Intelligent fault diagnosis method and system for rotating equipment of nuclear power plant based on digital twinning

Abstract

The application discloses a nuclear power plant rotating equipment intelligent fault diagnosis method and system based on digital twinning, relates to the technical field of intelligent nuclear power plants, and realizes mutual complementation of digital space and real space data through deep learning, solves the problem of insufficient nuclear power plant rotating equipment fault data, realizes multi-source data integration of a diagnosis model based on the idea of data fusion, and can improve the accuracy of diagnosis results; the application also proposes an updating method of a digital twinning model, so that the updating of the digital twinning model can be realized when new working conditions are generated in the operation process of the nuclear power plant rotating equipment or the trained twinning model cannot meet the requirements, thereby guaranteeing the consistency of the digital twinning model and the physical space model.

Description

Technical Field

[0001] This invention relates to the field of intelligent nuclear power plant technology, and in particular to an intelligent fault diagnosis method and system for rotating equipment in nuclear power plants based on digital twins. Background Technology

[0002] With the development of artificial intelligence technology and the continuous introduction of new development plans and requirements, the energy market is constantly evolving, and the demand for nuclear power digitalization is urgent. Combining artificial intelligence methods such as deep learning, fuzzy neural networks, and data fusion methods with traditional nuclear power technologies and equipment is one of the key ways to achieve the transformation of nuclear power technology.

[0003] Pumps, motors, steam turbines, and fans are key components widely present in nuclear power plants, playing a crucial role in their operation. The integrity of this rotating machinery directly impacts the safety and economic efficiency of the nuclear power plant. Due to the unique characteristics of nuclear power plants, the sample size of fault data during operation is significantly smaller compared to non-fault data, and experimental conditions are rarely identical to the real operating environment. Therefore, by leveraging digital twin models, combining experimental and operational data through order reduction techniques and deep learning, and integrating network-generated data with actual operational data, a more comprehensive and accurate digital twin model is obtained. Furthermore, data fusion and digital twin model update techniques ensure consistency between the digital twin model and the physical space model. Combining digital twins with intelligent fault diagnosis technology is of great significance for realizing intelligent fault diagnosis of rotating equipment in nuclear power plants within a digital twin framework and for achieving digital nuclear power. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for intelligent fault diagnosis of rotating equipment in nuclear power plants based on digital twins. This method can achieve mutual supplementation between digital space and physical space data, improve the accuracy of diagnostic results, and enable the updating of digital twin models, thereby ensuring the consistency between digital twin models and physical space models.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] A digital twin-based intelligent fault diagnosis method for rotating equipment in nuclear power plants includes the following steps:

[0007] Step 1: Perform data preprocessing on the operating and experimental data of the rotating equipment in the nuclear power plant;

[0008] Step 2: Store the running data and number of experiments obtained in Step 1 into the database;

[0009] Step 3: Call the running data and experimental data in the database, and perform order reduction processing through the SVD-POD algorithm to map the high-order data of the nuclear power plant rotating equipment to the low-order space to obtain the order-reduced data of the nuclear power plant rotating equipment under various modes.

[0010] Step 4: Based on the reduced-order data of the nuclear power plant rotating equipment obtained in Step 3 and the deep learning algorithm, construct a data-driven digital twin model of the nuclear power plant rotating equipment;

[0011] Step 5: Perform dynamic simulation based on the digital twin model constructed in Step 4 to obtain simulation data of the rotating equipment in the nuclear power plant. This data serves as a supplementary dataset for constructing the fault diagnosis model. Based on the database and the supplementary dataset, train and test the neural network model to obtain the fault diagnosis model.

[0012] Step 6: Acquire real-time multi-source monitoring signals from rotating equipment in the nuclear power plant. After processing the signals using the preprocessing and order reduction methods described in Steps 1 and 3, perform data fusion using DS evidence theory.

[0013] Step 7: Transfer the fused data to the fault diagnosis model;

[0014] Step 8: If the input operating conditions and test results are already available in the database, the fault diagnosis model will perform the diagnosis and output the diagnosis results.

[0015] Step 9: If the input working conditions and test results are unknown data, then the update signal will be sent back to the digital twin model;

[0016] Step 10: After receiving the update signal, the digital twin model establishes new operating mode and boundary conditions, thereby updating the digital twin model and generating corresponding twin data for the fault diagnosis model to learn, call and verify, and further update the fault diagnosis model.

[0017] Step 11: Output the diagnostic results using the updated fault diagnosis model.

[0018] Furthermore, the data preprocessing in step 1 includes: noise reduction and normalization.

[0019] Furthermore, step 4, based on the reduced-order data of the nuclear power plant rotating equipment obtained in step 3 and the deep learning algorithm, constructs a data-driven digital twin model of the nuclear power plant rotating equipment, including:

[0020] S4.1: Input the reduced-order data for rotating equipment in a nuclear power plant;

[0021] S4.2: Generate test and training sets;

[0022] S4.3: Abstract the test set in S4.2 to generate geometric topology information and boundary conditions as real samples;

[0023] S4.4: Abstract the training set in S4.2 to generate geometric topology information and boundary conditions;

[0024] S4.5: Input the geometric topology information and boundary conditions generated in S4.4 into the neural network model for initialization;

[0025] S4.6: Optimize the parameters of the initialized geometric topology information and boundary conditions, and determine whether the maximum number of iterations has been reached. If it has, proceed to S4.7; otherwise, re-optimize the parameters.

[0026] S4.7: Based on the parameter optimization results in S4.6, a trained deep learning model is obtained, and generated samples are obtained;

[0027] S4.8: Mix the real samples obtained in S4.3 with the generated samples obtained in S4.7 to obtain a mixed sample;

[0028] S4.9: Obtain a mathematically driven digital twin model based on the mixed samples obtained in S4.8.

[0029] Furthermore, in step 5, the supplementary dataset can also be operating condition data that has never appeared in the operating history of the supplementary equipment in the digital twin model.

[0030] Furthermore, in step 10, the method for updating the digital twin model includes:

[0031] S10.1: Input the detection results and operating mode;

[0032] S10.2: Validated using a digital twin model;

[0033] S10.3: Determine whether the operating conditions are met. If they are met, keep the condition unchanged; otherwise, proceed to S10.4.

[0034] S10.4: Input new operating mode and boundary conditions;

[0035] S10.5: Abstract the new working conditions and boundary conditions in S10.4 to generate geometric topology information and boundary conditions;

[0036] S10.6: Implement the update;

[0037] S10.7: Determine whether the updated working condition mode and boundary conditions meet the iteration accuracy conditions. If they do, complete the model update; otherwise, return to S10.6.

[0038] The present invention also provides an intelligent fault diagnosis system for rotating equipment in nuclear power plants based on digital twins, including: a data preprocessing module for preprocessing the operating data, experimental data and supplementary datasets of the rotating equipment in nuclear power plants;

[0039] Database: Used to store pre-processed operational and experimental data from rotating equipment in nuclear power plants, as well as supplementary datasets;

[0040] The order reduction module is used to reduce the order of the running and experimental data in the database using the SVD-POD algorithm, mapping the high-order data of the rotating equipment to the low-order space to obtain reduced-order data of the nuclear power plant rotating equipment under various modes; it is also used to reduce the order of the supplementary dataset.

[0041] Digital twin model module: used to generate digital twin models, train and simulate them, and establish new operating conditions and boundary conditions based on received update signals, update the digital twin model, and generate corresponding twin data for the fault diagnosis model to learn, call and verify.

[0042] Data fusion module: used to transmit multi-source monitoring signals from rotating equipment in nuclear power plants to the fault diagnosis system in real time. After preprocessing and reducing the order of the data, the data is fused using DS evidence theory.

[0043] Data transmission module: used to transmit the fused data to the intelligent fault diagnosis algorithm based on fuzzy neural network;

[0044] Fault diagnosis module: Used to determine whether the input operating conditions and detection results are existing data in the database. If so, it performs diagnosis on the existing fault diagnosis model and outputs the diagnosis results; if the input operating conditions and detection results are classified as unknown data, it transmits the new boundary conditions back to the digital twin model module.

[0045] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the embodiments.

[0046] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any embodiment.

[0047] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: In steps 3 and 4 of the intelligent fault diagnosis method and system for rotating equipment in nuclear power plants based on digital twins provided by the present invention, deep learning is used to achieve mutual supplementation between digital space and real space data, solving the problem of insufficient fault data for rotating equipment in nuclear power plants; in step 3, the SVD-POD order reduction method can quickly and effectively reduce the model order, and the reduced model can be well applied to the subsequent digital twin model construction and intelligent fault diagnosis of the present invention. Compared with other methods such as nonlinear order reduction methods or intelligent order reduction methods, it has stronger interpretability and universality, and is more mature. For rotating equipment in nuclear power plants, the latter method may lose some information or cause inaccurate reconstruction information after the model is reduced;

[0048] In step 5, the integration of multi-source data for the diagnostic model is achieved based on the idea of ​​data fusion, which can improve the accuracy of the diagnostic results to a certain extent.

[0049] Steps 7, 9, and 10 propose a method for updating the digital twin model, which ensures that when new operating conditions arise during the operation of rotating equipment in a nuclear power plant or when the trained twin model fails to meet the requirements, the digital twin model can be updated, thereby ensuring the consistency between the digital twin model and the physical space model.

[0050] This invention combines digital twins with intelligent fault diagnosis technology, which is of great significance for realizing intelligent fault diagnosis of rotating equipment in nuclear power plants under the digital twin framework and for digital nuclear power. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a schematic diagram of the fault diagnosis method for rotating equipment in a nuclear power plant based on digital twins according to the present invention.

[0053] Figure 2 This is a schematic diagram illustrating the implementation process of the digital twin model in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram illustrating the implementation process of updating the digital twin model according to an embodiment of the present invention; Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The purpose of this invention is to provide a method and system for intelligent fault diagnosis of rotating equipment in nuclear power plants based on digital twins. This method can achieve mutual supplementation between digital space and physical space data, improve the accuracy of diagnostic results, and enable the updating of digital twin models, thereby ensuring the consistency between digital twin models and physical space models.

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] Example 1

[0059] like Figure 1 As shown in the figure, the intelligent fault diagnosis method for rotating equipment in a nuclear power plant based on digital twins provided in this embodiment of the invention includes the following steps:

[0060] Step 1: Perform data preprocessing such as noise reduction and normalization on the operating data and experimental data of rotating equipment (e.g., pumps, motors, etc.) in the nuclear power plant;

[0061] Step 2: Store the operating data and experimental data of the nuclear power plant's rotating equipment obtained in Step 1 into the database;

[0062] Step 3: Call the running data and experimental data in the database, and perform order reduction processing through the SVD-POD algorithm to map the high-order data of the rotating equipment to the low-order space to obtain the order reduction data of the nuclear power plant rotating equipment under various modes;

[0063] Step 4: Based on the reduced-order data of the nuclear power plant rotating equipment obtained in Step 3 and the deep learning algorithm, construct a data-driven digital twin model of the nuclear power plant rotating equipment;

[0064] Step 5: Perform dynamic simulation based on the digital twin model constructed in Step 4 to obtain simulation data of the rotating equipment in the nuclear power plant. This data serves as a supplementary dataset for constructing the fault diagnosis model. Based on the database and the supplementary dataset, train and test the neural network model to obtain the fault diagnosis model.

[0065] Step 6: Acquire multi-source monitoring signals from rotating equipment in the nuclear power plant. First, preprocess and reduce the order of the data (using the same methods as Step 1 and Step 3), then fuse the data using the Dempster evidence theory.

[0066] Step 7: Transfer the fused data to the fault diagnosis model;

[0067] Step 8: If the input operating conditions and test results are already available in the database, then perform the diagnosis on the existing fault diagnosis model and output the diagnosis results;

[0068] Step 9: If the input working condition and detection classification are unknown data, then the update signal will be sent back to the digital twin model;

[0069] Step 10: After receiving the update signal, the digital twin model establishes new operating conditions and boundary conditions, thereby updating the digital twin model and generating corresponding twin data for the fault diagnosis model to learn, call, and verify, further updating the fault diagnosis model. The implementation process of the digital twin model update is as follows: Figure 3 As shown;

[0070] Step 11: Output the final diagnosis results using the updated fault diagnosis model.

[0071] In this embodiment, as Figure 2 As shown, step 4, based on the reduced-order data of the nuclear power plant rotating equipment obtained in step 3 and the deep learning algorithm, constructs a data-driven digital twin model of the nuclear power plant rotating equipment, including:

[0072] S4.1: Input the reduced-order data for rotating equipment in a nuclear power plant;

[0073] S4.2: Generate test and training sets;

[0074] S4.3: Abstract the test set in S4.2 to generate geometric topology information and boundary conditions as real samples;

[0075] S4.4: Abstract the training set in S4.2 to generate geometric topology information and boundary conditions;

[0076] S4.5: Input the geometric topology information and boundary conditions generated in S4.4 into the neural network model for initialization;

[0077] S4.6: Optimize the parameters of the initialized geometric topology information and boundary conditions, and determine whether the maximum number of iterations has been reached. If it has, proceed to S4.7; otherwise, re-optimize the parameters.

[0078] S4.7: Based on the parameter optimization results in S4.6, a trained deep learning model is obtained, and generated samples are obtained;

[0079] S4.8: Mix the real samples obtained in S4.3 with the generated samples obtained in S4.7 to obtain a mixed sample;

[0080] S4.9: Obtain a mathematically driven digital twin model based on the mixed samples obtained in S4.8.

[0081] In this embodiment, in step 5, the supplementary dataset can also be operating condition data that has never appeared in the operating history of the supplementary equipment in the digital twin model.

[0082] In this embodiment, as Figure 3 As shown, in step 10, the method for updating the digital twin model includes:

[0083] S10.1: Input the detection results and operating mode;

[0084] S10.2: Validated using a digital twin model;

[0085] S10.3: Determine whether the operating conditions are met. If they are met, keep the condition unchanged; otherwise, proceed to S10.4.

[0086] S10.4: Input new operating mode and boundary conditions;

[0087] S10.5: Abstract the new working conditions and boundary conditions in S10.4 to generate geometric topology information and boundary conditions;

[0088] S10.6: Implement the update;

[0089] S10.7: Determine whether the updated working condition mode and boundary conditions meet the iteration accuracy conditions. If they do, complete the model update; otherwise, return to S10.6.

[0090] Example 2

[0091] This embodiment provides an intelligent fault diagnosis system for rotating equipment in nuclear power plants based on digital twins, including: a data preprocessing module, used to preprocess the operating data, experimental data, and supplementary datasets of the rotating equipment in nuclear power plants;

[0092] Database: Used to store pre-processed operational and experimental data from rotating equipment in nuclear power plants, as well as supplementary datasets;

[0093] The order reduction module is used to reduce the order of the running and experimental data in the database using the SVD-POD algorithm, mapping the high-order data of the rotating equipment to the low-order space to obtain reduced-order data of the nuclear power plant rotating equipment under various modes; it is also used to reduce the order of the supplementary dataset.

[0094] Digital twin model module: used to generate digital twin models, train and simulate them, and establish new operating conditions and boundary conditions based on received update signals, update the digital twin model, and generate corresponding twin data for the fault diagnosis model to learn, call and verify.

[0095] Data fusion module: used to transmit multi-source monitoring signals from rotating equipment in nuclear power plants to the fault diagnosis system in real time. After preprocessing and reducing the order of the data, the data is fused using DS evidence theory.

[0096] Data transmission module: used to transmit the fused data to the intelligent fault diagnosis algorithm based on fuzzy neural network;

[0097] Fault diagnosis module: Used to determine whether the input operating conditions and detection results are existing data in the database. If so, it performs diagnosis on the existing fault diagnosis model and outputs the diagnosis results; if the input operating conditions and detection results are classified as unknown data, it transmits the new boundary conditions back to the digital twin model module.

[0098] In some embodiments, a computer-readable storage medium is also provided having a computer program stored thereon that, when executed by a processor, implements the methods described in any of the embodiments.

[0099] In some embodiments, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any embodiment.

[0100] In summary, this invention provides a method and system for intelligent fault diagnosis of rotating equipment in nuclear power plants based on digital twins. Steps 3 and 4 utilize deep learning to complement data from both the digital and physical spaces, addressing the problem of insufficient fault data for rotating equipment in nuclear power plants. Step 5 integrates multi-source data for the diagnostic model based on data fusion, which can improve the accuracy of diagnostic results to a certain extent. Steps 7, 9, and 10 propose a method for updating the digital twin model, ensuring that when new operating conditions arise during the operation of rotating equipment in nuclear power plants or when the trained twin model fails to meet requirements, the digital twin model can be updated, thus guaranteeing consistency between the digital twin model and the physical space model. Combining digital twins with intelligent fault diagnosis technology to achieve intelligent fault diagnosis of rotating equipment in nuclear power plants within a digital twin framework and to realize digital nuclear power is of great significance. Furthermore, since nonlinear or intelligent order reduction methods are not very interpretable or universal, and are relatively immature, the reduced-order model may lose some information or cause inaccurate reconstruction information for rotating equipment in nuclear power plants. Therefore, this invention adopts the SVD-POD method, which can quickly and effectively reduce the order of the model. The reduced-order model is well applicable to the subsequent construction of digital twin models and intelligent fault diagnosis in this invention.

[0101] The remaining technical features in this embodiment can be flexibly selected by those skilled in the art to meet different specific practical needs. However, it will be apparent to those skilled in the art that these specific details are not necessary to implement the present invention. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims. In the above description, numerous specific details have been set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to implement the present invention. In other instances, to avoid obscuring the present invention, well-known techniques, such as specific construction details, operating conditions, and other technical conditions, have not been specifically described.

[0102] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for intelligent fault diagnosis of rotating equipment in a nuclear power plant based on digital twins, characterized in that, Includes the following steps: Step 1: Perform data preprocessing on the operating and experimental data of the rotating equipment in the nuclear power plant; Step 2: Store the running data and experimental data obtained in Step 1 into the database; Step 3: Call the running data and experimental data in the database, and perform order reduction processing through the SVD-POD algorithm to map the high-order data of the nuclear power plant rotating equipment to the low-order space to obtain the order-reduced data of the nuclear power plant rotating equipment under various modes. Step 4: Based on the reduced-order data of the nuclear power plant rotating equipment obtained in Step 3 and the deep learning algorithm, construct a data-driven digital twin model of the nuclear power plant rotating equipment; Step 5: Perform dynamic simulation based on the digital twin model constructed in Step 4 to obtain simulation data of the rotating equipment in the nuclear power plant. This data serves as a supplementary dataset for constructing the fault diagnosis model. Based on the database and the supplementary dataset, train and test the neural network model to obtain the fault diagnosis model. Step 6: Acquire real-time multi-source monitoring signals from rotating equipment in the nuclear power plant, process them according to the preprocessing and order reduction methods in Steps 1 and 3, and then perform data fusion using DS evidence theory; Step 7: Transfer the fused data to the fault diagnosis model; Step 8: If the input operating conditions and test results are already available in the database, the fault diagnosis model will perform the diagnosis and output the diagnosis results. Step 9: If the input working conditions and test results are unknown data, then the update signal will be sent back to the digital twin model; Step 10: After receiving the update signal, the digital twin model establishes new operating mode and boundary conditions, thereby updating the digital twin model and generating corresponding twin data for the fault diagnosis model to learn, call and verify, and further update the fault diagnosis model. Step 11: Output the diagnostic results using the updated fault diagnosis model.

2. The intelligent fault diagnosis method for rotating equipment in nuclear power plants based on digital twins according to claim 1, characterized in that, The data preprocessing in step 1 includes: noise reduction and normalization.

3. The intelligent fault diagnosis method for rotating equipment in nuclear power plants based on digital twins according to claim 1, characterized in that, Step 4, based on the reduced-order data of the nuclear power plant's rotating equipment obtained in Step 3 and the deep learning algorithm, constructs a data-driven digital twin model of the nuclear power plant's rotating equipment, including: S4.1: Input the reduced-order data for rotating equipment in a nuclear power plant; S4.2: Generate test and training sets; S4.3: Abstract the test set in S4.2 to generate geometric topology information and boundary conditions as real samples; S4.4: Abstract the training set in S4.2 to generate geometric topology information and boundary conditions; S4.5: Input the geometric topology information and boundary conditions generated in S4.4 into the neural network model for initialization; S4.6: Optimize the parameters of the initialized geometric topology information and boundary conditions, and determine whether the maximum number of iterations has been reached. If it has, proceed to S4.7; otherwise, re-optimize the parameters. S4.7: Based on the parameter optimization results in S4.6, a trained deep learning model is obtained, and generated samples are obtained; S4.8: Mix the real samples obtained in S4.3 with the generated samples obtained in S4.7 to obtain a mixed sample; S4.9: Obtain a mathematically driven digital twin model based on the mixed samples obtained in S4.

8.

4. The intelligent fault diagnosis method for rotating equipment in a nuclear power plant based on digital twins according to claim 1, characterized in that, In step 5, the supplementary dataset also includes operating condition data that has never appeared in the operating history of the equipment supplemented by the digital twin model.

5. As described in claim 1, characterized in that, In step 10, the method for updating the digital twin model includes: S10.1: Input the detection results and operating mode; S10.2: Validated using a digital twin model; S10.3: Determine whether the operating conditions are met. If they are met, keep the condition unchanged; otherwise, proceed to S10.

4. S10.4: Input new operating mode and boundary conditions; S10.5: Abstract the new working conditions and boundary conditions in S10.4 to generate geometric topology information and boundary conditions; S10.6: Implement the update; S10.7: Determine whether the updated working condition mode and boundary conditions meet the iteration accuracy conditions. If they do, complete the model update; otherwise, return to S10.

6.

6. A digital twin-based intelligent fault diagnosis system for rotating equipment in a nuclear power plant, characterized in that, include: The data preprocessing module is used to preprocess the operating data and experimental data of the rotating equipment in the nuclear power plant, as well as the supplementary dataset. Database: Used to store pre-processed operational and experimental data from rotating equipment in nuclear power plants, as well as supplementary datasets; The order reduction module is used to reduce the order of the running and experimental data in the database using the SVD-POD algorithm, mapping the high-order data of the rotating equipment to the low-order space to obtain reduced-order data of the nuclear power plant rotating equipment under various modes; it is also used to reduce the order of the supplementary dataset. Digital twin model module: used to generate digital twin models, train and simulate them, establish new operating conditions and boundary conditions based on received update signals, update the digital twin model, and generate corresponding twin data for the fault diagnosis model to learn, call and verify. Data fusion module: used to transmit multi-source monitoring signals from rotating equipment in nuclear power plants to the fault diagnosis system in real time. After preprocessing and reducing the order of the data, the data is fused using DS evidence theory. Data transmission module: used to transmit the fused data to the intelligent fault diagnosis algorithm based on fuzzy neural network; Fault diagnosis module: Used to determine whether the input operating conditions and detection results are existing data in the database. If so, it performs diagnosis on the existing fault diagnosis model and outputs the diagnosis results; if the input operating conditions and detection results are classified as unknown data, it transmits the new boundary conditions back to the digital twin model module.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 5.

Images