Electric appliance non-intrusive magnetic induction intensity measurement method, equipment and medium

Through non-invasive magnetic induction intensity measurement methods, finite element software and machine learning technology, the contact problem of traditional magnetic density measurement methods is solved, and high-precision and lossless magnetic induction intensity measurement is achieved, providing online monitoring and fault diagnosis of relays. New ideas.

CN119087308APending Publication Date: 2024-12-06李文华
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411179575.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Traditional magnetic-tight measurement methods require physical contact, are complex in operation, time-consuming and labor-intensive, and may damage electrical appliances, affecting their performance and life.

Method used

Non-invasive magnetic induction intensity measurement method is used, combined with finite element software to analyze and model the internal magnetic field and spatial magnetic field of the relay, and use signal processing and machine learning technology to extract and match the external magnetic field signals. Through convolutional neural networks, Long-term short-term memory network model predicts internal magnetic induction intensity.

Benefits of technology

High-precision, fast and lossless measurement of magnetic induction strength is achieved, avoiding the disadvantages of traditional methods, and providing new methods for online monitoring and fault diagnosis of relays.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119087308A_ABST
    Figure CN119087308A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of electric appliance magnetic field measurement, in particular to an electric appliance non-intrusive magnetic induction intensity measurement method and device and a medium, the method comprises the following steps: according to an electric appliance topological structure, analyzing and modeling an internal magnetic field and a space magnetic field by using finite element software to obtain the magnetic induction intensity of a main magnetic circuit in a simulated electric appliance; selecting a measurement position, measuring the magnetic induction intensity of the external space of the electric appliance, obtaining the similarity between the magnetic induction intensity of the external space of the electric appliance and the magnetic induction intensity of the internal main magnetic circuit of the simulated electric appliance through dynamic planning, selecting the magnetic induction intensity of the external space, and obtaining an external magnetic field signal; and taking an external magnetic field signal as input, and obtaining an internal magnetic induction intensity signal based on a mapping prediction network model of a convolutional neural network and a long-short-term memory network. According to the invention, through a non-intrusive detection technology, internal magnetic field detection of power equipment such as a relay is realized, the measurement cost is reduced, and the measurement efficiency and accuracy are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electrical appliance magnetic field measurement, and in particular to a method, equipment and medium for measuring the non-invasive magnetic induction intensity of an electrical appliance. Background Art

[0002] As the core component of electrical drive, the electromagnetic mechanism has an important magnetic induction intensity, among which the accurate measurement of magnetic density characteristics plays a vital role in ensuring the stable operation of electrical performance. However, traditional magnetic density measurement methods often require physical contact or disassembly, which is not only complicated, time-consuming and labor-intensive, but may also damage the electrical appliance, affecting its performance and life.

[0003] With the continuous development of science and technology, non-invasive measurement technology has gradually attracted widespread attention. This technology does not physically contact the object being measured, but uses the interaction between the object and the measuring device to achieve measurement and analysis. It has the advantages of high precision, large range, fast response and good adaptability. In the field of electromagnetics, non-invasive measurement technology is also widely used in the measurement of parameters such as magnetic field distribution and magnetic induction intensity. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a non-invasive magnetic induction intensity measurement method for electrical appliances, which aims to solve the shortcomings of traditional magnetic density measurement methods. The method combines knowledge and technical means in multiple technical fields such as electromagnetism, signal processing, machine learning and deep learning, numerical calculation and simulation, and uses finite element software to analyze and model the internal magnetic field of the relay and the spatial magnetic field, and simulate the distribution of the main magnetic circuit inside the electrical appliance and the external space magnetic induction intensity. At the same time, signal processing technology and machine learning methods are used to extract features and perform similarity matching on the measured external magnetic field signals, and finally realize non-invasive relay magnetic density measurement.

[0005] This non-invasive magnetic induction intensity measurement method not only avoids the drawbacks of traditional measurement methods and improves the accuracy and efficiency of measurement, but also provides new ideas and methods for online monitoring and fault diagnosis of electrical components such as relays.

[0006] The present invention provides a non-invasive magnetic induction intensity measurement method for an electrical appliance, comprising: S1: According to the electrical topology, the internal magnetic field and the spatial magnetic field are analytically modeled using finite element software to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance; S2: selecting a measurement position according to the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, measuring the magnetic induction intensity of the space outside the electrical appliance at the measurement position, and obtaining multiple magnetic induction intensities of the space outside the electrical appliance; S3: By performing dynamic programming of two time series on the magnetic induction intensity of the external space of multiple electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances, the similarity between the magnetic induction intensity of the external space of the electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances is obtained; S4: selecting the external space magnetic induction intensity according to the similarity between the external space magnetic induction intensity of the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance to obtain an external magnetic field signal; S5: Taking the external magnetic field signal as input, the internal magnetic induction intensity signal is obtained based on the mapping prediction network model of convolutional neural network and long short-term memory network.

[0007] According to the present invention, a non-invasive magnetic induction intensity measurement method for an electrical appliance further includes the step S1, according to the electrical appliance topology, using finite element software to analytically model the internal magnetic field and the spatial magnetic field to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, including: S11: Establish an electrical model based on the electrical topology, use finite element software to give the electrical model material properties, divide the grid, apply boundary conditions and excitation; S12: setting parameters, and simulating the electrical model according to the set parameters to obtain the model magnetic induction intensity vector diagram and magnetic induction intensity distribution diagram; S13: Extracting the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance according to the model magnetic induction intensity vector diagram and the magnetic induction intensity distribution diagram.

[0008] According to a non-invasive magnetic induction intensity measurement method for an electrical appliance provided by the present invention, the parameters include convergence steps, simulation step length, fault tolerance percentage, excitation source and boundary condition value.

[0009] According to the present invention, a non-invasive magnetic induction intensity measurement method for an electrical appliance further includes, in the step S2, selecting a measurement position according to the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, measuring the magnetic induction intensity of the space outside the electrical appliance at the measurement position, and obtaining multiple magnetic induction intensities of the space outside the electrical appliance, including: S21: The electrical appliance is placed in a fixed position, the Gaussmeter is installed on the robotic arm, and the robotic arm has a preset measurement position; S22: Control the robotic arm to drive the Gaussmeter to move, and after reaching the preset measurement position, keep the Gaussmeter probe still; S23: Power on the electrical appliance, collect and store spatial magnetic induction intensity data measured by the Gauss meter probe; S24: Repeat steps S22 and S23 until all preset measurement positions are tested.

[0010] According to the present invention, a non-invasive magnetic flux density measurement method for an electrical appliance further includes the step S3, in which the magnetic flux density outside the electrical appliance and the magnetic flux density of the main magnetic circuit inside the simulated electrical appliance are dynamically programmed in two time series to obtain the similarity between the magnetic flux density outside the electrical appliance and the magnetic flux density of the main magnetic circuit inside the simulated electrical appliance; The magnetic induction intensity of the simulated internal main magnetic circuit is expressed as a length of The vector S of the electrical appliance is expressed as a vector of length A vector Q, where , , is the first vector points, is the first vector points; Through dynamic programming, we can find the best path between vector S and vector Q. Calculate vector points using Euclidean distance and The distance between the vector points and The distance between them is: in, is a vector point and vector point The distance between is the power index, ; The dynamic programming method is used to construct the cost matrix, and the calculation expression of the cost matrix is: in, is a vector point and vector point The cost matrix between To find the minimum function; Get the vector through the cost matrix and vector The best path between is calculated as: in, For vector and vector The best path between According to the vector and vector The length of the optimal path between is used to calculate the degree to which the curve deviates from the optimal path. The calculation expression for the degree to which the curve deviates from the optimal path is: in, is the length of the optimal path; is the length of the vector; is the degree to which the curve deviates from the optimal path; The similarity between the magnetic induction intensity of the space outside the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance is obtained according to the degree to which the curve deviates from the optimal path.

[0011] According to a non-invasive magnetic induction intensity measurement method for an electrical appliance provided by the present invention, the method further includes selecting the external magnetic induction intensity with the highest similarity as the external magnetic field signal in the step S4.

[0012] According to the present invention, a non-invasive magnetic induction intensity measurement method for an electrical appliance further includes the step S5, taking the external magnetic field signal as input, obtaining the internal magnetic induction intensity signal based on the mapping prediction network model of the convolutional neural network and the long short-term memory network, S51: Perform convolution operation on the input data to extract data features. The calculation expression is: in, For the The output features of the convolution layer, For the Layer The convolution kernel weights, is the size of the convolution window; For the Layer input data; S52: Select RELU function as the activation function, and the calculation expression is: in, For the Tier The feature map The characteristic activation value of a neuron, To find the maximum value function; S53: Forget the information that has no effect on the target task through the forget gate, and determine the amount of information to be transmitted; store the feature data information that needs to be retained in the unit through the input gate, and use the activation function to create new candidate values; determine the data to be output through the output layer, The calculation expression for the retention degree of historical information controlled by the forget gate is: in, for The forget gate controls the degree of retention of historical information. for The weight matrix of for The bias of for Output value at any time, is the sigmoid function; Control the retention degree of the current input information. The calculation expression is: in, for The degree of retention of the gate control information input at all times, for The weight matrix of for Bias of Establish candidate vectors, the calculation expression of candidate vectors is: in, is the candidate vector, for The weight matrix of the function, for The bias of the function, is the activation function; merge Moment and The state at the moment is used to obtain the output gate state. The output gate state expression is: in, for Output door status at all times, for Input the state of the door at all times; The calculation expression of the retention degree of output gate control information is: in, for The degree of retention of the output gate control information at all times, for The weight matrix of for Bias of The hidden state calculation expression of the output gate is: in, for Output the hidden state of the gate at all times.

[0013] According to a non-invasive magnetic induction intensity measurement method for an electrical appliance provided by the present invention, the method further includes using the mean absolute error and the root mean square error to judge the prediction accuracy of the non-invasive magnetic induction intensity measurement method for an electrical appliance, and the mean absolute error calculation expression is: in, is the mean absolute error, For the True value, For the Prediction values, is the total number of predicted samples; in, is the mean absolute error.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned non-invasive magnetic induction intensity measurement methods are implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned non-invasive magnetic induction intensity measurement methods are implemented.

[0016] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The present invention proposes a non-invasive magnetic induction intensity measurement method, which aims to solve the shortcomings of traditional magnetic flux density measurement methods. This method combines knowledge and technical means in multiple technical fields such as electromagnetism, signal processing, machine learning and deep learning, numerical calculation and simulation, etc., and uses finite element software to analyze and model the internal magnetic field of the relay and the spatial magnetic field, simulating the distribution of the main magnetic circuit inside the electrical appliance and the external space magnetic flux density. At the same time, signal processing technology and machine learning methods are used to extract features and perform similarity matching on the measured external magnetic field signals, and finally realize non-invasive relay flux density measurement.

[0017] This non-invasive magnetic induction intensity measurement method not only avoids the drawbacks of traditional measurement methods and improves the accuracy and efficiency of measurement, but also provides new ideas and methods for online monitoring and fault diagnosis of electrical components such as relays. Additional aspects and advantages of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 The present invention provides a flow chart of a method for measuring the magnetic induction intensity of an electrical appliance in a non-invasive manner.

[0020] Figure 2 The present invention provides a comparison diagram of the magnetic induction intensity of an electrical appliance provided by the simulation calculation and Gauss measurement.

[0021] Figure 3 The present invention provides a method for measuring the magnetic induction intensity of an electrical appliance in a non-invasive manner, and provides curves of the magnetic induction intensity of external space at 10 positions.

[0022] Figure 4 The present invention provides a non-invasive magnetic induction intensity measurement method for an electrical appliance, which includes an external space magnetic induction curve and an internal iron core magnetic induction intensity curve.

[0023] Figure 5 The present invention provides a block diagram of an electronic device for a method for measuring the magnetic induction intensity of an electrical appliance in a non-invasive manner. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme in the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0025] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0026] Combine the following Figures 1 to 5 A non-invasive magnetic induction intensity measurement method for an electrical appliance according to the present invention is described like Figure 1 As shown, a non-invasive magnetic induction intensity measurement method for electrical appliances, S1: According to the electrical topology, the internal magnetic field and the spatial magnetic field are analytically modeled using finite element software to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance; S11: Establish an electrical model based on the electrical topology, use finite element software to give the electrical model material properties, divide the grid, apply boundary conditions and excitation; S12: setting parameters, and simulating the electrical model according to the set parameters to obtain the model magnetic induction intensity vector diagram and magnetic induction intensity distribution diagram; Parameters include the number of convergence steps, simulation step size, error tolerance percentage, excitation source, and boundary condition values.

[0027] S13: Extracting the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance according to the model magnetic induction intensity vector diagram and the magnetic induction intensity distribution diagram.

[0028] In some embodiments of the present invention, the internal magnetic field and the spatial magnetic field are analytically modeled using finite element software according to the electrical topology to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, and the external spatial magnetic induction intensity can also be obtained.

[0029] According to the model magnetic induction intensity vector diagram and magnetic induction intensity distribution diagram, the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance is extracted, and the magnetic induction intensity of the external stray magnetic field can also be obtained.

[0030] S2: selecting a measurement position according to the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, measuring the magnetic induction intensity of the space outside the electrical appliance at the measurement position, and obtaining multiple magnetic induction intensities of the space outside the electrical appliance; S21: The electrical appliance is placed in a fixed position, the Gaussmeter is installed on the robotic arm, and the robotic arm has a preset measurement position; S22: Control the robotic arm to drive the Gaussmeter to move, and after reaching the preset measurement position, keep the Gaussmeter probe still; S23: Power on the electrical appliance, collect and store spatial magnetic induction intensity data measured by the Gauss meter probe; S24: Repeat steps S22 and S23 until all preset measurement positions are tested.

[0031] In some embodiments of the present invention, the data measured by the Gauss meter is used as the screening data. The external space magnetic induction intensity curves of the 10 measured positions are shown in FIG. Figure 3The simulation accuracy is verified by comparing the external space magnetic induction intensity curve measured by the Gauss meter with the magnetic induction intensity of the external stray magnetic field measured by simulation. The comparison results are shown in Figure 2 shown.

[0032] S3: By performing dynamic programming of two time series on the magnetic induction intensity of the external space of multiple electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances, the similarity between the magnetic induction intensity of the external space of the electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances is obtained; S31: The magnetic induction intensity of the simulated internal main magnetic circuit is expressed as a length of The vector S of the electrical appliance is expressed as a vector of length A vector Q, where , , is the first vector points, is the first vector points; S32: By using the dynamic programming method, find the optimal path between vector S and vector Q to obtain a regular path. The regular path calculation expression is: in, To regularize the path, is the optimal path of the first group, , For the The optimal path of the group, For the The optimal path of the group, , is the number of optimal paths.

[0033] The dynamic programming method is: Calculate vector points using Euclidean distance and The base distance between the vector points and The base distance between them is: in, is a vector point and vector point The base distance between is the power index, ; Finding the best regularized path requires three basic conditions; Condition 1: Determinism, the path starts from the first group of optimal paths and ends at the The optimal path of the group ends, and the best regular path must start from the optimal path of the first group to the The optimal path of the group ends; Condition 2: Continuity: Each consecutive point on the curved path moves along the path without jumping or deviating from the main direction; Condition 3: Monotonicity: Each point must move in one direction and cannot move in the opposite direction or deviate from the main direction. Each point on the path must move vertically or horizontally relative to the previous point, but cannot move backwards.

[0034] The dynamic programming method is used to construct the cost matrix, and the calculation expression of the cost matrix is: in, is a vector point and vector point The cost matrix between , , To find the minimum function; It is regarded as the sum of the distance value of the current element and the minimum value of the cumulative distance values ​​of the three conditions. Get the vector through the cost matrix and vector The best path between is calculated as: in, For vector and vector The best path between According to the vector and vector The length of the optimal path between is used to calculate the degree to which the curve deviates from the optimal path. The calculation expression for the degree to which the curve deviates from the optimal path is: in, is the length of the optimal path; is the length of the vector; is the degree to which the curve deviates from the optimal path, and the vector and vector are the same length; The similarity between the magnetic induction intensity of the space outside the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance is obtained according to the degree to which the curve deviates from the optimal path.

[0035] S4: Obtain an external magnetic field signal based on the similarity between the magnetic induction intensity of the space outside the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance.

[0036] The external magnetic induction intensity with the highest similarity is selected as the external magnetic field signal.

[0037] In some specific embodiments of the present invention, 10 measurement positions are selected outside the electrical appliance, 10 external magnetic induction intensity curves are extracted as screening data, a dynamic time warping algorithm is introduced to calculate the similarity of the internal and external curves, and the curve with the highest similarity is selected as the input for the next step.

[0038] S5: Taking the external magnetic field signal as input, the internal magnetic induction intensity signal is obtained based on the mapping prediction network model of convolutional neural network and long short-term memory network; S51: Perform convolution operation on the input data to extract data features. The calculation expression is: in, For the The output features of the convolution layer, For the Layer The convolution kernel weights, is the size of the convolution window; For the Layer input data; S52: Select RELU function as the activation function, and the calculation expression is: in, For the Tier The feature map The characteristic activation value of a neuron, To find the maximum value function; S53: Forget the information that has no effect on the target task through the forget gate, and determine the amount of information to be transmitted; store the feature data information that needs to be retained in the unit through the input gate, and use the activation function to create new candidate values; determine the data to be output through the output layer, The calculation expression for the retention degree of historical information controlled by the forget gate is: in, for The forget gate controls the degree of retention of historical information. for The weight matrix of for The bias of for Output value at any time, is the sigmoid function; Control the retention degree of the current input information. The calculation expression is: in, for The degree of retention of the gate control information input at all times, for The weight matrix of for Bias of Establish candidate vectors, the calculation expression of candidate vectors is: in, is the candidate vector, for The weight matrix of the function, for The bias of the function, is the activation function; merge Moment and The state at the moment is used to obtain the output gate state. The output gate state expression is: in, for Output door status at all times, for Input the state of the door at all times; The calculation expression of the retention degree of output gate control information is: in, for The degree of retention of the output gate control information at all times, for The weight matrix of for Bias of The hidden state calculation expression of the output gate is: in, for Output the hidden state of the gate at all times.

[0039] The mean absolute error and root mean square error are used to judge the prediction accuracy of a non-invasive magnetic induction intensity measurement method for electrical appliances. The mean absolute error calculation expression is: in, is the mean absolute error, For the True value, For the Prediction values, is the total number of predicted samples; in, is the mean absolute error.

[0040] In some embodiments of the present invention, the calculation of the magnetic induction intensity inside the core of the electrical appliance is achieved by establishing a nonlinear mapping relationship between the internal magnetic field of the electrical appliance parts and the external magnetic field, wherein the mean absolute error is 0.38 and the root mean square error is 0.55.

[0041] Figure 5 A block diagram of an electronic device is shown as an example. Figure 5 As shown, the electronic device may include: a processor 201, a communication interface 203, a memory 204 and a communication bus 202, wherein the processor 201, the communication interface 203 and the memory 204 communicate with each other through the communication bus 202. The processor 201 may call the logic instructions in the memory 204 to execute a non-invasive magnetic induction intensity measurement method for an electrical appliance.

[0042] In addition, the logic instructions in the above-mentioned memory 204 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of 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. Various media that can store program codes.

[0043] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a non-invasive magnetic induction intensity measurement method for an electrical appliance provided by the above methods.

[0044] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the above-mentioned non-invasive magnetic induction intensity measurement method for an electrical appliance.

[0045] The present invention proposes a non-invasive magnetic induction intensity measurement method, which aims to solve the shortcomings of traditional magnetic flux density measurement methods. This method combines knowledge and technical means in multiple technical fields such as electromagnetism, signal processing, machine learning and deep learning, numerical calculation and simulation, etc., and uses finite element software to analyze and model the internal magnetic field of the relay and the spatial magnetic field, simulating the distribution of the main magnetic circuit inside the electrical appliance and the external space magnetic flux density. At the same time, signal processing technology and machine learning methods are used to extract features and perform similarity matching on the measured external magnetic field signals, and finally realize non-invasive relay flux density measurement.

[0046] The non-invasive magnetic induction intensity measurement method of the present invention not only avoids the drawbacks of traditional measurement methods and improves the accuracy and efficiency of measurement, but also provides a new idea and method for online monitoring and fault diagnosis of electrical components such as relays.

[0047] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A non-invasive magnetic induction intensity measurement method for an electrical appliance, characterized in that: include: S1: According to the electrical topology, the internal magnetic field and the spatial magnetic field are analytically modeled using finite element software to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance; S2: selecting a measurement position according to the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, measuring the magnetic induction intensity of the space outside the electrical appliance at the measurement position, and obtaining multiple magnetic induction intensities of the space outside the electrical appliance; S3: By performing dynamic programming of two time series on the magnetic induction intensity of the external space of multiple electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances, the similarity between the magnetic induction intensity of the external space of the electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances is obtained; S4: selecting the external space magnetic induction intensity according to the similarity between the external space magnetic induction intensity of the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance to obtain an external magnetic field signal; S5: Taking the external magnetic field signal as input, the internal magnetic induction intensity signal is obtained based on the mapping prediction network model of convolutional neural network and long short-term memory network.

2. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: In the step S1, according to the electrical topology, the internal magnetic field and the spatial magnetic field are analytically modeled using finite element software to obtain the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, including: S11: Establish an electrical model based on the electrical topology, use finite element software to give the electrical model material properties, divide the grid, apply boundary conditions and excitation; S12: setting parameters, and simulating the electrical model according to the set parameters to obtain the model magnetic induction intensity vector diagram and magnetic induction intensity distribution diagram; S13: Extracting the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance according to the model magnetic induction intensity vector diagram and the magnetic induction intensity distribution diagram.

3. The non-invasive magnetic induction intensity measurement method of an electrical appliance according to claim 2, characterized in that: The parameters include convergence steps, simulation step length, error tolerance percentage, excitation source and boundary condition value.

4. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: In the step S2, a measurement position is selected according to the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance, and the magnetic induction intensity of the space outside the electrical appliance is measured at the measurement position to obtain multiple magnetic induction intensities of the space outside the electrical appliance, including: S21: The electrical appliance is placed in a fixed position, the Gaussmeter is installed on the robotic arm, and the robotic arm has a preset measurement position; S22: Control the robotic arm to drive the Gaussmeter to move, and after reaching the preset measurement position, keep the Gaussmeter probe still; S23: Power on the electrical appliance, collect and store spatial magnetic induction intensity data measured by the Gauss meter probe; S24: Repeat steps S22 and S23 until all preset measurement positions are tested.

5. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: In the step S3, the similarity between the magnetic induction intensity of the external space of the electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances is obtained by performing dynamic programming of two time series on the magnetic induction intensity of the external space of the electrical appliances and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliances; The magnetic induction intensity of the simulated internal main magnetic circuit is expressed as a length of The vector S of the electrical appliance is expressed as a vector of length A vector Q, where , , is the first vector points, is the first vector points; Through dynamic programming, we can find the best path between vector S and vector Q. Calculate vector points using Euclidean distance and The distance between the vector points and The distance between them is: in, is a vector point and vector point The distance between is the power index, ; The dynamic programming method is used to construct the cost matrix, and the calculation expression of the cost matrix is: in, is a vector point and vector point The cost matrix between To find the minimum function; Get the vector through the cost matrix and vector The best path between is calculated as: in, For vector and vector The best path between According to the vector and vector The length of the optimal path between is used to calculate the degree to which the curve deviates from the optimal path. The calculation expression for the degree to which the curve deviates from the optimal path is: in, is the length of the optimal path; is the length of the vector; is the degree to which the curve deviates from the optimal path; The similarity between the magnetic induction intensity of the space outside the electrical appliance and the magnetic induction intensity of the main magnetic circuit inside the simulated electrical appliance is obtained according to the degree to which the curve deviates from the optimal path.

6. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: In step S4, the external magnetic induction intensity with the highest similarity is selected as the external magnetic field signal.

7. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: In the step S5, the external magnetic field signal is used as input, and the internal magnetic induction intensity signal is obtained based on the mapping prediction network model of the convolutional neural network and the long short-term memory network. S51: Perform convolution operation on the input data to extract data features. The calculation expression is: in, For the The output features of the layer convolution, For the Layer The convolution kernel weights, is the size of the convolution window; For the Layer input data; S52: Select RELU function as the activation function, and the calculation expression is: in, For the Tier The feature map The characteristic activation value of a neuron, To find the maximum value function; S53: Forget the information that has no effect on the target task through the forget gate, and determine the amount of information to be transmitted; store the feature data information that needs to be retained in the unit through the input gate, and use the activation function to create new candidate values; determine the data to be output through the output layer, The calculation expression for the retention degree of historical information controlled by the forget gate is: in, for The forget gate controls the degree of retention of historical information. for The weight matrix of for The bias, for Output value at any time, is the sigmoid function; Control the retention degree of the current input information. The calculation expression is: in, for The degree of retention of the gate control information input at all times, for The weight matrix of for Bias of Establish candidate vectors, the calculation expression of candidate vectors is: in, is the candidate vector, for The weight matrix of the function, for The bias of the function, is the activation function; merge Moment and The state at the moment is used to obtain the output gate state. The output gate state expression is: in, for Output door status at all times, for Input the state of the door at all times; The calculation expression of the retention degree of output gate control information is: in, for The degree of retention of the output gate control information at all times, for The weight matrix of for Bias of The hidden state calculation expression of the output gate is: in, for Output the hidden state of the gate at all times.

8. The method for measuring the non-invasive magnetic induction intensity of an electrical appliance according to claim 1, characterized in that: The mean absolute error and root mean square error are used to judge the prediction accuracy of a non-invasive magnetic induction intensity measurement method for electrical appliances. The mean absolute error calculation expression is: in, is the mean absolute error, For the True value, For the Prediction values, is the total number of predicted samples; in, is the mean absolute error.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for non-invasively measuring the magnetic induction intensity of an electrical appliance as described in any one of claims 1 to 8 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for non-invasively measuring the magnetic induction intensity of an electrical appliance as claimed in any one of claims 1 to 8 are implemented.