技术领域Technical Field
本发明涉及基于数字孪生的数控机床远程故障诊断系统，尤其涉及一种基于数字孪生的数控机床远程故障诊断方法及系统。The present invention relates to a remote fault diagnosis system for CNC machine tools based on digital twins, and in particular to a remote fault diagnosis method and system for CNC machine tools based on digital twins.
背景技术Background Art
数控机床作为制造业的重要基础，一旦机床发生故障，轻则导致零件的报废，重则导致企业生产的停滞，造成不可挽回的经济损失。对数控机床运行状态进行实时监控是实现预测维修、减少停机损失、提高生产效率的重要途径。CNC machine tools are an important foundation of the manufacturing industry. Once a machine tool fails, it can cause the scrapping of parts at the least, or even lead to the stagnation of enterprise production, resulting in irreparable economic losses. Real-time monitoring of the operating status of CNC machine tools is an important way to achieve predictive maintenance, reduce downtime losses, and improve production efficiency.
采用传统的故障诊断方式对数控机床进行诊断，对于简单故障，通过口头或书面描述对用户提供诊断帮助和指导；对于复杂故障，有经验的工程师必须亲赴现场提供服务。这种模式一方面造成故障诊断敏捷性降低，服务效率降低，服务成本提高，另一方面影响企业的生产效率和产品质量，造成经济损失。The traditional fault diagnosis method is used to diagnose CNC machine tools. For simple faults, users are provided with diagnostic help and guidance through oral or written descriptions; for complex faults, experienced engineers must go to the site to provide services. This model reduces the agility of fault diagnosis, service efficiency, and service costs on the one hand, and affects the production efficiency and product quality of the enterprise on the other hand, causing economic losses.
因此，如何实现对数控机床的故障的实时远程诊断，以便于提高机床远程故障诊断的智能化程度和检测效率，成为了新的研究方向。Therefore, how to realize real-time remote diagnosis of CNC machine tool faults in order to improve the intelligence level and detection efficiency of machine tool remote fault diagnosis has become a new research direction.
发明内容Summary of the invention
本发明的实施例提供一种基于数字孪生的数控机床远程故障诊断方法及系统，能够对数控机床的故障进行实时远程诊断，提高机床远程故障诊断的智能化程度和检测效率。The embodiments of the present invention provide a method and system for remote fault diagnosis of CNC machine tools based on digital twins, which can perform real-time remote diagnosis of faults of CNC machine tools and improve the intelligence level and detection efficiency of remote fault diagnosis of machine tools.
为达到上述目的，本发明的实施例采用如下技术方案：To achieve the above object, the embodiments of the present invention adopt the following technical solutions:
第一方面，本发明的实施例提供的方法，包括：In a first aspect, an embodiment of the present invention provides a method comprising:
S101、接受从传感器数据采集模块获取数控机床的工作数据，所述工作数据包括：数控机床在工作期间的静态数据和动态数据；S101, receiving working data of a CNC machine tool from a sensor data acquisition module, wherein the working data includes: static data and dynamic data of the CNC machine tool during operation;
S102、识别所述数控机床，并从模型库中查询所述数控机床对应的数字孪生模型；S102, identifying the CNC machine tool, and querying a digital twin model corresponding to the CNC machine tool from a model library;
S103、将所述工作数据导入所述数控机床对应的数字孪生模型后，确定所述数控机床的运动行为，所述运动行为包括所述数控机床在工作过程中的缩放、平移和旋转动作；S103, after importing the working data into the digital twin model corresponding to the CNC machine tool, determining the motion behavior of the CNC machine tool, the motion behavior including the scaling, translation and rotation actions of the CNC machine tool during the working process;
S104、利用103中确定的运动行为，分析数控机床的工作状态的异常，并生成故障分析报告。S104, using the motion behavior determined in 103, analyzing the abnormality of the working state of the CNC machine tool and generating a fault analysis report.
第二方面，本发明的实施例提供的系统，包括：传感器数据采集模块、数字孪生模型构建模块、数据处理及故障诊断模块、数据传输模块和远程人机交互模块。In the second aspect, the system provided by an embodiment of the present invention includes: a sensor data acquisition module, a digital twin model construction module, a data processing and fault diagnosis module, a data transmission module and a remote human-computer interaction module.
所述传感器数据采集模块，用于采集数控机床的工作数据，所述工作数据包括：数控机床在工作期间的静态数据和动态数据；The sensor data acquisition module is used to collect the working data of the CNC machine tool, and the working data includes: static data and dynamic data of the CNC machine tool during operation;
所述数据传输模块，用于将采集到的数控机床的工作数据上传；The data transmission module is used to upload the collected working data of the CNC machine tool;
所述数字孪生构建模块，用于识别所述数控机床，并从模型库中查询所述数控机床对应的数字孪生模型；或者，根据采集的实时运行数据和预先存储的历史数据构建数控机床的数字孪生模型；The digital twin construction module is used to identify the CNC machine tool and query the digital twin model corresponding to the CNC machine tool from the model library; or, to construct the digital twin model of the CNC machine tool based on the collected real-time operation data and pre-stored historical data;
所述数据处理及故障诊断模块，用于将所述工作数据导入所述数控机床对应的数字孪生模型后，确定所述数控机床的运动行为，所述运动行为包括所述数控机床在工作过程中的缩放、平移和旋转动作；The data processing and fault diagnosis module is used to determine the motion behavior of the CNC machine tool after importing the working data into the digital twin model corresponding to the CNC machine tool, and the motion behavior includes the scaling, translation and rotation actions of the CNC machine tool during the working process;
所述远程人机交互模块，用于向人员的个人终端远程提供人机交互界面，交互界面中显示故障报警信息和诊断结果。The remote human-computer interaction module is used to remotely provide a human-computer interaction interface to a personal terminal of a person, and the fault alarm information and diagnosis results are displayed in the interaction interface.
本发明实施例提供的基于数字孪生的数控机床远程故障诊断方法及系统，数据传输模块，机床运行信息数据库中的信息通过串口输入传输层的NB-IoT模块，NB-IoT无线通信网络传输给NB-IoT云平台；数字孪生模型构建模块，根据云平台采集的实时运行数据和历史数据构建数控机床数字孪生模型；数据处理及故障诊断模块，采用事件检测的方式对数控机床进行故障诊断，分析数控机床的运行状态，并根据状态数据库中的属性数据进行对比分析，生成故障诊断报告；远程人机交互界面可收到报警并获取诊断结果。其中采用数字孪生技术对数控机床行为进行实时监控，对其性能进行精确预测，达到全生命周期的映射效果，同时在此基础上将数控机床故障诊断技术与无线通信技术相结合，实现对数控机床的故障的实时远程诊断，以便于提高机床远程故障诊断的智能化程度和检测效率。The embodiment of the present invention provides a remote fault diagnosis method and system for CNC machine tools based on digital twins, a data transmission module, the information in the machine tool operation information database is input into the NB-IoT module of the transmission layer through the serial port, and the NB-IoT wireless communication network is transmitted to the NB-IoT cloud platform; a digital twin model construction module, which constructs a digital twin model of the CNC machine tool according to the real-time operation data and historical data collected by the cloud platform; a data processing and fault diagnosis module, which uses event detection to diagnose faults of the CNC machine tool, analyzes the operation status of the CNC machine tool, and compares and analyzes the attribute data in the status database to generate a fault diagnosis report; the remote human-computer interaction interface can receive alarms and obtain diagnosis results. Among them, digital twin technology is used to monitor the behavior of the CNC machine tool in real time, accurately predict its performance, and achieve a mapping effect for the entire life cycle. At the same time, on this basis, the CNC machine tool fault diagnosis technology is combined with the wireless communication technology to realize real-time remote diagnosis of the faults of the CNC machine tool, so as to improve the intelligence level and detection efficiency of the remote fault diagnosis of the machine tool.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
图1为本发明实施例提供的基于数字孪生的数控机床远程故障诊断系统的总体架构示意图；FIG1 is a schematic diagram of the overall architecture of a remote fault diagnosis system for CNC machine tools based on digital twins provided by an embodiment of the present invention;
图2为本发明实施例提供的模型变换原理示意图；FIG2 is a schematic diagram of a model transformation principle provided by an embodiment of the present invention;
图3是事件检测的状态检测流程示意图。FIG. 3 is a schematic diagram of a state detection process of event detection.
图4为本发明实施例提供的方法流程示意图。FIG4 is a schematic diagram of a method flow chart provided by an embodiment of the present invention.
具体实施方式DETAILED DESCRIPTION
为使本领域技术人员更好地理解本发明的技术方案，下面结合附图和具体实施方式对本发明作进一步详细描述。下文中将详细描述本发明的实施方式，所述实施方式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方式是示例性的，仅用于解释本发明，而不能解释为对本发明的限制。本技术领域技术人员可以理解，除非特意声明，这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是，本发明的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件，但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元件、组件和/或它们的组。应该理解，当我们称元件被“连接”或“耦接”到另一元件时，它可以直接连接或耦接到其他元件，或者也可以存在中间元件。此外，这里使用的“连接”或“耦接”可以包括无线连接或耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的任一单元和全部组合。本技术领域技术人员可以理解，除非另外定义，这里使用的所有术语(包括技术术语和科学术语)具有与本发明所属领域中的普通技术人员的一般理解相同的意义。还应该理解的是，诸如通用字典中定义的那些术语应该被理解为具有与现有技术的上下文中的意义一致的意义，并且除非像这里一样定义，不会用理想化或过于正式的含义来解释。In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention will be described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention. It can be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "one", "said" and "the" used herein may also include plural forms. It should be further understood that the term "including" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used here may include wireless connection or coupling. The term "and/or" used herein includes any unit and all combinations of one or more associated listed items. It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as generally understood by those of ordinary skill in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.
本发明实施例提供一种基于数字孪生的数控机床远程故障诊断方法，如图4所示，包括：The embodiment of the present invention provides a remote fault diagnosis method for a CNC machine tool based on digital twin, as shown in FIG4 , comprising:
S101、接受从传感器数据采集模块获取数控机床的工作数据。S101, receiving the working data of the CNC machine tool from the sensor data acquisition module.
其中，所述工作数据包括：数控机床在工作期间的静态数据和动态数据；Wherein, the working data includes: static data and dynamic data of the CNC machine tool during operation;
S102、识别所述数控机床，并从模型库中查询所述数控机床对应的数字孪生模型；S102, identifying the CNC machine tool, and querying a digital twin model corresponding to the CNC machine tool from a model library;
S103、将所述工作数据导入所述数控机床对应的数字孪生模型后，确定所述数控机床的运动行为，从而具备对物理机床全生命周期的映射能力，增加物理机床的检测维度。S103. After importing the working data into the digital twin model corresponding to the CNC machine tool, the motion behavior of the CNC machine tool is determined, thereby having the ability to map the entire life cycle of the physical machine tool and increasing the detection dimension of the physical machine tool.
其中，所述运动行为包括所述数控机床在工作过程中的缩放、平移和旋转动作；Wherein, the motion behavior includes the scaling, translation and rotation actions of the CNC machine tool during operation;
S104、利用103中确定的运动行为，分析数控机床的工作状态的异常，并生成故障分析报告。S104, using the motion behavior determined in 103, analyzing the abnormality of the working state of the CNC machine tool and generating a fault analysis report.
本实施例中，在S103中，所述确定所述数控机床的数字孪生模型中的运动行为，包括：In this embodiment, in S103, determining the motion behavior in the digital twin model of the CNC machine tool includes:
S1031，建立所述数控机床的数字孪生模型中的基础运动模型，包括：缩放模型、平移模型和旋转模型；其中，将数控机床实体运动产生的所有实时数据进行收集，并传输到加载并运行了数字孪生模型的虚拟系统(比如目前市面上已有的仿真平台)中，处理完数据后使用这些实时数据驱动虚拟实体执行相应动作，完成数控机床实体到虚拟的实时映射，通过对基础运动的组合，实现数控机床所有运行动作的仿真，完成行为模型的构建。数控机床的孪生模型的基础运动主要为缩放、平移和旋转。S1031, establish the basic motion model in the digital twin model of the CNC machine tool, including: scaling model, translation model and rotation model; wherein, all real-time data generated by the physical motion of the CNC machine tool are collected and transmitted to the virtual system (such as the simulation platform currently available on the market) that loads and runs the digital twin model, and after processing the data, use these real-time data to drive the virtual entity to perform corresponding actions, complete the real-time mapping of the CNC machine tool entity to the virtual, and through the combination of basic motions, realize the simulation of all running actions of the CNC machine tool and complete the construction of the behavior model. The basic motions of the twin model of the CNC machine tool are mainly scaling, translation and rotation.
S1032，根据所述基础运动模型，建立所述运动行为模型；对于任意向量(x，y，z)，绕任意方向向量(Rx，Ry，Rz)旋转角度，平移向量表示为(Tx，Ty，Tz)，缩放向量为(S1，S2，S3)。根据缩放、旋转、再平移的原则，建立运动行为模型，其中包括了物体的运动变换矩阵。S1032, establishing the motion behavior model according to the basic motion model; for any vector (x, y, z), rotating around any direction vector (Rx , Ry , Rz ) Angle, translation vector is represented as (Tx ,Ty ,Tz ), scaling vector is (S1 ,S2 ,S3 ). According to the principle of scaling, rotation and then translation, the motion behavior model is established, which includes the motion transformation matrix of the object.
S1033，通过所述运动行为模型，进一步确定所述数控机床的三轴位移情况。S1033: further determining the three-axis displacement of the CNC machine tool through the motion behavior model.
具体的，S1031，包括：Specifically, S1031 includes:
其中，所述缩放模型用于表示向量(x，y，z)的缩放变换，为：其中，(Sx，Sy，Sz)为缩放变量，Sx、Sy、Sz分别表示模型在X、Y、Z轴的缩放因子的大小；The scaling model is used to represent the scaling transformation of the vector (x, y, z), which is: Among them, (Sx ,Sy , Sz ) are scaling variables, Sx ,Sy , Sz represent the size of the scaling factor of the model in the X, Y, and Z axes respectively;
所述平移模型用于表示向量平移向量(Tx，Ty，Tz)的平移变换，为：其中，Tx、Ty、Tz分别表示模型在X、Y、Z轴的平移距离；The translation model is used to represent the translation transformation of a vector translation vector (Tx ,Ty , Tz ), which is: Among them, Tx ,Ty , and Tz represent the translation distance of the model on the X, Y, and Z axes respectively;
所述旋转模型用于表示向量(x，y，z)绕方向向量(Rx，Ry，Rz)旋转角度为：The rotation model is used to represent the rotation angle of a vector (x, y, z) around a direction vector (Rx , Ry , Rz ) for:
Rx、Ry、Rz表示方向向量在xyz轴的坐标值。 Rx , Ry , and Rz represent the coordinate values of the direction vector on the xyz axis.
对于任意向量(x，y，z)，绕任意方向向量(Rx，Ry，Rz)旋转角度，平移向量表示为(Tx，Ty，Tz)，缩放向量为(S1，S2，S3)。根据缩放、旋转、再平移的原则，建立运动行为模型，其中包括了物体的运动变换矩阵为：For any vector (x, y, z), rotate around any direction vector (Rx ,Ry ,Rz ) Angle, translation vector is represented as (Tx ,Ty ,Tz ), and scaling vector is (S1 ,S2 ,S3 ). According to the principle of scaling, rotation, and then translation, a motion behavior model is established, which includes the motion transformation matrix of the object:
进一步的，S1033，包括：建立所述数控机床的在X轴、Y轴和Z轴的运动矩阵，分别位Mx、My、Mz；Further, S1033 includes: establishing motion matrices of the CNC machine tool on the X-axis, Y-axis and Z-axis, which are Mx ,My , and Mz respectively;
其中，机床X轴相对自身坐标系距离为x0，X轴只有相对机床坐标系的平移，则X轴的位移矩阵Mx求解如下：Among them, the distance between the X axis of the machine tool and its own coordinate system is x0 , and the X axis only has a translation relative to the machine tool coordinate system. The displacement matrix Mx of the X axis is solved as follows:
Y轴相对机床局部坐标系初始坐标为y0，Y轴只有相对机床坐标系的平移，同理，机床Y轴的运动矩阵My为：The initial coordinate of the Y axis relative to the local coordinate system of the machine tool is y0 , and the Y axis only has a translation relative to the machine tool coordinate system. Similarly, the motion matrixMy of the Y axis of the machine tool is:
Z轴的运动由Y轴的移动与Z轴相对机床坐标系的平移组合而成，运动的组合由矩阵的相乘表示。Z轴相对机床局部坐标系初始坐标为z0，其平移矩阵为Mtz，机床Z轴的运动矩阵Mz为：其中，x0、y0、z0分别为：所述数控机床的X轴相对自身坐标系距离、Y轴相对机床局部坐标系初始坐标、Z轴相对机床局部坐标系初始坐标。The motion of the Z axis is a combination of the movement of the Y axis and the translation of the Z axis relative to the machine tool coordinate system. The combination of motion is represented by matrix multiplication. The initial coordinate of the Z axis relative to the local coordinate system of the machine tool is z0 , and its translation matrix is Mtz . The motion matrix Mz of the machine tool Z axis is: Wherein, x0 , y0 , and z0 are respectively: the distance of the X axis of the CNC machine tool relative to its own coordinate system, the initial coordinate of the Y axis relative to the local coordinate system of the machine tool, and the initial coordinate of the Z axis relative to the local coordinate system of the machine tool.
本实施例中，在S104中，所述分析数控机床的工作状态是否异常，包括：通过事件检测对所述数控机床进行故障诊断，其中，所述数控机床状态通过有限集合表示，为G＝(S，∑，δ，s0)，其中S表示有限的且非空状态集，S＝{s0，s1，······，sm}，s0表示初始状态，s1～sm表示机床后续可能出现的第1至m种状态，；Σ可能发生的所有类型的生产事件的集合，Σ＝{E0，E0，······，En}，E0表示当前发生的事件，E1～En表示机床后续可能出现的第1至n种事件；δ为状态变换函数，用于处理生产事件，表示为δ：σ(S)→S',m、n作为为数字下标，具体为正整数，S’表示处理状态变换后的事件。In this embodiment, in S104, analyzing whether the working state of the CNC machine tool is abnormal includes: performing fault diagnosis on the CNC machine tool through event detection, wherein the state of the CNC machine tool is represented by a finite set, which is G=(S, ∑, δ, s0 ), wherein S represents a finite and non-empty state set, S={s0 , s1 , ······, sm }, s0 represents an initial state, s1 to sm represent the first to m states that may appear in the machine tool subsequently; Σ is a set of all types of production events that may occur, Σ={E0 , E0 , ······,En }, E0 represents a current event, E1 toEn represent the first to n events that may appear in the machine tool subsequently; δ is a state transformation function used to process production events, expressed as δ: σ(S)→S', m and n are digital subscripts, specifically positive integers, and S' represents an event after the processing state transformation.
“生产事件”反映了一个对象的状态转换，可以描述如下E＝{＜si，si+1＞，O，A，T，C}，E表示数控机床运行过程中发生的事件；＜si，si+1＞表示对象的状态从si转换为si+1；O表示事件源；A是产生触发条件的属性的集合，A＝{A0，A1，······，An}，A1～An表示第1至n类触发条件；T为生产事件发生时间，可以是以一个时间点(即T＝t0)或一段时间间隔(即T＝[t0，t1])，C是事件发生条件的有限集合；“Production event” reflects the state transition of an object, which can be described as follows: E={＜si , si+1 >, O, A, T, C}, where E represents the event occurring during the operation of the CNC machine tool; ＜si , si+1 > represents the state transition of the object from si to si+1 ; O represents the event source; A is the set of attributes that generate trigger conditions, A={A0 , A1 , ······,An }, A1 ~An represent the first to nth types of trigger conditions; T is the time when the production event occurs, which can be a time point (i.e., T=t0 ) or a time interval (i.e., T=[t0 , t1 ]), and C is a finite set of event occurrence conditions;
C的约束条件包括：其中，ci是第i个条件，用属性Ai表示部分约束关系；fi()是属性Ai的运算函数，例如某一时间点的瞬时值(传感器值)或某一时间间隔内的统计特性(平均值、最大值、最小值)；表示关系运算符，即α是数值常数，表示属性的某一阈值；表示关系运算符，即触发条件可以通过一个确定单属性(由某一传感器检测到)和多属性(由多个传感器检测到)构成，当属性值满足预定义条件时，事件发生。The constraints on C include: Where,ci is the i-th condition, and attributeAi is used to represent the partial constraint relationship;fi () is the operation function of attributeAi , such as the instantaneous value (sensor value) at a certain time point or the statistical characteristics (average value, maximum value, minimum value) within a certain time interval; represents a relational operator, i.e. α is a numerical constant, representing a certain threshold of the attribute; represents a relational operator, i.e. The trigger condition can be composed of a certain single attribute (detected by a certain sensor) and multiple attributes (detected by multiple sensors). When the attribute value meets the predefined conditions, the event occurs.
所述数据处理及故障诊断模块，在数控机床加工过程中可以接收到多项数据，用于与所述正常运行状态数据库和报警信息及状态数据库中的属性数据A进行比对，对其中关键的数据作进一步的分析，包括根据属性，如速度、电流、温度等指标判断机床的关键部件O，如主轴、进给轴等是否运行正常，对数控机床运行状态进行预警分析生成预警结果。例如：所述分析数控机床的工作状态是否异常为：分析数控机床的工作状态是否异常，主轴状态模型包括：The data processing and fault diagnosis module can receive multiple data during the CNC machine tool processing process, which are used to compare with the attribute data A in the normal operating status database and the alarm information and status database, and further analyze the key data, including judging whether the key components O of the machine tool, such as the spindle and feed axis, are operating normally according to attributes such as speed, current, temperature and other indicators, and performing early warning analysis on the operating status of the CNC machine tool to generate early warning results. For example: the analysis of whether the working status of the CNC machine tool is abnormal is: analyzing whether the working status of the CNC machine tool is abnormal, and the spindle status model includes:
G主轴＝(S主轴，Σ主轴，δ主轴，s0)，其中，S主轴＝{s0＝静止，s1＝空转，s2＝加工，s3＝故障}，Σ主轴＝{E0＝s0→s1，E1＝s0→s3，E2＝s1→s0，E3＝s1→s2，E4＝s1→s3，E5＝s2→s1，E6＝s2→s3，E7＝s3→s0}，δ主轴＝S主轴×Σ主轴→S'主轴。Gspindle = (Sspindle ,Σspindle ,δspindle , s0 ), whereSspindle = {s0 = stationary, s1 = idling, s2 = machining, s3 = fault},Σspindle = {E0 = s0 →s1 , E1 = s0 →s3 , E2 = s1 →s0 , E3 = s1 →s2 , E4 = s1 →s3 , E5 = s2 →s1 , E6 = s2 →s3 , E7 = s3 →s0 },δspindle =Sspindle ×Σspindle →S'spindle .
对象O＝{主轴}；属性值A＝{转速，电流，温度}，事件及其相应的触发条件的对应关系包括：Object O = {spindle}; attribute value A = {speed, current, temperature}, the corresponding relationship between events and their corresponding trigger conditions includes:
(1)E0＝{＜s0，s1＞，主轴，转速/电流，t0，C0}，C0＝c1∧c4；(1) E0 ={＜s0 ,s1 ＞,spindle,speed/current,t0 ,C0 },C0 =c1 ∧c4 ;
(2)E1＝{＜s0，s3＞，主轴，转速/电流/温度，t1，C1}，C1＝c2∧c6∧c8；(2) E1 ={＜s0 , s3 ＞, spindle, speed/current/temperature, t1 , C1 }, C1 =c2 ∧c6 ∧c8 ;
(3)E2＝{＜s1，s0＞，主轴，转速/电流，t2，C2}，C2＝c0∧c3；(3) E2 ={＜s1 , s0 ＞, spindle, speed/current, t2 , C2 }, C2 =c0 ∧c3 ;
(4)E3＝{＜s1，s2＞，主轴，转速/电流/温度，t3，C3}，C3＝c1∧c5∧c7；(4) E3 ={＜s1 , s2 ＞, spindle, speed/current/temperature, t3 , C3 }, C3 =c1 ∧c5 ∧c7 ;
(5)E4＝{＜s1，s3＞，主轴，转速/电流/温度，t4，C4}，C4＝c2∧c6∧c8；(5) E4 ={＜s1 , s3 ＞, spindle, speed/current/temperature, t4 , C4 }, C4 =c2 ∧c6 ∧c8 ;
(6)E5＝{＜s2，s1＞，主轴，转速/电流/温度，t5，C5}，C5＝c1∧c4∧c7；(6) E5 ={＜s2 , s1 ＞, spindle, speed/current/temperature, t5 , C5 }, C5 =c1 ∧c4 ∧c7 ;
(7)E6＝{＜s2，s3＞，主轴，转速/电流/温度，t6，C6}，C2＝c1∧c3∧c6∧c8；(7) E6 ={＜s2 ,s3 ＞,spindle,speed/current/temperature,t6 ,C6 },C2 =c1 ∧c3 ∧c6 ∧c8 ;
(8)E7＝{＜s3，s0＞，主轴，转速/电流/温度，t7，C7}，C2＝c0^c3^c7；(8) E7 ={＜s3 , s0 ＞, spindle, speed/current/temperature, t7 , C7 }, C2 =c0 ^c3 ^c7 ;
触发条件包括：Trigger conditions include:
(1)c0＝转速平均值为零；(1) c0 = the average speed is zero;
(2)c1＝0＜转速平均值≤α；(2) c1 = 0 < average speed ≤ α;
(3)c2＝转速平均值＞α；(3) c2 = average speed >α;
(4)c3＝电流平均值为零；(4) c3 = average current is zero;
(5)c4＝0＜电流平均值≤β0；(5) c4 =0＜current average value≤β0 ;
(6)c5＝β0＜电流平均值≤β1；(6) c5 = β0 < average current value ≤β 1 ;
(7)c6＝电流平均值＞β1；(7) c6 = average current value > β1 ;
(8)c7＝温度平均值≤γ；(8) c7 = average temperature ≤ γ;
(9)c8＝温度平均值＞γ。(9) c8 =average value of temperature>γ.
本实施例中，在S104中，所述生成故障分析报告，包括：将异常状态数据与历史运行数据中发生过的故障的特征数据进行匹配；In this embodiment, in S104, generating a fault analysis report includes: matching the abnormal state data with characteristic data of faults that have occurred in the historical operation data;
根据匹配结果生成故障分析报告，所述故障分析报告包括：所述数控机床当前发生的故障类型，和，所述数控机床当前发生的故障的排障历史数据。A fault analysis report is generated according to the matching result, wherein the fault analysis report includes: the type of fault currently occurring in the CNC machine tool, and historical troubleshooting data of the fault currently occurring in the CNC machine tool.
传感器数据采集模块，包括部署在所述数控机床所在车间的传感器组，其中传感器的类型包括：图像采集模块、位置传感器、速度传感器、加速度传感器、温度传感器、压力传感器、功率传感器和振动传感器。所述多传感器数据采集模块采集数控机床静态数据信息和动态数据信息，其中静态数据信息包括：数控机床结构、几何尺寸、物理属性、工作性能和机床型号；动态数据信息包括：实时速度、实时加速度、温度信息、振动信息、噪声信息和加载力信息。The sensor data acquisition module includes a sensor group deployed in the workshop where the CNC machine tool is located, wherein the types of sensors include: image acquisition module, position sensor, speed sensor, acceleration sensor, temperature sensor, pressure sensor, power sensor and vibration sensor. The multi-sensor data acquisition module collects static data information and dynamic data information of the CNC machine tool, wherein the static data information includes: CNC machine tool structure, geometric dimensions, physical properties, working performance and machine tool model; the dynamic data information includes: real-time speed, real-time acceleration, temperature information, vibration information, noise information and loading force information.
本实施例还提供一种基于数字孪生的数控机床远程故障诊断系统，包括：传感器数据采集模块、数字孪生模型构建模块、数据处理及故障诊断模块、数据传输模块和远程人机交互模块。This embodiment also provides a remote fault diagnosis system for CNC machine tools based on digital twins, including: a sensor data acquisition module, a digital twin model construction module, a data processing and fault diagnosis module, a data transmission module and a remote human-computer interaction module.
所述传感器数据采集模块，用于采集数控机床的工作数据，所述工作数据包括：数控机床在工作期间的静态数据和动态数据；The sensor data acquisition module is used to collect the working data of the CNC machine tool, and the working data includes: static data and dynamic data of the CNC machine tool during operation;
所述数据传输模块，用于将采集到的数控机床的工作数据上传；The data transmission module is used to upload the collected working data of the CNC machine tool;
所述数字孪生构建模块，用于识别所述数控机床，并从模型库中查询所述数控机床对应的数字孪生模型；或者，根据采集的实时运行数据和预先存储的历史数据构建数控机床的数字孪生模型；The digital twin construction module is used to identify the CNC machine tool and query the digital twin model corresponding to the CNC machine tool from the model library; or, to construct the digital twin model of the CNC machine tool based on the collected real-time operation data and pre-stored historical data;
所述数据处理及故障诊断模块，用于将所述工作数据导入所述数控机床对应的数字孪生模型后，确定所述数控机床的运动行为，所述运动行为包括所述数控机床在工作过程中的缩放、平移和旋转动作；例如：分析所述实时工作数据，得到数控机床的异常状态，将异常状态与所述历史运行数据中的故障特征数据相匹配，生成故障分析报告。The data processing and fault diagnosis module is used to import the working data into the digital twin model corresponding to the CNC machine tool, and then determine the movement behavior of the CNC machine tool, where the movement behavior includes the scaling, translation and rotation movements of the CNC machine tool during the working process; for example: analyze the real-time working data to obtain the abnormal state of the CNC machine tool, match the abnormal state with the fault feature data in the historical operation data, and generate a fault analysis report.
所述远程人机交互模块，用于向人员的个人终端远程提供人机交互界面，交互界面中显示故障报警信息和诊断结果。The remote human-computer interaction module is used to remotely provide a human-computer interaction interface to a personal terminal of a person, and the fault alarm information and diagnosis results are displayed in the interaction interface.
将所述数控机床的工作数据上传至IoT云平台，其中，所述IoT云平台提供API接口，客户端通过所述API接口与所述IoT云平台建立连接；IoT云平台用于维护实时运行数据，和预先存储历史数据。其中，IoT云平台具有数据接收和存储能力，满足机床大数据量存储需求。云平台提供了丰富的API接口供客户端调用。调用API接口，远程客户端可以简单快速地完成与云平台的对接，NB-IoT模块将数据上传至IoT云平台。The working data of the CNC machine tool is uploaded to the IoT cloud platform, wherein the IoT cloud platform provides an API interface, and the client establishes a connection with the IoT cloud platform through the API interface; the IoT cloud platform is used to maintain real-time operation data and pre-store historical data. Among them, the IoT cloud platform has the ability to receive and store data to meet the large data storage requirements of machine tools. The cloud platform provides a rich API interface for the client to call. By calling the API interface, the remote client can easily and quickly complete the docking with the cloud platform, and the NB-IoT module uploads the data to the IoT cloud platform.
实际应用中，传感器数据采集模块与数控机床实体相连，用于采集数控机床生产期间的实时工作数据，输入所述数据传输模块，数据传输模块将所采集的数据通过NB-IoT模块将数据上传至IoT云平台，IoT云平台提供API接口，客户端通过API接口与云平台对接，通过实时数据与历史数据构建数控机床数字孪生模型，数据处理及故障诊断模块分析工作数据，得到数控机床的异常状态，将异常状态与所述历史运行数据中的故障特征数据相匹配，生成故障分析报告，远程人机交互可向云平台请求读取诊断结果，实现远程故障诊断。In actual applications, the sensor data acquisition module is connected to the CNC machine tool entity to collect real-time working data during the production of the CNC machine tool and input the data into the data transmission module. The data transmission module uploads the collected data to the IoT cloud platform through the NB-IoT module. The IoT cloud platform provides an API interface. The client connects to the cloud platform through the API interface, and builds a digital twin model of the CNC machine tool through real-time data and historical data. The data processing and fault diagnosis module analyzes the working data to obtain the abnormal state of the CNC machine tool, matches the abnormal state with the fault feature data in the historical operation data, and generates a fault analysis report. Remote human-computer interaction can request the cloud platform to read the diagnosis results to achieve remote fault diagnosis.
在一种可能的应用方式中，可以根据云平台采集的实时运行数据和历史数据构建数控机床数字孪生模型；所述数字孪生模型构建模块，将读取到的数据进行预处理，去除数据异常值、噪声等，根据预处理后的数据和数控机床工作原理及运动学方程，建立动态数学模型，使用历史数据对建立的数学模型进行训练，将数据集分为训练集和验证集，使用训练集对模型进行训练，使用验证集评估模型的性能。对模型进行参数调整和优化，以提高模型的准确性和泛化能力。模型训练完成后，将训练好的模型部署在实际数控机床上，与实时数据进行对比，根据对比结果，对模型更新与优化，最终实现准确的孪生模型。In one possible application, a digital twin model of a CNC machine tool can be constructed based on the real-time operation data and historical data collected by the cloud platform; the digital twin model construction module preprocesses the read data to remove data outliers, noise, etc., and establishes a dynamic mathematical model based on the preprocessed data and the working principle and kinematic equation of the CNC machine tool. The established mathematical model is trained using historical data, and the data set is divided into a training set and a validation set. The model is trained using the training set, and the performance of the model is evaluated using the validation set. The model parameters are adjusted and optimized to improve the accuracy and generalization ability of the model. After the model training is completed, the trained model is deployed on the actual CNC machine tool and compared with the real-time data. According to the comparison results, the model is updated and optimized to finally achieve an accurate twin model.
具体举例来说，应用实例在实际应用中，可以参阅图1所示的总体架构，传感器数据采集模块与数控机床实体相连，用于采集数控机床生产期间的实时工作数据，输入所述数据传输模块，数据传输模块将所采集的数据通过NB-IoT模块将数据上传至IoT云平台，云平台提供API接口，远程客户端通过API接口与云平台对接，通过实时数据与历史数据构建数控机床数字孪生模型，数据处理及故障诊断模块分析工作数据，得到数控机床的异常状态，将异常状态与所述历史运行数据中的故障特征数据相匹配，生成故障分析报告，远程人机交互可向云平台请求读取诊断结果，实现远程故障诊断。For example, in actual applications, the overall architecture shown in Figure 1 can be referred to. The sensor data acquisition module is connected to the CNC machine tool entity to collect real-time working data during the production of the CNC machine tool and input the data into the data transmission module. The data transmission module uploads the collected data to the IoT cloud platform through the NB-IoT module. The cloud platform provides an API interface. The remote client connects to the cloud platform through the API interface. The digital twin model of the CNC machine tool is constructed through real-time data and historical data. The data processing and fault diagnosis module analyzes the working data to obtain the abnormal state of the CNC machine tool, matches the abnormal state with the fault feature data in the historical operation data, and generates a fault analysis report. The remote human-computer interaction can request the cloud platform to read the diagnosis results to achieve remote fault diagnosis.
在应用实例中，传感器数据采集模块包括的图像采集模块、位置传感器、速度传感器、加速度传感器、温度传感器、压力传感器、功率传感器和振动传感器等。In the application example, the sensor data acquisition module includes an image acquisition module, a position sensor, a velocity sensor, an acceleration sensor, a temperature sensor, a pressure sensor, a power sensor, a vibration sensor, etc.
在应用实例中，多传感器数据采集模块采集数控机床静态数据信息和动态数据信息，其中静态数据信息包括：数控机床结构、几何尺寸、物理属性、工作性能、机床型号等；动态数据信息包括：实时速度、实时加速度、温度信息、振动信息、噪声信息以及加载力信息等。In the application example, the multi-sensor data acquisition module collects static data information and dynamic data information of the CNC machine tool, where the static data information includes: CNC machine tool structure, geometric dimensions, physical properties, working performance, machine tool model, etc.; the dynamic data information includes: real-time speed, real-time acceleration, temperature information, vibration information, noise information and loading force information, etc.
数据传输模块将多传感器采集数据通过NB-IoT模块将数据上传至IoT云平台。IoT云平台具有数据接收和存储能力，满足机床大数据量存储需求。云平台提供了丰富的API接口供客户端调用。通过调用API接口，客户端可以简单快速地完成与云平台的对接。The data transmission module uploads the multi-sensor collected data to the IoT cloud platform through the NB-IoT module. The IoT cloud platform has the ability to receive and store data, meeting the large data storage requirements of machine tools. The cloud platform provides a rich API interface for the client to call. By calling the API interface, the client can easily and quickly complete the connection with the cloud platform.
在应用实例中，所述云平台，选用中国移动物联网有限公司为NB-IoT开发者提供的OneNET物联网云平台。In the application example, the cloud platform uses the OneNET Internet of Things cloud platform provided by China Mobile Internet of Things Co., Ltd. for NB-IoT developers.
数字孪生模型构建模块获取云平台的数据进行预处理，去除数据异常值、噪声等，根据预处理后的数据和数控机床工作原理及运动学方程，建立动态数学模型，使用历史数据对建立的数学模型进行训练，将数据集分为训练集和验证集，使用训练集对模型进行训练，使用验证集评估模型的性能。对模型进行参数调整和优化，以提高模型的准确性和泛化能力。模型训练完成后，将训练好的模型部署在实际数控机床上，与实时数据进行对比，根据对比结果，对模型更新与优化，最终实现准确的孪生模型。The digital twin model building module obtains data from the cloud platform for preprocessing, removes data outliers and noise, etc., and builds a dynamic mathematical model based on the preprocessed data and the working principle and kinematic equations of the CNC machine tool. The established mathematical model is trained using historical data, and the data set is divided into a training set and a validation set. The model is trained using the training set, and the performance of the model is evaluated using the validation set. The model parameters are adjusted and optimized to improve the accuracy and generalization ability of the model. After the model training is completed, the trained model is deployed on the actual CNC machine tool and compared with the real-time data. Based on the comparison results, the model is updated and optimized to finally achieve an accurate twin model.
将数控机床实体运动产生的所有实时数据进行收集，并传输到虚拟系统中，系统处理完数据后使用这些实时数据驱动虚拟实体执行相应动作，完成数控机床实体到虚拟的实时映射，通过对基础运动的组合，实现数控机床所有运行动作的仿真，完成行为模型的构建。All real-time data generated by the physical movement of the CNC machine tool are collected and transmitted to the virtual system. After processing the data, the system uses these real-time data to drive the virtual entity to perform corresponding actions, completing the real-time mapping of the CNC machine tool entity to the virtual. Through the combination of basic movements, the simulation of all operating actions of the CNC machine tool is realized, and the construction of the behavior model is completed.
在应用实例中，参阅图2模型变换原理图，数控机床的孪生模型的基础运动主要为缩放、平移和旋转。将缩放变量表示为(S1，S2，S3)，对于任意向量(x，y，z)其缩放变换为：In the application example, referring to the model transformation principle diagram in Figure 2, the basic movements of the twin model of the CNC machine tool are mainly scaling, translation and rotation. The scaling variable is represented as (S1 , S2 , S3 ), and for any vector (x, y, z) its scaling transformation is:
将平移变量表示为(S1，S2，S3)，对于任意向量(Tx，Ty，Tz)其缩放变换为：The translation variable is represented as (S1 , S2 , S3 ), and for any vector (Tx ,Ty , Tz ) its scaling transformation is:
对于向量(x，y，z)绕任意方向向量(Rx，Ry，Rz)旋转角度：Rotate a vector (x, y, z) around an arbitrary direction vector (Rx , Ry , Rz ) angle:
对于任意向量(x，y，z)，绕任意方向向量(Rx，Ry，Rz)旋转角度，平移向量表示为(Tx，Ty，Tz)，缩放向量为(S1，S2，S3)。根据缩放、旋转、再平移的原则，则此物体的运动变换矩阵为：For any vector (x, y, z), rotate around any direction vector (Rx ,Ry ,Rz ) The angle, translation vector is represented as (Tx ,Ty , Tz ), and the scaling vector is (S1 , S2 , S3 ). According to the principle of scaling, rotating, and then translating, the motion transformation matrix of this object is:
机床X轴相对自身坐标系距离为x0，X轴只有相对机床坐标系的平移，则X轴的位移矩阵Mx求解如下：The distance between the X-axis of the machine tool and its own coordinate system is x0 . The X-axis only has a translation relative to the machine tool coordinate system. The displacement matrix Mx of the X-axis is solved as follows:
Y轴相对机床局部坐标系初始坐标为y0，Y轴只有相对机床坐标系的平移，同理，机床Y轴的运动矩阵My为：The initial coordinate of the Y axis relative to the local coordinate system of the machine tool is y0 , and the Y axis only has a translation relative to the machine tool coordinate system. Similarly, the motion matrixMy of the Y axis of the machine tool is:
Z轴的运动由Y轴的移动与Z轴相对机床坐标系的平移组合而成，运动的组合由矩阵的相乘表示。Z轴相对机床局部坐标系初始坐标为z0，其平移矩阵为Mtz，机床Z轴的运动矩阵Mz为：The motion of the Z axis is a combination of the movement of the Y axis and the translation of the Z axis relative to the machine tool coordinate system. The combination of motion is represented by matrix multiplication. The initial coordinate of the Z axis relative to the local coordinate system of the machine tool is z0 , and its translation matrix is Mtz . The motion matrix Mz of the machine tool Z axis is:
应用实例中，所述数据处理及故障诊断模块采用事件检测的方式对数控机床进行故障诊断，分析数控机床的运行状态。数控机床状态可以由有限集合表示，具体模型如下：In the application example, the data processing and fault diagnosis module uses event detection to diagnose the faults of CNC machine tools and analyze the operating status of CNC machine tools. The status of CNC machine tools can be represented by a finite set, and the specific model is as follows:
G＝(S，∑，δ，s0) (8)G＝(S，∑，δ，s0 ) (8)
其中S表示有限的、非空状态集，即S＝{s0，s1，······，sm}；∑为可能发生的“事件”的集合，即∑＝{E0，E0，······，En}；δ是状态变换函数，用于处理事件，δ：σ(S)→S'；s0表示初始状态，s0∈S。这里的“事件”指生产事件，反映了一个对象的状态转换，可以描述如下：Where S represents a finite, non-empty state set, i.e., S = {s0 , s1 , ······, sm }; ∑ is a set of possible "events", i.e., ∑ = {E0 , E0 , ······,En }; δ is a state transformation function used to process events, δ: σ(S)→S'; s0 represents the initial state, s0 ∈S. The "event" here refers to a production event, which reflects the state transition of an object and can be described as follows:
E＝{＜si，si+1＞，O，A，T，C} (9)E＝{<si , si+1 >, O, A, T, C} (9)
其中E表示生产加工过程中发生的事件；＜si，si+1＞表示对象的状态从si转换为si+1；O即该对象本身，表示事件源；A是产生触发条件的属性的集合，即A＝{A0，A0，······，An}；T为事件发生时间，可以是以一个时间点(即T＝t0)或一段时间间隔(即T＝[t0，t1])，C是事件发生条件的有限集合，具体约束描述如下：Where E represents an event occurring during the production process; <si , si+1 > represents the state of the object changing from si to si+1 ; O is the object itself, representing the event source; A is the set of attributes that generate trigger conditions, i.e., A = {A0 , A0 , ······,An }; T is the time when the event occurs, which can be a time point (i.e., T = t0 ) or a time interval (i.e., T = [t0 , t1 ]); C is a finite set of event occurrence conditions, and the specific constraints are described as follows:
其中，ci是第i个条件，用属性Ai表示部分约束关系；fi()是属性Ai的运算函数，例如某一时间点的瞬时值(传感器值)或某一时间间隔内的统计特性(平均值、最大值、最小值)；表示关系运算符，即α是数值常数，表示属性的某一阈值；表示关系运算符，即触发条件可以通过一个确定单属性(由某一传感器检测到)和多属性(由多个传感器检测到)构成，当属性值满足预定义条件时，事件发生。Where,ci is the i-th condition, and attributeAi is used to represent the partial constraint relationship;fi () is the operation function of attributeAi , such as the instantaneous value (sensor value) at a certain time point or the statistical characteristics (average value, maximum value, minimum value) within a certain time interval; represents a relational operator, i.e. α is a numerical constant, representing a certain threshold of the attribute; represents a relational operator, i.e. The trigger condition can be composed of a certain single attribute (detected by a certain sensor) and multiple attributes (detected by multiple sensors). When the attribute value meets the predefined conditions, the event occurs.
数据处理及故障诊断模块，在数控机床加工过程中可以接收到多项数据，用于与所述正常运行状态数据库和报警信息及状态数据库中的属性数据A进行比对，对其中关键的数据作进一步的分析，包括根据属性，如速度、电流、温度等指标判断机床的关键部件O，如主轴、进给轴等是否运行正常，对数控机床运行状态进行预警分析生成预警结果。The data processing and fault diagnosis module can receive multiple data during the CNC machine tool processing process, which are used to compare with the attribute data A in the normal operating status database and the alarm information and status database, and further analyze the key data, including judging whether the key components O of the machine tool, such as the spindle, feed axis, etc., are operating normally based on attributes such as speed, current, temperature and other indicators, and performing early warning analysis on the operating status of the CNC machine tool to generate early warning results.
参阅图3事件检测的状态检测流程图，在应用实例中，首先设置初始化的状态，当完成一次数据采样时，系统提取相关指标进行分析，判断是否满足预定义的条件从而触发事件，若触发调用函数δ(E)来响应事件Ei，生成新的控制指令I并交由机床控制系统执行，然后判断是否结束采样，是，则结束，否，则重复上述步骤；若不触发则直接判断是否结束采样。Refer to the state detection flow chart of event detection in Figure 3. In the application example, the initialization state is first set. When a data sampling is completed, the system extracts relevant indicators for analysis to determine whether the predefined conditions are met to trigger the event. If triggered, the function δ(E) is called to respond to the event Ei, a new control instruction I is generated and handed over to the machine tool control system for execution, and then it is determined whether the sampling is ended. If yes, it is ended, otherwise, the above steps are repeated; if not triggered, it is directly determined whether the sampling is ended.
在应用实例中，将功率传感器部署到数控机床中进行能耗监控，事件属性为Power，当最近5秒内功率信号的平均值大于阈值1000W时，触发预定义条件，产生相关事件，该事件描述生产状态的转变，即从“待加工”转变为“正在加工”状态，在应用实例中，该事件描述为In the application example, the power sensor is deployed in the CNC machine tool for energy consumption monitoring. The event attribute is Power. When the average value of the power signal in the last 5 seconds is greater than the threshold value of 1000W, the predefined condition is triggered and a related event is generated. The event describes the change of the production state, that is, from "waiting for processing" to "processing". In the application example, the event is described as
E＝{＜待加工，正在加工＞，功率传感器，Power，7.22.10：35：20，平均(v0，v1，v2，v3，v4)＞1000W}。E＝{＜to be processed, processing＞, power sensor, Power, 7.22.10:35:20, average (v0 , v1 , v2 , v3 , v4 )＞1000W}.
在应用实例中，当对数控机床的主轴进行检测时，主轴状态模型设计如下：In the application example, when the spindle of a CNC machine tool is detected, the spindle state model is designed as follows:
G主轴＝(S主轴，∑主轴，δ主轴，s0)，其中，S主轴＝{s0＝静止，s1＝空转，s2＝加工，s3＝故障}，∑主轴＝{E0＝s0→s1，E1＝s0→s3，E2＝s1→s0，E3＝s1→s2，E4＝s1→s3，E5＝s2→s1，E6＝s2→s3，E7＝s3→s0}，δ主轴＝S主轴×∑主轴→S'主轴。Gspindle =(Sspindle ,∑spindle ,δspindle ,s0 ), whereSspindle ={s0 =stationary,s1 =idling,s2 =machining,s3 =fault},∑spindle ={E0 =s0 →s1 ,E1 =s0 →s3 , E2=s1→s0 ,E3 =s1 →s2 ,E4 =s1 →s3, E5=s2→s1, E6=s2→s3, E7=s3→s0},δspindle=Sspindle×∑spindle→S'spindle .
对象O＝{主轴}；属性值A＝{转速，电流，温度}，事件及其相应的触发条件如下：Object O = {spindle}; attribute value A = {speed, current, temperature}, events and their corresponding triggering conditions are as follows:
(1)E0＝{＜s0，s1＞，主轴，转速/电流，t0，C0}，C0＝c1∧c4；(1) E0 ={＜s0 ,s1 ＞,spindle,speed/current,t0 ,C0 },C0 =c1 ∧c4 ;
(2)E1＝{＜s0，s3＞，主轴，转速/电流/温度，t1，C1}，C1＝c2∧c6∧c8；(2) E1 ={＜s0 , s3 ＞, spindle, speed/current/temperature, t1 , C1 }, C1 =c2 ∧c6 ∧c8 ;
(3)E2＝{＜s1，s0＞，主轴，转速/电流，t2，C2}，C2＝c0∧c3；(3) E2 ={＜s1 , s0 ＞, spindle, speed/current, t2 , C2 }, C2 =c0 ∧c3 ;
(4)E3＝{＜s1，s2＞，主轴，转速/电流/温度，t3，C3}，C3＝c1∧c5∧c7；(4) E3 ={＜s1 , s2 ＞, spindle, speed/current/temperature, t3 , C3 }, C3 =c1 ∧c5 ∧c7 ;
(5)E4＝{＜s1，s3＞，主轴，转速/电流/温度，t4，C4}，C4＝c2∧c6∧c8；(5) E4 ={＜s1 , s3 ＞, spindle, speed/current/temperature, t4 , C4 }, C4 =c2 ∧c6 ∧c8 ;
(6)E5＝{＜s2，s1＞，主轴，转速/电流/温度，t5，C5}，C5＝c1∧c4∧c7；(6) E5 ={＜s2 , s1 ＞, spindle, speed/current/temperature, t5 , C5 }, C5 =c1 ∧c4 ∧c7 ;
(7)E6＝{＜s2，s3＞，主轴，转速/电流/温度，t6，C6}，C2＝c1∧c3∧c6∧c8；(7) E6 ={＜s2 ,s3 ＞,spindle,speed/current/temperature,t6 ,C6 },C2 =c1 ∧c3 ∧c6 ∧c8 ;
(8)E7＝{＜s3，s0＞，主轴，转速/电流/温度，t7，C7}，C2＝c0^c3^c7；(8) E7 ={＜s3 , s0 ＞, spindle, speed/current/temperature, t7 , C7 }, C2 =c0 ^c3 ^c7 ;
触发条件可分为：Trigger conditions can be divided into:
(1)c0＝转速平均值为零；(1) c0 = the average speed is zero;
(2)c1＝0＜转速平均值≤α；(2) c1 = 0 < average speed ≤ α;
(3)c2＝转速平均值＞α；(3) c2 = average speed >α;
(4)c3＝电流平均值为零；(4) c3 = average current is zero;
(5)c4＝0＜电流平均值≤β0；(5) c4 =0＜current average value≤β0 ;
(6)c5＝β0＜电流平均值≤β1；(6) c5 = β0 < average current value ≤β 1 ;
(7)c6＝电流平均值＞β1；(7) c6 = average current value > β1 ;
(8)c7＝温度平均值≤γ；(8) c7 = average temperature ≤ γ;
(9)c8＝温度平均值＞γ。(9) c8 =average value of temperature>γ.
在应用实例中，所述远程人机交互模块可收到报警并获取诊断结果。In the application example, the remote human-computer interaction module can receive an alarm and obtain a diagnosis result.
本实施例提供一种基于数字孪生的数控机床远程故障诊断系统，涉及数控机床远程故障诊断和数字孪生领域，能够对数控机床的故障进行实时远程诊断，提高机床远程故障诊断的智能化程度和检测效率。包含传感器数据采集模块，采集数控机床的数据信息；数据传输模块，机床运行信息数据库中的信息通过串口输入传输层的NB-IoT模块，NB-IoT无线通信网络传输给NB-IoT云平台；数字孪生模型构建模块，根据云平台采集的实时运行数据和历史数据构建数控机床数字孪生模型；数据处理及故障诊断模块，采用事件检测的方式对数控机床进行故障诊断，分析数控机床的运行状态，并根据状态数据库中的属性数据进行对比分析，生成故障诊断报告；远程人机交互界面可收到报警并获取诊断结果。其中采用数字孪生技术对数控机床行为进行实时监控，对其性能进行精确预测，达到全生命周期的映射效果，同时在此基础上将数控机床故障诊断技术与无线通信技术相结合，不仅可以解决有线网络布线复杂、电磁干扰大、机床操作受限、设备投入增加等问题，还可以提高机床远程故障诊断的智能化程度、保证信息的时效性以及故障反馈的及时性。This embodiment provides a remote fault diagnosis system for CNC machine tools based on digital twins, which involves the fields of remote fault diagnosis of CNC machine tools and digital twins, and can perform real-time remote diagnosis of faults of CNC machine tools, thereby improving the intelligence level and detection efficiency of remote fault diagnosis of machine tools. It includes a sensor data acquisition module, which collects data information of CNC machine tools; a data transmission module, in which the information in the machine tool operation information database is input into the NB-IoT module of the transmission layer through the serial port, and the NB-IoT wireless communication network transmits it to the NB-IoT cloud platform; a digital twin model construction module, which constructs a digital twin model of CNC machine tools based on the real-time operation data and historical data collected by the cloud platform; a data processing and fault diagnosis module, which uses event detection to perform fault diagnosis on CNC machine tools, analyzes the operation status of CNC machine tools, and performs comparative analysis based on the attribute data in the status database to generate a fault diagnosis report; a remote human-computer interaction interface can receive alarms and obtain diagnosis results. Digital twin technology is used to monitor the behavior of CNC machine tools in real time and accurately predict their performance to achieve a mapping effect for the entire life cycle. At the same time, on this basis, CNC machine tool fault diagnosis technology is combined with wireless communication technology. It can not only solve problems such as complex wired network wiring, large electromagnetic interference, limited machine tool operation, and increased equipment investment, but also improve the intelligence level of remote fault diagnosis of machine tools, ensure the timeliness of information and the promptness of fault feedback.
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于设备实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应该以权利要求的保护范围为准。Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The above is only a specific implementation method of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or replacements that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112875.6ACN117170310B (en) | 2023-08-30 | 2023-08-30 | Digital twin-based remote fault diagnosis method and system for numerical control machine tool |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112875.6ACN117170310B (en) | 2023-08-30 | 2023-08-30 | Digital twin-based remote fault diagnosis method and system for numerical control machine tool |
| Publication Number | Publication Date |
|---|---|
| CN117170310A CN117170310A (en) | 2023-12-05 |
| CN117170310Btrue CN117170310B (en) | 2024-11-01 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311112875.6AActiveCN117170310B (en) | 2023-08-30 | 2023-08-30 | Digital twin-based remote fault diagnosis method and system for numerical control machine tool |
| Country | Link |
|---|---|
| CN (1) | CN117170310B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117644431B (en)* | 2024-01-29 | 2024-04-02 | 南京航空航天大学 | CNC machine tool processing quality analysis method and system based on digital twin model |
| CN118349926A (en)* | 2024-03-18 | 2024-07-16 | 国网江苏省电力有限公司信息通信分公司 | A power big data analysis method and system based on cloud platform |
| CN118642428A (en)* | 2024-08-13 | 2024-09-13 | 深圳博尚精密制造有限公司 | Remote control method and system for numerical control machine tool |
| CN118672208B (en)* | 2024-08-22 | 2025-01-14 | 江苏奇科智能科技有限公司 | Numerical control machine tool running state monitoring system based on digital twin |
| CN119225281A (en)* | 2024-12-03 | 2024-12-31 | 中国石油大学(华东) | A machining process fault diagnosis method based on digital twin |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251754A (en)* | 2008-03-13 | 2008-08-27 | 西安交通大学 | A processing and control method of error flow in multi-process machining process |
| CN102819239A (en)* | 2011-06-08 | 2012-12-12 | 同济大学 | Intelligent fault diagnosis method of numerical control machine tool |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7602132B2 (en)* | 2006-09-27 | 2009-10-13 | Rockwell Automation Technologies, Inc. | Methods and system for motor drive information capture |
| CN203101932U (en)* | 2012-10-15 | 2013-07-31 | 辽宁省电力有限公司电力科学研究院 | Substation equipment state access controller |
| CN104281098B (en)* | 2014-10-27 | 2017-02-15 | 南京航空航天大学 | Modeling method for dynamic machining features of complex curved surface |
| CN108803552B (en)* | 2018-08-31 | 2021-08-03 | 承德建龙特殊钢有限公司 | Monitoring system and monitoring method for equipment fault |
| EP4066073A4 (en)* | 2019-11-25 | 2024-04-03 | Strong Force Iot Portfolio 2016, LLC | SMART VIBRATION DIGITAL TWIN SYSTEMS AND METHODS FOR INDUSTRIAL ENVIRONMENTS |
| CN113742964B (en)* | 2021-08-19 | 2023-10-27 | 三峡大学 | Digital twin construction method applied to numerical control machine tool |
| CN113641104A (en)* | 2021-08-23 | 2021-11-12 | 江南大学 | Limited frequency domain fault detection method for tank reactor under dynamic event triggering |
| CN114428481A (en)* | 2022-01-11 | 2022-05-03 | 南京开通自动化技术有限公司 | System for realizing remote diagnosis processing aiming at numerical control system |
| CN115630826A (en)* | 2022-11-10 | 2023-01-20 | 北京航空航天大学 | Digital twin exception handling method based on model fusion |
| CN116125958A (en)* | 2023-03-08 | 2023-05-16 | 中科海慧（北京）科技有限公司 | Intelligent factory fault diagnosis and decision-making system based on digital twinning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251754A (en)* | 2008-03-13 | 2008-08-27 | 西安交通大学 | A processing and control method of error flow in multi-process machining process |
| CN102819239A (en)* | 2011-06-08 | 2012-12-12 | 同济大学 | Intelligent fault diagnosis method of numerical control machine tool |
| Publication number | Publication date |
|---|---|
| CN117170310A (en) | 2023-12-05 |
| Publication | Publication Date | Title |
|---|---|---|
| CN117170310B (en) | Digital twin-based remote fault diagnosis method and system for numerical control machine tool | |
| CN112487584A (en) | Dynamics-based rolling bearing digital twin modeling method | |
| CN119471181B (en) | A smart grid fault early warning and diagnosis system | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN118210265B (en) | Air compression station transformation joint control management system | |
| CN118394017B (en) | Intelligent robot for optimizing and controlling energy consumption in medicine production and operation method | |
| CN118965236B (en) | A method and system for monitoring energy equipment data based on edge intelligent control | |
| CN117420792A (en) | Central control system for composite processing machine tool | |
| CN114239708A (en) | Combustion engine abnormity detection method based on quality control chart theory | |
| CN117689256A (en) | A quality traceability method for aluminum alloy melting and casting products | |
| CN120146411B (en) | Inspection system based on edge equipment gateway | |
| CN114970101A (en) | Management method and system of dehumidification device, electronic equipment and computer storage medium | |
| CN116910507A (en) | Abnormality detection method and device | |
| CN117454165A (en) | A network model training method, motor temperature prediction method and related equipment | |
| CN115114856A (en) | An intelligent manufacturing production line operation system based on digital twin | |
| CN119090152A (en) | A power plant visualization information management system based on digital twin technology | |
| CN105786635B (en) | A kind of Complex event processing system and method towards Fault-Sensitive point dynamic detection | |
| CN116520769B (en) | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium | |
| CN118446076A (en) | Digital twinning-oriented mapping data modeling and simulation method | |
| CN118642458A (en) | A numerical control machine tool fault prediction system and method | |
| CN115139336A (en) | Data acquisition and screening method for industrial robot health monitoring | |
| CN118094288A (en) | Cloud edge collaboration-based data processing method and system | |
| CN116776730A (en) | A method, equipment and storage device for predicting the remaining life of rotating equipment | |
| CN117332252A (en) | Rotary equipment trend early warning method based on vibration growth speed | |
| CN114997220A (en) | Equipment PHM system based on CPS framework |
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |