Calculation method and system for wave head and wave tail resistance values ​​of impulse voltage test device

Abstract

The present invention discloses a method and system for calculating the wave front and wave tail resistance values ​​of an impulse voltage test device. The method comprises: obtaining test environment temperature, atmospheric pressure, and air humidity data, and simultaneously obtaining test object equivalent capacitance data; and inputting the obtained data into a trained BP neural network model corresponding to the test object to obtain the wave front and wave tail resistance values ​​required by the test object. The present invention can obtain relatively accurate wave front and wave tail resistance values, achieving the purpose of outputting a standard impulse voltage test waveform, and avoiding the problem of the inability to accurately determine the wave front and wave tail resistance values ​​using traditional empirical methods or simple calculation methods.

Description

Technical Field

[0001] The present invention relates to the technical field of impulse voltage testing, and in particular to a method and system for calculating wave head and wave tail resistance values ​​of an impulse voltage testing device. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] When conducting type tests or routine tests on electrical equipment, impulse voltage tests are mandatory tests specified in national standards. Existing impulse voltage test devices use fixed-value non-inductive resistors as wave head and wave tail resistors. For different types of test objects (such as transformers, switchgear, reactors, disconnectors, etc.), due to the different equivalent capacitances of the test objects, it is necessary to frequently replace wave head or wave tail resistors with different resistance values ​​to adjust the charging and discharging process to achieve the purpose of outputting a standard impulse voltage waveform. For example, when conducting a lightning impulse voltage test, according to national standards, the standard lightning impulse The wavefront time of the impulse voltage waveform is 1.2μs, the half-peak time is 50μs, the allowable deviation of the wavefront time is ±30%, and the allowable deviation of the half-peak time is ±20%. When conducting lightning impulse voltage tests on two different types of test products, 10kV distribution transformers and 10kV high-voltage switchgear, or test products of the same type but different capacities and specifications, although the allowable deviation of the wavefront time and the wavetail time is large, due to the large difference in the equivalent capacitance of the test products, it is still necessary to frequently replace the wavehead and wavetail resistors for waveform adjustment to achieve the purpose of outputting the lightning impulse voltage waveform.

[0004] The traditional method of adjusting the impulse voltage waveform is mainly achieved by adjusting the wave head and wave tail resistance. The determination of the wave head and wave tail resistance value is mainly based on the experience accumulated during a long test process or simple calculation. It cannot guarantee the use of more accurate wave head and wave tail resistance, which will cause the output impulse voltage amplitude to exceed the maximum allowable value of the output voltage specified in the national standard, and the wave front time and half-peak time will not meet the requirements of the national standard, causing insulation breakdown and damage due to reasons other than the performance of the test product itself. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes a method and system for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device, which can achieve a relatively accurate prediction of the wave head and wave tail of the impulse voltage device based on the BP (Back Propagation) neural network model, and achieve the purpose of outputting an impulse voltage waveform that meets the standard requirements without frequently changing the wave head and wave tail resistance.

[0006] In some embodiments, the following technical solutions are adopted:

[0007] A method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device, comprising:

[0008] Obtain the temperature, atmospheric pressure and air humidity data of the test environment, and at the same time obtain the equivalent capacitance value data of the test product;

[0009] The acquired data is input into the trained BP neural network model corresponding to the test sample to obtain the wave head resistance value and wave tail resistance value required by the test sample.

[0010] The training process of the BP neural network model includes:

[0011] Perform impulse voltage tests on different types of test products, adjust the wave head and wave tail resistance so that the output impulse voltage waveform is basically within the set error range with the parameters of the standard impulse voltage waveform; record the wave head resistance value and wave tail resistance value at this time, as well as the experimental environment parameters and the equivalent capacitance value of the test product;

[0012] Construct a neural network training dataset using the above data;

[0013] The BP neural network model is trained using the training data set until the output error of the neural network is reduced to an allowable range; and the neural network models and weight values ​​of each layer of the test samples of different categories are obtained.

[0014] In other embodiments, the following technical solutions are adopted:

[0015] A system for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device, comprising:

[0016] The data acquisition module is used to obtain the temperature, atmospheric pressure and air humidity data of the test environment, and the equivalent capacitance value data of the test product;

[0017] The neural network model prediction module is used to input the acquired data into the trained BP neural network model corresponding to the test sample to predict the wave head resistance value and wave tail resistance value required by the test sample.

[0018] In other embodiments, the following technical solutions are adopted:

[0019] A terminal device includes a processor and a memory, the processor is used to implement various instructions; the memory is used to store multiple instructions, and the instructions are suitable for the processor to load and execute the above-mentioned method for calculating the wave head and wave tail resistance values ​​of the impulse voltage test device.

[0020] In other embodiments, the following technical solutions are adopted:

[0021] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] (1) The present invention calculates the wave head and wave tail resistance of the impulse voltage test device through the BP neural network model, and can obtain relatively accurate wave head and wave tail resistance values, thereby achieving the purpose of outputting a standard impulse voltage test waveform, avoiding the problem that the wave head and wave tail resistance values ​​cannot be determined relatively accurately by traditional empirical methods or simple calculation methods; avoiding the time-consuming and labor-intensive frequent replacement of resistors due to the inability of traditional methods to accurately determine the resistance values; and avoiding the equipment impulse voltage breakdown and damage caused by reasons other than the performance of the test product itself due to resistance value mismatch.

[0024] Other features and advantages of additional aspects 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 practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Schematic diagram of the BP neural network structure in an embodiment of the present invention;

[0026] Figure 2 This is a flow chart of a method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0028] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0029] Example 1

[0030] In one or more embodiments, a method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device is disclosed, combined with Figure 2 , specifically including the following process:

[0031] (1) Obtain the temperature, atmospheric pressure and air humidity data of the test environment, and at the same time obtain the equivalent capacitance value data of the test product;

[0032] (2) The acquired data is input into the trained BP neural network model corresponding to the test product to obtain the wave head resistance value and wave tail resistance value required by the test product, and then carry out the impulse voltage test.

[0033] In this embodiment, impulse voltage tests are performed on different types of test products (for example, transformers, switchgear, reactors, disconnectors, etc.), and the wave head and wave tail resistances are adjusted so that the output impulse voltage waveform is basically consistent with the parameters such as the amplitude, wave front time, and half-peak time of the standard impulse voltage waveform specified in the national standard "GB / T16927.1-2011 High Voltage Test Technology Part 1: General Definitions and Test Requirements". The deviation is within the deviation range specified in the standard and the deviation value is small. The wave head and wave tail resistance values ​​at this time, as well as laboratory environmental parameters, including temperature, air pressure, humidity and other information, are recorded. At the same time, parameters such as the equivalent capacitance value of the test product are measured by measuring instruments.

[0034] This step requires testing with a large sample size, and each category of materials requires test data with a large sample size.

[0035] Construct a BP neural network model. The BP neural network algorithm includes the information forward propagation process and the error back propagation process. The external information of the algorithm is input through the neurons in the input layer. The hidden layer is the internal information processing layer. Finally, the hidden layer transmits the information of each neuron to the output layer to complete a forward propagation of learning. When the output does not meet the expected output, the error back propagation begins. The error is back propagated through the output layer to the hidden layer and input layer. In this process, the weights and thresholds of each layer are corrected according to the gradient descent principle. The information forward propagation and error back propagation processes are continuously circulated, which means that the weights of each layer are continuously adjusted. This is the BP neural network training process. The training process will not end until the output error of the neural network is reduced to within the allowable range, or it stops because the number of learning times set in advance is exceeded. The schematic diagram of the BP neural network structure is shown as follows. Figure 1 shown.

[0036] First, determine the inputs to the BP neural network model's input layer. Analysis confirmed the inputs to be four variables: the test object's equivalent capacitance C, ambient temperature T, atmospheric pressure P, and humidity d. The outputs of the output layer are the wave head resistance R1 and the wave tail resistance R2. The number of hidden layers and the number of neurons in each layer need to be determined through trial and error based on actual conditions and training. A larger number of hidden layers or neurons will affect the convergence speed of neural network training, while a smaller number of layers or neurons will affect output accuracy.

[0037] The training process of the neural network is as follows:

[0038] The data obtained by the above-mentioned impulse voltage test on different categories of test products, specifically the equivalent capacitance value of the test product recorded during the test and the temperature, atmospheric pressure and air humidity data of the experimental environment, are used as the input data group I = {C, T, P, d}, and the wave head and wave tail resistance values ​​recorded during the test are used as the output data group O = {R1, R2}. The constructed BP neural network model is used, and the neural network training is performed separately according to the type of test product to obtain the neural network model and weight value of each layer of different categories of materials.

[0039] Example 2

[0040] In one or more embodiments, a system for calculating wave front and wave tail resistance values ​​of an impulse voltage test device is disclosed, comprising:

[0041] The data acquisition module is used to obtain the temperature, atmospheric pressure and air humidity data of the test environment, and the equivalent capacitance value data of the test product;

[0042] The neural network model prediction module is used to input the acquired data into the trained BP neural network model corresponding to the test sample to predict the wave head resistance value and wave tail resistance value required by the test sample.

[0043] As an optional embodiment, it further includes: a neural network training module, and the training process of the BP neural network model includes:

[0044] Perform impulse voltage tests on different types of test products, adjust the wave head and wave tail resistance so that the output impulse voltage waveform is basically within the set error range with the parameters of the standard impulse voltage waveform; record the wave head resistance value and wave tail resistance value at this time, as well as the experimental environment parameters and the equivalent capacitance value of the test product;

[0045] Construct a neural network training dataset using the above data;

[0046] The BP neural network model is trained using the training data set until the output error of the neural network is reduced to an allowable range; and the neural network models and weight values ​​of each layer of the test samples of different categories are obtained.

[0047] The specific implementation process of each of the above modules has been described in Example 1 and will not be described in detail here.

[0048] Example 3

[0049] In one or more embodiments, a terminal device is disclosed, including a server. The server includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for calculating the wave head and wave tail resistance values ​​of the impulse voltage test device described in Example 1 is implemented. For the sake of brevity, this description is omitted here.

[0050] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0051] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0052] During implementation, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or by instructions in the form of software.

[0053] Example 4

[0054] In one or more embodiments, a computer-readable storage medium is disclosed, which stores multiple instructions suitable for being loaded and executed by a processor of a terminal device for executing the method for calculating the wave head and wave tail resistance values ​​of the impulse voltage test device described in Example 1.

[0055] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device, characterized in that: include: Obtain the temperature, atmospheric pressure and air humidity data of the test environment, and at the same time obtain the equivalent capacitance value data of the test product; Input the acquired data into the trained BP neural network model corresponding to the test sample to obtain the wave head resistance value and wave tail resistance value required by the test sample; The training process of the BP neural network model includes: Perform impulse voltage tests on different types of test products, adjust the wave head and wave tail resistance so that the output impulse voltage waveform is basically within the set error range with the parameters of the standard impulse voltage waveform; record the wave head resistance value and wave tail resistance value at this time, as well as the experimental environment parameters and the equivalent capacitance value of the test product; Construct a neural network training dataset using the above data; The BP neural network model is trained using the training data set until the output error of the neural network is reduced to an allowable range; Obtain the neural network model and weight values ​​of each layer for different categories of test samples.

2. The method for calculating the wave front and wave tail resistance values ​​of an impulse voltage test device according to claim 1, characterized in that: The BP neural network model includes an information forward propagation process and an error back propagation process. The acquired data is input through each neuron in the input layer. The hidden layer is the internal information processing layer. Finally, the hidden layer transmits the information of each neuron to the output layer to complete a forward propagation of learning.

3. The method for calculating the wave front and wave tail resistance values ​​of an impulse voltage test device according to claim 2, characterized in that: When the output does not reach the expected output, the error enters the back propagation phase, and the error propagates back through the output layer to the hidden layer and input layer. In this process, the weights and thresholds of each layer are corrected according to the gradient descent principle.

4. A calculation system for the wave front and wave tail resistance values ​​of an impulse voltage test device, characterized in that: include: The data acquisition module is used to obtain the temperature, atmospheric pressure and air humidity data of the test environment, and the equivalent capacitance value data of the test product; The neural network model prediction module is used to input the acquired data into the trained BP neural network model corresponding to the test sample to predict the wave head resistance value and wave tail resistance value required by the test sample; The neural network training module includes the following steps: Perform impulse voltage tests on different types of test products, adjust the wave head and wave tail resistance so that the output impulse voltage waveform is basically within the set error range with the parameters of the standard impulse voltage waveform; record the wave head resistance value and wave tail resistance value at this time, as well as the experimental environment parameters and the equivalent capacitance value of the test product; Construct a neural network training dataset using the above data; The BP neural network model is trained using the training data set until the output error of the neural network is reduced to an allowable range; Obtain the neural network model and weight values ​​of each layer for different categories of test samples.

5. A terminal device comprising a processor and a memory, wherein the processor is used to implement various instructions; the memory is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the method for calculating the wave head and wave tail resistance values ​​of the impulse voltage test device according to any one of claims 1 to 3.

6. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instruction is suitable for being loaded by a processor of a terminal device and executing the method for calculating the wave head and wave tail resistance values ​​of an impulse voltage test device according to any one of claims 1 to 3.

Images