Fault prediction method and device based on coupling model, equipment and storage medium

Through the fault prediction method based on the coupled model, the digital twin transformer model is used to automatically analyze the transformer status, which solves the problems of manual dependence and data processing complexity in traditional detection technology, and realizes accurate and timely evaluation of the transformer operating status and potential fault prediction.

CN119066726APending Publication Date: 2024-12-03GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411107305.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional transformer detection technology relies on manual visual inspection and is difficult to process large amounts of real-time data and complex system models, resulting in insufficient predictive maintenance capabilities and limited accuracy and reliability.

Method used

Using a fault prediction method based on the coupling model, a digital twin transformer model is predicted by obtaining transformer data parameters and constructing a digital twin transformer model, including electromagnetic-vibration coupling sub-model and electromagnetic-fluid-temperature coupling sub-model, automated analysis and diagnosis of the transformer operating status.

Benefits of technology

It realizes accurate and timely evaluation of the operating status of the transformer, reduces manual intervention and misjudgment, reduces detection costs, and improves predictive maintenance capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066726A_ABST
    Figure CN119066726A_ABST
Patent Text Reader

Abstract

The invention discloses a fault prediction method and device based on a coupling model, equipment and a storage medium. The method comprises the steps that transformer data parameters corresponding to a target transformer to be subjected to fault analysis are acquired, and the transformer data parameters at least comprise electrical parameters, winding parameters, iron core parameters and transformer oil parameters; transformer decision data are determined according to the transformer data parameters and a pre-constructed digital twin transformer model, and the digital twin transformer model at least comprises an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model; and comparing the transformer decision data with the predetermined preset transformer reference data, and predicting the transformer fault information of the target transformer, so that the operation state of the transformer can be automatically analyzed and diagnosed, the maintenance demand and potential fault of the transformer can be accurately predicted, the possibility of manual intervention and misjudgment can be reduced, and the maintenance efficiency can be improved. And the detection cost is low.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of transformer detection technology, and in particular to a fault prediction method, device, equipment and storage medium based on a coupling model. Background Art

[0002] Transformers are an indispensable key component in the power system. They are mainly used to adjust the voltage to meet the needs of different power equipment. Transformers play a vital role in the power system. They are one of the key devices for realizing power transmission, distribution and operation of electrical equipment. Their safety and stability determine the safe and stable operation of the power system. The safety and stability of the transformer directly determine the performance and efficiency of the entire power system.

[0003] Traditional technology mainly relies on manual visual inspection and experience to detect transformers to determine the operating status of the transformer. Traditional technology has difficulty in processing large amounts of real-time data and complex system models, and lacks comprehensive evaluation and predictive maintenance capabilities. It is easily affected by subjective factors of operators, and its accuracy and reliability are limited. Summary of the invention

[0004] The present invention provides a fault prediction method, device, equipment and storage medium based on a coupling model, which can automatically analyze and diagnose the operating status of the transformer, accurately predict the maintenance needs and potential faults of the transformer, reduce the possibility of manual intervention and misjudgment, and have a low detection cost.

[0005] According to one aspect of the present invention, a fault prediction method based on a coupling model is provided. The method comprises:

[0006] Obtaining transformer data parameters corresponding to the target transformer to be analyzed for fault, wherein the transformer data parameters at least include electrical parameters, winding parameters, core parameters and transformer oil parameters;

[0007] Determine transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model, wherein the digital twin transformer model includes at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model;

[0008] The transformer decision data is compared with predetermined preset transformer reference data to predict transformer fault information of the target transformer.

[0009] According to another aspect of the present invention, a fault prediction device based on a coupling model is provided. The device comprises:

[0010] A transformer data parameter acquisition module, used to acquire transformer data parameters corresponding to a target transformer to be analyzed for faults, wherein the transformer data parameters at least include electrical parameters, winding parameters, core parameters and transformer oil parameters;

[0011] A transformer decision data determination module, used to determine the transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model, wherein the digital twin transformer model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model;

[0012] The transformer fault information determination module is used to compare the transformer decision data with the predetermined preset transformer reference data to predict the transformer fault information of the target transformer.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault prediction method based on the coupling model described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the coupling model-based fault prediction method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains transformer data parameters corresponding to the target transformer to be analyzed for fault, wherein the transformer data parameters include at least electrical parameters, winding parameters, core parameters and transformer oil parameters. According to the transformer data parameters and a pre-constructed digital twin transformer model, the transformer decision data is determined, wherein the digital twin transformer model includes at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model. The transformer decision data is compared and processed with predetermined preset transformer reference data to predict the transformer fault information of the target transformer. Through the digital twin technology, the operation data of the transformer can be monitored and analyzed in real time, providing a more accurate and timely status assessment, which helps to discover potential faults and problems and reduce the possibility of manual intervention and misjudgment.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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.

[0021] Figure 1 is a flow chart of a fault prediction method based on a coupling model provided according to Embodiment 1 of the present invention;

[0022] Figure 2 is an implementation architecture diagram of a digital twin transformer model provided according to Embodiment 1 of the present invention;

[0023] Figure 3 is a flow chart of a fault prediction method based on a coupling model provided according to Embodiment 2 of the present invention;

[0024] Figure 4 is a transformer geometric model diagram provided according to the second embodiment of the present invention;

[0025] Figure 5 is a structural diagram of a fault prediction device based on a coupling model provided according to Embodiment 3 of the present invention;

[0026] Figure 6 It is a structural schematic diagram of an electronic device for implementing the fault prediction method based on a coupling model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 A flowchart of a fault prediction method based on a coupling model is provided for the first embodiment of the present invention. This embodiment can be applied to predicting the operating status of a transformer. The method can be performed by a fault prediction device based on a coupling model. The fault prediction device based on a coupling model can be implemented in the form of hardware and / or software. The fault prediction device based on a coupling model can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S101. Obtain transformer data parameters corresponding to a target transformer to be analyzed for faults.

[0032] The target transformer may refer to a transformer for which operating status prediction is to be performed. The transformer data parameters may refer to important relevant data of the target transformer itself, such as electromagnetic characteristics, thermal characteristics, and mechanical characteristics of the transformer. Exemplarily, the transformer data parameters include at least electrical parameters, winding parameters, core parameters, and transformer oil parameters.

[0033] Exemplarily, electrical parameters may include rated voltage, rated capacity, rated current, rated frequency, connection group number, number of winding turns, ohmic loss, longitudinal eddy current loss and no-load current, etc. Winding parameters may be divided into high-voltage winding parameters and low-voltage winding parameters, core parameters, etc. Winding parameters may include winding density, Young's modulus, Poisson's ratio, relative magnetic permeability, constant-pressure specific heat capacity and thermal conductivity, etc. Core parameters may include core density, Poisson's ratio and relative magnetic permeability, etc. Transformer oil parameters may include transformer oil density, constant-pressure specific heat capacity, convection heat transfer coefficient and thermal conductivity, etc.

[0034] Specifically, transformer data parameters are acquired through sensors and monitoring systems, and can be transmitted to a monitoring center or a data acquisition system via wired or wireless means.

[0035] S102: Determine transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model.

[0036] The digital twin transformer model is a virtual digital model corresponding to the target transformer established in a digital way, so that the target transformer can be monitored, simulated, predicted and optimized through the digital twin transformer to determine whether the target transformer will have an operating failure after a certain period of time. Transformer decision data can refer to comparison data used to determine whether the target transformer has an operating failure.

[0037] Figure 2 Figure 2 is the implementation architecture diagram of the digital twin transformer model. Figure 2 As shown, the present invention involves that the digital twin of power equipment requires an IoT platform as a carrier, takes oil-immersed transformers as the research object, and establishes an IoT-based transformer digital twin implementation architecture, which mainly includes five parts: physical layer, perception layer, IaaS (Infrastructure-as-a-Service, infrastructure service layer), PaaS (Platform-as-a-Service, platform service layer) and SaaS (Software-as-a-Service, software service layer).

[0038] Among them, the digital twin transformer model is composed of at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model, and it can also be composed of other coupling sub-models according to actual needs.

[0039] Specifically, the transformer data parameters are input into the digital twin transformer model to make transformer data decisions, and the transformer decision data is obtained based on the output of the digital twin transformer model, thereby ensuring the accuracy of the transformer decision data.

[0040] Exemplarily, determining the transformer decision data based on the transformer data parameters and a pre-built digital twin transformer model includes: determining the transformer displacement deformation data based on the electrical parameters, the winding parameters, the core parameters and the electromagnetic-vibration coupling sub-model; and / or determining the transformer flow oil temperature data based on the electrical parameters, the winding parameters, the transformer oil parameters and the electromagnetic-fluid-temperature coupling sub-model.

[0041] The transformer decision data may be composed of transformer displacement deformation data and / or transformer oil flow temperature data, and its specific components are determined according to the components of the transformer data parameters.

[0042] Specifically, when the transformer data parameters are composed of electrical parameters, winding parameters and core parameters, the electrical parameters, winding parameters and core parameters are input into the electromagnetic-vibration coupling sub-model, and the displacement deformation data of the transformer can be obtained by performing the movement deformation operation through the electromagnetic-vibration coupling sub-model. When the transformer data is composed of electrical parameters, winding parameters and transformer oil parameters, the electrical parameters, winding parameters and transformer oil parameters can be input into the electromagnetic-fluid-temperature coupling sub-model, and the flow oil temperature can be calculated through the electromagnetic-fluid-temperature coupling sub-model to obtain the transformer flow oil temperature data. In addition, when the transformer data is composed of electrical parameters, winding parameters, core parameters and transformer oil parameters, the transformer displacement deformation data and transformer flow oil temperature data can be calculated through the electromagnetic-vibration coupling sub-model and the electromagnetic-fluid-temperature coupling sub-model respectively.

[0043] Exemplarily, determining the transformer displacement deformation data according to the electrical parameters, the winding parameters, the core parameters and the electromagnetic-vibration coupling sub-model includes: determining the high-voltage rated current of the high-voltage side of the target transformer based on the electrical parameters. Inputting the high-voltage rated current, the winding parameters and the core parameters into the electromagnetic-vibration coupling sub-model for vibration analysis to obtain the transformer displacement deformation data.

[0044] Specifically, the high-voltage rated current of the target transformer on the high-voltage side is calculated through electrical parameters. In practice, the electromagnetic-vibration coupling sub-model in the digital twin transformer model can be imported into the ANSYS Maxwell electromagnetic analysis module, and the sub-model is set based on the winding parameters and the core parameters. For example, the number of nodes is set to 432016. Since structural vibration belongs to a dynamic problem and the vibration signal is a time series parameter, the transient electromagnetic field solver is selected, and the analysis time is set to 0.1s and the time step is 0.0005s. By adjusting the electrical parameters, the low-voltage side of the transformer is short-circuited, and the primary side current reaches the rated current value by adjusting the high-voltage side voltage. At this time, the digital twin transformer model can be regarded as full-load operation, and the vibration signal and temperature parameter state distribution under the experimental full-load condition can be used to obtain the physical field parameter limit under the rated condition of the transformer, and then the corresponding transformer displacement deformation data at each moment can be obtained.

[0045] Exemplarily, the high and low voltage windings of the electromagnetic-vibration coupling sub-model are both star-connected. According to the actual operation data of the short-circuit test, the three-phase high-voltage coil in the equivalent circuit is set to a three-phase sinusoidal AC voltage source of 400V, the phase angle of the A phase voltage source is 0°, the phase angle of the B phase voltage source is 120° ahead of the A phase, and the phase angle of the C phase voltage source is 120° behind the A phase. According to the material properties of the actual transformer core and winding, the core selects the silicon steel material DW3 10_35 with magnetostrictive effect, that is, the width of the silicon steel sheet is 3 10mm and the thickness is 35mm; the winding selects copper material.

[0046] Exemplarily, determining the transformer oil flow temperature data according to the electrical parameters, the winding parameters, the transformer oil parameters and the electromagnetic-fluid-temperature coupling sub-model includes: determining the load loss data of the target transformer according to the electrical parameters; inputting the load loss data, the winding parameters and the transformer oil parameters into the electromagnetic-fluid-temperature coupling sub-model for temperature analysis to obtain the transformer oil flow temperature data.

[0047] Specifically, the load loss data of the target transformer is calculated by electrical parameters. In ANSYSworkbench, the Maxwell and Fluent modules are coupled to import the electromagnetic-fluid-temperature coupling submodel, with a node number of 8732925, and the electromagnetic-fluid-temperature coupling submodel is set by the winding parameters and the transformer oil parameters. At the same time, the initial temperature of the digital twin transformer oil and the heat exchange coefficient between the fluid wall and the outside air are given. The load loss data is mapped and imported into Fluent as the heat source item of the temperature field, and the load loss generated by the single-phase high-voltage winding is obtained by calculation. Since natural convection heat transfer does not apply external force, it only relies on the buoyancy generated by the change of fluid density with temperature to cause the hot flow to rise and the cold flow to sink, thereby generating a flow rate. Therefore, the vertical downward gravity acceleration is set, and the k-epsilon turbulence model is used for transient calculation. According to the Fluent calculation, the temperature distribution of the winding and the oil flow is obtained, and the heat source items and boundary conditions are applied to the fluid and solid areas respectively. The temperature field distribution under the natural convection heat transfer mode is analyzed, and the transformer flow oil temperature data is obtained.

[0048] S103: Compare the transformer decision data with predetermined preset transformer reference data to predict transformer fault information of the target transformer.

[0049] The preset transformer reference data may include preset displacement reference data and preset temperature reference data.

[0050] Specifically, when the transformer decision data is transformer displacement deformation data, the transformer displacement deformation data is compared with preset displacement reference data. When the transformer displacement deformation data is greater than or equal to the preset displacement reference data, it indicates that the target transformer will have an operation failure. Otherwise, it indicates that the target transformer will not have an operation failure. When the transformer decision data is transformer oil flow temperature data, the transformer oil flow temperature data is compared with preset temperature reference data. When the transformer oil flow temperature data is greater than or equal to the preset temperature reference data, it indicates that the target transformer will have an operation failure. Otherwise, it indicates that the target transformer will not have an operation failure.

[0051] When the target transformer is about to experience an operational failure, further manual inspection can be performed to comprehensively evaluate the transformer's operating status and provide more comprehensive information and suggestions.

[0052] The technical solution of the embodiment of the present invention obtains transformer data parameters corresponding to the target transformer to be analyzed for fault, wherein the transformer data parameters include at least electrical parameters, winding parameters, core parameters and transformer oil parameters. According to the transformer data parameters and a pre-constructed digital twin transformer model, the transformer decision data is determined, wherein the digital twin transformer model includes at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model. The transformer decision data is compared and processed with predetermined preset transformer reference data to predict the transformer fault information of the target transformer. Through the digital twin technology, the operation data of the transformer can be monitored and analyzed in real time, providing a more accurate and timely status assessment, which helps to discover potential faults and problems and reduce the possibility of manual intervention and misjudgment.

[0053] Embodiment 2

[0054] Figure 3 This is a flowchart of a fault prediction method based on a coupling model provided in the second embodiment of the present invention. Based on the above embodiments, this embodiment further introduces the construction of a digital twin transformer. Figure 3 As shown, the method includes:

[0055] S201. Collect transformer-related parameters of the target transformer.

[0056] The transformer-related parameters include at least operating parameters, geometric parameters and sensor parameters. Operating parameters may include but are not limited to voltage, current, temperature, oil pressure, vibration signals, etc. Geometric parameters may include geometric dimensions, material properties, fluid dynamic parameters and thermodynamic parameters, etc. Sensor parameters include deploying temperature, pressure and vibration sensors at key parts of the transformer to achieve real-time data collection.

[0057] Specifically, relevant parameters of the target transformer are collected, cleaned and preprocessed to obtain transformer-related parameters and ensure the quality and accuracy of the data.

[0058] S202: construct a transformer geometric model corresponding to the target transformer according to the transformer-related parameters.

[0059] Specifically, a three-dimensional modeling software (such as SolidWorks, AutoCAD, etc.) is used to construct a transformer geometric model including key components such as the core, winding, oil tank, cooling system, etc. according to relevant parameters of the transformer. Figure 4 Figure 2 is the transformer geometric model diagram corresponding to the target transformer.

[0060] As for the electromagnetic, vibration and temperature characteristics of transformers, the fundamental sources of their generation mainly include iron core and windings. Therefore, the present invention uses SOLIDWORKS software to perform three-dimensional geometric modeling on the above components respectively. This model will serve as the main body for subsequent physical field simulation calculation and analysis. Its internal structure, component type, mechanical connection, and electromagnetic relationship are equivalent to the actual transformer. After the iron core and winding are modeled, the assembly function is used to assemble the two into a whole, and the xt format is saved and imported into ANSYS finite element analysis software for the next step of simulation calculation.

[0061] Exemplarily, after the transformer geometric model is constructed, the physical properties of each component may be defined in finite element analysis software, including electromagnetic, mechanical, thermodynamic and fluid dynamic properties.

[0062] The operation of the transformer involves multiple physical parameters such as electromagnetic, force, heat, and fluid. Multi-physics simulation, as a key technical component of digital twins, deeply analyzes the physical and chemical properties of the equipment from the perspective of micro-element, and simulates and calculates the magnetic conductivity, structural strength, and heat dissipation effect, thereby realizing multi-physics digital twins. The three-dimensional finite element modeling of the transformer entity belongs to spatial discretization. This paper uses four-node tetrahedral units to divide the computational grid. The generalized coordinate expression of its interpolation function is: r = a1 + a2x + a3y + a4z.

[0063] The above formula can be expressed in matrix form as r = [G] T {α}, where [G]=[1, x, y, z] T Sum [a] = [a1, a2, a3, a4] T are Cartesian coordinate vectors and generalized coordinate vectors respectively. Substituting the node coordinates and variable values, the shape function can be obtained as follows:

[0064] N1=g 11 +g 21 x+g 31 y+g 41 z

[0065] N2=g 12 +g 22 x+g 32 y+g 42 z

[0066] N3=g 13 +g 23 x+g 33 y+g 43 z

[0067] N4=g 14 +g 24 x+g 34 y+g 44 z

[0068] S203: Establish a single physical field sub-model based on the transformer geometric model.

[0069] Wherein, the single physical field sub-model at least includes an electromagnetic sub-model, a vibration sub-model, a fluid sub-model and a temperature sub-model.

[0070] Specifically, the electromagnetic field sub-model is established using finite element analysis software to simulate electromagnetic effects in the winding, such as eddy current and hysteresis loss. Based on the electromagnetic force generated by the electromagnetic field model, a vibration sub-model is established to simulate the vibration response. A fluid sub-model is established to simulate the flow of cooling oil and its effect on heat transfer. Combining electromagnetic loss, vibration energy conversion and fluid heat transfer, a temperature sub-model is established to predict the temperature distribution.

[0071] S204. Construct a digital twin transformer model according to the single physical field sub-model.

[0072] Specifically, the single physical field sub-models are mutually integrated to obtain a digital twin transformer model. It should be noted that the present invention does not specifically limit the integration between the single physical field sub-models, and they can be combined according to actual functional requirements.

[0073] Exemplarily, constructing a digital twin transformer model based on the single physical field sub-model includes: constructing a multi-physical field coupling sub-model based on the single physical field sub-model; and constructing a digital twin transformer model based on the multi-physical field coupling sub-model.

[0074] The multi-physics field coupling sub-model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model.

[0075] Specifically, by fusing the single physical field sub-models with each other, a multi-physical field sub-fusion model can be constructed, and then the multi-physical field sub-fusion model can be combined to obtain a digital twin transformer model.

[0076] Exemplarily, constructing a multi-physical field coupling sub-model based on the single physical field sub-model includes: coupling the electromagnetic sub-model with the vibration sub-model to obtain an electromagnetic-vibration coupling sub-model; fusing the electromagnetic sub-model, the fluid sub-model and the temperature sub-model to obtain an electromagnetic-fluid-temperature coupling sub-model.

[0077] Specifically, the electromagnetic sub-model is coupled with the vibration sub-model to consider the influence of electromagnetic force on structural vibration. The electromagnetic sub-model is coupled with the fluid sub-model and the temperature sub-model to consider the influence of electromagnetic loss and fluid heat transfer on temperature. The electromagnetic-vibration coupling model is further combined with the electromagnetic-fluid-temperature coupling model to form a comprehensive multi-physics coupling model.

[0078] In practice, for the finite element numerical modeling of the electromagnetic-vibration coupling sub-model, the elastic dynamic mathematical model of the winding axial vibration is established, and the Galileo finite element equation is further established for solution. According to the minimum potential energy principle, the dynamic system can be expressed by the strain energy, inertia potential energy, damping potential energy and external load potential energy of the elastic material as follows:

[0079]

[0080] Where: V is the volume area; π is the system potential energy (J), which changes with the displacement x s changes, so it is called x s Functional of .

[0081] According to the variational principle, when the variation of the functional δπ=δx sn δπ / δx sn When is zero, the real displacement can make the system reach the minimum value. Therefore, the above formula can be expressed as the dynamic energy equation satisfied by the winding under the influence of mass inertia force, damping force, strain force, preload force, electromagnetic force and its own gravity.

[0082] According to the winding dynamics energy equation derived in the previous article, in order to establish the Galerkin finite element full-order model, the space domain is first discretized into a finite number of units. According to the Galerkin criterion, the tetrahedral unit shape function N is taken for the weight function. Since the system belongs to a spatial problem, the shape function can be expressed as: The tetrahedral unit nodes i, j, m, k are defined, and the displacement and vibration signals involved in the dynamic problem are vector parameters. Therefore, each node should contain three directional degrees of freedom u, v, w, so N can be expressed as:

[0083]

[0084] The true displacement x is converted into the element shape function and the node displacement column vector x sn Expressed as displacement interpolation function x s =Nx sn, n=i,j,m,k, as the shape function of each tetrahedral unit is calculated, the N-order node displacement vector is finally obtained, where N is the number of degrees of freedom of the system. Substituting the displacement interpolation function into the equation yields:

[0085]

[0086] The above equation can be transformed into the mass matrix, stiffness matrix, damping matrix of NN and the external load vector of N1 and the node displacement vector x sn , the simplified control equation consisting of the node velocity vector and the node acceleration vector:

[0087]

[0088]

[0089]

[0090] This paper uses the Newmark method to discretize the time term, and each time unit is Δt. Therefore, the node acceleration and node velocity can be expressed by the node vibration displacement at each moment as follows:

[0091]

[0092] Therefore, the node displacement vector at each moment can be obtained through recursive update calculation, and the velocity and acceleration distribution can be further solved according to the above formula.

[0093] For the finite element numerical modeling of the electromagnetic-fluid-temperature coupling sub-model, the Galerkin-type weighted residual method is used to establish the finite element integral equation to achieve spatial domain discretization. Different from the vector problem involved in dynamics, temperature is a scalar parameter, and there is no need to consider how the temperature is transmitted in each direction, so each unit contains only one degree of freedom. The finite element discretization equation is as follows:

[0094]

[0095] The time term is discretized in the time domain using the Galerkin difference format. Similar to the discretization method in the space domain, the time domain is dispersed into several units, where the unit is the time step t. The interpolation function of the temperature changing with time is constructed and substituted into the result:

[0096]

[0097] In summary, by giving the initial value of the node temperature at time t0, the node temperature value at each moment can be calculated by recursively calculating and updating the parameter matrix Ct, Kt, Qt for each grid node in turn.

[0098] S205. Obtain transformer data parameters corresponding to the target transformer to be analyzed for faults.

[0099] S206. Determine transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model.

[0100] S207: Compare the transformer decision data with predetermined preset transformer reference data to predict transformer fault information of the target transformer.

[0101] The technical solution of the embodiment of the present invention collects transformer-related parameters of the target transformer. According to the transformer-related parameters, a transformer geometric model corresponding to the target transformer is constructed. Based on the transformer geometric model, a single physical field sub-model is established. According to the single physical field sub-model, a digital twin transformer model is constructed, which can comprehensively consider multiple parameters and factors, and comprehensively evaluate the operating status of the transformer, which can provide more accurate and timely status evaluation, and help to discover potential faults and problems.

[0102] Embodiment 3

[0103] Figure 5 This is a schematic diagram of the structure of a fault prediction device based on a coupling model provided in the third embodiment of the present invention. Figure 5 As shown, the device comprises:

[0104] The transformer data parameter acquisition module 301 is used to acquire transformer data parameters corresponding to the target transformer to be analyzed for faults, wherein the transformer data parameters at least include electrical parameters, winding parameters, core parameters and transformer oil parameters;

[0105] A transformer decision data determination module 302 is used to determine transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model, wherein the digital twin transformer model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model;

[0106] The transformer fault information determination module 303 is used to compare the transformer decision data with the predetermined preset transformer reference data to predict the transformer fault information of the target transformer.

[0107] The technical solution of the embodiment of the present invention obtains transformer data parameters corresponding to the target transformer to be analyzed for fault, wherein the transformer data parameters include at least electrical parameters, winding parameters, core parameters and transformer oil parameters. According to the transformer data parameters and a pre-constructed digital twin transformer model, the transformer decision data is determined, wherein the digital twin transformer model includes at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model. The transformer decision data is compared and processed with predetermined preset transformer reference data to predict the transformer fault information of the target transformer. Through the digital twin technology, the operation data of the transformer can be monitored and analyzed in real time, providing a more accurate and timely status assessment, which helps to discover potential faults and problems and reduce the possibility of manual intervention and misjudgment.

[0108] Optionally, the device further comprises a transformer model building module.

[0109] Transformer model building blocks, including:

[0110] A related parameter acquisition unit, used for collecting transformer related parameters of the target transformer, wherein the transformer related parameters at least include operating parameters, geometric parameters and sensor parameters;

[0111] A geometric model building unit, used to build a transformer geometric model corresponding to the target transformer according to the transformer related parameters;

[0112] A single physical field construction unit, used to establish a single physical field sub-model based on the transformer geometric model, wherein the single physical field sub-model at least includes an electromagnetic sub-model, a vibration sub-model, a fluid sub-model and a temperature sub-model;

[0113] The transformer model construction unit is used to construct a digital twin transformer model according to the single physical field sub-model.

[0114] Optionally, a transformer model building unit comprises:

[0115] A multi-physics field construction sub-unit, used to construct a multi-physics field coupling sub-model according to the single physics field sub-model, wherein the multi-physics field coupling sub-model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model;

[0116] The transformer model construction subunit is used to construct a digital twin transformer model based on the multi-physics field coupling submodel.

[0117] Optionally, a multiphysics building block is provided, specifically for:

[0118] The electromagnetic sub-model is coupled with the vibration sub-model to obtain an electromagnetic-vibration coupling sub-model;

[0119] The electromagnetic sub-model, the fluid sub-model and the temperature sub-model are fused to obtain an electromagnetic-fluid-temperature coupling sub-model.

[0120] Optionally, the transformer decision data includes transformer displacement deformation data and / or transformer oil flow temperature data;

[0121] The transformer decision data determination module 302 includes:

[0122] A displacement deformation data determination unit, configured to determine the transformer displacement deformation data according to the electrical parameters, the winding parameters, the core parameters and the electromagnetic-vibration coupling sub-model;

[0123] and / or,

[0124] The oil flow temperature data determining unit is used to determine the transformer oil flow temperature data according to the electrical parameters, the winding parameters, the transformer oil parameters and the electromagnetic-fluid-temperature coupling sub-model.

[0125] Optionally, the displacement deformation data determining unit is specifically used to:

[0126] Based on the electrical parameters, determining the high voltage rated current of the high voltage side of the target transformer;

[0127] The high voltage rated current, the winding parameters and the core parameters are input into the electromagnetic-vibration coupling sub-model for vibration analysis to obtain transformer displacement deformation data.

[0128] Optionally, the oil flow temperature data determination unit is specifically used to:

[0129] Determining load loss data of the target transformer according to the electrical parameters;

[0130] The load loss data, the winding parameters and the transformer oil parameters are input into the electromagnetic-fluid-temperature coupling sub-model for temperature analysis to obtain transformer oil flow temperature data.

[0131] The coupling model-based fault prediction device provided in the embodiment of the present invention can execute the coupling model-based fault prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0132] Embodiment 4

[0133] Figure 6A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0134] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0135] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0136] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the method for fault prediction based on the coupling model.

[0137] In some embodiments, the method for fault prediction based on the coupling model may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for fault prediction based on the coupling model described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for fault prediction based on the coupling model in any other appropriate manner (e.g., by means of firmware).

[0138] Various implementations 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 chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0140] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0142] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0143] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0144] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0145] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A fault prediction method based on a coupling model, characterized in that: include: Obtaining transformer data parameters corresponding to the target transformer to be analyzed for fault, wherein the transformer data parameters at least include electrical parameters, winding parameters, core parameters and transformer oil parameters; Determine transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model, wherein the digital twin transformer model includes at least an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model; The transformer decision data is compared with predetermined preset transformer reference data to predict transformer fault information of the target transformer.

2. The method according to claim 1, characterized in that The construction process of the digital twin transformer model includes: Collecting transformer-related parameters of the target transformer, wherein the transformer-related parameters at least include operating parameters, geometric parameters, and sensor parameters; Constructing a transformer geometric model corresponding to the target transformer according to the transformer-related parameters; Based on the transformer geometric model, a single physical field sub-model is established, wherein the single physical field sub-model at least includes an electromagnetic sub-model, a vibration sub-model, a fluid sub-model and a temperature sub-model; Based on the single physical field sub-model, a digital twin transformer model is constructed.

3. The method according to claim 2, characterized in that The digital twin transformer model is constructed according to the single physical field sub-model, comprising: According to the single physical field sub-model, a multi-physical field coupling sub-model is constructed, wherein the multi-physical field coupling sub-model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model; A digital twin transformer model is constructed based on the multi-physics field coupling sub-model.

4. The method according to claim 3, characterized in that The step of constructing a multi-physics field coupling sub-model according to the single physics field sub-model comprises: The electromagnetic sub-model is coupled with the vibration sub-model to obtain an electromagnetic-vibration coupling sub-model; The electromagnetic sub-model, the fluid sub-model and the temperature sub-model are fused to obtain an electromagnetic-fluid-temperature coupling sub-model.

5. The method according to claim 1, characterized in that The transformer decision data includes transformer displacement deformation data and / or transformer oil flow temperature data; the transformer decision data is determined according to the transformer data parameters and a pre-built digital twin transformer model, including: Determining transformer displacement deformation data according to the electrical parameters, the winding parameters, the core parameters and the electromagnetic-vibration coupling sub-model; and / or, Transformer oil flow temperature data is determined according to the electrical parameters, the winding parameters, the transformer oil parameters and the electromagnetic-fluid-temperature coupling sub-model.

6. The method according to claim 5, characterized in that Determining the transformer displacement deformation data according to the electrical parameters, the winding parameters, the core parameters and the electromagnetic-vibration coupling sub-model includes: Based on the electrical parameters, determining the high voltage rated current of the high voltage side of the target transformer; The high voltage rated current, the winding parameters and the core parameters are input into the electromagnetic-vibration coupling sub-model for vibration analysis to obtain transformer displacement deformation data.

7. The method according to claim 5, characterized in that Determining transformer oil flow temperature data according to the electrical parameters, the winding parameters, the transformer oil parameters and the electromagnetic-fluid-temperature coupling sub-model includes: Determining load loss data of the target transformer according to the electrical parameters; The load loss data, the winding parameters and the transformer oil parameters are input into the electromagnetic-fluid-temperature coupling sub-model for temperature analysis to obtain transformer oil flow temperature data.

8. A fault prediction device based on a coupling model, characterized in that: include: A transformer data parameter acquisition module, used to acquire transformer data parameters corresponding to a target transformer to be analyzed for faults, wherein the transformer data parameters at least include electrical parameters, winding parameters, core parameters and transformer oil parameters; A transformer decision data determination module, used to determine the transformer decision data according to the transformer data parameters and a pre-built digital twin transformer model, wherein the digital twin transformer model at least includes an electromagnetic-vibration coupling sub-model and an electromagnetic-fluid-temperature coupling sub-model; The transformer fault information determination module is used to compare the transformer decision data with the predetermined preset transformer reference data to predict the transformer fault information of the target transformer.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the coupling model-based fault prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the coupling model-based fault prediction method according to any one of claims 1 to 7 when executed.

Citation Information

Cited By

  • Real-time response method, device and equipment for temperature distribution in transformer coil

    CN120087062A