Production line intelligent fault diagnosis early warning method based on digital twinning technology

Abstract

The invention discloses a production line intelligent fault diagnosis early warning method based on a digital twinning technology. The method comprises the following steps: S1, constructing a digital twinning system; s2, the virtual system and a real production line operate synchronously, and a simulation operation scene of the virtual system is displayed in a scheduling platform in real time; s3, the virtual system compares and judges the real-time data transmitted by the sensor with the parameter range; and S4, the user automatically evaluates and decides abnormal data through the scheduling platform or the scheduling platform. According to the method, the real production line and the virtual system are combined, the production line digital twin system is constructed, the operation state of the production line is monitored in real time through the scheduling platform, intelligent diagnosis and early warning are performed during faults, manual inspection is reduced, and the monitoring efficiency is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of Internet of Things, and in particular to a production line intelligent fault diagnosis and early warning method based on digital twin technology. BACKGROUND

[0002] The digital twin establishes a high-fidelity model of a physical entity through a digital method, maps the attributes, behaviors, states and performance of the physical entity to a virtual space, and simultaneously uses data fusion, data analysis and decision optimization to analyze, simulate and predict the real-time performance and working state of the physical entity. It corresponds to entities or processes in the real world and provides in-depth understanding and prediction capabilities for entities or processes by collecting, integrating and analyzing data.

[0003] The digital twin technology provides feasibility for solving some technical problems, for example, the fault detection and monitoring and early warning method of the existing production lines in parks and workshops. The method is mostly operated and maintained through artificial regular inspection and camera monitoring, which is low in efficiency, lacks flexibility in process, and is relatively low in detection accuracy, so that some potential faults and dangers cannot be discovered in time, thereby causing potential safety hazards to the operation of the production line and the safety of users. At the same time, due to the lack of support of automatic and intelligent technical means in the traditional production line, real-time monitoring and fault early warning cannot be realized, and the operation and maintenance work of the production line is not convenient and efficient, which is a problem. SUMMARY

[0004] In order to solve the above problems, the application provides a production line intelligent fault diagnosis and early warning method based on digital twin technology.

[0005] The application is realized through the following technical solutions: A production line intelligent fault diagnosis and early warning method based on digital twin technology, characterized by the following steps: S1, a digital twin system is constructed, a virtual system corresponding to the real production line is created, the real production line is simulated, and then a scheduling platform is created, which is used to access the virtual system, receive feedback information of the virtual system or issue instructions to the real production line; S2, production parameters of the real production line are collected through sensors, real-time data are transmitted to the virtual system, the virtual system and the real production line are synchronously operated, and a simulation operation scene of the virtual system is displayed in real time on the scheduling platform; S3, the virtual system compares the real-time data transmitted by the sensor with the parameter range, when the parameter is within the specified range, the virtual system normally simulates operation, when the transmitted parameter is out of or lower than the specified range, the virtual system issues an early warning to the scheduling platform and displays the abnormal data; S4, a user evaluates the abnormal data through the scheduling platform or the scheduling platform, and issues instructions to the real system according to the evaluation result.

[0006] Further optimization, the digital twin system comprises a real production line, a virtual system and a scheduling platform, the virtual system is used for simulating the real production line and monitoring the real production line in real time, and abnormal data is warned.

[0007] Further optimization, the virtual system comprises a data acquisition module, a data judgment module, a simulation running module and a fault alarm module, the data acquisition module acquires production parameters of the production line in real time and transmits the production parameters to the data judgment module, the data judgment module judges the data twice, and transmits the data to the simulation running module or the fault alarm module.

[0008] Further optimization, in step s3, the data judgment module first judges whether the data is out of or lower than the specified range, if the data is within the specified range, the data is transmitted to the simulation running module for normal simulation running, if the data is not within the specified range, the abnormal data is subjected to second-step judgment comparison, whether the abnormal data is dangerous data is judged, the dangerous data is directly transmitted to the fault alarm module, and the non-dangerous data is transmitted to the simulation running module.

[0009] Further optimization, the fault alarm module transmits the dangerous data to the scheduling platform, and the scheduling platform automatically issues a shutdown instruction to the production line.

[0010] Further optimization, the simulation running module transmits the non-dangerous abnormal data to the scheduling platform, and displays the abnormal position in the production line of the virtual system.

[0011] Further optimization, the scheduling platform comprises a data receiving module, an abnormality analysis module, a central control center, an action module and an intelligent decision module.

[0012] Further optimization, the data receiving module is used for receiving and transmitting abnormal data, the abnormality analysis module is used for analyzing reasons and results of corresponding abnormal data, a user makes a decision on the abnormal data through the central control center, the action module processes the abnormality according to the decision of the central control center, and the intelligent decision module collects and deduces a relationship between the abnormal data and the decision of the central control center, and establishes a feature model.

[0013] Further optimization, the intelligent decision module simulates the decision of the central control center based on the feature model, receives the abnormal data transmitted by the data receiving module, and performs early warning or fault elimination.

[0014] Further optimization, when the action module receives different decisions of the central control center and the intelligent decision module at the same time, the action module feeds back to the central control center for secondary confirmation.

[0015] The beneficial effects of the application are: The method combines the real production line with the virtual system, constructs a production line digital twin system, monitors the running state of the production line in real time through the scheduling platform, intelligently diagnoses and warns when a fault occurs, reduces manual inspection, and improves monitoring efficiency.

[0016] The virtual system displays the fault position through the scheduling platform when a fault occurs, and gives the cause and result of the fault, for the staff of the control center to handle; the data judgment module in the virtual system judges the dangerous range of abnormal data, and when the abnormal data belongs to the dangerous range, gives a warning prompt and automatically stops processing.

[0017] The scheduling platform is provided with an intelligent decision module, taking abnormal data as an index and the decision of the central control center as a result, taking the two as training samples, using the algorithm of deep neural network to establish a feature model of the relationship between the two, which can assist decision-making without people and is more intelligent. BRIEF DESCRIPTION OF DRAWINGS

[0018] Fig. 1 The flowchart of the present application.

[0019] Fig. 2 The flowchart of the virtual system of the present application.

[0020] Fig. 3 The flowchart of the scheduling platform of the present application. DETAILED DESCRIPTION

[0021] In order to clearly illustrate the technical features of the present application, the present application will be described in detail below with specific embodiments, and the accompanying drawings cannot be understood as limiting the present application.

[0022] As shown in Figs. 1-3 The present application provides a production line intelligent fault diagnosis and warning method based on digital twin technology, comprising the following steps: S1, digital twin system construction, collecting production line data and integrating existing or artificially modeled models to ensure that the data and models match, then establishing the logical and correlation relationship between the equipment model, production line model, raw material model and product model by machine learning and statistical analysis method, creating a virtual system mapping the real production line, simulating the real production line, and then creating a scheduling platform to complete the construction of the digital twin system. The scheduling platform is used to access the virtual system, receive feedback information from the virtual system or issue instructions to the real production line; S2, collect the production parameters of the real production line through the sensor, and transfer the data to the virtual system in real time, the virtual system and the real production line run synchronously, and the simulation running scene of the virtual system is displayed in real time in the scheduling platform; S3, the virtual system compares the real-time data transmitted by the sensor with the parameter range twice, when the parameter is within the specified range, the virtual system normally simulates the running, when the transmitted parameter is out of or lower than the specified range, it is further judged whether it is dangerous data for immediate shutdown processing, if yes, it automatically shuts down and alarms, if not, the virtual system sends a warning to the dispatch platform, and displays the abnormal data; S4, the user intelligently evaluates the abnormal data through the dispatch platform or the dispatch platform, and issues an instruction to the real system according to the evaluation result.

[0023] As a preferred embodiment, the digital twin system comprises a real production line, a virtual system and a dispatch platform, the virtual system is used to simulate and emulate the real production line, and real-time monitor the real production line, and give a warning to abnormal data, the dispatch platform receives the information feedback of the virtual production line, and issues an instruction to the real production line.

[0024] As a preferred embodiment, the virtual system comprises a data acquisition module, a data judgment module, a simulation running module and a fault alarm module, the data acquisition module acquires the production parameters of the production line in real time, and transmits them to the data judgment module, the data judgment module judges the data twice, and transmits the data to the simulation running module or the fault alarm module.

[0025] In step s3, the data judgment module first judges whether the data is out of or lower than the specified range, if it is within the specified range, it is transmitted to the simulation running module for normal simulation running, if it is not within the specified range, it is judged again in the second step, whether the abnormal data is dangerous data, the dangerous data is directly transmitted to the fault alarm module, and the non-dangerous data is transmitted to the simulation running module. The abnormal data may be humidity, voltage, pressure, speed, smoke and other parameter abnormalities, and the dangerous data may be smoke and other parameters.

[0026] As a preferred embodiment, the fault alarm module transmits the dangerous data to the dispatch platform, the dispatch platform automatically issues a shutdown instruction to the production line, the dangerous data does not need to be manually evaluated or analyzed, and needs to be immediately shut down for processing.

[0027] As a preferred embodiment, the simulation running module transmits the non-dangerous abnormal data to the dispatch platform, and displays the abnormal position in the production line of the virtual system.

[0028] As a preferred embodiment, the dispatch platform comprises a data receiving module, an abnormal analysis module, a central control center, an action module and an intelligent decision module.

[0029] The data receiving module is used for receiving and transmitting abnormal data from a virtual system, and the abnormality analyzing module is used for analyzing and screening the cause and result of the corresponding abnormal data; when a scheduling platform is created, the cause and result of parameter abnormality are put into the abnormality analyzing module; the central control center is provided with a display device and a prompt device; a user makes a decision on the abnormal data according to the emergency degree and processing time of the cause and result through the central control center; and the action module processes the abnormality according to the decision of the central control center. The intelligent decision module collects and deduces the relationship between the abnormal data received by the data receiving module and the decision of the central control center, takes the two as training samples, and establishes a feature model based on a neural network.

[0030] The intelligent decision module simulates the decision of the central control center based on the feature model and the abnormal data transmitted by the data receiving module, and assists in early warning or fault elimination.

[0031] As a preferred embodiment, when the action module receives different decisions of the central control center and the intelligent decision module at the same time, the action module feeds back to the central control center for secondary confirmation, so as to ensure the accuracy of the decision.

[0032] The details not described in the present application are the known technology of the skilled in the art. Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the purpose and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A production line intelligent fault diagnosis and early warning method based on digital twin technology, characterized by: The following steps are involved: S1. Build a digital twin system, creating a virtual system that maps to the real production line, simulating the real production line, and then creating a scheduling platform. The scheduling platform is used to access the virtual system, receive feedback from the virtual system, or issue instructions to the real production line. S2. Sensors collect production parameters from the real production line and transmit the data to the virtual system in real time. The virtual system and the real production line run synchronously, and the simulated operation scene of the virtual system is displayed in real time on the scheduling platform. S3. The virtual system compares the real-time data transmitted by the sensor with the parameter range. When the parameter is within the specified range, the virtual system simulates normal operation. When the transmitted parameter exceeds or falls below the specified range, the virtual system issues an early warning to the dispatching platform and displays the data anomaly. S4. The user evaluates the abnormal data through the scheduling platform or the scheduling platform itself, and issues instructions to the real system based on the evaluation results.

2. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 1 is characterized by: The digital twin system includes a real production line, a virtual system and a scheduling platform. The virtual system is used to simulate the real production line, monitor the real production line in real time, and issue early warnings for abnormal data.

3. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 1 is characterized by: The virtual system includes a data acquisition module, a data judgment module, a simulation operation module and a fault alarm module. The data acquisition module collects production parameters of the production line in real time and transmits them to the data judgment module. The data judgment module judges the data twice and transmits the data to the simulation operation module or the fault alarm module.

4. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 3 is characterized by: In step s3, the data judgment module first judges and compares whether the data exceeds or falls below the specified range. If it is within the specified range, it is transmitted to the simulation operation module for normal simulation operation. If it is not within the specified range, the abnormal data is subjected to a second step of judgment and comparison to determine whether the abnormal data is dangerous data. Dangerous data is directly transmitted to the fault alarm module, and non-dangerous data is transmitted to the simulation operation module.

5. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 4 is characterized by: The fault alarm module transmits the dangerous data to the scheduling platform, and the scheduling platform automatically issues a shutdown instruction to the production line.

6. The intelligent fault diagnosis and early warning method for production lines based on digital twin technology according to claim 4 is characterized by: The simulation operation module transmits non-dangerous abnormal data to the scheduling platform and displays the abnormal location in the production line of the virtual system.

7. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 6 is characterized by: The scheduling platform includes a data receiving module, an abnormality analysis module, a central control center, an action module and an intelligent decision-making module.

8. The intelligent fault diagnosis and early warning method for production lines based on digital twin technology according to claim 7 is characterized by: The data receiving module is used to receive and transmit abnormal data, the abnormal analysis module is used to analyze the causes and consequences of the corresponding abnormal data, the user makes a decision on the abnormal data through the central control center, the action module handles the abnormality according to the decision of the central control center, and the intelligent decision module collects and deduces the relationship between the abnormal data and the decision of the central control center, and establishes a feature model.

9. The production line intelligent fault diagnosis and early warning method based on digital twin technology according to claim 8 is characterized by: The intelligent decision-making module receives abnormal data transmitted by the data receiving module based on the feature model to simulate the central control center to make decisions, perform early warnings or troubleshooting.

10. The intelligent fault diagnosis and early warning method for production lines based on digital twin technology according to claim 8, characterized in that: When the action module receives different decisions from the central control center and the intelligent decision module at the same time, it feeds back to the central control center for secondary confirmation.

Images