Dynamic updating method and system for digital twinborn model of transformer

Abstract

The invention discloses a dynamic updating method and system for a digital twin model of a transformer, and relates to the field of digital management of power equipment. The method comprises: obtaining a structure data set of a transformer; based on the structure data set of the transformer, constructing an initial digital twinborn model of the transformer; collecting a multi-source real-time data set; substituting the multi-source real-time data set and the initial digital twinborn model of the transformer into a model updating module to generate a visual dynamically updated digital twinborn model of the transformer and an updating adjustment scheme corresponding to the transformer; and when judging that the model meets the updating condition, executing dynamic updating on the current digital twinborn model of the transformer based on the updating adjustment scheme. According to the method, the state change of the transformer is dynamically and visually displayed, the updating frequency of the transformer is adaptively adjusted according to different working conditions of the transformer, the current digital twinborn model of the transformer is dynamically updated, the timeliness of the digital twinborn model of the transformer is ensured, and meanwhile, long-time occupation of resources is reduced.

Description

Technical Field

[0001] This disclosure relates to the field of digital management technology for power equipment, and in particular to a method and system for dynamic updating of digital twin models of transformers. Background Technology

[0002] With the rapid development of smart grids, transformer digital twin technology has become an important management tool. Through digital twin technology, maintenance personnel can monitor the operating status of transformers in real time in a virtual environment and predict potential fault risks. A key characteristic of digital twin models is that the digital twin of the transformer in the virtual space remains synchronized with its physical counterpart. When the state of the physical transformer changes, its digital twin should change accordingly. However, a universal update method is lacking. Existing technologies for constructing and updating 3D digital twin models still suffer from the following problems: poor data timeliness: existing models have low update frequencies, and due to the large amount of multi-source heterogeneous data generated during transformer operation, efficient real-time fusion is difficult, resulting in an inability to reflect transformer state changes in real time; fixed update mechanism: existing models often use a fixed update frequency, directly affecting the model's accuracy and real-time performance.

[0003] To address the aforementioned issues, there is an urgent need for a three-dimensional digital twin model method that can be dynamically updated in real time, enabling the transformer model to reflect the actual operating status of the equipment in real time, thereby better supporting equipment management and decision-making. Summary of the Invention

[0004] This disclosure provides a method and system for dynamically updating digital twin models of transformers, which solves the technical problems of poor data timeliness in the construction and updating of three-dimensional digital twin models in the prior art, which leads to the inability to reflect the state changes of transformers in real time, and the fixed update mechanism, which affects the accuracy and real-time performance of the model.

[0005] According to a first aspect of this disclosure, a method for dynamically updating a digital twin model of a transformer is provided. The method includes: acquiring a structural dataset of the transformer, wherein the structural dataset includes at least internal structural data and external structural data of the transformer;

[0006] Based on the structural dataset of transformers, an initial digital twin model of transformers is constructed;

[0007] Collect multi-source real-time datasets, wherein the multi-source real-time datasets include at least transformer operating data and transformer environmental data;

[0008] The multi-source real-time dataset and the initial digital twin model of the transformer are substituted into the model update module to generate a visualized dynamically updated digital twin model of the transformer and an update adjustment scheme corresponding to the transformer. The update adjustment scheme includes at least the update frequency and abnormal adjustment standard parameters.

[0009] When the model meets the update conditions, the current digital twin model of the transformer is dynamically updated based on the update adjustment scheme.

[0010] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the construction of the initial digital twin model of the transformer based on the transformer's structural dataset includes:

[0011] The transformer structure dataset is preprocessed to obtain the preprocessed transformer structure dataset.

[0012] Based on the preprocessed transformer structure dataset, an initial digital twin model of the transformer is constructed.

[0013] As described above and in any possible implementation, a further implementation is provided in which, before substituting the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module, the method further includes:

[0014] Acquire initial operating data at the initial moment of transformer operation, wherein the initial operating data includes at least initial operating temperature, initial vibration parameters, and initial load parameters;

[0015] Based on the initial operating data, the initial digital twin model of the transformer is initialized to obtain the initial digital twin model of the transformer with initial configuration.

[0016] As described above and in any possible implementation, a further implementation is provided, wherein the acquisition of multi-source real-time datasets includes:

[0017] In response to the update command or initial update command of the transformer, real-time environmental data of the load connected to the transformer and the internal components of the transformer are collected, wherein the environmental data includes at least the temperature parameters, vibration parameters, voltage parameters and current parameters of the load or components;

[0018] Collect real-time transformer operating data, wherein the operating data includes at least the transformer's operating current, operating voltage, operating temperature, and operating vibration parameters;

[0019] The real-time environmental data of the load connected to the transformer, the internal components of the transformer, and the real-time operating data of the transformer are preprocessed to obtain preprocessed environmental data and operating data.

[0020] Based on the preprocessed environmental and operational data, a multi-source real-time dataset is selectively constructed using the preprocessed environmental and operational data.

[0021] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the step of substituting the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module to generate a visualized dynamically updated digital twin model of the transformer and an update and adjustment scheme corresponding to the transformer includes:

[0022] Based on multi-source real-time datasets, the initial digital twin model of the transformer is adjusted and labeled to obtain an initial digital twin model of the transformer with multiple adjustment labels.

[0023] Based on multi-source real-time datasets, prediction and simulation are performed to dynamically update the initial digital twin model of a transformer with multiple adjustment markers, resulting in a dynamically updated digital twin model of the transformer.

[0024] The dynamically updated digital twin model of the transformer is visualized to obtain a visualized digital twin model of the transformer.

[0025] Based on multi-source real-time datasets, update and adjustment schemes and generation times are generated in real time.

[0026] Based on the latest generated update and adjustment scheme, the update and adjustment scheme corresponding to the transformer is selectively updated to obtain the latest update and adjustment scheme corresponding to the transformer.

[0027] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the adjustment and labeling of the initial digital twin model of the transformer based on a multi-source real-time dataset to obtain an initial digital twin model of the transformer with multiple adjustment labels includes:

[0028] Feature extraction is performed on multi-source real-time datasets to obtain feature data values ​​of various extracted features;

[0029] Based on the feature data values ​​of the extracted multiple features, the initial digital twin model of the transformer is adjusted and marked to obtain an initial digital twin model of the transformer with multiple adjustment marks.

[0030] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the prediction and simulation based on multi-source real-time datasets, and the dynamic updating of the initial digital twin model of the transformer with multiple adjustment markers, to obtain the dynamically updated digital twin model of the transformer, includes:

[0031] The predicted state of the transformer is obtained by making predictions based on multi-source real-time datasets;

[0032] Simulation calculations were performed based on multi-source real-time datasets and a pre-set finite element analysis module to obtain simulation results of the transformer.

[0033] Based on the simulation results of the transformer, multi-source real-time datasets, and the predicted state of the transformer, the initial digital twin model of the transformer with multiple adjustment markers is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

[0034] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the initial digital twin model of the transformer with multiple adjustment markers is dynamically updated based on the transformer simulation calculation results, multi-source real-time datasets, and the predicted state of the transformer, to obtain a dynamically updated digital twin model of the transformer, including:

[0035] Based on the predicted state of the transformer and multiple adjustment markers in the initial digital twin model of the transformer, multiple dynamically updated adjustment directions and adjustment parameters for each adjustment direction are determined.

[0036] Based on the simulation results of the transformer and the multi-source real-time dataset, the dynamically updated multiple adjustment directions and the adjustment parameters of each adjustment direction are fused and adjusted to obtain the fused adjustment multiple adjustment directions and the adjustment parameters of each adjustment direction.

[0037] Based on the multiple adjustment directions after fusion and the adjustment parameters of each adjustment direction, the initial digital twin model of the transformer with multiple adjustment marks is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

[0038] As described above and any possible implementation, a further implementation is provided, wherein the real-time generation and update adjustment scheme based on multi-source real-time datasets and the generation time include:

[0039] An initial update frequency is generated based on multi-source real-time datasets and the predicted state of the transformer.

[0040] Based on multi-source real-time datasets and transformer simulation results, the initial update frequency is adjusted to obtain the final update frequency.

[0041] Based on the predicted state of the transformer, multi-source real-time datasets, and transformer simulation results, the standard parameters for abnormal adjustment are determined.

[0042] An update and adjustment scheme is constructed using the ultimate update frequency and abnormal adjustment standard parameters, and the generation time of the update and adjustment scheme is recorded.

[0043] According to a second aspect of this disclosure, a dynamic update system for a transformer digital twin model is provided. The system includes: a communication device, a data acquisition device, a model update module, and a control device. The communication device is used to realize information interaction between the data acquisition device and the transformer. The data acquisition device is at least used to acquire a structural dataset and a multi-source real-time dataset of the transformer. The model update module is used to generate a visualized, dynamically updated digital twin model of the transformer and an update and adjustment scheme corresponding to the transformer based on the multi-source real-time dataset and an initial digital twin model of the transformer. The control device includes a memory and a processor. The memory stores a computer program, and the processor executes the program to implement the methods described above.

[0044] The above-disclosed technical solutions have at least one or more of the following beneficial effects:

[0045] By acquiring the structural dataset of the transformer, an initial digital twin model of the transformer is constructed, enabling comprehensive acquisition of relevant transformer information for accurate initial digital twin model construction. The collected multi-source real-time dataset and the initial digital twin model are then fed into the model update module to generate a visualized, dynamically updated digital twin model of the transformer, along with a corresponding update and adjustment scheme. This provides an intuitive reflection of the transformer's state changes, achieving a dynamic visualization effect. The digital twin model of the transformer can reflect its actual operating status in real time, thus better supporting equipment management and decision-making. Furthermore, through the update and adjustment scheme corresponding to the transformer, the update frequency of the transformer is adaptively adjusted for different operating conditions. Based on this update and adjustment scheme, the current digital twin model of the transformer is dynamically updated, ensuring the timeliness of the digital twin model while reducing long-term resource occupation. This improves the management efficiency of transformers and other power equipment, reduces failure rates, and promotes the intelligent and digital development of the power system.

[0046] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0047] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0048] Figure 1 A flowchart is shown for a method for dynamically updating a digital twin model of a transformer according to an embodiment of the present disclosure;

[0049] Figure 2 A schematic diagram of the transformer digital twin model architecture and dynamic update method according to another embodiment of the present disclosure is shown;

[0050] Figure 3 A physical model update strategy according to another embodiment of this disclosure is shown;

[0051] Figure 4 A sound field model updating method according to another embodiment of the present disclosure is shown; Figure 5 A block diagram of a system for constructing and dynamically updating a three-dimensional digital twin model of a transformer according to an embodiment of the present disclosure is shown.

[0052] List of reference numerals in the attached diagram:

[0053] 200: Construction and dynamic update system; 201: Control device; 2011: Processor; 2012: Memory; 2013: Program code; 202: Model update module; 203: Communication device; 204: Data acquisition device. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0055] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0056] Digital twin architecture can generally be divided into four layers, such as Figure 2As shown: ① Physical layer: Represents the physical space in which the transformer operates, including geometric parameters, material properties, and operating environment. ② Sensing layer: Information in the physical space is collected from various sensors, including top oil temperature, winding temperature, tank vibration, external noise, electric field strength, and magnetic field strength. ③ Interaction layer: Information exchange occurs between the virtual and physical spaces; the proposed dynamic update method for the digital twin model belongs to this layer. ④ Virtual layer: The digital twin of the transformer in the virtual space, containing both the geometric and physical models of the transformer. The geometric model includes static and dynamic models, while the physical model includes the internal temperature field, electromagnetic field, and sound field affecting both the internal and external environments of the transformer. (See appendix for details.) Figure 1 , Figure 1 A flowchart illustrating a method for dynamically updating a transformer digital twin model according to an embodiment of this disclosure is shown. Figure 1 As shown, the dynamic update method for the digital twin model of a transformer in this embodiment mainly includes the following steps S101-S105.

[0057] Step S101: Obtain the transformer structure dataset, wherein the transformer structure dataset includes at least the transformer's internal structure data and the transformer's external structure data;

[0058] Specifically, the internal structure data of the transformer includes at least the rated operating parameters of the transformer's internal components, wherein the internal components may include windings, core, and resistors, and the rated operating parameters may include rated voltage, rated current, rated power, and short-circuit impedance. The external structure data of the transformer includes at least the rated operating parameters of the cooling device and the load.

[0059] Step S102: Based on the transformer's structural dataset, construct an initial digital twin model of the transformer;

[0060] In some embodiments, constructing an initial digital twin model of the transformer based on the transformer's structural dataset includes:

[0061] The transformer structure dataset is preprocessed to obtain the preprocessed transformer structure dataset.

[0062] Based on the preprocessed transformer structure dataset, an initial digital twin model of the transformer is constructed.

[0063] Specifically, the preprocessing method for the transformer structure dataset can be any existing data preprocessing method. The preprocessing process can sequentially include data cleaning, data denoising, outlier removal, and data format conversion to ensure the integrity and accuracy of data collection. This facilitates the construction of an initial digital twin model of the transformer based on a transformer structure dataset with the same data format. The choice of preprocessing method here is merely illustrative. In actual testing, those skilled in the art can choose according to actual needs, as long as the preprocessed transformer structure dataset meets the data requirements for constructing the initial digital twin model of the transformer. Further details are omitted here.

[0064] Specifically, the construction method of the initial digital twin model of the transformer can adopt the existing digital twin model construction method. The choice of construction method here is only an example. In actual testing, those skilled in the art can choose according to actual needs, as long as it can realize the construction of the initial digital twin model of the transformer through the preprocessed transformer structure dataset. It will not be elaborated here.

[0065] Step S103: Collect multi-source real-time datasets, wherein the multi-source real-time datasets include at least transformer operating data and transformer environmental data;

[0066] In some embodiments, the acquisition of multi-source real-time datasets includes:

[0067] In response to the update command or initial update command of the transformer, real-time environmental data of the load connected to the transformer and the internal components of the transformer are collected, wherein the environmental data includes at least the temperature parameters, vibration parameters, voltage parameters and current parameters of the load or components;

[0068] Collect real-time transformer operating data, wherein the operating data includes at least the transformer's operating current, operating voltage, operating temperature, and operating vibration parameters;

[0069] The real-time environmental data of the load connected to the transformer, the internal components of the transformer, and the real-time operating data of the transformer are preprocessed to obtain preprocessed environmental data and operating data.

[0070] Based on the preprocessed environmental and operational data, a multi-source real-time dataset is selectively constructed using the preprocessed environmental and operational data.

[0071] Specifically, the preprocessing method for preprocessing the real-time load connected to the transformer, the environmental data of the transformer's internal components, and the real-time operating data of the transformer is the same as the preprocessing method for preprocessing the transformer's structural dataset.

[0072] Specifically, the selective formation of a multi-source real-time dataset based on preprocessed environmental and operational data includes:

[0073] Based on the preprocessed environmental data and operational data, determine whether at least one preset key data is missing from the preprocessed environmental data and operational data:

[0074] If the determination is yes, then re-collect environmental data and operational data, and execute subsequent steps;

[0075] If the determination is negative, then the preprocessed environmental data and operational data are used to form a multi-source real-time dataset.

[0076] Specifically, the preset key data of the at least one may include data of any parameter of any one or more loads or components, or any data of the transformer. The setting of the preset key data of the at least one is only an illustrative example. In actual testing, those skilled in the art can set it according to actual needs, which will not be elaborated here.

[0077] In the above embodiments, in response to the transformer's update command or initial update command, relevant data of the transformer is collected, and the collected data is preprocessed to ensure the accuracy and integrity of the data. After preprocessing, a multi-source real-time dataset is formed, realizing the time synchronization processing of data from different sources, so as to provide reliable input for subsequent dynamic updates of the model.

[0078] Step S104: Substitute the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module to generate a visualized dynamically updated digital twin model of the transformer and an update adjustment scheme corresponding to the transformer. The update adjustment scheme includes at least the update frequency and abnormal adjustment standard parameters.

[0079] In some embodiments, before incorporating the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module, the method further includes:

[0080] Acquire initial operating data at the initial moment of transformer operation, wherein the initial operating data includes at least initial operating temperature, initial vibration parameters, and initial load parameters;

[0081] Based on the initial operating data, the initial digital twin model of the transformer is initialized to obtain the initial digital twin model of the transformer with initial configuration.

[0082] Specifically, the initial vibration parameters may include the frequency, amplitude, and direction of the vibration; the initial load parameters may include the current, voltage, and power factor of the load.

[0083] Specifically, the initialization process of the initial digital twin model of the transformer based on the initial operating data to obtain the initial digital twin model of the transformer with initial configuration includes:

[0084] Based on the initial operating temperature of the initial operating data, the initial temperature of the initial digital twin model of the transformer is determined.

[0085] Based on the initial vibration parameters of the initial operating data, the initial vibration parameters of the initial digital twin model of the transformer are determined.

[0086] Based on the initial load parameters of the initial operating data, the initial load parameters of the initial digital twin model of the transformer are determined.

[0087] In the above embodiments, by initializing the initial digital twin model of the transformer, the initial digital twin model of the transformer with the initial operating state of the transformer is matched, thereby improving the accuracy of the initial digital twin model of the transformer in reflecting the operating state of the transformer.

[0088] In some embodiments, the step of substituting the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module to generate a visualized dynamically updated digital twin model of the transformer and an update and adjustment scheme corresponding to the transformer includes:

[0089] Based on multi-source real-time datasets, the initial digital twin model of the transformer is adjusted and labeled to obtain an initial digital twin model of the transformer with multiple adjustment labels.

[0090] Based on multi-source real-time datasets, prediction and simulation are performed to dynamically update the initial digital twin model of a transformer with multiple adjustment markers, resulting in a dynamically updated digital twin model of the transformer.

[0091] The dynamically updated digital twin model of the transformer is visualized to obtain a visualized digital twin model of the transformer.

[0092] Based on multi-source real-time datasets, update and adjustment schemes and generation times are generated in real time.

[0093] Based on the latest generated update and adjustment scheme, the update and adjustment scheme corresponding to the transformer is selectively updated to obtain the latest update and adjustment scheme corresponding to the transformer, so as to ensure that the update and adjustment scheme matches the transformer.

[0094] In some embodiments, adjusting the initial digital twin model of the transformer based on a multi-source real-time dataset to obtain an initial digital twin model of the transformer with multiple adjustment tags includes:

[0095] Feature extraction is performed on multi-source real-time datasets to obtain feature data values ​​of various extracted features;

[0096] Based on the feature data values ​​of the extracted multiple features, the initial digital twin model of the transformer is adjusted and marked to obtain an initial digital twin model of the transformer with multiple adjustment marks.

[0097] Specifically, the types of the multiple features can be preset key data, or any data among temperature change trends and vibration parameters, or multiple features that affect the update and adjustment scheme selected by a trained intelligent machine model. The selection of the types of multiple features and the selection method here are only illustrative examples. In actual testing, those skilled in the art can select according to actual needs, as long as the feature data values ​​of the extracted multiple features can affect the update and adjustment scheme. Further details are not provided here.

[0098] In some embodiments, the prediction and simulation based on multi-source real-time datasets, and the dynamic updating of the initial digital twin model of the transformer with multiple adjustment markers to obtain the dynamically updated digital twin model of the transformer, includes:

[0099] The predicted state of the transformer is obtained by making predictions based on multi-source real-time datasets;

[0100] Simulation calculations were performed based on multi-source real-time datasets and a pre-set finite element analysis module to obtain simulation results of the transformer.

[0101] Based on the simulation results of the transformer, multi-source real-time datasets, and the predicted state of the transformer, the initial digital twin model of the transformer with multiple adjustment markers is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

[0102] Specifically, the simulation calculation technology used by the preset finite element analysis module is the same as that used in the existing finite element analysis module. The selection of simulation calculation technology here is only an example. In actual testing, those skilled in the art can select according to actual needs, as long as it can realize the simulation calculation of the transformer based on the multi-source real-time dataset and the preset finite element analysis module. Further details are omitted here.

[0103] Specifically, the visualization method for visualizing the dynamically updated digital twin model of the transformer can adopt existing visualization methods. It can use color gradients and structural deformation to intuitively reflect the state changes of the transformer and achieve a dynamic visualization effect. The choice of visualization method here is only an example. In actual testing, those skilled in the art can choose according to actual needs, as long as it can achieve the visualization of the dynamically updated digital twin model of the transformer and obtain a visualized digital twin model of the transformer. Further details are omitted here.

[0104] Specifically, the step of selectively updating the update and adjustment scheme corresponding to the transformer based on the latest generated update and adjustment scheme includes:

[0105] Based on the generation time of each update and adjustment plan, determine the latest generated update and adjustment plan and the currently executed update and adjustment plan;

[0106] Simulations were performed on the latest generated update and adjustment scheme and the currently executed update and adjustment scheme, respectively, to obtain simulation data for the latest generated update and adjustment scheme and the currently executed update and adjustment scheme.

[0107] Based on the simulation data of the latest generated update and adjustment scheme and the currently executed update and adjustment scheme, the evaluation scores of the latest generated update and adjustment scheme and the currently executed update and adjustment scheme are obtained respectively.

[0108] If the latest generated update adjustment scheme is consistent with the currently executed update adjustment scheme, or if the evaluation score of the latest generated update adjustment scheme is consistent with the currently executed update adjustment scheme, or if the evaluation score of the currently executed update adjustment scheme is higher than the evaluation score of the latest generated update adjustment scheme, then the update adjustment scheme corresponding to the transformer will not be updated.

[0109] If the evaluation score of the newly generated update and adjustment plan is higher than the evaluation score of the currently executed update and adjustment plan, then the newly generated update and adjustment plan will be updated based on the newly generated update and adjustment plan.

[0110] Specifically, the evaluation scores of the newly generated update and adjustment scheme and the currently executed update and adjustment scheme are obtained using the same formula, as follows:

[0111]

[0112] Where S represents the evaluation score, n represents the total number of performance indicators, and the performance indicators can be voltage stability, current efficiency, power factor, temperature distribution uniformity, and ω. i This represents the weight corresponding to the i-th performance metric, where the sum of the weights of all performance metrics is 1. f(X i () represents the contribution of performance indicators to the overall evaluation score.

[0113] Among them, the contribution of performance indicators to the overall evaluation score f(X) i It is obtained through the following formula:

[0114]

[0115] Where p, q, and r represent three preset parameter values, where p takes the value of [-1, 1], q takes the value of (0, 1], and r takes the value of [-1, 1].

[0116] In some embodiments, the dynamic updating of the initial digital twin model of the transformer with multiple adjustment markers based on the transformer simulation calculation results, multi-source real-time datasets, and the predicted state of the transformer, to obtain the dynamically updated digital twin model of the transformer, includes:

[0117] Based on the predicted state of the transformer and multiple adjustment markers in the initial digital twin model of the transformer, multiple dynamically updated adjustment directions and adjustment parameters for each adjustment direction are determined.

[0118] Based on the simulation results of the transformer and the multi-source real-time dataset, the dynamically updated multiple adjustment directions and the adjustment parameters of each adjustment direction are fused and adjusted to obtain the fused adjustment multiple adjustment directions and the adjustment parameters of each adjustment direction.

[0119] Based on the multiple adjustment directions after fusion and the adjustment parameters of each adjustment direction, the initial digital twin model of the transformer with multiple adjustment marks is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

[0120] In some embodiments, the real-time generation of the update and adjustment scheme based on multi-source real-time datasets and the generation time include:

[0121] An initial update frequency is generated based on multi-source real-time datasets and the predicted state of the transformer.

[0122] Based on multi-source real-time datasets and transformer simulation results, the initial update frequency is adjusted to obtain the final update frequency.

[0123] Based on the predicted state of the transformer, multi-source real-time datasets, and transformer simulation results, the standard parameters for abnormal adjustment are determined.

[0124] An update and adjustment scheme is constructed using the ultimate update frequency and abnormal adjustment standard parameters, and the generation time of the update and adjustment scheme is recorded.

[0125] Specifically, the specific generation method for generating the update and adjustment scheme and the specific update method for dynamically updating the initial digital twin model of the transformer with multiple adjustment marks can be obtained using a trained neural network model or an intelligent learning model. The selection of the specific generation and update methods here is only an example. In actual testing, those skilled in the art can choose according to actual needs, as long as it can realize the real-time generation of the update and adjustment scheme and the generation time based on the multi-source real-time dataset, and the dynamic update of the initial digital twin model of the transformer with multiple adjustment marks based on the transformer simulation calculation results, the multi-source real-time dataset, and the predicted state of the transformer, to obtain the dynamically updated digital twin model of the transformer, it is acceptable. Further details are omitted here.

[0126] In the above embodiments, during module processing, the initial digital twin model of the transformer is adjusted and marked with multiple adjustment tags using a multi-source real-time dataset. This facilitates targeted adjustments and dynamic updates to the initial digital twin model. Then, prediction and simulation are performed using the multi-source real-time dataset to dynamically update the initial digital twin model, resulting in a dynamically updated digital twin model. Temperature data from the multi-source real-time dataset is used to update the temperature distribution of the tank and windings, while vibration data is used to display the operational stability of the equipment. Finally, visualization is used to intuitively reflect the transformer's state changes, achieving a dynamic visualization effect. Then, by using multi-source real-time datasets, update and adjustment schemes and their generation times are generated in real time, and the latest update and adjustment scheme corresponding to the transformer is selectively updated to ensure that the update and adjustment scheme matches the transformer. This achieves automatic adjustment according to the transformer's operating conditions to improve update efficiency, and also achieves adaptive adjustment of the update frequency of the digital twin model. For high load or fault warning states, the update frequency is increased to ensure the timeliness of the model; and under normal operating conditions, the update frequency is automatically reduced to reduce resource consumption, thereby improving the responsiveness under different transformer operating conditions and ensuring the efficiency and stability of model updates.

[0127] Step S105: When it is determined that the model meets the update conditions, based on the update adjustment scheme, dynamically update the current digital twin model of the transformer. Specifically, the dynamic update of the current digital twin model of the transformer based on the update adjustment scheme includes:

[0128] Based on the aforementioned update and adjustment scheme, multiple issuance times for the update command of the transformer are determined;

[0129] When multiple times when an update command for any transformer is issued are reached, an update command is issued to the transformer to facilitate the collection of multi-source real-time datasets.

[0130] Specifically, if, in response to the update command of the transformer, a multi-source real-time dataset is collected, the method further includes:

[0131] If any data in the multi-source real-time dataset reaches the abnormal adjustment standard parameter in the update and adjustment scheme, then the "collect multi-source real-time dataset" and subsequent steps will be executed again.

[0132] Otherwise, proceed to the next step of "collecting multi-source real-time datasets".

[0133] Specifically, the abnormal adjustment standard parameter in the update and adjustment scheme can be a data threshold for any data or a quantity value for any data, so as to realize automatic detection of data anomalies and ensure that when data loss or data mutation occurs during data transmission, the anomaly can be automatically repaired, thereby ensuring the continuity and reliability of the update.

[0134] Specifically, the method further includes:

[0135] When multiple real-time datasets from multiple sources are acquired, and any data in any of the acquired datasets meets the abnormal adjustment standard parameters in the update and adjustment scheme, and the multiple acquisitions reach a preset repetition threshold, the transformer is determined to be in an abnormal state. An alarm command is then automatically issued, and the multiple real-time datasets from multiple sources are sent to the management terminal to provide timely early warning information to the maintenance personnel at the management terminal. This enables the detection of abnormal transformer states through real-time data, automatic alarm triggering, and improved timely response and maintenance of transformer anomalies, thereby achieving intelligent monitoring of the transformer.

[0136] Preferably, the method further includes: determining whether the model meets the update conditions by verifying whether the sensing data of the perception layer is consistent with the key node data of the digital twin of the virtual layer. Here, the key nodes are the positions of each sensor, thereby ensuring the accuracy of the sensing data. If so, the update conditions are not met and the model remains unchanged; otherwise, the update conditions are met and the target parameters that need to be updated are determined based on the update adjustment scheme.

[0137] A geometric model describes the shape and size of a physical object using geometric parameters (length, width, diameter, etc.). Since a transformer is a static device, its static geometric model is determined by the design documents and typically remains unchanged. The dynamic geometric model is updated using an event-driven model update strategy, meaning that an update is triggered when events such as transformer maintenance, return to factory, or bushing replacement occur. Preferably, in another embodiment, the specific physical model update strategy is as follows: Figure 3 As shown:

[0138] ① Determine the update parameters. Based on the differences between the sensor data and the digital twin model, determine the strongly correlated parameters to be updated.

[0139] ② Construct the objective function: Based on the determined update parameters, construct the objective function to make the output of the digital twin model as close as possible to reality.

[0140] ③ Design optimization algorithms: Design corresponding optimization algorithms (Gauss-Newton equations, nonlinear least squares method, etc.) to find the optimal solution.

[0141] ④ Process sensor data: Based on the determined parameters to be updated and the constructed objective function, determine which sensor data should be collected and preprocess the sensor data (cleaning, noise reduction, integration, etc.).

[0142] ⑤ Evaluate model error by comparing the updated digital twin model output with the sensor data to determine if the model meets the requirements. If it does, update the model; otherwise, return to the design optimization algorithm.

[0143] The physical model update strategy is illustrated using the sound field as an example. The sound field model update method is as follows: Figure 4 As shown:

[0144] ① Using finite element simulation, the transformer core and windings are treated as equivalent sound sources. The fluid-structure interaction of vibration in oil is considered, and a propagation model of vibration in oil is established. Combined with the sound field boundary conditions, the three-dimensional sound field distribution of the transformer is calculated.

[0145] ② The sound-vibration signals of the transformer are collected by using vibration sensors installed on the surface of the transformer tank and acoustic microphones outside the tank, and preprocessed by filtering, noise reduction and normalization.

[0146] ③ When there is a difference between the simulation calculation results and the measured signal, the three-dimensional sound field distribution is determined as the parameter to be updated.

[0147] ④ To minimize the error in calculating the sound field, construct the objective function:

[0148]

[0149] Where θ represents the parameters to be optimized in the model, and p sim and p meas The simulated and measured sound pressure levels are respectively, r i It is a spatial vector.

[0150] ⑤ The objective function is optimized by combining Bayesian optimization and Gaussian process regression.

[0151] ⑥ Mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are selected as indicators to evaluate the calculation error of the model.

[0152]

[0153] ⑦ When the model calculation error meets the requirements, the optimized sound field distribution replaces the original data to update the sound field distribution of the digital twin model.

[0154] According to the embodiments of this disclosure, the following technical effects are achieved:

[0155] By acquiring the structural dataset of the transformer, an initial digital twin model of the transformer is constructed, enabling comprehensive acquisition of relevant transformer information for accurate initial digital twin model construction. The collected multi-source real-time dataset and the initial digital twin model are then fed into the model update module to generate a visualized, dynamically updated digital twin model of the transformer, along with a corresponding update and adjustment scheme. This provides an intuitive reflection of the transformer's state changes, achieving a dynamic visualization effect. The digital twin model of the transformer can reflect its actual operating status in real time, thus better supporting equipment management and decision-making. Furthermore, through the update and adjustment scheme corresponding to the transformer, the update frequency of the transformer is adaptively adjusted for different operating conditions. Based on this update and adjustment scheme, the current digital twin model of the transformer is dynamically updated, ensuring the timeliness of the digital twin model while reducing long-term resource occupation. This improves the management efficiency of transformers and other power equipment, reduces failure rates, and promotes the intelligent and digital development of the power system. It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0156] The above is an introduction to the method embodiments. The following system embodiments will further illustrate the solution described in this disclosure.

[0157] Furthermore, this disclosure also provides a dynamic update system for a digital twin model of a transformer.

[0158] See appendix Figure 5 , Figure 5 A block diagram of a transformer digital twin model dynamic update system according to an embodiment of the present disclosure is shown. Figure 5As shown, the dynamic update system 200 in this embodiment includes at least a communication device 203, a data acquisition device 204, a model update module 202, and a control device 201, which are respectively installed inside and outside the battery swapping cabinet. The communication device 203 is used to realize information interaction between the data acquisition device 204 and the transformer. The data acquisition device 204 is used to acquire at least the transformer's structural dataset and multi-source real-time dataset. The model update module 202 is used to generate a visualized dynamically updated digital twin model of the transformer and an update and adjustment scheme corresponding to the transformer based on the multi-source real-time dataset and the transformer's initial digital twin model. The control device 201 includes a processor 2011 and a memory 2012. The memory 2012 can be configured to store program code 2013 for executing the transformer three-dimensional digital twin model construction and dynamic update method of the above method embodiment. The processor 2011 can be configured to execute the program code 2013 in the memory 2012. The program code 2013 includes, but is not limited to, the program code 2013 for executing the transformer three-dimensional digital twin model construction and dynamic update method of the above method embodiment. For ease of explanation, only the parts relevant to the embodiments of this disclosure are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this disclosure. The control device 201 may be a control device comprising various electronic devices.

[0159] Specifically, the communication device 203 can be connected via Wi-Fi, Bluetooth, or wired connection. The choice of communication device 203 is merely illustrative. Those skilled in the art can choose according to actual usage needs, as long as the communication device 203 enables mutual communication between the acquisition device 204 and the transformer, thereby realizing information interaction between the acquisition device 204 and the transformer. Further details are omitted here.

[0160] Specifically, the acquisition device 204 can be a variety of sensors installed around the transformer or a variety of sensors installed inside the transformer. The type of acquisition device 204 is not limited. Those skilled in the art can choose according to actual usage needs, as long as the acquisition device 204 can acquire the structural dataset and multi-source real-time dataset of the transformer. Further details are omitted here.

[0161] Specifically, the system also includes a preset finite element analysis module, which is used to perform simulation calculations based on multi-source real-time datasets to obtain the simulation calculation results of the transformer.

[0162] In one implementation, the specific function can be described in steps S101-S105.

[0163] The aforementioned dynamic update system 200 is used to perform Figure 2 The embodiments of the transformer three-dimensional digital twin model construction and dynamic update method shown are similar in technical principle, technical problem solved and technical effect produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the dynamic update system 200 can be referred to the contents described in the embodiments of the transformer digital twin model dynamic update method, which will not be repeated here.

[0164] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment of this disclosure can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 2011, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0165] Furthermore, the construction and dynamic update system of this disclosure also includes a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to this disclosure, the computer-readable storage medium may be configured to store program code 2013 for executing the transformer three-dimensional digital twin model construction and dynamic update method of the above method embodiments. The program code 2013 may be loaded and run by processor 2011 to implement the above transformer three-dimensional digital twin model construction and dynamic update method. For ease of explanation, only the parts related to the embodiments of this disclosure are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this disclosure. The computer-readable storage medium may be a memory 2012 device including various electronic devices. Optionally, in the embodiments of this disclosure, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0166] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the apparatus of this disclosure, the physical devices corresponding to these modules may be the processor 2011 itself, or a part of the software, hardware, or a combination of software and hardware within the processor 2011. Therefore, the number of modules shown in the figures is merely illustrative.

[0167] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor 2011, which may be a dedicated or general-purpose programmable processor 2011, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0168] The program code 2013 used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code 2013 may be provided to a processor 2011 or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor 2011 or controller, the program code 2013 causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code 2013 may be executed entirely on a machine, partially on a machine, partially on a remote machine as a standalone software package, or entirely on a remote machine or server.

[0169] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0170] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for dynamically updating a digital twin model of a transformer, characterized in that, include: Obtain a structural dataset of the transformer, which includes at least internal and external structural data. Based on this dataset, construct an initial digital twin model of the transformer. Collect multi-source real-time datasets, including at least operational and environmental data of the transformer. Substitute the multi-source real-time datasets and the initial digital twin model into a model update module to generate a visualized, dynamically updated digital twin model of the transformer and a corresponding update and adjustment scheme. This update and adjustment scheme includes at least an update frequency and abnormal adjustment standard parameters. When the model meets the update conditions, dynamically update the current digital twin model of the transformer based on the update and adjustment scheme.

2. The method according to claim 1, characterized in that, The initial digital twin model of the transformer, based on the transformer-based structural dataset, includes: The transformer structure dataset is preprocessed to obtain the preprocessed transformer structure dataset. Based on the preprocessed transformer structure dataset, an initial digital twin model of the transformer is constructed.

3. The method according to claim 2, characterized in that, Before substituting the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module, the method further includes: Acquire initial operating data at the initial moment of transformer operation, wherein the initial operating data includes at least initial operating temperature, initial vibration parameters, and initial load parameters; Based on the initial operating data, the initial digital twin model of the transformer is initialized to obtain the initial digital twin model of the transformer with initial configuration.

4. The method according to claim 3, characterized in that, The collected multi-source real-time dataset includes: In response to the update command or initial update command of the transformer, real-time environmental data of the load connected to the transformer and the internal components of the transformer are collected, wherein the environmental data includes at least the temperature parameters, vibration parameters, voltage parameters and current parameters of the load or components; Collect real-time transformer operating data, wherein the operating data includes at least the transformer's operating current, operating voltage, operating temperature, and operating vibration parameters; The real-time environmental data of the load connected to the transformer, the internal components of the transformer, and the real-time operating data of the transformer are preprocessed to obtain preprocessed environmental data and operating data. Based on the preprocessed environmental and operational data, a multi-source real-time dataset is selectively constructed using the preprocessed environmental and operational data.

5. The method according to claim 4, characterized in that, The step of inputting the multi-source real-time dataset and the initial digital twin model of the transformer into the model update module to generate a visualized dynamically updated digital twin model of the transformer and the corresponding update and adjustment scheme includes: Based on multi-source real-time datasets, the initial digital twin model of the transformer is adjusted and labeled to obtain an initial digital twin model of the transformer with multiple adjustment labels. Based on multi-source real-time datasets, prediction and simulation are performed to dynamically update the initial digital twin model of a transformer with multiple adjustment markers, resulting in a dynamically updated digital twin model of the transformer. The dynamically updated digital twin model of the transformer is visualized to obtain a visualized digital twin model of the transformer. Based on multi-source real-time datasets, update and adjustment schemes and generation times are generated in real time. Based on the latest generated update and adjustment scheme, the update and adjustment scheme corresponding to the transformer is selectively updated to obtain the latest update and adjustment scheme corresponding to the transformer.

6. The method according to claim 5, characterized in that, The process of adjusting and marking the initial digital twin model of the transformer based on multi-source real-time datasets to obtain an initial digital twin model of the transformer with multiple adjustment marks includes: Feature extraction is performed on multi-source real-time datasets to obtain feature data values ​​of various extracted features; Based on the feature data values ​​of the extracted multiple features, the initial digital twin model of the transformer is adjusted and marked to obtain an initial digital twin model of the transformer with multiple adjustment marks.

7. The method according to claim 6, characterized in that, The prediction and simulation based on multi-source real-time datasets, and the dynamic updating of the initial digital twin model of the transformer with multiple adjustment markers, yields the dynamically updated digital twin model of the transformer, including: The predicted state of the transformer is obtained by making predictions based on multi-source real-time datasets; Simulation calculations were performed based on multi-source real-time datasets and a pre-set finite element analysis module to obtain simulation results of the transformer. Based on the simulation results of the transformer, multi-source real-time datasets, and the predicted state of the transformer, the initial digital twin model of the transformer with multiple adjustment markers is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

8. The method according to claim 7, characterized in that, The initial digital twin model of the transformer with multiple adjustment markers is dynamically updated based on the transformer simulation calculation results, multi-source real-time datasets, and the predicted state of the transformer, resulting in a dynamically updated digital twin model of the transformer, including: Based on the predicted state of the transformer and multiple adjustment markers in the initial digital twin model of the transformer, multiple dynamically updated adjustment directions and adjustment parameters for each adjustment direction are determined. Based on the simulation results of the transformer and the multi-source real-time dataset, the dynamically updated multiple adjustment directions and the adjustment parameters of each adjustment direction are fused and adjusted to obtain the fused adjustment multiple adjustment directions and the adjustment parameters of each adjustment direction. Based on the multiple adjustment directions after fusion and the adjustment parameters of each adjustment direction, the initial digital twin model of the transformer with multiple adjustment marks is dynamically updated to obtain the dynamically updated digital twin model of the transformer.

9. The method according to claim 8, characterized in that, The real-time generation and update adjustment scheme based on multi-source real-time datasets and the generation time include: An initial update frequency is generated based on multi-source real-time datasets and the predicted state of the transformer. Based on multi-source real-time datasets and transformer simulation results, the initial update frequency is adjusted to obtain the final update frequency. Based on the predicted state of the transformer, multi-source real-time datasets, and transformer simulation results, the standard parameters for abnormal adjustment are determined. An update and adjustment scheme is constructed using the ultimate update frequency and abnormal adjustment standard parameters, and the generation time of the update and adjustment scheme is recorded.

10. A system for constructing and dynamically updating a three-dimensional digital twin model of a transformer, characterized in that, The system includes a communication device, a data acquisition device, a model update module, and a control device. The communication device is used to realize information interaction between the data acquisition device and the transformer. The data acquisition device is used to acquire at least the transformer's structural dataset and multi-source real-time dataset. The model update module is used to generate a visualized, dynamically updated digital twin model of the transformer and an update and adjustment scheme corresponding to the transformer based on the multi-source real-time dataset and the transformer's initial digital twin model. The control device includes a processor and a memory. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the transformer three-dimensional digital twin model construction and dynamic update method according to any one of claims 1 to 9.

Images