Multi-granularity and multi-dimension power transmission and transformation equipment digital twinning mechanism method and system

Abstract

The invention discloses a multi-granularity multi-dimensional power transmission and transformation equipment digital twinning mechanism method and system, and relates to the technical field of power transmission and transformation equipment digital modeling, and the method comprises the steps: collecting multi-dimensional physical field data, and carrying out the preprocessing; constructing a layered multi-physics field coupling model; carrying out integration and parameter adjustment on the output of the layered multi-physics field coupling model to form a unified multi-physics field coupling model; and performing simultaneous analysis on multiple physical fields to complete dynamic simulation and fault prediction. By improving the finite element analysis method and the hierarchical multi-physics field modeling technology, the technical problem that the operation state of the power transmission and transformation equipment in a complex multi-physics field coupling environment is difficult to accurately monitor and predict the fault in real time is technically solved, and the effects of improving the monitoring precision and enhancing the fault diagnosis real-time performance and the prediction accuracy are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital modeling of power transmission and transformation equipment, and specifically to a multi-granularity and multi-dimensional digital twin mechanism method and system for power transmission and transformation equipment. Background Art

[0002] In modern power systems, power transmission and transformation equipment is a key infrastructure, and its operating status is directly related to the stability and safety of the power system. However, since power transmission and transformation equipment will be affected by the complex and changeable working environment during operation, including the interaction of multiple physical fields such as electromagnetic, thermal and mechanical stress, traditional equipment status monitoring and fault diagnosis methods still have great deficiencies in accuracy and real-time performance. With the increase in power demand and the increase in equipment complexity, the limitations of existing methods in dealing with multi-physical field coupling and accurate simulation are gradually emerging. Therefore, it is an important direction of current research to build a digital twin model that can fully reflect the actual working status of the equipment to improve the accuracy of equipment monitoring and diagnosis.

[0003] Previous studies have explored the application of digital twins and big data mining technologies in power transmission and transformation equipment fault diagnosis. Using digital twin technology, a method of monitoring and evaluating the status of power transmission and transformation equipment is developed through data collection, data governance, model building and other levels. This method achieves a comprehensive perception of equipment operation data and performs fault diagnosis through data mining and model evaluation. However, the model mainly relies on big data analysis and empirical evaluation of equipment monitoring data, and fails to fully utilize the multi-physical field coupling mechanism for refined physical field modeling. Therefore, it is difficult to deeply simulate the multi-dimensional coupling characteristics of the equipment under extreme working conditions, resulting in limited accuracy of fault diagnosis. In addition, data cleaning and sensor data fusion are still the main difficulties of this method, and it lacks the ability to accurately model complex scenarios.

[0004] At the same time, mathematical methods such as fuzzy pattern recognition are used to deal with uncertain factors in the operation of power transmission and transformation equipment, which can achieve rapid online fault detection. However, since its model is mainly based on fault data mining and fault tree analysis, it lacks deep physical field modeling capabilities, especially in complex multi-physical field coupling scenarios. It is difficult to perform refined simulation and multi-granular modeling of equipment status. These shortcomings limit its accurate prediction and real-time monitoring effects in multi-dimensional scenarios, affecting the accuracy and real-time performance of fault diagnosis.

[0005] In view of the shortcomings of the above methods, the present invention proposes a multi-granularity, multi-dimensional digital twin mechanism model of power transmission and transformation equipment based on an improved finite element analysis method, focusing on solving the shortcomings of existing models in multi-physical field coupling analysis and refined simulation. The present invention innovatively uses improved finite element analysis technology as the main modeling method to construct a unified coupling model of multiple physical fields such as electromagnetic, thermal, and mechanical stress, and finely reflects the multi-dimensional operating characteristics of the equipment through multi-granularity hierarchical modeling (macroscopic layer, mesoscopic layer, and microscopic layer). Compared with previous methods, this model can realize dynamic simulation of multiple physical fields at different spatial and temporal granularities, and through multi-layer data fusion and precision calibration, it greatly improves the monitoring accuracy of the equipment's operating status and the accuracy of fault diagnosis, providing more reliable technical support for applications such as equipment status assessment and fault prediction. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is: how to construct a unified digital twin model through an improved finite element analysis method combined with multi-granularity hierarchical modeling technology to accurately reflect the dynamic operating state of power transmission and transformation equipment under the action of electromagnetic field, thermal field and mechanical stress field, thereby improving the accuracy and real-time performance of fault prediction.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment, which comprises the following steps:

[0009] Collect multi-dimensional physical field data and perform pre-processing;

[0010] Construct a hierarchical multi-physics coupling model based on preprocessed data;

[0011] Integrate and adjust parameters of the hierarchical multi-physics coupling model output to form a unified multi-physics coupling model;

[0012] The unified coupling model is used to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction.

[0013] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the collection of multi-dimensional physical field data and preprocessing includes:

[0014] Use sensors to collect multi-dimensional status information of the equipment, including electric field strength, magnetic induction strength, temperature and stress distribution;

[0015] The preprocessing is to clean and remove noise from the collected multi-dimensional data.

[0016] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the hierarchical multi-physical field coupling model constructed based on preprocessed data includes:

[0017] An improved finite element analysis method is used to construct a hierarchical multi-physics coupling model from the macro, meso and micro levels;

[0018] At the macro level, a global coupling model of the electromagnetic field and the thermal field is constructed based on the geometric characteristics of the overall structure of the device to generate the global electromagnetic field distribution matrix and the thermal field distribution matrix;

[0019] At the mesoscopic level, for key components such as transformer windings and insulation structures, a coupling model of local electromagnetic field and thermal field is constructed, and the effect of mechanical stress field is added to generate the local response matrix of key components;

[0020] At the microscopic level, a stress-strain model is constructed based on the physical properties of the material, and the local deformation behavior of the material is analyzed in combination with the thermal expansion characteristics.

[0021] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the hierarchical multi-physical field coupling model includes:

[0022] The global boundary conditions output by the macroscopic model include the overall electromagnetic field strength and thermal field temperature distribution of the equipment, which serve as input parameters of the mesoscopic model;

[0023] The stress distribution of key components and the change of local temperature field output by the mesoscopic model are used as the input conditions of the microscopic model;

[0024] The local deformation parameters and thermal expansion effect data of the material output by the microscopic model are used to correct the local response results of the mesoscopic model.

[0025] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the output of the hierarchical multi-physics field coupling model is integrated and the parameters are adjusted to form a unified multi-physics field coupling model, including:

[0026] The output results of the hierarchical model are fused using multimodal data fusion technology to generate unified model input data across levels. The parameters of the macro, meso and micro models are adjusted using a global optimization algorithm based on gradient descent. The fused and optimized model results are imported into a unified multi-physics field coupling framework to generate a set of simultaneous equations.

[0027] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the use of a unified coupling model to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction includes:

[0028] In the combined multi-physics field coupling equations, the dynamic changes of the equipment's electromagnetic field, thermal field, and mechanical stress field are simulated in real time through numerical solution methods. The dynamic simulation results are classified and processed to generate simulation data of normal operation, abnormal operation, and fault status. Based on the fault status data, deep learning algorithms are used to predict faults and generate diagnostic reports on the fault location and type.

[0029] As a preferred solution of the multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment described in the present invention, wherein: the use of a unified coupling model to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction also includes:

[0030] Compare the simulation results with the historical operation data of the equipment, update the equipment status database, generate operation and maintenance optimization strategies based on the fault prediction results, and transmit them to the equipment management platform through the interface.

[0031] Another object of the present invention is to provide a multi-granularity and multi-dimensional digital twin mechanism system for power transmission and transformation equipment, which can collect multi-dimensional physical field data of power transmission and transformation equipment in real time through a distributed sensor network, combine an improved finite element analysis method to perform multi-granularity hierarchical modeling, and complete equipment status monitoring and fault prediction through model integration and dynamic simulation analysis, thereby solving the problems of insufficient accuracy of multi-physical field coupling modeling, poor real-time performance, and difficulty in accurately simulating equipment status under extreme working conditions in existing power transmission and transformation equipment monitoring and fault diagnosis methods.

[0032] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-granularity and multi-dimensional digital twin mechanism system for power transmission and transformation equipment, comprising: a data acquisition and preprocessing module, a hierarchical multi-physics field modeling module, a model integration and parameter optimization module, and a dynamic simulation and fault prediction module;

[0033] The data acquisition and preprocessing module collects multi-dimensional physical field data of power transmission and transformation equipment in real time through a distributed high-precision sensor network, and performs denoising, formatting and standardization on the collected raw data;

[0034] The hierarchical multi-physics modeling module is based on an improved finite element analysis method, constructs a multi-physics coupling model from three levels: macroscopic, mesoscopic and microscopic, and reflects the multi-dimensional characteristics of the equipment at different spatial granularities and time dimensions through hierarchical modeling;

[0035] The model integration and parameter optimization module integrates the results of the hierarchical model, unifies the outputs of the macro, meso and micro models into a complete multi-physics field coupling model through a multimodal data fusion method, and optimizes and adjusts the model parameters;

[0036] The dynamic simulation and fault prediction module is based on a unified coupling model, jointly analyzing the interaction between electromagnetic fields, thermal fields and mechanical stress fields, using dynamic simulation technology to simulate the state of equipment under different operating conditions, generating real-time operating data, and using big data analysis and fault prediction algorithms to identify potential fault locations and types.

[0037] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment are implemented as described above.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment as described above.

[0039] Beneficial effects of the invention: The invention solves the technical problem that it is difficult to accurately monitor the operating status and predict real-time faults of power transmission and transformation equipment in a complex multi-physical field coupling environment by improving the finite element analysis method and hierarchical multi-physical field modeling technology, thereby achieving the effect of improving monitoring accuracy, enhancing the real-time nature of fault diagnosis and prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0041] Figure 1 An overall flow chart of a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment provided for the first embodiment of the present invention;

[0042] Figure 2 A multi-granularity hierarchical modeling flow chart in a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment provided in the first embodiment of the present invention;

[0043] Figure 3 A schematic diagram of multi-physical field coupling of a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment provided for the first embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] Example 1, reference Figure 1 As an embodiment of the present invention, a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment is provided, including:

[0046] Step 1: Multi-dimensional physical field data collection and preprocessing. The state of power transmission and transformation equipment is affected by multiple factors such as electromagnetic field, thermal field and mechanical stress field. Accurately collecting data from these physical fields is the first step in high-precision modeling. This step uses a high-precision sensor network to obtain multi-dimensional state information of the equipment, including electric field strength ( E ), magnetic induction intensity ( B ),temperature( T ) and stress distribution ( σ ), and clean and preprocess these data to ensure their suitability for subsequent modeling.

[0047] (1) Data acquisition. The electromagnetic field describes the charge, flux, and current distribution of the device, and its behavior is described by Maxwell's equations:

[0048]

[0049]

[0050] Among them, D is the electric displacement vector, B is the magnetic induction intensity, ρ is the charge density, and J is the current density. These parameters are collected in real time through high-precision sensors to provide basic data for electromagnetic field modeling.

[0051] The thermal behavior of the device is modeled using the heat conduction equation:

[0052]

[0053] Where ρ is the density, c p is the specific heat capacity, k is the thermal conductivity, and Q is the heat source term. The distribution and change information of the internal temperature of the equipment is collected by the sensor, which can reflect the thermal characteristics of the equipment under high load or fault conditions.

[0054] The distribution of mechanical stress field is directly related to the structural stability of the equipment. The stress field data is described by the mechanical equilibrium equation:

[0055]

[0056] Where σ represents the stress tensor, F ext By collecting this data, the structural strength of the equipment under the combined effects of electromagnetic force, temperature and external force can be monitored.

[0057] (2) Data cleaning and denoising. To ensure the accuracy of the data, the collected multidimensional data is cleaned and denoised. The denoised signal can be expressed as:

[0058] X cleaned =X raw -α·N noise ,

[0059] Where X cleaned is the denoised data, α is the denoising factor, N noise is the noise estimation vector. The cleaned and preprocessed data provides high-quality input for subsequent modeling, ensuring that the model can accurately reflect the true state of the equipment.

[0060] Step 2: Multi-granularity hierarchical modeling. With the support of the improved finite element analysis (FEA) method, the present invention uses a hierarchical modeling strategy to model the equipment step by step from the macro level to the micro level, which is specifically divided into three levels: macro (overall structure), meso (key components) and micro (material details). The finite element method plays a key role at each level. By discretizing the continuous physical field into finite elements and gradually solving the state variables at each level, high-precision hierarchical simulation is achieved. Figure 2 The process of multi-granularity hierarchical modeling is demonstrated.

[0061] Reference Figure 2 Multi-granularity hierarchical modeling process:

[0062] (1) Macro modeling (overall device layer). At the macro level, the model aims to describe the overall operating state of the device, and constructs the distribution of electromagnetic and thermal fields in the global range of the device through the finite element method. The main goal of this layer is to capture the operating characteristics of the device under overall conditions and provide boundary conditions and global constraints for the meso and micro levels.

[0063] The electromagnetic field is described by Maxwell's equations at the macroscopic level. In order to solve the partial differential equations of the electromagnetic field in a discrete system, they are transformed into a series of discrete equations through the finite element method to form the electromagnetic stiffness matrix K em The description of the thermal field uses the heat conduction equation, which is discretized into a series of algebraic equations through the finite element method to form the global stiffness matrix K of the thermal field. thermal At the macroscopic level, the electromagnetic field and thermal field equations are combined to form the electromagnetic stiffness matrix K em and the thermal stiffness matrix K thermalThe overall coupled equations are formed:

[0064] K macro ·U macro =F macro ,

[0065] Among them, K macro =K em +K thermal , U macro is the state variable vector of the entire device, F macro The finite element method plays the role of discretizing continuous partial differential equations into algebraic equations in macroscopic modeling, so that complex global electromagnetic and thermal fields can be discretely solved on the computer, and the stiffness matrix formed can reflect the response of the overall structure of the equipment.

[0066] (2) Meso-level modeling (key component layer). The meso-level modeling mainly focuses on the detailed modeling of key components in the equipment that are critical to the operating status, such as the windings and insulation structure of the transformer. Since these components work in a coupled environment of multiple physical fields, more detailed multi-field coupling modeling is required. The meso-level modeling adopts the finite element method similar to the macro model, but further considers the local characteristics of the components and adds the influence of the mechanical stress field.

[0067] At the level of key components, the distribution of electromagnetic and thermal fields is significantly affected by the geometric structure and material properties of the components. The finite element method is used to locally discretize each component area to form the electromagnetic and thermal coupling stiffness matrix K em and K thermal , its local equation is:

[0068] K em ·E+K thermal T=F local ,

[0069] Where E represents the local electric field intensity, T represents the local temperature field, and F local is the load acting on the key components. Through the above equation, the response of the components under the electromagnetic-thermal environment can be obtained. The mechanical stress field is further added to the mesoscopic layer, especially the deformation response of the components under electromagnetic and thermal effects. The mechanical equilibrium equation is used to perform finite element discretization on the stress distribution of the components to generate the mechanical stiffness matrix k mech , by discretizing the mechanical equilibrium equations, equations used to describe the mechanical state of key components are generated.

[0070] At the mesoscopic level, the coupled equations for the electromagnetic, thermal, and mechanical stress fields of key components are:

[0071] K em ·E+K thermal ·T+Kmech σ=F local ,

[0072] Where σ is the stress distribution of the component, and the above equations describe the multi-physics coupling effect of the key components. The finite element method is used to discretize the local components more finely at the mesoscopic level, especially by constructing a stiffness matrix of multi-physics coupling to analyze the comprehensive response of the key components under the action of electromagnetic, thermal and mechanical stress fields. This hierarchical modeling ensures that the complex multi-field effects of the key components are accurately reflected in the overall model.

[0073] (3) Microscopic modeling (material detail layer). At the microscopic level, the focus is on the mechanical properties of the materials used in the device under a multi-physics environment. Especially in extreme environments, the stress-strain relationship and thermal response characteristics of the material have an important influence on the stability of the entire device. Modeling at the microscopic level through finite element analysis can capture subtle changes inside the material to achieve high-precision material property analysis.

[0074] The microscopic model focuses on describing the stress-strain response of the material. Assuming the material is elastic, its stress-strain relationship can be expressed as:

[0075] σ=E·ε,

[0076] Where E is the elastic modulus of the material and ε is the strain. The material stress distribution is discretized by the finite element method to form a local stiffness matrix at the microscopic level, which is used to analyze the deformation response of the material. Under the action of multiple physical fields, temperature changes will affect the mechanical properties of the material. Considering the effect of temperature on stress, the stress response of the material can be further expressed as:

[0077] σ=E·ε+α·T,

[0078] Where α is the thermal expansion coefficient of the material and T is the temperature change. At this level, the finite element method ensures that the thermal expansion effect is reflected in the mechanical response of the material by meshing the material details.

[0079] At the microscopic level, by combining the material's stress-strain relationship, temperature effect, and local field intensity, the following coupled equation is formed:

[0080] K micro ·U micro =F micro ,

[0081] Where K micro Including the elasticity, thermal expansion and microstructural properties of the material, U micro is the material state vector, F microis the local load at the microscopic level. The above equations describe the response of materials in complex environments. The finite element method is used to discretize material properties locally with high precision at the microscopic level to reflect the true behavior of materials under the combined effects of electromagnetic fields, thermal fields, and mechanical stress fields, ensuring accurate feedback of material details on the overall response of the device.

[0082] Each level of hierarchical modeling is discretized and solved through finite element analysis, and a multi-physics coupling model from the whole to the local is formed through the corresponding stiffness matrix. The macro model provides boundary conditions for the meso and micro layers, and the material properties of the micro layer are fed back to the upper model, thus forming a closed-loop multi-physics coupling modeling system. This hierarchical method significantly improves the accuracy and computational efficiency of the simulation, allowing the operating status of the equipment in a complex environment to be accurately characterized.

[0083] Step 3: Application of multi-physics field coupling and improved finite element analysis. In the actual operation of power transmission and transformation equipment, the interaction between electromagnetic field, thermal field and mechanical stress field forms a complex multi-physics field coupling phenomenon.

[0084] (1) Multi-physics field coupling. The Joule heat generated by the electromagnetic field will cause the internal temperature of the device to rise, changing the thermal field distribution of the device. The schematic diagram of multi-physics field coupling is shown in Figure 3 shown.

[0085] Joule heat is calculated by the following formula:

[0086] Q joule = J.E,

[0087] Where J is the current density and E is the electric field strength. Joule heat is input as a heat source term in the heat conduction equation:

[0088]

[0089] Changes in the thermal field will cause thermal expansion or contraction of the material, thereby changing the stress distribution of the material. The generation of this thermal stress is described by the following formula:

[0090] σ thermal =αT,

[0091] Where α is the thermal expansion coefficient and T is the temperature change. The electromagnetic field acts on the material through the Lorentz force, affecting the mechanical stress distribution. The Lorentz force is expressed by the following formula:

[0092] F lorentz =J×B,

[0093] Where B is the magnetic induction intensity.

[0094] (2) Improved application of finite element analysis in multi-physical field coupling. In order to efficiently solve the complex coupling relationship of multi-physical fields, the present invention makes key improvements to the finite element method to support dynamic interactions between multiple fields. The improved finite element method integrates the coupling equations of electromagnetic field, thermal field and mechanical stress field into the global coupling matrix through a unified framework. The specific coupling matrix form is:

[0095]

[0096] Where K em represents the electromagnetic stiffness matrix, K thermal represents the thermal field stiffness matrix, K mech represents the mechanical stiffness matrix, and the other terms represent the field coupling terms. In the process of solving multi-physics fields, the improved finite element method adopts an adaptive meshing strategy to dynamically adjust the mesh density according to the local gradient. The adaptive meshing formula is:

[0097]

[0098] where h is the local grid size, h max is the maximum grid size, β is the adjustment coefficient, is the local physical quantity gradient. The improved method uses the multi-grid method to solve the global coupling matrix in layers. The multi-grid method achieves efficient convergence by iterative optimization between coarse and fine grids:

[0099] U n+1 =U n -ω·K -1 ·(K·U n -F),

[0100] Where ω is the relaxation factor. The unified coupling model and efficient iterative optimization enable accurate simulation of the dynamic behavior of the device under complex multi-field effects.

[0101] Step 4: Accuracy calibration. To ensure the reliability of the simulation results, the present invention uses experimental data for accuracy calibration and applies the calibrated model to the monitoring and maintenance of the equipment. The simulation error is calculated by comparing the simulation results with the experimental data. The error formula is:

[0102]

[0103] Among them, U simulated Output result of simulation model, U measuredis the experimental data, and Δ is the error percentage. By analyzing the error distribution, the error sources of the model in different regions and physical fields can be located, such as insufficient meshing, physical parameter deviation, etc. The calibrated model can be directly used in practical application scenarios, such as real-time monitoring of equipment operation status to capture abnormal information, quickly locate fault locations, and predict the remaining life of equipment through micro-level analysis.

[0104] Embodiment 2 is an embodiment of the present invention, which provides a system for a multi-granularity and multi-dimensional digital twin mechanism method of power transmission and transformation equipment, including: a data acquisition and preprocessing module, a hierarchical multi-physics field modeling module, a model integration and parameter optimization module, and a dynamic simulation and fault prediction module;

[0105] The data acquisition and preprocessing module collects multi-dimensional physical field data of power transmission and transformation equipment in real time through a distributed high-precision sensor network, and performs denoising, formatting and standardization on the collected raw data;

[0106] The hierarchical multi-physics modeling module is based on an improved finite element analysis method, constructs a multi-physics coupling model from three levels: macroscopic, mesoscopic and microscopic, and reflects the multi-dimensional characteristics of the equipment at different spatial granularities and time dimensions through hierarchical modeling;

[0107] The model integration and parameter optimization module integrates the results of the hierarchical model, unifies the outputs of the macro, meso and micro models into a complete multi-physics field coupling model through a multimodal data fusion method, and optimizes and adjusts the model parameters;

[0108] The dynamic simulation and fault prediction module is based on a unified coupling model, jointly analyzing the interaction between electromagnetic fields, thermal fields and mechanical stress fields, using dynamic simulation technology to simulate the state of equipment under different operating conditions, generating real-time operating data, and using big data analysis and fault prediction algorithms to identify potential fault locations and types.

[0109] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0111] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] Embodiment 3: In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0114] The power transmission and transformation equipment used in this experiment is a 10kV oil-immersed power transformer, and high-precision sensor equipment is used to collect multi-physical field data such as electromagnetic, thermal and mechanical stress. The laboratory is equipped with the following main experimental equipment:

[0115] (1) High-precision electromagnetic field sensor: used to monitor the distribution of electric and magnetic fields around and inside the transformer, with the measurement range covering normal operation and overload conditions.

[0116] (2) Thermal sensor array: arranged in different parts of the transformer, including core components (such as coils and cores) and the casing, to measure temperature distribution and changes.

[0117] (3) Stress sensor: installed on key structural parts to detect the response of mechanical stress to changes in current.

[0118] (4) Data acquisition and processing system: collects various sensor data in real time and stores them at high resolution to ensure data integrity and continuity.

[0119] Before the device is operated, the initial state of the device is recorded, and initial data such as electromagnetic field, thermal field, and mechanical stress are collected to be used as reference values ​​for model calibration. In the experimental process, the device is tested one by one under different operating conditions to comprehensively evaluate the applicability of the method of the present invention under various conditions. Different operating conditions are loaded as shown in the following table.

[0120] Table 1 Different operating conditions

[0121]

[0122]

[0123] The setting of these experimental conditions ensures a comprehensive evaluation of the method of the present invention under various typical working conditions, providing high-precision verification data for subsequent fault diagnosis and life prediction.

[0124] The experiment compares the proposed method with existing evaluation methods in the literature. The main indicators include simulation error rate, fault diagnosis accuracy, and calculation time under complex working conditions. For the same set of experimental monitoring data of power transmission and transformation equipment, the full-link state evaluation model based on digital twins and the fault diagnosis model based on big data mining are tested respectively. Table 2 is a comparison of the implementation effects of different methods.

[0125] Table 2 Comparison of indicators of three methods

[0126]

[0127] Experimental results show that the simulation error rate of the method of the present invention is only 2.1%, which is significantly better than the other two classic models. This is due to the improved finite element analysis and multi-physics field coupling technology, which enables the electromagnetic field, thermal field, and mechanical stress field to accurately characterize the equipment status under a unified model; the fault diagnosis accuracy of the method of the present invention is 98.5%, which is more than 12.8% higher than the traditional method. The hierarchical modeling and comprehensive analysis of multi-physics fields can capture the subtle changes of the equipment under different working conditions, significantly improving the fault identification ability; in complex tasks, the calculation time of the method of the present invention is 75.2 seconds, which is nearly 25.9% and 21.7% higher than the two traditional methods, respectively. This reflects the application of optimization algorithms such as the multi-grid method to improve computing efficiency.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment, characterized in that: include: Collect multi-dimensional physical field data and perform pre-processing; Construct a hierarchical multi-physics coupling model based on preprocessed data; Integrate and adjust parameters of the hierarchical multi-physics coupling model output to form a unified multi-physics coupling model; The unified coupling model is used to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction.

2. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment according to claim 1, characterized in that: The collecting of multi-dimensional physical field data and preprocessing thereof include: Use sensors to collect multi-dimensional status information of the equipment, including electric field strength, magnetic induction strength, temperature and stress distribution; The preprocessing is to clean and remove noise from the collected multi-dimensional data.

3. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment according to claim 2, characterized in that: The constructing of a hierarchical multi-physics coupling model based on preprocessed data includes: An improved finite element analysis method is used to construct a hierarchical multi-physics coupling model from the macro, meso and micro levels; At the macro level, a global coupling model of the electromagnetic field and the thermal field is constructed based on the geometric characteristics of the overall structure of the device to generate the global electromagnetic field distribution matrix and the thermal field distribution matrix; At the mesoscopic level, for key components such as transformer windings and insulation structures, a coupling model of local electromagnetic field and thermal field is constructed, and the effect of mechanical stress field is added to generate the local response matrix of key components; At the microscopic level, a stress-strain model is constructed based on the physical properties of the material, and the local deformation behavior of the material is analyzed in combination with the thermal expansion characteristics.

4. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment as claimed in claim 3, characterized in that: The hierarchical multi-physics coupling model includes: The global boundary conditions output by the macroscopic model include the overall electromagnetic field strength and thermal field temperature distribution of the equipment, which serve as input parameters of the mesoscopic model; The stress distribution of key components and the change of local temperature field output by the mesoscopic model are used as the input conditions of the microscopic model; The local deformation parameters and thermal expansion effect data of the material output by the microscopic model are used to correct the local response results of the mesoscopic model.

5. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment as claimed in claim 4, characterized in that: The integration and parameter adjustment of the output of the hierarchical multi-physics coupling model to form a unified multi-physics coupling model includes: The output results of the hierarchical model are fused using multimodal data fusion technology to generate unified model input data across levels. The parameters of the macro, meso and micro models are adjusted using a global optimization algorithm based on gradient descent. The fused and optimized model results are imported into a unified multi-physics field coupling framework to generate a set of simultaneous equations.

6. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment according to claim 5, characterized in that: The use of a unified coupling model to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction includes: In the combined multi-physics field coupling equations, the dynamic changes of the equipment's electromagnetic field, thermal field, and mechanical stress field are simulated in real time through numerical solution methods. The dynamic simulation results are classified and processed to generate simulation data of normal operation, abnormal operation, and fault status. Based on the fault status data, deep learning algorithms are used to predict faults and generate diagnostic reports on the fault location and type.

7. A multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment according to claim 6, characterized in that: The use of a unified coupling model to jointly analyze multiple physical fields to complete dynamic simulation and fault prediction also includes: Compare the simulation results with the historical operation data of the equipment, update the equipment status database, generate operation and maintenance optimization strategies based on the fault prediction results, and transmit them to the equipment management platform through the interface.

8. A system using a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition and preprocessing module, hierarchical multi-physics modeling module, model integration and parameter optimization module, dynamic simulation and fault prediction module; The data acquisition and preprocessing module collects multi-dimensional physical field data of power transmission and transformation equipment in real time through a distributed high-precision sensor network, and performs denoising, formatting and standardization on the collected raw data; The hierarchical multi-physics modeling module is based on an improved finite element analysis method, constructs a multi-physics coupling model from three levels: macroscopic, mesoscopic and microscopic, and reflects the multi-dimensional characteristics of the equipment at different spatial granularities and time dimensions through hierarchical modeling; The model integration and parameter optimization module integrates the results of the hierarchical model, unifies the outputs of the macro, meso and micro models into a complete multi-physics field coupling model through a multimodal data fusion method, and optimizes and adjusts the model parameters; The dynamic simulation and fault prediction module is based on a unified coupling model, jointly analyzing the interaction between electromagnetic fields, thermal fields and mechanical stress fields, using dynamic simulation technology to simulate the state of equipment under different operating conditions, generating real-time operating data, and using big data analysis and fault prediction algorithms to identify potential fault locations and types.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it implements the steps of a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment according to any one of claims 1 to 7.

10. 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 a multi-granularity and multi-dimensional digital twin mechanism method for power transmission and transformation equipment as described in any one of claims 1 to 7 are implemented.

Images