH002), it can be seen that if the battery voltage is detected to be low, if the vehicle still maintains a high speed, it is very easy to A battery undervoltage fault has occurred. Through this method, all the data related to vehicle driving can be deeply excavated, and some hidden knowledge can be excavated, which has an important guiding role in discovering the failure mechanism of some vehicles.
进一步地，可以将通过频繁模式增长法挖掘出来的关联结果推送给车载终端、用户终端或是研发后台，收集专家、用户的意见和体验，并将有效意见反馈回数据处理阶段、阈值划分阶段或关联规则知识库生成步骤，形成闭环反馈。Further, the association results mined by the frequent pattern growth method can be pushed to the vehicle terminal, user terminal or R&D background, collecting opinions and experiences of experts and users, and feeding back effective opinions to the data processing stage, threshold division stage or The association rule knowledge base generation step forms a closed-loop feedback.
一示例中，在得到车辆故障及相关特征的关联结果之后，可以进行故障溯源分析或提供故障预警服务。具体地，可以根据得到故障关联建立模型，进行故障的溯源分析，然后基于故障关联关系及其分析的结果提供故障知识预警服务，具体地可以通过移动网络或者无线网络将该相关数据及分析结果发送至车载终端的显示屏、中控台或移动端应用软件中。可以理解的是，数据分析结果可以以多种可视化的形式表现，包括但不限于饼状图、条状图、曲线图、时序表图和透视表。本示例中运用挖掘出的故障关联特征对可能发生的故障进行预测，以提高维修质量和车辆安全运行的可靠性，降低维修成本，提升行车安全指数，带来较大的经济效益。In one example, after obtaining the correlation results of vehicle faults and related features, fault traceability analysis can be performed or fault early warning services can be provided. Specifically, a model can be established according to the obtained fault correlation, and the fault source can be traced and analyzed, and then a fault knowledge early warning service can be provided based on the fault correlation relationship and the analysis result. Specifically, the relevant data and analysis results can be sent through a mobile network or a wireless network. To the display screen of the vehicle terminal, the center console or the mobile application software. It is understood that the data analysis results can be presented in a variety of visual forms, including but not limited to pie charts, bar charts, graphs, time series charts, and pivot tables. In this example, the fault correlation features excavated are used to predict the possible faults, so as to improve the maintenance quality and the reliability of the safe operation of the vehicle, reduce the maintenance cost, improve the driving safety index, and bring greater economic benefits.
一实施例中，本公开中另一车辆故障分析方法的流程可以如图3所示，S301，根据车辆大数据监控平台数据，获取不同工况不同故障的发生时刻和故障特征，其中，工况相当于车辆状态，故障特征可以从故障数据中提取获得，具体实施细节可参考上述一示例中的S101和S102，此处不再赘述。In an embodiment, the flow of another vehicle fault analysis method in the present disclosure may be as shown in FIG. 3 . S301 , according to the data of the vehicle big data monitoring platform, the occurrence time and fault characteristics of different faults under different working conditions are obtained, wherein the working condition Equivalent to the vehicle state, the fault feature can be extracted from the fault data, and the specific implementation details can refer to S101 and S102 in the above example, which will not be repeated here.
S302，根据故障时刻划分故障群组，依据运行参数上下限及工程经验对车辆信号数据进行离散化，并与所述故障群组特征进行组合，形成故障事件集，其中，故障群组相当于故障时段及该时段对应的故障数据、运行数据以及车辆状态，故障事件集相当于故障特征数据集，对故障群组进行处理的步骤可参考上述示例中S103，此处不再赘述。S302: Divide the fault group according to the fault time, discretize the vehicle signal data according to the upper and lower limits of the operating parameters and engineering experience, and combine with the fault group characteristics to form a fault event set, where the fault group is equivalent to the fault The time period and the corresponding fault data, operation data and vehicle status of the time period, the fault event set is equivalent to the fault feature data set, the steps of processing the fault group can refer to S103 in the above example, and will not be repeated here.
S303，采用频繁模式增长法挖掘车辆故障事件集，先获取频繁事件项集全集，再组合成事件发生规则，抽取其中强关联对照确定车辆故障关联关系数据库，其中，“组合成事件发生规则”具体通过频繁模式增长法的支持度计算公式和置信度公式实现，具体实施细节可参考上一示例中S201-S203,此处不再赘述。S303, the frequent pattern growth method is used to mine the vehicle fault event set, first obtain the complete set of frequent event items, and then combine them into event occurrence rules, extract the strong correlation among them and determine the vehicle fault correlation database, wherein, "combining into event occurrence rules" specifically It is realized by the support calculation formula and the confidence formula of the frequent pattern growth method. For the specific implementation details, please refer to S201-S203 in the previous example, which will not be repeated here.
S304，对关系库规则池进行筛选排序，结合专家经验调整，充实故障知识库，并将高风险故障模式推送给客户。可根据计算出能代表特征之间关联强度的规则置信度进行排序，然后将关联性排名靠前的故障特征及相关特征推送给相关人士进行人工审阅，将审阅后的数据放入故障知识库，并推荐给客户，提醒其在之后的驾驶过程中注意。S304 , filter and sort the rule pool of the relational library, adjust it in combination with expert experience, enrich the fault knowledge base, and push the high-risk fault mode to the customer. It can be sorted according to the confidence of the rules that can represent the correlation strength between the features, and then push the fault features and related features with the top correlation ranking to the relevant personnel for manual review, and put the reviewed data into the fault knowledge base. And recommend it to customers to remind them to pay attention in the subsequent driving process.
上述示例可以选择车辆的基础故障和常见信号特征作为数据源输入和频繁模式增长数方法作为挖掘车辆潜在故障发生的匹配模式和异常特征，具备数据来源简便易得、数据存储和数值计算压力小、精度可控的优点。In the above example, the basic faults and common signal characteristics of the vehicle can be selected as the data source input and the frequent pattern growth number method can be used as the matching mode and abnormal characteristics for mining potential vehicle faults. The advantage of controllable precision.
一实施例中，本公开中再一车辆故障分析方法的流程可以如图4所示，开始先采集故障特征数据，然后提取相应的故障特征，再之后设置好关联分析中的阈值，包括置信度的阈值Fmin和支持度的阈值Smin，设置好阈值后，利用支持度计算公式对故障特征数据集中的数据进行扫描计算，先计算单项，再计算双项，再计算三项……直到计算出K项的支持度和K+1项的支持度一样，最终得到K项的支持度记录。计算过程中，舍弃支持度小于支持度的阈值Smin的结果，将剩下的作为对应项数的频繁项集。In an embodiment, the flow of another vehicle fault analysis method in the present disclosure may be shown in FIG. 4 , firstly collecting fault feature data, then extracting corresponding fault features, and then setting thresholds in correlation analysis, including confidence levels The threshold value Fmin and the threshold value Smin of support degree, after setting the threshold value, use the support degree calculation formula to scan and calculate the data in the fault feature data set, first calculate the single item, then calculate the double item, and then calculate the three items... until the calculation The support degree of K items is the same as the support degree of K+1 items, and finally the support degree record of K items is obtained. In the calculation process, the result whose support degree is less than the threshold value Smin of the support degree is discarded, and the remainder is used as the frequent itemsets corresponding to the number of items.
计算完K项的支持度并获得对应的频繁项集后，开始进行置信度的计算。具体地，从双项频繁项集中遍历所有可能的特征，分别作为置信度计算的前项和后项(也叫左部和右部)进行置信度计算，得到规则置信度的数值，将其与置信度的阈值Fmin，留下大于阈值的前项和后项，放入强规则池；然后依次从三项、四项……直到K项频繁项集中遍历所有可能的特征，计算置信度，将置信度大于阈值的前项和后项放入强规则池。具体可参考上一示例中S201-S202，此处不做赘述。After the support of K items is calculated and the corresponding frequent itemsets are obtained, the calculation of confidence is started. Specifically, all possible features are traversed from the double-item frequent item set, and the confidence is calculated as the previous item and the latter item (also called the left part and the right part) of the confidence calculation, and the value of the rule confidence is obtained. The threshold of confidence Fmin , leaving the previous and subsequent items greater than the threshold, put them into the strong rule pool; then traverse all possible features from the three items, four items... until the K items of frequent itemsets, and calculate the confidence level, Put the antecedents and consequent items with confidence greater than a threshold into the strong rule pool. For details, refer to S201-S202 in the previous example, which will not be repeated here.
图5示出本公开一实施例的车辆故障的分析装置结构框图，如图5所示，该装置具体包括：FIG. 5 shows a structural block diagram of an apparatus for analyzing vehicle faults according to an embodiment of the present disclosure. As shown in FIG. 5 , the apparatus specifically includes:
确定模块501，用于根据车辆的故障数据确定故障时段；A
获取模块502，用于获取该故障时段内车辆的运行数据及车辆状态；an
分析模块503，用于分析该故障时段内的故障数据、运行数据和车辆状态，获得对应于车辆状态的故障特征数据集；An
挖掘模块504，用于利用频繁模式增长法挖掘该故障特征数据集，得到车辆故障及相关特征的关联结果。The
一示例中，该获取模块用于：In one example, the acquisition module is used to:
获取该故障时段内按预设时间间隔采集的车辆的运行数据及车辆状态，该运行数据包括车辆的信号数据与环境数据。The operation data and vehicle state of the vehicle collected at preset time intervals within the fault period are acquired, and the operation data includes signal data and environmental data of the vehicle.
一示例中，该分析模块用于：In one example, the analysis module is used to:
根据预设的一个或多个阈值对该故障时段内的运行数据进行离散化和归一化处理，并与该故障时段内的故障数据组合后，按照该车辆状态分类，得到对应于车辆状态的故障特征数据集。According to one or more preset thresholds, the operating data in the fault period is discretized and normalized, and after combining with the fault data in the fault period, it is classified according to the vehicle state, and the corresponding vehicle state is obtained. Fault feature dataset.
图6示出本公开一实施例的挖掘模块结构框图，如图6所示，该模块具体包括：Fig. 6 shows a structural block diagram of a mining module according to an embodiment of the present disclosure. As shown in Fig. 6, the module specifically includes:
支持度计算单元601，用于利用频繁模式增长法的支持度计算，挖掘该故障特征数据集，得到符合预设支持度阈值的频法和繁项集；The support
置信度计算单元602，用于对该频繁项集内的所有项进行任意组合并计算每个组合的置信度；Confidence
筛选单元603，用于根据该置信度筛选出符合预设置信度阈值的组合作为车辆故障及相关特征的关联结果。The
一示例中，该挖掘模块还包括：In one example, the mining module further includes:
排序单元604，用于将得到的多个该关联结果按照置信度从高到低进行排序，选出排序在前的指定个数的关联结果推送给车载终端或用户终端。The sorting unit 604 is configured to sort the obtained association results in descending order of confidence, and select a specified number of association results that are ranked first and push them to the vehicle-mounted terminal or the user terminal.
图7示出本公开另一实施例的车辆故障的分析装置结构框图，如图7所示，该装置具体包括：FIG. 7 shows a structural block diagram of an apparatus for analyzing vehicle faults according to another embodiment of the present disclosure. As shown in FIG. 7 , the apparatus specifically includes:
确定模块701，用于根据车辆的故障数据确定故障时段；A
获取模块702，用于获取该故障时段内车辆的运行数据及车辆状态；an
分析模块703，用于分析该故障时段内的故障数据、运行数据和车辆状态，获得对应于车辆状态的故障特征数据集；An
挖掘模块704，用于利用频繁模式增长法挖掘该故障特征数据集，得到车辆故障及相关特征的关联结果；The
服务模块705，用于根据该关联结果进行故障溯源分析或提供故障预警服务。The
本公开实施例各装置中的各单元、模块或子模块的功能可以参见上述方法实施例中的对应描述，在此不再赘述。For the functions of the units, modules or sub-modules in the apparatuses in the embodiments of the present disclosure, reference may be made to the corresponding descriptions in the foregoing method embodiments, and details are not described herein again.
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
图8示出了可以用来实施本公开的实施例的示例电子设备800的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或要求的本公开的实现。FIG. 8 shows a schematic block diagram of an example
如图8所示，电子设备800包括计算单元801，其可以根据存储在只读存储器(ROM)802中的计算机程序或者从存储单元808加载到随机访问存储器(RAM)803中的计算机程序来执行各种适当的动作和处理。在RAM 803中，还可存储电子设备800操作所需的各种程序和数据。计算单元801、ROM 802以及RAM 803通过总线804彼此相连。输入输出(I/O)接口805也连接至总线804。As shown in FIG. 8 , the
电子设备800中的多个部件连接至I/O接口805，包括：输入单元806，例如键盘、鼠标等；输出单元807，例如各种类型的显示器、扬声器等；存储单元808，例如磁盘、光盘等；以及通信单元809，例如网卡、调制解调器、无线通信收发机等。通信单元809允许电子设备800通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。Various components in the
计算单元801可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元801的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元801执行上文所描述的各个方法和处理，例如支持度的计算或置信度的计算。例如，在一些实施例中，车辆故障的分析方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元808。在一些实施例中，计算机程序的部分或者全部可以经由ROM 802和/或通信单元809而被载入和/或安装到电子设备800上。当计算机程序加载到RAM 803并由计算单元801执行时，可以执行上文描述的车辆故障的分析方法中的一个或多个步骤。备选地，在其他实施例中，计算单元801可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行车辆故障的分析方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入、或者触觉输入来接收来自用户的输入。To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input to receive input from the user.
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, no limitation is imposed herein.
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.
Claims (14)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110815025.7ACN113515560A (en) | 2021-07-19 | 2021-07-19 | Analysis method, device, electronic device and storage medium for vehicle failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110815025.7ACN113515560A (en) | 2021-07-19 | 2021-07-19 | Analysis method, device, electronic device and storage medium for vehicle failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113515560Atrue CN113515560A (en) | 2021-10-19 |
Family
ID=78067396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110815025.7APendingCN113515560A (en) | 2021-07-19 | 2021-07-19 | Analysis method, device, electronic device and storage medium for vehicle failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113515560A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114661787A (en)* | 2022-03-17 | 2022-06-24 | 桂林电子科技大学 | Itemset mining method and device |
| CN114779747A (en)* | 2022-05-11 | 2022-07-22 | 中国第一汽车股份有限公司 | Vehicle fault cause determination system and method |
| CN114897256A (en)* | 2022-05-31 | 2022-08-12 | 三一汽车制造有限公司 | A vehicle health state analysis method, device, system and engineering vehicle |
| CN114935457A (en)* | 2022-05-17 | 2022-08-23 | 重庆长安汽车股份有限公司 | Self-adaptive aggregation processing method and system for automobile fault data |
| CN115587300A (en)* | 2022-09-29 | 2023-01-10 | 驭势（上海）汽车科技有限公司 | A vehicle risk assessment method, device, equipment and medium |
| CN120234707A (en)* | 2025-05-29 | 2025-07-01 | 城满电能源科技有限公司 | Shared bicycle fault vehicle marking method and system based on multi-dimensional data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294076A (en)* | 2016-08-24 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | A kind of server relevant fault Forecasting Methodology and system thereof |
| CN107092993A (en)* | 2017-06-05 | 2017-08-25 | 国网陕西省电力公司电力科学研究院 | Reclosing success rate association analysis method based on Disasters Type and line information |
| CN108958215A (en)* | 2018-06-01 | 2018-12-07 | 天泽信息产业股份有限公司 | A kind of engineering truck failure prediction system and its prediction technique based on data mining |
| CN112884179A (en)* | 2021-03-30 | 2021-06-01 | 北京交通大学 | Urban rail turn-back fault diagnosis method based on machine fault and text topic analysis |
- 2021
- 2021-07-19CNCN202110815025.7Apatent/CN113515560A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294076A (en)* | 2016-08-24 | 2017-01-04 | 浪潮(北京)电子信息产业有限公司 | A kind of server relevant fault Forecasting Methodology and system thereof |
| CN107092993A (en)* | 2017-06-05 | 2017-08-25 | 国网陕西省电力公司电力科学研究院 | Reclosing success rate association analysis method based on Disasters Type and line information |
| CN108958215A (en)* | 2018-06-01 | 2018-12-07 | 天泽信息产业股份有限公司 | A kind of engineering truck failure prediction system and its prediction technique based on data mining |
| CN112884179A (en)* | 2021-03-30 | 2021-06-01 | 北京交通大学 | Urban rail turn-back fault diagnosis method based on machine fault and text topic analysis |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114661787A (en)* | 2022-03-17 | 2022-06-24 | 桂林电子科技大学 | Itemset mining method and device |
| CN114779747A (en)* | 2022-05-11 | 2022-07-22 | 中国第一汽车股份有限公司 | Vehicle fault cause determination system and method |
| CN114935457A (en)* | 2022-05-17 | 2022-08-23 | 重庆长安汽车股份有限公司 | Self-adaptive aggregation processing method and system for automobile fault data |
| CN114897256A (en)* | 2022-05-31 | 2022-08-12 | 三一汽车制造有限公司 | A vehicle health state analysis method, device, system and engineering vehicle |
| CN114897256B (en)* | 2022-05-31 | 2025-02-07 | 三一汽车制造有限公司 | Vehicle health status analysis method, device, system and engineering vehicle |
| CN115587300A (en)* | 2022-09-29 | 2023-01-10 | 驭势（上海）汽车科技有限公司 | A vehicle risk assessment method, device, equipment and medium |
| CN120234707A (en)* | 2025-05-29 | 2025-07-01 | 城满电能源科技有限公司 | Shared bicycle fault vehicle marking method and system based on multi-dimensional data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113515560A (en) | Analysis method, device, electronic device and storage medium for vehicle failure | |
| CN112596495A (en) | Industrial equipment fault diagnosis method and system based on knowledge graph | |
| US11681282B2 (en) | Systems and methods for determining relationships between defects | |
| WO2024067387A9 (en) | User portrait generation method based on characteristic variable scoring, device, vehicle, and storage medium | |
| CN117196066A (en) | Smart operation and maintenance information analysis model | |
| CN112100164A (en) | Intelligent auditing method, system and readable storage medium | |
| CN111680855A (en) | A method and system for automatic detection and early warning of project whole process risk | |
| CN102809965A (en) | A hydraulic equipment fault early warning method based on frequent fault mode | |
| CN111898385B (en) | Earthquake disaster assessment method and system | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN111242170B (en) | Food inspection and detection project prediction method and device | |
| CN117194919A (en) | Production data analysis system | |
| CN104281525A (en) | Defect data analytical method and method for shortening software testing programs by using same | |
| CN116468292A (en) | Nuclear power equipment health assessment method and system based on data analysis | |
| CN114312930B (en) | Train operation abnormality diagnosis method and device based on log data | |
| Jing et al. | A microservice fault identification method based on LightGBM | |
| CN114116831B (en) | Big data mining processing method and device | |
| CN119862181A (en) | Method and system for intelligent operation and maintenance diagnosis tree of database based on multidimensional index | |
| CN117035563B (en) | Product quality safety risk monitoring method, device, monitoring system and medium | |
| CN113340547A (en) | Winch vibration diagnosis method based on improved lumped mean-square decomposition | |
| CN116738328B (en) | Industry classification and accounting method | |
| CN117951177A (en) | Vehicle data processing method, device, electronic device and storage medium | |
| CN106228248A (en) | A kind of system automatic trouble diagnosis method analyzed based on fuzzy FMEA | |
| CN116882632A (en) | Vehicle safety assessment method, system, device, equipment and storage medium | |
| CN117291575A (en) | Equipment maintenance method, equipment maintenance device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20211019 |