Fault diagnosis method, device and equipment based on digital twinning and storage medium

Abstract

The invention relates to a fault diagnosis method, device and equipment based on digital twinning and a storage medium, an intelligent production line digital twinning system is built based on a digital twinning system five-dimensional model framework, physical entity equipment is modeled, electromechanical attributes, kinematic pairs and constraints are set, and the positions and speeds of the kinematic pairs are defined; a digital twinning virtual model corresponding to physical equipment is constructed, production data of the physical equipment is collected and transmitted in real time, and based on an intelligent production line digital twinning system, actual operation data of a physical entity and real-time simulation data of a virtual entity are compared, and historical data are analyzed. According to the method, reasons of operation index deviation or errors between a physical entity and a virtual entity are diagnosed, and fault positioning and intelligent decision making are carried out in combination with modeling rules of equipment in the physical entity, so that the problems in existing production monitoring, fault diagnosis and vocational education practical training are solved, and the practical training efficiency is improved. And the purposes of high-efficiency management of the production process and accurate diagnosis and prediction of equipment faults are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to a fault diagnosis method, device, equipment and storage medium based on digital twins. Background Art

[0002] At a time when global manufacturing competition is becoming increasingly fierce, my country is actively promoting the transformation of manufacturing to high-end, intelligent and green. However, in terms of production monitoring, traditional manufacturing relies on manual inspections and simple sensor systems, which are inefficient and have poor real-time performance. It is difficult to detect potential equipment hazards in a timely manner, which can easily cause production line shutdowns, increase maintenance costs and production delays. Although intelligent production lines have introduced advanced technologies, data communication and interoperability between different devices and systems are poor, and there is a lack of effective data analysis methods, making it difficult to accurately predict and diagnose equipment failures. In the field of vocational education, traditional practical training relies on expensive and safety-risky actual production equipment, and students have limited practical training opportunities; virtual simulation teaching is far from the actual scene, and cannot provide real operating experience. It is difficult for students to quickly adapt to job requirements after graduation. Digital twin technology brings hope to solve these problems, but its application in the field of fault diagnosis is still in its infancy, with problems such as complex model construction, difficulty in ensuring accuracy and reliability, and low integration with actual production systems. Therefore, it is of great significance to develop fault diagnosis methods based on digital twins. Summary of the invention

[0003] The main purpose of the present invention is to provide a fault diagnosis method, device, equipment and storage medium based on digital twins, so as to solve the problems in existing production monitoring, fault diagnosis and vocational education training, and improve the efficient management of production processes and the accurate diagnosis and prediction of equipment faults.

[0004] To achieve the above object, the present invention provides a fault diagnosis method based on digital twin, comprising the following steps: Building a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system, which includes physical entities, virtual entities, services, twin data, and connections between the components; Use NX MCD to model the physical entity equipment, set each electromechanical property, kinematic pair and constraint, and define the position and speed of the kinematic pair, and build a digital twin virtual model corresponding to the physical equipment; Connect the devices in the physical entity to the network nodes, and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet. The production data includes but is not limited to warehouse logistics data, machine tool working data, robot motion planning data, robot guide rail data and operation history data, and use the OPC UA standard specification to build a twin database; Based on the intelligent production line digital twin system, the actual operation data of the physical entity is compared with the real-time simulation data of the virtual entity and the historical data is analyzed to diagnose the causes of deviations or errors in the operation indicators between the physical entity and the virtual entity. In combination with the modeling rules of each device in the physical entity, fault location and intelligent decision-making are carried out.

[0005] Furthermore, in the step of collecting the real-time operation data of the physical production line, the AGV and the industrial robot communicate with the PLC via Profinet or MODBUS TCP to collect data.

[0006] Furthermore, in the process of building a data-driven digital twin system for intelligent production lines, all manufacturing data and virtual simulation data generated will be collected into the system's twin data module to form big data, and the production lines and equipment will be controlled, diagnosed and predicted through data model driving.

[0007] Furthermore, when real-time simulation and status monitoring are performed in the virtual entity, the position and speed of the kinematic pair are defined, and the kinematic pair is used as an actuator. When the kinematic pair reaches the specified position according to the preset target position and specified speed, the corresponding information is fed back to the PLC.

[0008] Furthermore, when collecting production data of physical equipment, the inverter collects and transmits its own operating data through industrial Ethernet, and the AGV and industrial robot communicate with the PLC through Profinet or MODBUS TCP.

[0009] Furthermore, when building a twin database, an integrated OPC UA server is embedded in the physical field devices, PLCs, robots, and RFIDs, and the OPC UA standard specifications are used to convert various types of device information and production data into data that supports the OPC UA protocol and store it in the server's address space.

[0010] Furthermore, when conducting fault diagnosis and location, neural network-based machine learning technology is used to learn and analyze historical data and real-time data. By building a multi-layer perceptron neural network model, the collected physical equipment operation data is used as input, and after feature extraction and nonlinear transformation, the fault diagnosis results are output to identify equipment abnormalities and locate the source of the fault.

[0011] The present invention also provides a fault diagnosis device based on digital twin, comprising: System building module, used to build a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system; The model building module is used to model the physical entity equipment using NX MCD, set each electromechanical property, kinematic pair and constraint, and define the position and speed of the kinematic pair, so as to build a digital twin virtual model corresponding to the physical device; The data acquisition module is used to access the network nodes of the devices in the physical entity and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet; The fault diagnosis module is used to compare the actual operation data of the physical entity with the real-time simulation data of the virtual entity and analyze the historical data based on the digital twin system of the intelligent production line, diagnose the causes of the deviation or error of the operating indicators between the physical entity and the virtual entity, and combine the modeling rules of each device in the physical entity to perform fault location and intelligent decision-making.

[0012] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned digital twin-based fault diagnosis method when executing the computer program.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned digital twin-based fault diagnosis method are implemented.

[0014] The digital twin-based fault diagnosis method, device, equipment and storage medium provided by the present invention have the following beneficial effects: (1) By acquiring production line operation data in real time and presenting it in virtual space, real-time visual monitoring is achieved, historical data is used for fault diagnosis and location, and intelligent decision-making is achieved by combining intelligent rule modeling, such as optimizing production scheduling and reducing production delays; (2) The digital twin model monitors the equipment operating status in real time, predicts the time and location of failure, arranges maintenance plans in advance, reduces equipment downtime, and reduces maintenance costs. At the same time, it monitors and analyzes the energy consumption of the production line in real time, optimizes equipment operating parameters and production plans, and reduces energy consumption; (3) The digital twin model of the production line is highly authentic to the actual production environment and is safe to use. It solves problems such as the high cost of setting up a real production environment, poor safety of practical teaching, and the large gap between virtual simulation and reality, providing an effective way to cultivate talents related to intelligent manufacturing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of a fault diagnosis method based on digital twins in one embodiment of the present invention; Figure 2 is a structural block diagram of a fault diagnosis device based on digital twins in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0016] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Reference Figure 1 , which is a flow chart of a fault diagnosis method based on digital twin proposed by the present invention, comprising the following steps: S1, building a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system, which includes physical entities, virtual entities, services, twin data, and connections between the components; S2, use NX MCD to model the physical entity equipment, set each electromechanical property, kinematic pair and constraint one by one, and define the position and speed of the kinematic pair, so as to build a digital twin virtual model corresponding to the physical equipment; S3, connect the devices in the physical entity to the network nodes, and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet. The production data includes but is not limited to warehouse logistics data, machine tool working data, robot motion planning data, robot guide rail data and operation history data, and build a twin database using the OPC UA standard specification; S4, based on the digital twin system of the intelligent production line, compares the actual operation data of the physical entity with the real-time simulation data of the virtual entity and analyzes the historical data, diagnoses the causes of the deviation or error of the operation indicators between the physical entity and the virtual entity, and combines the modeling rules of each device in the physical entity to perform fault location and intelligent decision-making.

[0019] As described in step S1 above, the five-dimensional model framework of the digital twin system includes physical entities (PE), virtual entities (VE), services (Ss), twin data (DD) and connections (CN) between the components, which are used as the basic architecture for building the digital twin system of the intelligent production line. During the construction process, all the manufacturing data and virtual simulation data generated are collected into the twin data module of the system to form big data. The production line and equipment are controlled, diagnosed and predicted through data model drive. Manufacturing data comes from various parameters of physical entity equipment in the actual production process, and virtual simulation data is the data generated by the virtual entity simulating the operation of the physical entity. The big data formed by the combination of the two provides a rich information basis for subsequent fault diagnosis. The service system in the system monitors and predicts the operating status of the production line and equipment in real time based on the virtual workshop, and provides a visual interface for staff to view, so as to intuitively understand the real-time situation of the production line and discover potential problems in time.

[0020] As described in step S2 above, the physical entity equipment is modeled using professional NX MCD software, and the corresponding electromechanical properties are set for each detail. For example, the spindle, tool holder, tool, and workbench inside the machine tool need to set the corresponding rigid body and collision body properties. The setting of these properties is conducive to more accurately simulating the mechanical characteristics of the physical equipment in actual operation, making the virtual model closer to the real situation. When performing real-time simulation and status monitoring in the virtual entity, the position and speed of the kinematic pair are defined, and the kinematic pair is used as an actuator. When the kinematic pair reaches the specified position according to the preset target position and the specified speed, the corresponding information is fed back to the PLC. For example, the kinematic pairs such as the X-axis, Y-axis, and Z-axis in the machine tool, accurate motion simulation and information feedback can ensure the consistency of the virtual model and the physical entity in the motion state, and realize the real mapping of the physical device in the virtual space.

[0021] As described in step S3 above, devices in the physical entity, such as sensors, PLCs, RFIDs, etc., are connected to the industrial Ethernet through network nodes for data collection. Among them, AGVs and industrial robots communicate with PLCs through Profinet or MODBUS TCP, and the inverter collects and transmits its own operating data through the industrial Ethernet. Different devices use their own private protocols to ensure the pertinence and effectiveness of data collection. When building a twin database, by embedding and integrating OPC UA servers in field devices, PLCs, robots, RFIS, etc., various types of device information and production data are converted into data that supports the OPC UA protocol using the OPC UA standard specification and stored in the server's address space. This standardized data processing method can achieve unified management and integration of data from different devices, and facilitate subsequent data analysis.

[0022] As described in step S4 above, the constructed digital twin system of the intelligent production line is used to compare the data collected during the actual operation of the physical entity with the data generated by the real-time simulation of the virtual entity. At the same time, historical data are analyzed. These historical data contain various information of the equipment at different operation stages, which can provide a reference for judging whether the current operation status is normal. When performing fault diagnosis and location, the machine learning technology based on neural networks is used to learn and analyze historical data and real-time data. By constructing a multi-layer perceptron neural network model, the collected physical equipment operation data is used as input, and after feature extraction and nonlinear transformation, the fault diagnosis results are output to identify the abnormal conditions of the equipment and locate the source of the fault. Combined with the modeling rules of each device in the physical entity, intelligent decision-making is made after the fault is diagnosed. For example, according to the severity and scope of the fault, the maintenance plan is reasonably arranged, the production scheduling is adjusted, etc., so as to reduce the impact of the fault on production and improve production efficiency.

[0023] In one embodiment, taking the intelligent production line of an automobile parts manufacturing company as an example, the production line includes multiple CNC machine tools, industrial robots, and warehousing and logistics equipment. When building a digital twin system, the overall design is first carried out based on the five-dimensional model framework of the digital twin system.

[0024] During the production process, CNC machine tools generate manufacturing data such as processing time, tool wear, and spindle speed; industrial robots generate data such as motion trajectory and load conditions; and storage and logistics equipment generates data such as goods in and out of the warehouse and inventory quantity. At the same time, virtual entities simulate these devices and generate virtual simulation data. All of this data is collected in the twin data module to form a huge data set. For example, tens of thousands of data on the operating status of equipment are collected every day.

[0025] These big data are analyzed and processed through data models. For example, a prediction model for equipment operation status is established using data analysis algorithms to predict possible equipment failures based on historical data and real-time data. The service system monitors the operation status of the entire production line in real time based on the virtual workshop. Operators can view the real-time operating parameters, production progress, and equipment health status of each device through a visual interface. Once an abnormal fluctuation in the spindle speed of a CNC machine tool is found, the system will immediately issue an alarm and highlight the relevant information of the device on the visual interface.

[0026] For the CNC machine tools in the production line, NX MCD software is used for modeling. Detailed attribute settings are made for each component inside the machine tool. For example, the spindle is set as a rigid body, and the mass, inertia and other parameters are set according to its actual material and size; the collision body attributes are set for the tool holder to simulate its collision during work. This can more accurately simulate the mechanical characteristics of the machine tool in actual operation. The position and speed of the machine tool's X-axis, Y-axis, Z-axis and other kinematic pairs are defined. The target position of the X-axis is set to 500mm, and the specified speed is 100mm / s. When the kinematic pair reaches the specified position according to the preset parameters, it will feedback information to the PLC. After receiving the feedback information, the PLC will control the next operation according to the preset program, such as starting the cutting action of the tool. In this way, the real mapping of physical equipment in the virtual space is achieved, ensuring that the motion state of the virtual model is consistent with that of the physical entity.

[0027] In the production line of this auto parts manufacturer, various devices are connected to network nodes to achieve real-time data collection and transmission. Sensors, PLCs, RFID and other devices use their own private protocols to collect and transmit data through Industrial Ethernet. For example, sensors installed on CNC machine tools will collect data such as the temperature and vibration of the spindle in real time, and transmit the data to the data acquisition server through Industrial Ethernet. The inverter collects and transmits its own operating data, such as output frequency and current, through Industrial Ethernet. AGV and industrial robots communicate with PLC through Profinet or MODBUS TCP, and transmit their own position, working status and other information to PLC.

[0028] The OPC UA server is embedded in field devices, PLCs, robots, and RFID. Taking an industrial robot as an example, the data such as its motion trajectory and load condition are converted into a data format that supports the OPC UA protocol through the OPC UA server and stored in the address space of the server. The data of all devices are processed and stored in this way, and finally a unified twin database is built. This database can easily query, analyze and manage data, providing a solid data foundation for subsequent fault diagnosis.

[0029] Based on the established digital twin system of the intelligent production line, fault diagnosis and intelligent decision-making are carried out. The system will compare the actual operation data of the physical entity with the real-time simulation data of the virtual entity in real time. For example, when it is found that the actual processing time of a CNC machine tool is longer than the time predicted by the virtual simulation model, the historical data will be further analyzed to see whether the machine tool has also had the problem of long processing time in similar situations in the past. At the same time, other operating parameters of the machine tool, such as spindle speed, tool wear, etc., are analyzed to determine whether there are any abnormalities.

[0030] Use machine learning technology based on neural networks for fault diagnosis. Construct a multi-layer perceptron neural network model and use the collected physical equipment operation data as input, such as the temperature, vibration, speed and other data of the machine tool. After feature extraction and nonlinear transformation of the neural network, the fault diagnosis results are output. For example, if the model output shows that the machine tool has a tool wear fault, the system will immediately locate the specific tool and display the fault information on the visual interface. Combined with the modeling rules of each device in the physical entity, intelligent decision-making is made. When a device is diagnosed to have a fault, the system will automatically adjust the production plan according to the severity and scope of the fault. If a non-critical device fails, the system will temporarily assign the production task of the device to other idle devices to ensure the normal operation of the production line; if a critical device fails, the system will promptly arrange maintenance personnel for repair and adjust the subsequent production schedule to reduce the impact of the fault on the production progress.

[0031] Reference Figure 2 , is a structural block diagram of a fault diagnosis device based on digital twins in one embodiment of the present invention, including: System building module, used to build a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system; The model building module is used to model the physical entity equipment using NX MCD, set each electromechanical property, kinematic pair and constraint, and define the position and speed of the kinematic pair, so as to build a digital twin virtual model corresponding to the physical device; The data acquisition module is used to access the network nodes of the devices in the physical entity and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet; The fault diagnosis module is used to compare the actual operation data of the physical entity with the real-time simulation data of the virtual entity and analyze the historical data based on the digital twin system of the intelligent production line, diagnose the causes of the deviation or error of the operating indicators between the physical entity and the virtual entity, and combine the modeling rules of each device in the physical entity to perform fault location and intelligent decision-making.

[0032] For the specific implementation of each module in the above device example, please refer to the above method embodiment, which will not be repeated here.

[0033] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown in the figure. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the above method.

[0034] Those skilled in the art can understand that Figure 3 the structure shown in the figure is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0035] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0036] In summary, based on the five-dimensional model framework of the digital twin system, a data-driven intelligent production line digital twin system is built. Use NX MCD to model the physical entity devices, set each mechanical and electrical property, kinematic pair and constraint one by one, and define the position and speed of the kinematic pair to construct the digital twin virtual model corresponding to the physical device. Connect the devices in the physical entity to the network nodes, and use their respective private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet. Based on the intelligent production line digital twin system, compare the actual operation data of the physical entity with the real-time simulation data of the virtual entity and analyze the historical data, diagnose the reasons for the deviation or error of the operation indicators between the physical entity and the virtual entity, and combine the modeling rules of each device in the physical entity to perform fault location and intelligent decision-making. To achieve the purpose of solving the problems in existing production monitoring, fault diagnosis, and vocational education training, and improving the efficient management of the production process, accurate diagnosis and prediction of equipment faults.

[0037] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0038] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0039] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A fault diagnosis method based on digital twins, characterized in that: The following steps are involved: Building a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system, which includes physical entities, virtual entities, services, twin data, and connections between the components; Use NX MCD to model the physical entity equipment, set each electromechanical property, kinematic pair and constraint, and define the position and speed of the kinematic pair, and build a digital twin virtual model corresponding to the physical equipment; Connect the devices in the physical entity to the network nodes, and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet. The production data includes but is not limited to warehouse logistics data, machine tool working data, robot motion planning data, robot guide rail data and operation history data, and use the OPC UA standard specification to build a twin database; Based on the intelligent production line digital twin system, the actual operation data of the physical entity is compared with the real-time simulation data of the virtual entity and the historical data is analyzed to diagnose the causes of deviations or errors in the operation indicators between the physical entity and the virtual entity. In combination with the modeling rules of each device in the physical entity, fault location and intelligent decision-making are carried out.

2. The fault diagnosis method based on digital twin according to claim 1, characterized in that: In the step of real-time collection of physical production line operation data, the AGV and industrial robot communicate with the PLC via Profinet or MODBUS TCP to collect data.

3. The fault diagnosis method based on digital twin according to claim 1, characterized in that: In the process of building a data-driven digital twin system for intelligent production lines, all manufacturing data and virtual simulation data generated are collected into the system's twin data module to form big data, and the production lines and equipment are controlled, diagnosed and predicted through data model driving.

4. The fault diagnosis method based on digital twin according to claim 1, characterized in that: When performing real-time simulation and status monitoring in a virtual entity, the position and speed of the kinematic pair are defined, and the kinematic pair is used as an actuator. When the kinematic pair reaches the specified position according to the preset target position and specified speed, the corresponding information is fed back to the PLC.

5. The fault diagnosis method based on digital twin according to claim 1, characterized in that: When collecting production data of physical equipment, the inverter collects and transmits its own operating data through Industrial Ethernet, and AGV and industrial robots communicate with PLC through Profinet or MODBUS TCP.

6. The fault diagnosis method based on digital twin according to claim 1, characterized in that: When building a twin database, an integrated OPC UA server is embedded in the physical field devices, PLCs, robots, and RFIDs, and the OPC UA standard specifications are used to convert various types of device information and production data into data that supports the OPC UA protocol and store it in the server's address space.

7. The fault diagnosis method based on digital twin according to claim 1, characterized in that: When conducting fault diagnosis and location, neural network-based machine learning technology is used to learn and analyze historical data and real-time data. By building a multi-layer perceptron neural network model, the collected physical equipment operation data is used as input, and after feature extraction and nonlinear transformation, the fault diagnosis results are output to identify equipment abnormalities and locate the source of the fault.

8. A fault diagnosis device based on digital twins, characterized in that: include: System building module, used to build a data-driven intelligent production line digital twin system based on the five-dimensional model framework of the digital twin system; The model building module is used to model the physical entity equipment using NX MCD, set each electromechanical property, kinematic pair and constraint, and define the position and speed of the kinematic pair, so as to build a digital twin virtual model corresponding to the physical device; The data acquisition module is used to access the network nodes of the devices in the physical entity and use their own private protocols to collect and transmit the production data of the physical devices in real time through the industrial Ethernet; The fault diagnosis module is used to compare the actual operation data of the physical entity with the real-time simulation data of the virtual entity and analyze the historical data based on the digital twin system of the intelligent production line, diagnose the causes of the deviation or error of the operating indicators between the physical entity and the virtual entity, and combine the modeling rules of each device in the physical entity to perform fault location and intelligent decision-making.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the digital twin-based fault diagnosis method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the digital twin-based fault diagnosis method described in any one of claims 1 to 7 are implemented.

Images