A digital twin health monitoring method and system for an energy storage converter

Abstract

The application provides a digital twin health monitoring method and system of an energy storage converter, the method comprising: collecting and preprocessing operation data of the energy storage converter, and constructing a digital twin model comprising a geometric model and a mathematical model based on the operation data and physical characteristics of the energy storage converter; inputting the preprocessed operation data into the digital twin model for real-time simulation to obtain internal state parameters and stress parameters of the energy storage converter; determining health indexes of components in the energy storage converter based on the internal state parameters; predicting the remaining service life of the energy storage converter according to the stress parameters; and determining the health state grade and maintenance suggestions of the energy storage converter according to the health indexes and / or the remaining service life. The technical scheme provided by the application realizes real-time and accurate evaluation of the health state of the energy storage converter, scientific prediction of the remaining life, and collaborative early warning of faults, and significantly improves the reliability and operation and maintenance efficiency of the equipment.

Description

Technical Field

[0001] This application relates to the field of energy storage converter monitoring technology, and in particular to a digital twin health monitoring method and system for energy storage converters. Background Technology

[0002] With the continuous increase in the proportion of new energy power generation, energy storage systems are playing an increasingly crucial role in grid peak shaving, frequency support, and improving the absorption capacity of renewable energy. As the core power conversion and control equipment of energy storage systems, the stability and reliability of the energy storage converter directly affect the performance, lifespan, and economic benefits of the entire energy storage system.

[0003] Currently, the industry's monitoring of energy storage converter operation mainly relies on data acquisition and monitoring systems, whose functions are mostly limited to real-time display, historical storage, and over-limit alarms of basic operating parameters such as voltage, current, and temperature. These traditional methods have several prominent drawbacks: 1. One-sided and delayed condition assessment: Existing monitoring methods can only acquire limited, superficial operating parameters, failing to intuitively reflect real-time changes in key internal state parameters such as junction temperature of power devices and equivalent series resistance of capacitors. Health status assessment often relies on simple threshold comparisons, lacking a comprehensive and quantitative assessment of the overall performance degradation of the equipment. Alarms are usually triggered only after significant performance degradation or failure, a "post-event" approach that cannot provide early warning. 2. Lack of scientific lifespan prediction capabilities: Current technology struggles to effectively predict the remaining lifespan of energy storage converters, especially their easily aging components (such as IGBT modules and DC support capacitors). Maintenance strategies are mainly based on fixed time periods or operational experience, potentially leading to "over-maintenance" increasing costs or "under-maintenance" causing unexpected downtime, resulting in suboptimal equipment utilization and economic efficiency. 3. Isolated Monitoring Indicators and a Single Early Warning Mechanism: Alarm information generated by the system is usually isolated, only reflecting the exceeding of limits for a single parameter, failing to correlate and coordinate health indicators reflecting the "current state" with life prediction indicators reflecting the "future trend." This results in insufficient accuracy of early warnings and cannot provide clear and well-founded guidance for maintenance decisions. 4. Lack of Dynamic Simulation and Verification Methods: Traditional methods cannot construct a virtual model synchronized with the physical equipment in real time. Therefore, they cannot simulate and extrapolate the operating status of the equipment under complex conditions such as different loads and environments, nor can they simulate and analyze the impact of potential faults, limiting the foresight and adaptability of operation and maintenance decisions. In summary, the current health management methods for energy storage converters are insufficient to meet the urgent needs of new power systems for high reliability, high availability, and intelligent operation and maintenance. Therefore, there is an urgent need for an intelligent health monitoring technology that can deeply integrate real-time data, achieve accurate status assessment, scientific life prediction, and support forward-looking decision-making. Summary of the Invention

[0004] This application provides a digital twin health monitoring method and system for energy storage converters, which at least solves the technical problems of traditional monitoring methods for energy storage converters being unable to reflect the true internal state in real time, lacking quantitative health assessment and scientific life prediction capabilities, thus leading to delayed early warning and inaccurate maintenance.

[0005] The first aspect of this application provides a digital twin health monitoring method for an energy storage converter, the method comprising: Collect and preprocess the operating data of the energy storage converter, and construct a digital twin model containing geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter; The preprocessed operating data is input into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter. The health index of each component in the energy storage converter is determined based on the internal state parameters. Predict the remaining service life of the energy storage converter based on the stress parameters; The health status level and maintenance recommendations for the energy storage converter are determined based on the health index and / or the remaining service life.

[0006] Preferably, the process of collecting and preprocessing the operating data of the energy storage converter includes: A distributed sensor network is used to collect operating data from the energy storage converter, and redundant data is processed through a data fusion algorithm.

[0007] Furthermore, the construction of a digital twin model, comprising geometric and mathematical models, based on the operational data and the physical characteristics of the energy storage converter includes: Based on the aforementioned operating data and the physical characteristics of the energy storage converter, a digital twin model containing geometric and mathematical models is constructed using a multiphysics coupling modeling method. The internal state parameters include: the junction temperature of the power semiconductor device, the equivalent series resistance of the capacitor, or the core saturation of the inductor.

[0008] Furthermore, determining the health index of each component within the energy storage converter based on the internal state parameters includes: Identify multiple evaluation indicators that affect the health of components; The analytic hierarchy process (AHP) is used to assign weights to each evaluation indicator. The fuzzy comprehensive evaluation method is used to determine the membership degree of the component to each evaluation index based on the internal state parameters; The health index is calculated by weighting based on the weights and membership degrees.

[0009] Furthermore, the formula for calculating the remaining service life of the energy storage converter includes:

[0010] In the formula, RUL represents the remaining lifetime. Where S is the reference life and S is the stress level. The reference stress level is n, where n is the stress exponent. The activation energy is given by k, Boltzmann constant is given by T, and T is given by T. Reference temperature; The stress parameters include: stress level and stress index.

[0011] Furthermore, determining the health status level and maintenance recommendations for the energy storage converter based on the health index and the remaining service life includes: The current status level of the energy storage converter is determined based on the preset health level classification threshold. An alert is triggered when the current status level corresponding to the health index is a warning level, or when the remaining lifespan is less than a preset time warning threshold. An alert is triggered when the current status level corresponding to the health index is the attention level and the remaining lifespan is less than N times the time warning threshold; where N is a coefficient greater than 1. The current status levels include: normal level, attention level, and warning level; The preset health level classification thresholds include: a first health level classification threshold and a second health level classification threshold, wherein the first health level classification threshold is greater than the second health level classification threshold. When the health index is greater than or equal to the first health level classification threshold, the current status level of the energy storage converter is determined to be normal. When the health index is greater than or equal to the second health level classification threshold and less than the first health level classification threshold, the current status level of the energy storage converter is determined to be the attention level. When the health index is less than the second health level threshold, the current status level of the energy storage converter is determined to be a warning level.

[0012] Preferably, the method further includes: In the 3D visualization interface, the health index is marked on the corresponding component of the 3D model of the energy storage converter using color mapping. The interface displays the remaining service life value and its trend curve side by side.

[0013] A second aspect of this application provides a digital twin health monitoring system for an energy storage converter, comprising: A construction module is used to collect and preprocess the operating data of the energy storage converter, and to construct a digital twin model containing geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter. The simulation module is used to input the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter. The first determining module is used to determine the health index of each component in the energy storage converter based on the internal state parameters. The prediction module is used to predict the remaining service life of the energy storage converter based on the stress parameters. The second determining module is used to determine the health status level and maintenance recommendations of the energy storage converter based on the health index and / or the remaining service life.

[0014] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the method described in the first aspect embodiment.

[0015] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in the first aspect.

[0016] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects: This application proposes a digital twin health monitoring method and system for energy storage converters. The method includes: collecting and preprocessing operating data of the energy storage converter; constructing a digital twin model including geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter; inputting the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter; determining the health index of each component within the energy storage converter based on the internal state parameters; predicting the remaining service life of the energy storage converter based on the stress parameters; and determining the health status level and maintenance recommendations of the energy storage converter based on the health index and / or the remaining service life. The technical solution proposed in this application achieves real-time and accurate assessment of the health status of energy storage converters, scientific prediction of remaining service life, and collaborative early warning of faults, providing intelligent support for preventive maintenance and significantly improving equipment reliability and operation and maintenance efficiency.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a digital twin health monitoring method for an energy storage converter according to an embodiment of this application; Figure 2 This is a structural diagram of a digital twin health monitoring system for an energy storage converter according to an embodiment of this application. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0020] This application proposes a digital twin health monitoring method and system for energy storage converters. The method includes: collecting and preprocessing operating data of the energy storage converter; constructing a digital twin model including geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter; inputting the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter; determining the health index of each component within the energy storage converter based on the internal state parameters; predicting the remaining service life of the energy storage converter based on the stress parameters; and determining the health status level and maintenance recommendations of the energy storage converter based on the health index and / or the remaining service life. The technical solution proposed in this application achieves real-time and accurate assessment of the health status of the energy storage converter, scientific prediction of its remaining service life, and collaborative early warning of faults, providing intelligent support for preventative maintenance and significantly improving equipment reliability and operation and maintenance efficiency.

[0021] The following description, with reference to the accompanying drawings, illustrates a digital twin health monitoring method and system for an energy storage converter according to an embodiment of this application.

[0022] Example 1 Figure 1 This is a flowchart illustrating a digital twin health monitoring method for an energy storage converter according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes: Step 1: Collect and preprocess the operating data of the energy storage converter, and construct a digital twin model containing geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter; In this embodiment of the disclosure, the step of collecting and preprocessing the operating data of the energy storage converter includes: A distributed sensor network is used to collect operating data from the energy storage converter, and redundant data is processed through a data fusion algorithm.

[0023] In this embodiment of the disclosure, the construction of a digital twin model comprising a geometric model and a mathematical model based on the operating data and the physical characteristics of the energy storage converter includes: Based on the aforementioned operating data and the physical characteristics of the energy storage converter, a digital twin model containing geometric and mathematical models is constructed using a multiphysics coupling modeling method. It should be noted that sensors installed at key locations within the energy storage converter collect real-time operating parameters such as voltage, current, temperature, humidity, and vibration. These real-time monitored operating parameters are denoted as Pi, where i represents different points in time. The monitored Pi is then compared to a preset threshold Qi, where Qi is a preset standard value. If Pi < Qi, the data undergoes simple filtering before storage; if Pi ≥ Qi, the confirmed operating parameter at that moment is denoised as Wi, and a specific preprocessing algorithm is used to denoise and normalize the data to improve accuracy and reliability.

[0024] During data acquisition, a distributed sensor network is employed to ensure the comprehensiveness and accuracy of the data. Simultaneously, to improve data reliability, a redundant design is adopted, with multiple sensors measuring key parameters. Redundant data is processed using a data fusion algorithm, the specific formula of which is as follows: in, The merged data values For the data value collected by the i-th sensor, Let be the weight of the i-th sensor, and satisfy . .

[0025] Based on the collected operational data and the physical characteristics of the energy storage converter, a digital twin model is constructed. First, a geometric model of the energy storage converter is generated using 3D modeling software, including key components such as power devices, cooling systems, and control circuits. Then, based on the working principle and physical equations of the energy storage converter, mathematical models of each component are established, such as the thermal model of the power devices and the topological model of the circuits. The geometric and mathematical models are then integrated to form a complete digital twin model.

[0026] In the process of constructing the digital twin model, considering the nonlinear characteristics of the energy storage converter, a multiphysics coupling modeling method is adopted, and the specific formula is as follows: Where u is the state variable. For convection terms, The diffusion coefficient is... For source terms.

[0027] Step 2: Input the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter; It should be noted that the internal state parameters include: the junction temperature of the power semiconductor device, the equivalent series resistance of the capacitor, or the core saturation of the inductor.

[0028] It should be noted that the preprocessed operating data is input into the digital twin model for real-time simulation. The simulation yields the internal state parameters and stress parameters of each component of the energy storage converter, such as the junction temperature of power devices, the equivalent series resistance of capacitors, and the magnetic flux of inductors.

[0029] The stress parameters include: stress level and stress index.

[0030] Step 3: Determine the health index of each component in the energy storage converter based on the internal state parameters; In this embodiment of the disclosure, step 3 specifically includes: Identify multiple evaluation indicators that affect the health of components; The analytic hierarchy process (AHP) is used to assign weights to each evaluation indicator. The fuzzy comprehensive evaluation method is used to determine the membership degree of the component to each evaluation index based on the internal state parameters; The health index is calculated by weighting based on the weights and membership degrees.

[0031] It should be noted that the health status of the energy storage converter is assessed based on simulation results. Assessment indicators include the aging degree of components and the level of potential failure risk. The specific assessment method is as follows: An assessment period T is set, where T is a preset value. Based on the current moment, a set of operating data with a period of T is extracted from the preprocessed data. The changing trends of key parameters are extracted from the operating data, and a specific assessment algorithm is used to calculate the health index Hi of each component, where Hi ranges from 0 to 1, with 0 indicating complete component failure and 1 indicating the component is in an ideal state.

[0032] The health index is calculated using a combination of the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method. The specific formula is as follows: ,in, Let be the health index of the i-th component. Let j be the weight of the j-th evaluation index. Let be the membership degree of the i-th component to the j-th evaluation index.

[0033] Step 4: Predict the remaining service life of the energy storage converter based on the stress parameters; In this embodiment of the disclosure, the formula for calculating the remaining service life of the energy storage converter includes:

[0034] In the formula, RUL represents the remaining lifetime. Where S is the baseline lifespan and S is the stress level. The reference stress level is n, where n is the stress exponent. The activation energy is given by k, Boltzmann constant is given by T, and T is given by T. This is the reference temperature.

[0035] It should be noted that the remaining lifespan of the energy storage converter is predicted based on real-time simulation results. The influence of various factors on lifespan, such as temperature cycling, electrical stress, and mechanical vibration, is considered.

[0036] The life prediction model combines accelerated life test data and real-time monitoring data. The specific formula is as follows: Where RUL stands for Remaining Lifetime. Where S is the baseline lifespan and S is the stress level. The reference stress level is n, where n is the stress exponent. The activation energy is given by k, Boltzmann constant is given by T, and T is given by T. This is the reference temperature.

[0037] Step 5: Determine the health status level and maintenance recommendations for the energy storage converter based on the health index and / or the remaining service life.

[0038] In this embodiment of the disclosure, step 5 specifically includes: The current status level of the energy storage converter is determined based on the preset health level classification threshold. An alert is triggered when the current status level corresponding to the health index is a warning level, or when the remaining lifespan is less than a preset time warning threshold. An alert is triggered when the current status level corresponding to the health index is the attention level and the remaining lifespan is less than N times the time warning threshold; where N is a coefficient greater than 1. The current status levels include: normal level, attention level, and warning level; The preset health level classification thresholds include: a first health level classification threshold and a second health level classification threshold, wherein the first health level classification threshold is greater than the second health level classification threshold. When the health index is greater than or equal to the first health level classification threshold, the current status level of the energy storage converter is determined to be normal. When the health index is greater than or equal to the second health level classification threshold and less than the first health level classification threshold, the current status level of the energy storage converter is determined to be the attention level. When the health index is less than the second health level threshold, the current status level of the energy storage converter is determined to be a warning level.

[0039] It should be noted that fault warnings and maintenance decisions are made based on health status assessment results and lifespan predictions. When the health index Hi falls below the preset warning threshold Hw, a fault warning signal is generated, indicating the potential fault location and type. Simultaneously, based on the remaining lifespan prediction RUL and maintenance costs, optimal maintenance strategies are formulated, such as the timing and content of preventative maintenance.

[0040] The fault early warning system employs a multi-threshold decision-making method, with the specific formula as follows: in, The first health level classification threshold is the high threshold. The threshold for the second health level is the low threshold.

[0041] In this embodiment of the disclosure, the method further includes: In the 3D visualization interface, the health index is marked on the corresponding component of the 3D model of the energy storage converter using color mapping. The interface displays the remaining service life value and its trend curve side by side.

[0042] It should be noted that generating a 3D scene of the energy storage converter visualizes the simulation results and health status assessment results of the digital twin model. The 3D scene includes all components of the energy storage converter and related monitoring indicators. Through 3D visualization, operators can intuitively understand the operating status and health condition of the energy storage converter. Specifically, the generation method is as follows: based on the 3D model of the energy storage converter and real-time monitoring data, the simulation results of the digital twin model are mapped onto the 3D scene. The location and monitoring points of each component of the energy storage converter are determined, and information such as health indices and operating parameters are associated with the corresponding components in the 3D scene, visualized using colors, icons, and other methods.

[0043] 3D visualization utilizes virtual reality technology to achieve an immersive monitoring experience. The specific implementation method is as follows: in, For screen coordinates, As a world coordinate system, For the model matrix, For the view matrix, This is the projection matrix.

[0044] In this embodiment of the disclosure, the method further includes: This system enables data interaction between a digital twin model and the actual energy storage converter, optimizing the digital twin model based on actual operating data. The simulation results of the digital twin model are periodically compared with the actual operating data to analyze the reasons for discrepancies and adjust and optimize model parameters to improve the model's accuracy and reliability. The specific interaction and optimization method involves setting a data interaction cycle. Within each cycle, the actual operating data is compared with the predicted data from the digital twin model, and the error is calculated. If the error exceeds a preset range, potential problems in the model are analyzed, such as unreasonable parameter settings or incomplete model structure, and corresponding optimizations and adjustments are made.

[0045] The model optimization employs an adaptive parameter estimation method, the specific formula of which is as follows: in, The parameter estimates for the k-th iteration are... For Kalman gain, These are actual measured values. These are the model's predicted values.

[0046] In this embodiment of the disclosure, the method further includes: This study simulates the operating status of energy storage converters under different conditions, providing a more comprehensive basis for life prediction and maintenance decisions. Considering various load conditions, ambient temperature, grid voltage, and other factors, multi-condition simulations are performed on the digital twin model. The health status changes of the energy storage converter under various conditions are analyzed to support the development of more adaptive maintenance strategies. Specifically, the simulation method involves setting different operating parameters based on the range of operating conditions that may be encountered in actual operation, such as load rate from 20% to 100% and ambient temperature from -20℃ to 50℃. Simulations are performed for each operating condition, recording the operating data and health index changes of each component of the energy storage converter.

[0047] Multi-condition simulation employs orthogonal experimental design method, with the specific formula as follows: Where Y is the response variable, For the i-th factor, For constant terms, Main effect coefficient This is the interaction effect coefficient. This is the error term.

[0048] In summary, the digital twin health monitoring method for energy storage converters proposed in this embodiment enables real-time and accurate assessment of the health status of energy storage converters, scientific prediction of remaining lifespan, and collaborative early warning of faults. This provides intelligent support for preventive maintenance and significantly improves equipment reliability and operation and maintenance efficiency.

[0049] Example 2 Figure 2This is a structural diagram of a digital twin health monitoring system for an energy storage converter according to an embodiment of this application, as shown below. Figure 2 As shown, the system includes: The construction module 100 is used to collect and preprocess the operating data of the energy storage converter, and to construct a digital twin model containing a geometric model and a mathematical model based on the operating data and the physical characteristics of the energy storage converter. The simulation module 200 is used to input the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter. The internal state parameters include: the junction temperature of the power semiconductor device, the equivalent series resistance of the capacitor, or the core saturation of the inductor. The stress parameters include: stress level and stress index.

[0050] The first determining module 300 is used to determine the health index of each component in the energy storage converter based on the internal state parameters. Prediction module 400 is used to predict the remaining service life of the energy storage converter based on the stress parameters; The formula for calculating the remaining service life of the energy storage converter includes:

[0051] In the formula, RUL represents the remaining lifetime. Where S is the baseline lifespan and S is the stress level. The reference stress level is n, where n is the stress exponent. The activation energy is given by k, Boltzmann constant is given by T, and T is given by T. This is the reference temperature.

[0052] The second determining module 500 is used to determine the health status level and maintenance recommendations of the energy storage converter based on the health index and / or the remaining service life.

[0053] In this embodiment of the disclosure, the construction module 100 is further configured to: A distributed sensor network is used to collect operating data from the energy storage converter, and redundant data is processed through a data fusion algorithm.

[0054] In this embodiment of the disclosure, the construction module 100 is further configured to: A distributed sensor network is used to collect operating data from the energy storage converter, and redundant data is processed through a data fusion algorithm.

[0055] In this embodiment of the disclosure, the construction module 100 is further configured to: Based on the operational data and the physical characteristics of the energy storage converter, a digital twin model containing geometric and mathematical models is constructed using a multiphysics coupling modeling method.

[0056] In this embodiment of the disclosure, the first determining module 300 is further configured to: Identify multiple evaluation indicators that affect the health of components; The analytic hierarchy process (AHP) is used to assign weights to each evaluation indicator. The fuzzy comprehensive evaluation method is used to determine the membership degree of the component to each evaluation index based on the internal state parameters; The health index is calculated by weighting based on the weights and membership degrees.

[0057] In this embodiment of the disclosure, the second determining module 500 is further configured to: The current status level of the energy storage converter is determined based on the preset health level classification threshold. An alert is triggered when the current status level corresponding to the health index is a warning level, or when the remaining lifespan is less than a preset time warning threshold. An alert is triggered when the current status level corresponding to the health index is the attention level and the remaining lifespan is less than N times the time warning threshold; where N is a coefficient greater than 1. The current status levels include: normal level, attention level, and warning level; The preset health level classification thresholds include: a first health level classification threshold and a second health level classification threshold, wherein the first health level classification threshold is greater than the second health level classification threshold. When the health index is greater than or equal to the first health level classification threshold, the current status level of the energy storage converter is determined to be normal. When the health index is greater than or equal to the second health level classification threshold and less than the first health level classification threshold, the current status level of the energy storage converter is determined to be the attention level. When the health index is less than the second health level threshold, the current status level of the energy storage converter is determined to be a warning level.

[0058] In this embodiment of the disclosure, the second determining module 500 is further configured to: In the 3D visualization interface, the health index is marked on the corresponding component of the 3D model of the energy storage converter using color mapping. The interface displays the remaining service life value and its trend curve side by side.

[0059] In summary, the digital twin health monitoring system for energy storage converters proposed in this embodiment enables real-time and accurate assessment of the health status of energy storage converters, scientific prediction of remaining lifespan, and collaborative early warning of faults. It provides intelligent support for preventive maintenance and significantly improves equipment reliability and operation and maintenance efficiency.

[0060] Example 3 To implement the above embodiments, this disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the method described in Embodiment 1.

[0061] Example 4 To implement the above embodiments, this disclosure also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in Embodiment 1.

[0062] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0063] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0064] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A digital twin health monitoring method for an energy storage converter, characterized in that, The method includes: Collect and preprocess the operating data of the energy storage converter, and construct a digital twin model containing geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter; The preprocessed operating data is input into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter. The health index of each component in the energy storage converter is determined based on the internal state parameters. Predict the remaining service life of the energy storage converter based on the stress parameters; The health status level and maintenance recommendations for the energy storage converter are determined based on the health index and / or the remaining service life.

2. The method as described in claim 1, characterized in that, The process of collecting and preprocessing the operating data of the energy storage converter includes: A distributed sensor network is used to collect operating data from the energy storage converter, and redundant data is processed through a data fusion algorithm.

3. The method as described in claim 2, characterized in that, The construction of a digital twin model, comprising geometric and mathematical models, based on the operational data and the physical characteristics of the energy storage converter, includes: Based on the aforementioned operating data and the physical characteristics of the energy storage converter, a digital twin model containing geometric and mathematical models is constructed using a multiphysics coupling modeling method. The internal state parameters include: the junction temperature of the power semiconductor device, the equivalent series resistance of the capacitor, or the core saturation of the inductor.

4. The method as described in claim 3, characterized in that, The process of determining the health index of each component within the energy storage converter based on the internal state parameters includes: Identify multiple evaluation indicators that affect the health of components; The analytic hierarchy process (AHP) is used to assign weights to each evaluation indicator. The fuzzy comprehensive evaluation method is used to determine the membership degree of the component to each evaluation index based on the internal state parameters; The health index is calculated by weighting based on the weights and membership degrees.

5. The method as described in claim 4, characterized in that, The formula for calculating the remaining service life of the energy storage converter includes: In the formula, RUL represents the remaining lifetime. Where S is the reference life and S is the stress level. The reference stress level is n, where n is the stress exponent. The activation energy is given by k, Boltzmann constant is given by T, and T is given by T. Reference temperature; The stress parameters include: stress level and stress index.

6. The method as described in claim 5, characterized in that, The process of determining the health status level and maintenance recommendations for the energy storage converter based on the health index and the remaining service life includes: The current status level of the energy storage converter is determined based on the preset health level classification threshold. An alert is triggered when the current status level corresponding to the health index is a warning level, or when the remaining lifespan is less than a preset time warning threshold. An alert is triggered when the current status level corresponding to the health index is the attention level and the remaining lifespan is less than N times the time warning threshold; where N is a coefficient greater than 1. The current status levels include: normal level, attention level, and warning level; The preset health level classification thresholds include: a first health level classification threshold and a second health level classification threshold, wherein the first health level classification threshold is greater than the second health level classification threshold. When the health index is greater than or equal to the first health level classification threshold, the current status level of the energy storage converter is determined to be normal. When the health index is greater than or equal to the second health level classification threshold and less than the first health level classification threshold, the current status level of the energy storage converter is determined to be the attention level. When the health index is less than the second health level threshold, the current status level of the energy storage converter is determined to be a warning level.

7. The method as described in claim 1, characterized in that, The method further includes: In the 3D visualization interface, the health index is marked on the corresponding component of the 3D model of the energy storage converter using color mapping. The interface displays the remaining service life value and its trend curve side by side.

8. A digital twin health monitoring system for an energy storage converter, characterized in that, The system includes: A construction module is used to collect and preprocess the operating data of the energy storage converter, and to construct a digital twin model containing geometric and mathematical models based on the operating data and the physical characteristics of the energy storage converter. The simulation module is used to input the preprocessed operating data into the digital twin model for real-time simulation to obtain the internal state parameters and stress parameters of the energy storage converter. The first determining module is used to determine the health index of each component in the energy storage converter based on the internal state parameters. The prediction module is used to predict the remaining service life of the energy storage converter based on the stress parameters. The second determining module is used to determine the health status level and maintenance recommendations of the energy storage converter based on the health index and / or the remaining service life.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1-7.

10. 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 1-7.

Images