Method and device for optimizing digital twin model of power equipment

Abstract

The invention relates to a method and a device for optimizing a digital twin model of power equipment. The method comprises the following steps: acquiring operation monitoring data and a digital twinborn simulation result of target power equipment to perform difference analysis, and determining a deviation between a digital twinborn model of the target power equipment and an actual operation state of the equipment; a prediction error matrix updated in real time is obtained based on the deviation, parameters of the digital twin model are dynamically adjusted according to the prediction error matrix, and a model after parameter correction is obtained; simulating dynamic characteristics of the target power equipment under different fault conditions by adopting the model after parameter correction, and correcting according to the dynamic characteristics to obtain a fault scene adaptation model; and performing parameter distribution optimization and model uncertainty correction on the fault scene adaptation model through model iteration processing to obtain an optimized digital twin model of the target power equipment. By adopting the method, dynamic correction and optimization of the digital twinborn body of the power equipment under complex working conditions can be realized, and the precision and reliability of the digital twinborn model are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of digital twin technology, and in particular, to a method, device, computer device, computer-readable storage medium, and computer program product for optimizing a digital twin model of a power device. Background Art

[0002] The digital twin of a power device is a virtual representation form of the power device entity in the digital space, which can support the digitization and intelligentization of the power device during its entire life cycle.

[0003] With the complexity and dynamics of the operating conditions of power system equipment, traditional digital twin models are difficult to reflect the actual operating state of the equipment in real time when the boundary conditions, material parameters, or geometric structures change; and traditional evaluation methods rely on fixed parameters and initial conditions and lack the ability of dynamic adjustment, resulting in a decrease in the accuracy and consistency of the digital twin, affecting the accuracy of the health state assessment of power equipment and the reliability of fault diagnosis. Moreover, under the action of multi-physical field coupling, the complex characteristics and dynamic evolution process during the operation of power equipment have not been comprehensively captured, which will pose higher requirements for the model update and optimization of the digital twin.

[0004] Therefore, there is a problem of poor optimization effect of the digital twin of power equipment in the related art. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for optimizing a digital twin model of a power device, which can improve the optimization effect of the digital twin of the power device.

[0006] In a first aspect, the present application provides a method for optimizing a digital twin model of a power device, the method including:

[0007] Obtain the operation monitoring data of the target power device and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power device and the actual operation state of the device;

[0008] Based on the deviation, obtain a prediction error matrix updated in real time, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0009] Use the model with corrected parameters to simulate the dynamic characteristics of the target power device under different fault conditions, and correct and obtain a fault scenario adaptation model according to the dynamic characteristics;

[0010] Through model iterative processing, optimize the parameter distribution of the fault scenario adaptation model and correct the model uncertainty to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status assessment, fault prediction, and equipment operation and maintenance on the target power equipment.

[0011] In one embodiment, the obtaining the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis to determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment includes:

[0012] Collect the operation monitoring data of the target power equipment in real time through sensors, and obtain the digital twin simulation results of the target power equipment;

[0013] Compare the operation monitoring data and the digital twin simulation results to identify the deviation between the digital twin model and the actual operation state of the target power equipment;

[0014] Among them, the deviation is caused by changes in the boundary conditions, material parameters, and geometric structure of the target power equipment.

[0015] In one embodiment, the obtaining the real-time updated prediction error matrix based on the deviation includes:

[0016] Use the parameter correction algorithm, combine the deviation, the preset state update formula, and the preset error covariance update formula to obtain the prediction error matrix.

[0017] In one embodiment, the dynamically adjusting the parameters of the digital twin model according to the prediction error matrix includes:

[0018] Based on the prediction error matrix, through the recursive iteration of the filter, optimize the gap between the predicted value and the actual observed value of the digital twin model, and adjust the parameters of the digital twin model.

[0019] In one embodiment, the obtaining the fault scenario adaptation model according to the dynamic characteristic correction includes:

[0020] Combine the particle filter algorithm to correct the dynamic characteristics, and estimate and correct the model parameter distribution through the particle weight update mechanism to obtain the fault scenario adaptation model.

[0021] In one embodiment, the through model iterative processing, optimizing the parameter distribution of the fault scenario adaptation model and correcting the model uncertainty includes:

[0022] During the model iteration process, a genetic algorithm is used to optimize the parameter distribution of the fault scenario adaptation model; the genetic algorithm is used to correct material parameters or geometric changes;

[0023] Through Bayesian updating, the uncertainty of parameter correction for the fault scenario adaptation model is quantified.

[0024] In a second aspect, the present application also provides a power equipment digital twin model optimization device, and the device includes:

[0025] A difference analysis module, configured to obtain the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment;

[0026] A parameter correction module, configured to obtain a prediction error matrix updated in real time based on the deviation, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0027] A fault scenario adaptation module, configured to use the model with corrected parameters to simulate the dynamic characteristics of the target power equipment under different fault conditions, and correct to obtain a fault scenario adaptation model according to the dynamic characteristics;

[0028] A model optimization processing module, configured to optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model through model iteration processing to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status evaluation, fault prediction, and equipment operation and maintenance on the target power equipment.

[0029] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0030] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0031] In a fifth aspect, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0032] The above-mentioned optimization method, device, computer equipment, computer-readable storage medium and computer program product for the digital twin model of power equipment perform difference analysis by obtaining the operation monitoring data and digital twin simulation results of the target power equipment, determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment, then obtain a real-time updated prediction error matrix based on the deviation, dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters, adopt the model with corrected parameters to simulate the dynamic characteristics of the target power equipment under different fault conditions, correct and obtain a fault scenario adaptation model according to the dynamic characteristics, and then through model iteration processing, optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model to obtain an optimized digital twin model of the target power equipment. This optimized digital twin model is used for real-time status evaluation, fault prediction and equipment operation and maintenance of the target power equipment, realizes adaptive correction and optimization of its digital twin model according to the change of the equipment operation state, can be applied to the dynamic correction and optimization of the digital twin body of power equipment under complex working conditions, effectively improves the accuracy and reliability of the digital twin model, and helps the accurate prediction and intelligent operation and maintenance of the power equipment operation state. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0034] Figure 1 It is a schematic flowchart of a method for optimizing the digital twin model of power equipment in an embodiment;

[0035] Figure 2 It is a schematic flowchart of the model optimization steps in an embodiment;

[0036] Figure 3 It is a schematic flowchart of a method for optimizing the digital twin model of power equipment in another embodiment;

[0037] Figure 4 It is a structural block diagram of a device for optimizing the digital twin model of power equipment in an embodiment;

[0038] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] In an exemplary embodiment, as Figure 1 shown, a method for optimizing a digital twin model of a power device is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 101 to step 104. Among them:

[0041] Step 101, obtain the operation monitoring data of the target power device and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power device and the actual operation state of the device.

[0042] As an example, by performing multi-physical field simulation modeling on the target power device, a multi-physical field numerical simulation model can be established as the digital twin model of the target power device.

[0043] In practical applications, by real-time collecting sensor data (such as temperature, stress, current, deformation, etc.) as the operation monitoring data of the target power device, and obtaining the digital twin simulation results of the target power device, which can be used to characterize the simulation situation of the comprehensive state of the target power device. Furthermore, the results of the simulation of the comprehensive state of the power device can be compared with the actual operation data of the power device, and the deviation between the model and the actual operation state can be identified based on dynamic data fusion.

[0044] Optionally, a multi-physical field numerical simulation model can be used to perform multi-physical field simulation analysis on the target power device to obtain multi-physical field simulation results (i.e., digital twin simulation results); for example, based on the multi-physical field numerical simulation model, the weight method can be used to obtain the weight values of each device component in the target power device, and the results of the simulation of the comprehensive state of the target power device can be obtained.

[0045] Step 102, obtain a prediction error matrix updated in real time based on the deviation, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters.

[0046] In a specific implementation, a real-time updated prediction error matrix can be obtained based on the deviation, and then a parameter correction algorithm can be adopted to dynamically adjust the parameters of the digital twin model according to the prediction error matrix, obtaining a model with corrected parameters, which can be used to predict the operating state of power equipment in a digital environment; Exemplarily, the Kalman filtering algorithm can be introduced as the core to dynamically adjust the model parameters for the digital twin model. Thus, by correcting the digital twin model, the mapping matching between the physical entity device and its corresponding digital twin model can be optimized.

[0047] Step 103: Use the model with corrected parameters to simulate the dynamic characteristics of the target power equipment under different fault conditions, and correct and obtain a fault scenario adaptation model according to the dynamic characteristics.

[0048] Specifically, the model with corrected parameters can be a multi-physics field simulation model constructed based on finite element analysis. By simulating the dynamic characteristics of power equipment under different fault conditions with the model, the particle filtering algorithm can be combined to correct the complex non-linear characteristics, obtaining a model adapted to the fault scenario.

[0049] Step 104: Through model iterative processing, optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model to obtain the optimized digital twin model of the target power equipment.

[0050] Among them, the optimized digital twin model can be used for real-time state assessment, fault prediction and equipment operation and maintenance of the target power equipment; For example, it can be applied to real-time state assessment, fault prediction and operation and maintenance optimization of complex power equipment such as transformers and switchgear.

[0051] In the process of model dynamic optimization, through model iterative processing, the genetic algorithm and the Bayesian update method can be combined to automatically optimize the parameter distribution during the model iteration process and quantify the uncertainty of model correction, obtaining the optimized digital twin model of the target power equipment, thereby ensuring the stability and credibility of the model results.

[0052] In an example, based on the power equipment digital twin model optimization method of this embodiment, by constructing a dynamic correction and optimization framework, the corresponding digital twin can be adaptively corrected and optimized according to the change of the equipment operating state, which can be applied to the dynamic correction and optimization of the digital twin of power equipment under complex working conditions, effectively improving the real-time performance, accuracy and adaptability of the digital twin model, and providing good technical support for equipment health management and fault prediction.

[0053] Compared with the problem that the digital twin model is inconsistent with the actual operation state of the device due to changes in boundary conditions, material parameters, and geometric structures existing in traditional methods, the technical solution of this embodiment can improve the accuracy and reliability of the digital twin by comparing and analyzing the real-time sensor monitoring data with the simulation model results, and using Kalman filtering, particle filtering, and optimization algorithms to achieve dynamic parameter adjustment and boundary condition correction. Moreover, for the digital twin model established by combining multi-physics field simulation and historical operation data, by constructing a dynamic update mechanism, the digital twin can be adaptively optimized under complex working conditions, providing technical support for the accurate prediction of the device operation state and intelligent operation and maintenance.

[0054] In the above digital twin model optimization method for power equipment, by obtaining the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis, determining the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment, then obtaining a real-time updated prediction error matrix based on the deviation, dynamically adjusting the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters, using the model with corrected parameters to simulate the dynamic characteristics of the target power equipment under different fault conditions, correcting to obtain a fault scenario adaptation model according to the dynamic characteristics, and then through model iteration processing, optimizing the parameter distribution and correcting the model uncertainty of the fault scenario adaptation model to obtain the optimized digital twin model of the target power equipment, which realizes the adaptive correction and optimization of its digital twin model according to the changes in the equipment operation state, can be applied to the dynamic correction and optimization of the digital twin of power equipment under complex working conditions, effectively improving the accuracy and reliability of the digital twin model, and contributing to the accurate prediction of the power equipment operation state and intelligent operation and maintenance.

[0055] In an exemplary embodiment, the step of obtaining the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis to determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment may include the following steps:

[0056] Real-time collect the operation monitoring data of the target power equipment through sensors, and obtain the digital twin simulation results of the target power equipment; compare the operation monitoring data and the digital twin simulation results to identify the deviation between the digital twin model and the actual operation state of the target power equipment.

[0057] Among them, the deviation is caused by changes in the boundary conditions, material parameters, and geometric structures of the target power equipment.

[0058] In practical applications, by obtaining the sensing data collected by multiple preset sensors on the target power equipment, the real-time operation data of the target power equipment (i.e., operation monitoring data) can be obtained. Furthermore, based on the real-time data, updates and fusions can be performed. By comparing the real-time operation data of the equipment with the initial conditions and current states of the digital twin model (i.e., digital twin simulation results), the deviations between the model parameters and the actual data can be identified.

[0059] In an alternative embodiment, for the digital twin of power equipment, when the boundary conditions, material parameters, and geometric structures of the physical model change, the adaptive correction process needs to iteratively optimize and correct the model parameters and boundary conditions by combining the actual monitoring data and the simulation model to ensure the accuracy and consistency of the digital twin.

[0060] In this embodiment, by using sensors to collect the operation monitoring data of the target power equipment in real time and obtaining the digital twin simulation results of the target power equipment, and then comparing the operation monitoring data with the digital twin simulation results to identify the deviations between the digital twin model and the actual operation state of the target power equipment, it can help improve the accuracy and reliability of the operation state monitoring of power equipment.

[0061] In an exemplary embodiment, obtaining the real-time updated prediction error matrix based on the deviation may include the following steps:

[0062] Using a parameter correction algorithm, combining the deviation, a preset state update formula, and a preset error covariance update formula to obtain the prediction error matrix.

[0063] In one example, the parameter correction algorithm can be a filtering algorithm. For example, the Kalman filter can be applied to the state estimation of dynamic systems, and a real-time updated prediction error covariance matrix (i.e., the prediction error matrix) can be obtained through the Kalman filter.

[0064] The relevant state update formula is:

[0065]

[0066] Where, is the predicted state, K k is the Kalman gain, Z k is the actual observation value, H k is the observation matrix.

[0067] The relevant error covariance update formula is:

[0068]

[0069] Where, is the predicted error covariance, and I is the identity matrix.

[0070] In this embodiment, by utilizing a parameter correction algorithm, combined with a deviation, a preset state update formula, and a preset error covariance update formula, a prediction error matrix is ​​obtained, which provides data support for further parameter adjustment.

[0071] In an exemplary embodiment, dynamically adjusting the parameters of the digital twin model according to the prediction error matrix may include the following steps:

[0072] Based on the prediction error matrix, the gap between the predicted value and the actual observed value of the digital twin model is optimized through recursive iteration of the filter, and the parameters of the digital twin model are adjusted.

[0073] In the specific implementation, the gap between the model prediction value and the observation value can be optimized through the real-time updated prediction error covariance matrix to improve the consistency of the digital twin; illustratively, the Kalman filter can fuse the real-time monitoring data of the sensor with the prediction results of the simulation model through recursive iteration to correct the model parameters and boundary conditions.

[0074] In an optional embodiment, during the adaptive correction process of the digital twin, an optimization algorithm can be used to perform parameter inversion on boundary conditions, material parameters, and geometric structures. For example, the observed data can be input into the inverse problem solving framework to iteratively optimize the model parameters so that the simulation results are consistent with the actual data. A dynamic correction algorithm can also be used to make real-time adjustments to changes in boundary conditions caused by environmental changes or changes in operating conditions, thereby ensuring the effectiveness of the model under new conditions.

[0075] In this embodiment, by recursively iterating the filter based on the prediction error matrix, optimizing the gap between the predicted value and the actual observed value of the digital twin model, and adjusting the parameters of the digital twin model, accurate adjustment of the model parameters can be achieved.

[0076] In an exemplary embodiment, the obtaining of the fault scenario adaptation model according to the dynamic characteristic correction may include the following steps:

[0077] The dynamic characteristics are corrected in combination with a particle filter algorithm, and the distribution of model parameters is estimated and corrected through a particle weight update mechanism to obtain the fault scenario adaptation model.

[0078] In one example, the particle filter algorithm can be used to handle nonlinear and non-Gaussian distribution problems, and the particle filter algorithm can be combined to correct complex nonlinear characteristics, and the distribution of model parameters can be estimated and corrected by adopting a particle weight update mechanism.

[0079] The relevant state update formula is:

[0080]

[0081] The relevant weight update formula is as follows:

[0082]

[0083] Wherein, is the particle state, is the weight, is the observation likelihood function.

[0084] In this embodiment, by combining the particle filter algorithm to correct the dynamic characteristics, and through the particle weight update mechanism to estimate and correct the distribution of model parameters, a fault scenario adaptation model is obtained, which can improve the adaptability and accuracy of the model under fault scenarios.

[0085] In an exemplary embodiment, as Figure 2 shown, in step 104, through model iterative processing, parameter distribution optimization and model uncertainty correction are performed on the fault scenario adaptation model, including steps 201 to 202. Wherein:

[0086] Step 201, during the model iteration process, a genetic algorithm is used to optimize the parameter distribution of the fault scenario adaptation model; the genetic algorithm is used to correct material parameters or geometric changes.

[0087] Step 202, through Bayesian updating, the uncertainty of parameter correction for the fault scenario adaptation model is quantified.

[0088] In practical applications, the genetic algorithm can be an Adaptive Genetic Algorithm (AGA). For complex optimization problems, the adaptive genetic algorithm can be used to correct material parameters or geometric changes, and the fitness function can be used to evaluate the model prediction error, and the mutation rate and crossover rate of genetic operations can be adjusted to achieve fast convergence.

[0089] In one example, Bayesian Updating can be used to dynamically update the model parameter probability distribution when new observation data arrives. Its relevant update formula is as follows:

[0090]

[0091] Wherein, is the parameter, D is the observation data, is the posterior probability distribution.

[0092] In yet another example, through the combined application of algorithms, such as using a Kalman filter or particle filter for real-time correction of boundary conditions and state parameters in the face of dynamic environmental changes, using a genetic algorithm for global search and optimization of material parameters or geometric characteristics for complex parameter optimization, and combining Bayesian updating to quantify the uncertainty of parameter correction for handling model uncertainty, the credibility of the model can be ensured. Thus, efficient adaptive correction of the digital twin of power equipment is achieved in a multi-dimensional dynamic scenario, ensuring accurate mapping and response of the model to the actual operating state of the equipment.

[0093] In this embodiment, during the model iteration process, a genetic algorithm is used to optimize the parameter distribution of the fault scenario adaptation model, and Bayesian updating is used to quantify the uncertainty of parameter correction for the fault scenario adaptation model, enabling efficient adaptive optimization of the digital twin of power equipment.

[0094] In an exemplary embodiment, as Figure 3 shown, a flowchart of another method for optimizing the digital twin model of power equipment is provided. In this embodiment, the method includes the following steps:

[0095] In step 301, the operation monitoring data of the target power equipment is collected in real time through sensors, and the digital twin simulation results of the target power equipment are obtained. In step 302, the operation monitoring data and the digital twin simulation results are compared to identify the deviation between the digital twin model and the actual operating state of the target power equipment. In step 303, using a parameter correction algorithm, combining the deviation, a preset state update formula, and a preset error covariance update formula, a prediction error matrix is obtained. In step 304, based on the prediction error matrix, through the recursive iteration of the filter, the gap between the predicted value and the actual observed value of the digital twin model is optimized, and the parameters of the digital twin model are adjusted to obtain a model with corrected parameters. In step 305, the model with corrected parameters is used to simulate the dynamic characteristics of the target power equipment under different fault conditions. In step 306, the particle filter algorithm is combined to correct the dynamic characteristics, and the distribution estimation and correction of the model parameters are performed through the particle weight update mechanism to obtain a fault scenario adaptation model. In step 307, during the model iteration process, a genetic algorithm is used to optimize the parameter distribution of the fault scenario adaptation model, and Bayesian updating is used to quantify the uncertainty of parameter correction for the fault scenario adaptation model to obtain an optimized digital twin model of the target power equipment.

[0096] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a method for optimizing the digital twin model of power equipment described above, and will not be elaborated here.

[0097] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.

[0098] Based on the same inventive concept, an embodiment of the present application further provides a digital twin model optimization device for a power device for implementing the above-mentioned digital twin model optimization method for a power device. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the digital twin model optimization device for a power device provided below can refer to the limitations on the digital twin model optimization method for a power device in the above text, and will not be repeated here.

[0099] In an exemplary embodiment, as Figure 4 shown, a digital twin model optimization device for a power device is provided, including:

[0100] A difference analysis module 401, configured to obtain the operation monitoring data of the target power device and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power device and the actual operation state of the device;

[0101] A parameter correction module 402, configured to obtain a prediction error matrix updated in real time based on the deviation, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0102] A fault scenario adaptation module 403, configured to use the model with corrected parameters to simulate the dynamic characteristics of the target power device under different fault conditions, and correct and obtain a fault scenario adaptation model according to the dynamic characteristics;

[0103] A model optimization processing module 404, configured to optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model through model iteration processing to obtain the optimized digital twin model of the target power device; the optimized digital twin model is used to perform real-time state evaluation, fault prediction, and equipment operation and maintenance on the target power device.

[0104] In one embodiment, the difference analysis module 401 is specifically configured to collect the operation monitoring data of the target power device in real time through a sensor, and obtain the digital twin simulation result of the target power device; compare the operation monitoring data with the digital twin simulation result to identify the deviation between the digital twin model and the actual operation state of the target power device; wherein, the deviation is caused by changes in the boundary conditions, material parameters, and geometric structure of the target power device.

[0105] In one embodiment, the parameter correction module 402 is specifically configured to use a parameter correction algorithm, combine the deviation, a preset state update formula, and a preset error covariance update formula to obtain the prediction error matrix.

[0106] In one embodiment, the parameter correction module 402 is specifically configured to, based on the prediction error matrix, optimize the gap between the predicted value and the actual observed value of the digital twin model through recursive iteration of a filter, and adjust the parameters of the digital twin model.

[0107] In one embodiment, the fault scenario adaptation module 403 is specifically configured to correct the dynamic characteristics in combination with a particle filter algorithm, and perform distribution estimation and correction on the model parameters through a particle weight update mechanism to obtain the fault scenario adaptation model.

[0108] In one embodiment, the model optimization processing module 404 is specifically configured to, during the model iteration process, use a genetic algorithm to optimize the parameter distribution of the fault scenario adaptation model; the genetic algorithm is used to correct material parameters or geometric changes; through Bayesian update, the uncertainty of parameter correction for the fault scenario adaptation model is quantified.

[0109] Each module in the above digital twin model optimization device for power equipment can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0110] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it realizes an optimization method for a digital twin model of a power device. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0111] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0112] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0113] Obtain the operation monitoring data and digital twin simulation results of the target power device for differential analysis, and determine the deviation between the digital twin model of the target power device and the actual operation state of the device;

[0114] Based on the deviation, obtain a real-time updated prediction error matrix, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0115] Adopt the model with corrected parameters to simulate the dynamic characteristics of the target power device under different fault conditions, and correct and obtain a fault scenario adaptation model according to the dynamic characteristics;

[0116] Through model iterative processing, optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status assessment, fault prediction, and equipment operation and maintenance on the target power equipment.

[0117] In one embodiment, when the processor executes the computer program, it also implements the steps of the power equipment digital twin model optimization method in the above-mentioned other embodiments.

[0118] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0119] Obtain the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment;

[0120] Based on the deviation, obtain a real-time updated prediction error matrix, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0121] Adopt the model with corrected parameters to simulate the dynamic characteristics of the target power equipment under different fault conditions, and correct and obtain a fault scenario adaptation model according to the dynamic characteristics;

[0122] Through model iterative processing, optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status assessment, fault prediction, and equipment operation and maintenance on the target power equipment.

[0123] In one embodiment, when the computer program is executed by a processor, it also implements the steps of the power equipment digital twin model optimization method in the above-mentioned other embodiments.

[0124] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0125] Obtain the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment;

[0126] Based on the deviation, obtain a real-time updated prediction error matrix, and dynamically adjust the parameters of the digital twin model according to the prediction error matrix to obtain a model with corrected parameters;

[0127] Using the parameter-corrected model, simulate the dynamic characteristics of the target power equipment under different fault conditions, and correct the fault scenario adaptation model according to the dynamic characteristics;

[0128] Through model iteration processing, optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used for real-time status evaluation, fault prediction and equipment operation and maintenance of the target power equipment.

[0129] In one embodiment, when the computer program is executed by the processor, it also implements the steps of the power equipment digital twin model optimization method in the above other embodiments.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0131] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0132] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0133] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for optimizing a digital twin model of electric power equipment, characterized in that: The method comprises: Obtaining the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis to determine the deviation between the digital twin model of the target power equipment and the actual operation status of the equipment; Obtaining a real-time updated prediction error matrix based on the deviation, dynamically adjusting the parameters of the digital twin model according to the prediction error matrix, and obtaining a parameter-corrected model; The model after parameter correction is used to simulate the dynamic characteristics of the target power equipment under different fault conditions, and a fault scenario adaptation model is obtained according to the correction of the dynamic characteristics; Through model iteration processing, the parameter distribution of the fault scenario adaptation model is optimized and the model uncertainty is corrected to obtain an optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status assessment, fault prediction and equipment operation and maintenance of the target power equipment.

2. The method according to claim 1, characterized in that The obtaining of the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis to determine the deviation between the digital twin model of the target power equipment and the actual operation state of the equipment includes: Collecting the operation monitoring data of the target power equipment in real time through sensors, and obtaining the digital twin simulation results of the target power equipment; Comparing the operation monitoring data with the digital twin simulation result to identify the deviation between the digital twin model and the actual operation state of the target power equipment; The deviation is caused by changes in boundary conditions, material parameters, and geometric structures of the target power equipment.

3. The method according to claim 1, characterized in that The method of obtaining a real-time updated prediction error matrix based on the deviation includes: The prediction error matrix is ​​obtained by utilizing a parameter correction algorithm in combination with the deviation, a preset state update formula, and a preset error covariance update formula.

4. The method according to claim 3, characterized in that The dynamically adjusting the parameters of the digital twin model according to the prediction error matrix includes: Based on the prediction error matrix, the gap between the predicted value and the actual observed value of the digital twin model is optimized through recursive iteration of the filter, and the parameters of the digital twin model are adjusted.

5. The method according to claim 1, characterized in that The correcting and obtaining a fault scenario adaptation model according to the dynamic characteristics includes: The dynamic characteristics are corrected in combination with a particle filter algorithm, and the distribution of model parameters is estimated and corrected through a particle weight update mechanism to obtain the fault scenario adaptation model.

6. The method according to any one of claims 1 to 5, characterized in that: The parameter distribution optimization and model uncertainty correction of the fault scenario adaptation model are performed through model iteration processing, including: In the model iteration process, a genetic algorithm is used to optimize the parameter distribution of the fault scenario adaptation model; the genetic algorithm is used to correct material parameters or geometric changes; Through Bayesian updating, the uncertainty of the correction of the model quantization parameters is adapted for the fault scenario.

7. A digital twin model optimization device for electric power equipment, characterized in that: The device comprises: A difference analysis module is used to obtain the operation monitoring data of the target power equipment and the digital twin simulation results for difference analysis, and determine the deviation between the digital twin model of the target power equipment and the actual operation status of the equipment; A parameter correction module, used to obtain a real-time updated prediction error matrix based on the deviation, dynamically adjust the parameters of the digital twin model according to the prediction error matrix, and obtain a parameter-corrected model; A fault scenario adaptation module, used to use the parameter-corrected model to simulate the dynamic characteristics of the target power equipment under different fault conditions, and obtain a fault scenario adaptation model according to the dynamic characteristics correction; The model optimization processing module is used to optimize the parameter distribution and correct the model uncertainty of the fault scenario adaptation model through model iteration processing, so as to obtain the optimized digital twin model of the target power equipment; the optimized digital twin model is used to perform real-time status assessment, fault prediction and equipment operation and maintenance of the target power equipment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images