Health management system for optoelectronic equipment based on digital twinning

Abstract

The application discloses an optoelectronic equipment health management system based on digital twinning, which comprises an optoelectronic equipment health management system, a portable diagnostic tool ATE and an in-field health management training platform; wherein the optoelectronic equipment health management system comprises a real-time state monitoring module, a fault diagnosis module, a fault prediction module and the like; the portable diagnostic tool ATE is used for deep fault diagnosis, online maintenance, data collection, expert algorithm model updating and parameter updating; the in-field health management training platform is used for supporting the optimization iteration of intelligent algorithm models and parameters of fault prediction and diagnosis, health management, task decision and support decision, and the in-field model training is completed by connecting the in-field health management training platform with the portable diagnostic tool ATE brought back from the field, importing the state data and health management process data of the field optoelectronic equipment, and the like. The application can accurately predict the health state of the field optoelectronic equipment, accurately generate a maintenance time and a maintenance strategy, and effectively solves the problem of optoelectronic equipment health management.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of equipment maintenance support, in particular to a kind of optoelectronic equipment health management system based on digital twinning. BACKGROUND

[0002] The existing optoelectronic equipment health management is still in the primary stage, can only collect the state of some key components, and roughly judge whether there is a fault according to the state. For example, whether the voltage or current of the circuit board is abnormal, whether the case temperature is too high, whether the detector cannot be cooled, etc. The existing optoelectronic equipment health management technology cannot support high-efficiency maintenance support at this stage, either until the equipment cannot work to carry out maintenance, delaying the task progress, or in the case of healthy equipment state, carrying out component replacement, causing resource waste. It is urgently needed to carry out research on optoelectronic equipment health management technology based on digital twinning to improve the maintenance support capability for optoelectronic equipment. SUMMARY

[0003] The main purpose of the present application is to provide an optoelectronic equipment health management system based on digital twinning, which can establish a parallel digital prototype of the optoelectronic equipment in the actual use process through digital technology, predict the health state of the optoelectronic equipment in real time, carry out maintenance strategy design, optimize the maintenance time and task to the greatest extent, save support cost, and improve support efficiency.

[0004] The technical scheme adopted by the present application is:

[0005] An optoelectronic equipment health management system based on digital twinning is provided, which comprises an optoelectronic equipment health management system, a portable diagnostic tool ATE and an in-field health management training platform; wherein:

[0006] The optoelectronic equipment health management system comprises a real-time state monitoring module, a fault diagnosis module, a fault prediction module, a health management module, a task decision module and a support decision module. The real-time state monitoring module collects the multi-physical parameters of each key component and subsystem of the optoelectronic equipment and transmits them to the fault diagnosis module, the fault prediction module and the health management module. The fault diagnosis module and the fault prediction module use fault prediction algorithms to perform fault diagnosis and prediction according to the real-time state monitoring data. The health management module determines the health state according to the fault diagnosis and prediction. The task decision module and the support decision module determine the maintenance strategy and maintenance time according to the fault condition and health state;

[0007] The portable diagnostic tool ATE is used for deep fault diagnosis, online maintenance, data collection, expert algorithm model updating and parameter updating;

[0008] The internal field health management training platform is used for supporting optimization iteration of intelligent algorithm models and parameters of fault prediction and diagnosis, health management, task decision and support decision, and is connected with the portable diagnostic tool ATE brought back from the external field, imports state data and health management process data of the photoelectric equipment in the external field, and completes internal field model training.

[0009] According to the technical solution, the photoelectric equipment health management system further includes a man-machine interaction module and a data storage module, the data storage module is responsible for storing data, and the man-machine interaction module is used for providing services for equipment users in the form of man-machine interaction, and the man-machine interaction includes state display, fault display, BIT display, health state, prediction state, resource monitoring and decision tracking.

[0010] According to the technical solution, the internal field health management training platform is further used for updating health management related parameters in the digital twin system of the photoelectric equipment, keeping synchronization with the state of the equipment in the external field, and achieving the health management function in the laboratory.

[0011] According to the technical solution, the simulated photoelectric equipment system is generated in advance based on the digital twin technology.

[0012] According to the technical solution, the photoelectric equipment system simulation model library is established based on the Modelica technology.

[0013] According to the technical solution, the photoelectric equipment health management system adopts a five-layer structure based on a J2EE multi-layer architecture system, and the five layers are, from bottom to top, a persistence layer, a data access layer, a business application layer, a Web interface layer and a man-machine interaction layer.

[0014] According to the technical solution, the photoelectric equipment health management system further includes an external data interface and a public service architecture.

[0015] According to the technical solution, the persistence layer is used for saving related data of the system, and a corresponding database is selected according to the use situation and scene of the system.

[0016] The data access layer is used for completing basic operations of data required by the system.

[0017] The business application layer is used for dividing function modules according to related business logic functions, and realizing related business functions.

[0018] The business application layer is used for dividing function modules according to related business logic functions, and realizing related business functions.

[0019] The Web interface layer provides external systems with interfaces to access these systems via the HTTP protocol. This layer performs basic validation on the data related to the access operation. Simultaneously, it passes the request to the business application layer for further business processing. Finally, the interface returns the data results in a specific format, commonly including JSON or XML data.

[0020] The human-computer interaction layer includes the pages requested by the user, showcasing the system's business modules, and handling user-related requests.

[0021] Following the above technical solution, wherein:

[0022] The public service architecture is used to provide a standard framework including the OSA-CBM open architecture for condition-based maintenance, a power supply system simulation model algorithm configuration management framework, and a user permission management framework based on Spring Security.

[0023] External data interfaces are used to support the exchange of different types of data.

[0024] Following the above technical solution, the business application layer is also used for data transmission. The basic business domain objects used inherit from the relevant interfaces defined by the OSA-CBM standard to ensure that data systems can be exchanged. Through the corresponding algorithm running engine, the relevant configuration files are parsed, the relevant business module algorithms are dynamically loaded, and the relevant simulations are automatically configured.

[0025] The beneficial effects of this invention are as follows: The optoelectronic equipment health management system based on digital twins constructed by this invention can store data such as status monitoring data, prediction results, and actual failure modes during operation. Field data can be brought back using a portable diagnostic tool (ATE), and the health management model can be continuously optimized using an indoor offline training platform. The optimized model is then updated using the portable diagnostic tool ATE to update the field optoelectronic equipment failure prediction and health management model. Through this digital twin system, the health status of field optoelectronic equipment can be accurately predicted, and maintenance timing and strategies can be accurately generated. This invention effectively solves the problem of optoelectronic equipment health management. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1is a structural schematic diagram of a photoelectric equipment fault prediction and health management system of an embodiment of the present application;

[0028] Figure 2 is a health management simulation modeling technology roadmap based on digital twinning of an embodiment of the present application;

[0029] Figure 3 is a Modelica model construction flowchart of a key component of an embodiment of the present application;

[0030] Figure 4 is a Modelica model schematic diagram of an embodiment of the present application;

[0031] Figure 5 is a fault injection flowchart of an embodiment of the present application;

[0032] Figure 6 is a general function framework diagram of a photoelectric equipment PHM software of an embodiment of the present application;

[0033] Figure 7 is a software framework schematic diagram of an online monitoring and health management software system. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0035] The overall framework of the photoelectric equipment health management system based on digital twinning of an embodiment of the present application is as shown in Figure 1 , which is divided into three parts, including a photoelectric equipment health management system, a portable diagnostic tool ATE and an in-field health management training platform.

[0036] The optoelectronic equipment health management system comprises a real-time state monitoring module, a fault diagnosis module, a fault prediction module, a health management module, a task decision module, a support decision module, a man-machine interaction module, and a data storage module. The real-time state monitoring module collects and transmits the multi-physical parameters of each key component and subsystem of the optoelectronic equipment to the fault diagnosis module, the fault prediction module, and the health management module. The fault diagnosis and prediction module performs fault diagnosis and prediction by using a fault prediction algorithm software according to the real-time state monitoring data. The health management module determines the health state according to the fault diagnosis and prediction. The task decision and support decision module determines the maintenance strategy and timing according to the fault condition and the health state. In order to continuously optimize and iterate the health management model, the monitoring state data of the equipment at all times, as well as the fault prediction and health state data, need to be stored. The data storage unit is responsible for storing the data. The health management system of the optoelectronic equipment needs to provide services for the equipment users in the form of man-machine interaction. The man-machine interaction includes state display, fault display, BIT display, health state, prediction state, resource monitoring, and decision tracking.

[0037] The portable diagnostic tool ATE is used for deep fault diagnosis, online maintenance, data collection, expert algorithm model updating, and parameter updating. During the support maintenance of the optoelectronic equipment, the portable diagnostic tool ATE is connected with the optoelectronic equipment maintenance special interface to complete the corresponding tasks.

[0038] The in-field health management training platform supports the optimization and iteration of intelligent algorithm models such as fault prediction and diagnosis models, health management models, task decision and support decision models, and parameters. It is connected with the portable diagnostic tool ATE brought back from the field, imports the state data and health management process data of the field optoelectronic equipment, and completes the in-field model training. The in-field health management training platform updates the health management related parameters in the optoelectronic equipment digital twin system, keeps the state synchronization with the field equipment, and achieves the health management function in the laboratory. Combined with the digital twin, the quality characteristics of the optoelectronic equipment are demonstrated and designed.

[0039] The health management simulation modeling technology route based on digital twin is shown in Figure 2 , which mainly includes the following processes:

[0040] (1) Optoelectronic equipment system simulation modeling technology based on Modelica

[0041] ① Establishment of key component Modelica simulation model library

[0042] Firstly, the photoelectric equipment system composition is analyzed, and the system and subsystem are decomposed into the most basic bottom components, such as resistance, capacitance, mechanical link, etc. according to the field. Then, the physical equations for describing the working principle of the components are constructed from the aspects of fluid dynamics, structural mechanics, electricity, etc. according to the different fields of the basic components, so as to realize the quantitative description of the mutual relationship of each variable inside the component and the input and output of the component. And the parameter values required for modeling are determined according to the design file, industry standard, structure size, etc. of the component. On this basis, the component model is constructed using Modelica language based on the system of equations. Then, the basic components are defined as class objects by using the object-oriented modeling characteristics of Modelica language, and the reusability of the basic components is improved and the modeling workload is reduced by means of component inheritance and derivation. Finally, the relatively complex high-level components or subsystems in the field are gradually built based on the bottom components in each field, and a clear and well-organized model library with clear hierarchical structure is finally formed in each field. The above model construction process is as shown in Figure 3 .

[0043] ②Establishment of photoelectric equipment system simulation model

[0044] In order to realize the data interaction between models in different fields and study the mutual coupling relationship between components, especially the transmission relationship of control signals, energy and matter between different types of components, the definition of model interface is needed, including translation interface, mechanical interface, gas interface, rotary interface, real number interface, current interface, etc. Different variable types and data structures are designed in the interface, such as defining flow variables, potential variables, input and output vectors, etc. to realize the signal interaction of components in different fields through specific interfaces. According to the structure of the system, the components in each field in the model library are called and connected through specific interfaces to complete the establishment of the physical layer architecture of the photoelectric shielding system. Finally, the necessary control logic, termination conditions and other constraint codes are written using Modelica language to complete the establishment of the overall model of the multi-field system. A typical Modelica model diagram is as shown in Figure 4 .

[0045] ③Verification and optimization of model

[0046] There are a large number of coefficients and model parameters in the system of equations of each field model which cannot be accurately determined and are valued according to experience. Therefore, the simulation model parameter selection is verified and optimized by using the key parameters such as fuel consumption rate and engine speed as the evaluation index of the accuracy of the simulation model.

[0047] Considering the large number of model parameters, different processing methods should be taken for different parameters: if the component has only a single uncertain modeling parameter or each parameter is relatively independent, the test data can be directly fitted to obtain the parameter estimate. For the key parameters of the main components of the model, such as the flow contraction coefficient of thin-walled holes and short holes, the area of small holes, the viscosity of oil leakage in slender holes and the travel of liquid resistance, etc., the interpolation method can be used to find the appropriate numerical range, and the parameters of the corresponding balance equation in the experimental data curve are fitted; such as liquid viscosity parameters, etc., the method of machine learning can be used for iterative fitting to obtain the estimated value of the parameter, and ensure the consistency of the model with the actual running state. For parameter changes under different working conditions, non-key parts of the model, such as the bulk modulus of the oil, the rate of volume change, etc., since their influence on the main output parameters of the entire system is not large, they can be screened and estimated, and linear programming, least squares regression, etc. can be used to quickly obtain the parameter value.

[0048] For components with complex physical processes, considering the correlation between each modeling coefficient, the analysis of a single modeling parameter cannot obtain the optimal simulation model. The robust parameter design method based on generalized linear model is used to identify the significance of each modeling parameter to be determined, and the model is iteratively optimized according to the Bayesian evaluation criterion DIC to select the key parameters and coefficients of the component modeling.

[0049] (2) Environmental loading technology of optoelectronic device simulation model

[0050] ① Study on the relevance of environmental variables and simulation models

[0051] Environmental temperature, vibration, humidity and other factors have a significant impact on the dynamic working process of mechanical, hydraulic and fluid fields, and should be the main environmental factors studied. Components in various fields will be affected by the environment to varying degrees. In order to simplify modeling and calculation, components and parameters that are not significantly affected by the environment are excluded, and only the changes of parameters that are significantly affected by the environment under different environmental conditions are considered. First, through the analysis of the actual use data of optoelectronic devices, it is clear which components or modeling parameters are significantly affected by environmental factors and are selected as the research object; then, environmental tests are conducted on the selected components or modeling parameters, the input-output relationship and the change of related performance parameters of the components under different environmental conditions are analyzed, and the test data is fitted into the empirical formula of the modeling parameters with the change of the environment combined with the original modeling physical equation set; finally, the above empirical formula is written and integrated into the Modelica model of the component to establish the association between the environment and the simulation model.

[0052] ② Study on environmental factor loading technology based on Simulink

[0053] According to the analysis results of the component environmental test, environmental input interfaces are added to the modeling parameters affected by the environment in the Modelica model of the related components, the environmental variables are introduced from outside the component to the inside, and the modeling parameters change in real time with the environment in the calculation iteration. Add input and output interfaces for each environmental variable and necessary model output in the overall system level model, and encapsulate the model into a Simulink calculation module with simple structure and only input and output interfaces through MWorks software. Based on the Simulink platform, connect the sensor and acquisition card, and collect environmental variable data in various potential system operating environments. Preprocess the data in Simulink to change the data structure to be compatible with the Modelica model of the system, such as adjusting the frequency of environmental data to match the iteration interval of the Modelica model. The types of environmental variables are different, and their distribution and loading methods are also different. For temperature and humidity, there is no obvious rule in their distribution and change, so they can be directly loaded into the system model through the input interface; for vibration signals, the value is usually related to the running state of the system itself, such as the vibration intensity of the photoelectric control motor at different speeds, which has a significant difference, in this case, different vibration signal data should be loaded according to the running state data output by the output interface of the system model. The above loading logic is implemented in the Simulink environment programming to complete the loading of environmental variables.

[0054] (3) Fault simulation injection and sample feature extraction technology based on simulation model

[0055] ① Fault modeling and injection of photoelectric equipment system

[0056] With the help of FMEA files, the FTA method is used to study the fault mechanism of typical fault modes of photoelectric equipment system, such as unstable scanning servo and air-tight cavity leakage, etc., to clearly define the causes of the fault, the consequences of the fault and the affected modeling parameters, and to establish the correspondence between the fault mode and the model parameters. Define the fault parameters and map the fault causes to the modeling parameters. Combine the component's own working principle equation set and the influence of fault parameters on component function implementation, and write fault parameters into modeling equations according to test, historical data fitting, empirical formula, etc. Different types of faults have different fault modeling methods, which are divided into sudden faults and functional degradation faults. For sudden faults, add a logical switch inside the component model, change the values of related fault parameters and modeling parameters in a jump way according to certain logical rules, to realize the suddenness of the fault; for degradation faults, add degradation equations to related model parameters, so that the parameters naturally decay according to certain rules, to realize the gradual degradation of component performance, and realize the modeling injection of faults, the main process is as shown in Figure 5

[0057] ② Fault sample feature extraction technology​

[0058] Using the simulation model after fault injection, the fault simulation is checked, each simulation variable is analyzed, and the difference between the value in the fault state and the normal working state is analyzed, such as variable value producing unstable fluctuation, producing significant drift or change trend change. Taking the fault source as the starting point, the variables producing synchronous change in time are extracted, the path of fault propagation is summarized, and the fault propagation event chain is constructed. For the injected fault, repeated simulation is carried out under different environments and different fault severity, and a plurality of groups of value samples of simulation variables on the event chain are extracted. Using SVM, PCA and other machine learning algorithms, the data characteristics are analyzed, the actual impact of the injected fault on the system is summarized, the difference between different fault modes in the fault characteristic value is distinguished, and the development of fault diagnosis algorithm is guided.

[0059] As shown in Figure 6 , the online monitoring and health management software of optoelectronic equipment mainly realizes the functions of health status overview, monitoring parameter real-time curve display, health status evaluation, fault diagnosis, fault early warning, historical fault information recording and management, fault prediction and the like.

[0060] Based on the software framework realized by the online monitoring and health management software system, considering the cross-platform and convenient use and the like, a B / S framework based on Java web is selected as the realization mode. The specific framework structure is as shown in Figure 7 .

[0061] The system is designed by using B / S architecture and J2EE multi-layer architecture system. It can support various system environments such as domestic operating system and Windows operating system. The system has platform independence, and after the system deployment is completed, any platform can be used to realize the access operation of the system by using the related browser.

[0062] The system adopts a five-layer structure based on J2EE multi-layer architecture system, which is persistence layer, data access layer, business application layer, Web interface layer and human-computer interaction layer from bottom to top. In addition, the system also contains external data interface and public service architecture. By using the structure, the system has good expansibility, flexibility and stability.

[0063] The persistence layer is used to save the related data of the system. According to the business needs of the user, the system divides the data content in the system, establishes the related data table, saves the data in the system, and according to the use situation and scene of the system, the corresponding database (such as Oracle, SqlServer) can be selected.

[0064] Data access layer, the system through the data access layer to complete the basic operation of the data required by the system. According to the system requirements, and the characteristics of the related database can choose the original ODBC / JDBC or use mature framework such as: Hibernate, etc.

[0065] Business application layer, according to the system related business logic function, for the function module is divided, realizes the related business function. For data transmission, the basic business domain object used in the interface is inherited from the OSA-CBM standard definition, which ensures the exchange between data systems. Through the algorithm running engine, the related configuration file is parsed, and the related business module algorithm is dynamically loaded, and the related simulation is completed flexibly.

[0066] Web interface layer, provides external system through HTTP protocol method system related interface, web interface layer to access the operation of the related data for simple check. While completing the related check, the request is transmitted into the business application layer to complete the related business processing. Finally, the interface returns the related data results according to certain form, common form includes JSON format data, XML type data, etc.

[0067] Human-computer interaction layer, including the related page of user request, showing the business module of the system. Process the related request of user processing.

[0068] Common service architecture: provides the OSA-CBM (open architecture for state maintenance) standard framework, power supply system simulation model algorithm configuration management framework, and user permission management framework based on Spring Security.

[0069] External data interface: supports different types of data exchange, with the characteristics of modularization, strong scalability, etc.

[0070] After completing the overall architecture of the system, according to the related function of the demand, the system is designed in detail, including the decomposition of each function module, the classes and interfaces included in each module, etc. At the same time, the database design is carried out on the selected data, and the design of the related tables, views, etc. of the system is completed.

[0071] Development and system test: after completing the system design work, carry out the specific development work, before the actual development work, the system development plan should be made, and the related commissioning test work should be arranged in time to follow up. Reduce the risk of a large number of rework in the development work. Online monitoring and health management system needs to be considered in different situations, and different parameters of the target equipment may be generated. After completing the development of all related function modules, system integration test needs to be carried out. Ensure the correct and stable operation of the system.

[0072] In summary, the present application fills the blank in the field of health management of photoelectric equipment in China. During the operation of the field photoelectric equipment fault prediction and health management system, state monitoring data, prediction results, actual fault modes and other data are stored. The field data is brought back through the portable diagnostic tool ATE, and the health management model is continuously optimized by using the off-line training platform in the field. Then the optimized model is updated to the field photoelectric equipment fault prediction and health management model through the portable diagnostic tool ATE. Through the digital twin system, the health status of the field photoelectric equipment is accurately predicted, and the maintenance opportunity and maintenance strategy are accurately generated. The present application effectively solves the problem of health management of photoelectric equipment.

[0073] It should be understood that, for those skilled in the art, improvements or changes can be made according to the above description, and all these improvements and changes shall belong to the protection scope of the appended claims of the present application.

Claims

1. A digital-twin-based optoelectronic equipment health management system, characterized in that, The application relates to a photoelectric equipment health management system, a portable diagnostic tool ATE and an in-field health management training platform. The photoelectric equipment health management system comprises a real-time state monitoring module, a fault diagnosis module, a fault prediction module, a health management module, a task decision module and a support decision module, wherein the real-time state monitoring module collects multiple physical parameters of key components and subsystems of photoelectric equipment and transmits the parameters to the fault diagnosis module, the fault prediction module and the health management module; the fault diagnosis module and the fault prediction module perform fault diagnosis and prediction by using a fault prediction algorithm according to real-time state monitoring data; the health management module determines a health state according to the fault diagnosis and prediction; and the task decision module and the support decision module determine a maintenance strategy and a maintenance time according to the fault condition and the health state. The portable diagnostic tool ATE is used for deep fault diagnosis, online maintenance, data collection, expert algorithm model updating and parameter updating. The in-field health management training platform is used for supporting optimization and iteration of intelligent algorithm models and parameters of fault prediction and diagnosis, health management, task decision and support decision, and the platform is connected with the portable diagnostic tool ATE brought back from a field, imports state data and health management process data of photoelectric equipment in the field, and completes in-field model training. The simulation modeling process of the photoelectric equipment health management system is as follows: a Modelica simulation model library of key components of photoelectric equipment systems is constructed; components in each field in the model library are called and connected through specific interfaces to complete establishment of an overall simulation model at a physical level; the overall simulation model is verified and optimized; environment variables are loaded to the optimized simulation model; different types of fault models of photoelectric equipment systems are injected into the simulation model; fault simulation is performed by using the fault-injected simulation model, fault sample features are extracted, and a fault propagation event chain is constructed.

2. The digital-twin-based optoelectronic equipment health management system according to claim 1, characterized in that, The photoelectric equipment health management system further comprises a man-machine interaction module and a data storage module, the data storage module is responsible for storing data, and the man-machine interaction module is used for providing services for equipment users in the form of man-machine interaction, and man-machine interaction includes state display, fault display, BIT display, health state, prediction state, resource monitoring and decision tracking.

3. The digital-twin-based optoelectronic equipment health management system according to claim 1, wherein, The in-field health management training platform is also used for updating health management related parameters in a photoelectric equipment digital twin system, keeping synchronization with a state of equipment in a field and achieving health management functions in a laboratory.

4. The digital-twin-based optoelectronic equipment health management system of claim 1, wherein, The photoelectric equipment health management system adopts a five-layer structure based on a J2EE multi-layer architecture system, and the five layers are, from bottom to top, a persistence layer, a data access layer, a business application layer, a Web interface layer and a man-machine interaction layer.

5. The digital-twin-based optoelectronic equipment health management system of claim 1, wherein, The photoelectric equipment health management system further comprises an external data interface and a public service architecture.

6. The digital-twin-based optoelectronic equipment health management system according to claim 5, characterized in that, The persistence layer is used for saving related data of the system, and a corresponding database is selected according to a use condition and a scene of the system; 7. The digital-twin-based optoelectronic equipment health management system according to claim 5, wherein, The data access layer is used for completing basic operations of data required by the system; The business application layer is used for dividing function modules according to relevant business logic functions and realizing relevant business functions; ​ ​ The web interface layer provides relevant interfaces of the system for external systems through HTTP protocol methods, and performs simple verification on relevant data of an access operation; when the relevant verification is completed, the web interface layer transmits a request into a business application layer to complete relevant business processing; finally, the interface returns relevant data results in a certain form, and common forms include JSON format data and XML type data. The human-computer interaction layer includes relevant pages of a user request, and presents business modules of the system; the human-computer interaction layer processes relevant requests handled by the user.

8. The digital-twin-based optoelectronic equipment health management system according to claim 6, wherein, Among them: The common service architecture is used for providing a standard framework of an open system architecture for condition-based maintenance (OSA-CBM), a power supply system simulation model algorithm configuration management framework, and a user permission management framework based on Spring Security; The external data interface is used for supporting exchange of different types of data.

9. The digital-twin-based optoelectronic equipment health management system according to claim 7, wherein, The business application layer is also used for data transmission, basic business domain objects used are inherited from relevant interfaces defined in the OSA-CBM standard, data systems are guaranteed to be exchangeable, and through a corresponding algorithm running engine, relevant configuration files are parsed, relevant business module algorithms are dynamically loaded, and relevant simulation is automatically configured.

Images