Method and device for predicting surface flashover voltage of composite insulator after forest fire, terminal equipment and storage medium

Abstract

The invention discloses a method and a device for predicting surface flashover voltage of a composite insulator after forest fire, terminal equipment and a storage medium. The method comprises the following steps: firstly, acquiring pollution parameters and model factors of the composite insulator in a to-be-detected area after forest fire; inputting the pollution parameters and the model factor into a preset flashover voltage prediction model, so that the preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the to-be-detected area according to the pollution parameters, the model factor and a correction relational expression corresponding to each pollution parameter; wherein the correction relational expression corresponding to each smear parameter is constructed according to the correction coefficients corresponding to the smear parameters of the composite insulator under different smear tests. Through the implementation of the method, on the basis of considering the salt density and the ash density, the influence of the parameter of the carbon particle size on the final predicted value of the flashover voltage is also considered, so that the final calculation result is more accurate and accords with the actual situation.

Description

Technical Field

[0001] The present invention relates to the technical field of flashover voltage prediction, and in particular to a method, device, terminal equipment and storage medium for predicting the surface flashover voltage of a composite insulator after a wildfire. Background Art

[0002] High-voltage transmission lines often pass through mountainous areas with dense vegetation. When a forest fire occurs, the burning of vegetation will quickly increase the temperature of the surrounding environment and produce a large amount of smoke particles. The flames and smoke particles may reduce the insulation performance of the composite insulators of the transmission line and increase the risk of insulation failure of the composite insulators of the transmission line. Once a flashover occurs, it may not only cause a tripping accident, but also pose a serious threat to the stability and safety of the power system.

[0003] At present, the prediction of flashover voltage of composite insulators is mainly based on pollution zone classification and pollution degree, which mainly considers the influence of salt density and ash density. However, in actual situations, in addition to the above factors, special pollution such as carbon particles generated under wildfire conditions will also affect the flashover voltage. Summary of the invention

[0004] The present invention provides a method, device, terminal equipment and storage medium for predicting the surface flashover voltage of a composite insulator after a wildfire. On the basis of considering the salt density and ash density, the influence of the parameter of carbon particle size on the predicted value of the final flashover voltage is also considered, so that the final calculation result is more accurate and in line with the actual situation.

[0005] An embodiment of the present invention provides a method for predicting the surface flashover voltage of a composite insulator after a wildfire, comprising:

[0006] Obtaining the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and average surface temperature of the composite insulators in the test area;

[0007] Input the above-mentioned contamination parameters and model factors into a preset flashover voltage prediction model, so that the above-mentioned preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the above-mentioned test area according to the above-mentioned contamination parameters, model factors and the correction relationship corresponding to each contamination parameter;

[0008] The correction relation corresponding to each pollution parameter is constructed according to the correction coefficient corresponding to the pollution parameter of the composite insulator under different pollution tests.

[0009] Furthermore, the hydrophobicity value is calculated based on the burning time and the average surface temperature of the composite insulator in the test area, including:

[0010] The experimental hydrophobicity values ​​of composite insulators at different experimental burning times and experimental surface average temperatures were measured;

[0011] According to the above experimental combustion time, the experimental surface average temperature and the above experimental hydrophobicity value, a relationship between the experimental hydrophobicity value, the experimental combustion time and the experimental surface average temperature is obtained;

[0012] The hydrophobicity value is calculated based on the combustion time, the average surface temperature and the relationship.

[0013] Furthermore, the training of the preset flashover voltage prediction model includes:

[0014] Obtaining several groups of samples and the actual flashover voltage corresponding to each group of samples; wherein the samples include: contamination parameter samples and model factor samples;

[0015] Inputting each group of samples and the corresponding actual flashover voltage into the flashover voltage prediction model to be trained, so that the flashover voltage prediction model calculates the first correction coefficient corresponding to each contamination parameter sample according to the contamination parameter sample and the corresponding correction relationship;

[0016] Calculate and obtain a first predicted flashover voltage according to each first correction coefficient and the above model factor sample;

[0017] Calculating a prediction error according to the first predicted flashover voltage and the actual flashover voltage;

[0018] If the prediction error is less than the preset error threshold, the training of the flashover voltage prediction model is completed; otherwise, after adjusting the parameters in the flashover voltage prediction model according to the prediction error, the training of the flashover voltage prediction model continues.

[0019] Furthermore, when the above-mentioned contamination parameter is salt density or the above-mentioned carbon particle size, the construction of the correction relationship corresponding to the above-mentioned contamination parameter includes:

[0020] For each contamination parameter, obtaining a first flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes;

[0021] According to the first flashover voltage measurement value and the corresponding contamination parameter, the equivalent contamination degree corresponding to the contamination parameters of different sizes is calculated;

[0022] According to the above-mentioned contamination parameters and the corresponding equivalent degree of contamination, the correction coefficient of the contamination parameters is calculated;

[0023] The above-mentioned contamination parameters and the correction coefficients of the above-mentioned contamination parameters are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0024] Furthermore, when the above-mentioned smearing parameter is relative humidity, the above-mentioned ash density or the above-mentioned ash distribution area, the construction of the correction relationship corresponding to the above-mentioned smearing parameter includes:

[0025] For each contamination parameter, obtaining a second flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes;

[0026] According to the second flashover voltage measurement value and the corresponding contamination parameter, the equivalent salt density of the contamination parameters of different sizes is calculated;

[0027] According to the above-mentioned smearing parameters and the corresponding equivalent salt density, the correction coefficient of the smearing parameters is calculated;

[0028] The above-mentioned contamination parameters and the correction coefficients of the above-mentioned contamination parameters are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0029] Furthermore, when the above-mentioned smearing parameter is the above-mentioned voltage type, the construction of the correction relationship corresponding to the above-mentioned smearing parameter includes:

[0030] Obtaining the third flashover voltage measurement value of the composite insulator under different voltage types;

[0031] Calculate the correction coefficient of the voltage type according to the third flashover voltage measurement value;

[0032] According to the voltage types and the correction coefficients corresponding to the voltage types, the correction relationship corresponding to the contamination parameters is calculated.

[0033] Furthermore, when the above-mentioned contamination parameter is the above-mentioned hydrophobic value, the construction of the correction relationship corresponding to the above-mentioned contamination parameter includes:

[0034] Obtaining first hydrophobic values ​​of a composite insulator with a completely clean surface at different heating times and different heating temperatures, and fourth flashover voltage measurement values ​​corresponding to each first hydrophobic value;

[0035] Calculating each first hydrophobicity correction coefficient according to each first hydrophobicity value and the corresponding fourth flashover voltage measurement value;

[0036] The correction coefficients of the above-mentioned first hydrophobic values ​​and the corresponding first hydrophobic values ​​are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0037] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0038] The present invention provides a device for predicting the surface flashover voltage of a composite insulator after a wildfire, comprising:

[0039] Data acquisition module and flashover voltage prediction module;

[0040] The data acquisition module is used to obtain the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and average surface temperature of the composite insulators in the test area;

[0041] The above-mentioned flashover voltage prediction module is used to input the above-mentioned contamination parameters and model factors into a preset flashover voltage prediction model, so that the above-mentioned preset flashover voltage prediction model can calculate the predicted flashover voltage of the composite insulator in the above-mentioned test area according to the above-mentioned contamination parameters, model factors and the correction relationship corresponding to each contamination parameter; wherein the correction relationship corresponding to each contamination parameter is constructed according to the correction coefficient corresponding to the contamination parameter of the composite insulator under different contamination tests.

[0042] Based on the above method embodiment, the present invention provides a terminal device embodiment;

[0043] The present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for predicting the surface flashover voltage of a composite insulator after a wildfire described in any embodiment of the present invention is implemented.

[0044] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0045] The present invention provides a storage medium, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for predicting the surface flashover voltage of a composite insulator after a wildfire described in any embodiment of the present invention is implemented.

[0046] The embodiments of the present invention have the following beneficial effects:

[0047] The present invention provides a method, device, terminal equipment and storage medium for predicting the surface flashover voltage of a composite insulator after a wildfire. The method comprises: first obtaining the contamination parameters and model factors of the composite insulator in the area to be tested after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and the average surface temperature of the composite insulator in the area to be tested; then the contamination parameters and model factors are input into a preset flashover voltage prediction model, so that the preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the area to be tested according to the contamination parameters, model factors and the correction relationship corresponding to each contamination parameter; wherein the correction relationship corresponding to each contamination parameter is constructed according to the correction coefficient corresponding to the contamination parameter of the composite insulator under different contamination tests. Therefore, the present invention conducts a contamination test on parameters including carbon particle size, obtains a correction relationship between the parameters and the corresponding correction coefficient, and then calculates the predicted flashover voltage according to the actual combustion parameters including carbon particle size and the preset flashover voltage prediction model. Therefore, the present invention not only considers the salt density and ash density, but also considers the influence of the carbon particle size parameter on the predicted value of the final flashover voltage, so that the final calculation result is more accurate and in line with the actual situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention is a flowchart of a method for predicting the surface flashover voltage of a composite insulator after a wildfire, provided by one embodiment of the present invention.

[0049] Figure 2 It is a structural schematic diagram of a flashover voltage prediction model provided by an embodiment of the present invention.

[0050] Figure 3 The present invention is a schematic structural diagram of a device for predicting the surface flashover voltage of a composite insulator after a wildfire, provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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 are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting the surface flashover voltage of a composite insulator after a wildfire, comprising:

[0053] Step S101: Obtaining the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and the average surface temperature of the composite insulators in the test area;

[0054] Specifically, drones are used to record the burning time of wildfires and the average surface temperature of composite insulators, so as to obtain the hydrophobicity value based on the burning time and the average surface temperature. After the wildfire is extinguished, drones are used to identify the ash density (i.e., the density of carbon particles), ash distribution area, carbon particle size, and salt density that conform to the surface of the insulator, and the relative humidity of the on-site environment is detected at the same time. Based on the operation and maintenance data, the model factor of the composite insulator is obtained. The voltage types are divided into DC and AC, and whether it is a DC line or an AC line is determined based on the actual situation of the area to be tested.

[0055] In a preferred embodiment, the hydrophobicity value is calculated based on the burning time and the average surface temperature of the composite insulator in the test area, including:

[0056] The experimental hydrophobicity values ​​of composite insulators at different experimental burning times and experimental surface average temperatures were measured;

[0057] According to the above experimental combustion time, the experimental surface average temperature and the above experimental hydrophobicity value, a relationship between the experimental hydrophobicity value, the experimental combustion time and the experimental surface average temperature is obtained;

[0058] The hydrophobicity value is calculated based on the combustion time, the average surface temperature and the relationship.

[0059] Specifically, the load insulator is tested at different burning times and different average surface temperatures in advance, and its flashover voltage is measured at different burning times and different average surface temperatures, and then the relationship between the hydrophobic value, burning time and average surface temperature can be obtained. Then, the hydrophobic value is obtained based on the burning time, average surface temperature and the above relationship obtained by the drone.

[0060] In this preferred embodiment, the hydrophobicity value of the composite insulator in the area to be tested is calculated based on the burning time and the average surface temperature of the composite insulator in the area to be tested.

[0061] Step S102: inputting the above-mentioned contamination parameters and model factors into a preset flashover voltage prediction model, so that the above-mentioned preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the above-mentioned test area according to the above-mentioned contamination parameters, model factors and the correction relationship corresponding to each contamination parameter;

[0062] The correction relation corresponding to each pollution parameter is constructed according to the correction coefficient corresponding to the pollution parameter of the composite insulator under different pollution tests.

[0063] Preferably, before the above-mentioned contamination parameters and model factors are input into the preset flashover voltage prediction model, the above-mentioned contamination parameters and model factors are first normalized.

[0064] Specifically, firstly, the DC 50% flashover voltage obtained under the specified conditions is calculated according to the model factor, salt density and the following formula:

[0065] U 50％ =a*SDD b

[0066] Where U 50％ It represents the DC 50% flashover voltage obtained under specified conditions. a represents the parameter determined by the above model factor, which is a constant. b represents the law that the flashover voltage decays with the increase of salt density. Both a and b can be obtained by fitting the flashover test results. SDD represents the salt density in mg / cm 2 .

[0067] Specifically, the flashover voltage is initially corrected based on the known ash density correction factor, i.e., the surface insoluble salt density correction factor, the upper and lower surface area pollution ratio correction factor, the altitude correction factor, the diameter correction factor, the multi-connection or multi-column correction factor, and the product of the DC 50% flashover voltage obtained under specified conditions:

[0068] U n =U 50％ *K N *K CUR *K H *K d *K s

[0069] Where U n Indicates the initial corrected flashover voltage, K N Indicates the gray density correction coefficient, K CUR Indicates the upper and lower surface area pollution ratio correction factor, K H Indicates the altitude correction factor, K d Indicates the diameter correction factor, K s Indicates the multi-connection or multi-column correction factor.

[0070] Specifically, according to each contamination parameter and the corresponding correction relationship, the correction coefficient corresponding to each contamination parameter is calculated, and the initially corrected flashover voltage is corrected according to these correction coefficients to obtain the final predicted flashover voltage:

[0071] U′ n=K1*K2*K3*K4*K5*K6*K7*U n

[0072] In the formula, U′ n represents the predicted flashover voltage, K1 represents the correction coefficient of salt density, K2 represents the correction coefficient of carbon particle size, K3 represents the correction coefficient of relative humidity, K4 represents the correction coefficient of ash density, K5 represents the correction coefficient of ash distribution area, K6 represents the correction coefficient of voltage type, and K7 represents the correction coefficient of hydrophobicity.

[0073] In a preferred embodiment, the training of the preset flashover voltage prediction model includes:

[0074] Obtaining several groups of samples and the actual flashover voltage corresponding to each group of samples; wherein the samples include: contamination parameter samples and model factor samples;

[0075] Inputting each group of samples and the corresponding actual flashover voltage into the flashover voltage prediction model to be trained, so that the flashover voltage prediction model calculates the first correction coefficient corresponding to each contamination parameter sample according to the contamination parameter sample and the corresponding correction relationship;

[0076] Calculate and obtain a first predicted flashover voltage according to each first correction coefficient and the above model factor sample;

[0077] Calculating a prediction error according to the first predicted flashover voltage and the actual flashover voltage;

[0078] If the prediction error is less than the preset error threshold, the training of the flashover voltage prediction model is completed; otherwise, after adjusting the parameters in the flashover voltage prediction model according to the prediction error, the training of the flashover voltage prediction model continues.

[0079] Specifically, the above-mentioned flashover voltage prediction model is constructed based on BP neural network. The structural schematic diagram of the flashover voltage prediction model is as follows: Figure 2 As shown in the figure, there are input layer, hidden layer and output layer in the model. Figure 2 The y1~y8 in the model are the outputs of the hidden layers corresponding to the smear parameters, and z represents the expected value of the flashover voltage, that is, the first predicted flashover voltage. During the initial training, the connection weights ω between the input layer and the hidden layer in the model are first calculated. ij , the connection weights between the hidden layer and the output layer ω jk Random initialization is performed, and the value range of the two connection weights is (-1, 1), an error function for calculating the above prediction error is selected, and the above preset error threshold is preset to ε.

[0080] Specifically, after each group of samples and the corresponding actual flashover voltage are input into the flashover voltage prediction model to be trained, the model will obtain the corresponding first predicted flashover voltage, and then calculate the prediction error according to the error function:

[0081]

[0082] Where E represents the prediction error, m represents the number of nodes in the hidden layer, T represents the total number of actual flashover voltages, M represents the total number of the first predicted flashover voltages, and z (k) represents the kth predicted flashover voltage, w (i) represents the i-th actual flashover voltage.

[0083] Specifically, when the prediction error is greater than the preset error threshold, the partial derivative δ of the neurons in the output layer is solved according to the prediction error. k (t), and then according to the connection weight between the hidden layer and the output layer, the partial derivative δ k (t), and prediction error, solve the partial derivative δ of the prediction error with respect to each neuron in the hidden layer j (t), and then using the partial derivative δ k (t) and the output of the hidden layer to the connection weight ω between the hidden layer and the output layer jk Make adjustments and use the partial derivative δ j (t) and the input of the input layer to the connection weight ω between the input layer and the hidden layer ij After the adjustment is completed, continue to train the model.

[0084] In this preferred embodiment, the flashover voltage prediction model is trained based on the samples and the corresponding actual flashover voltages.

[0085] In another preferred embodiment, when the above-mentioned contamination parameter is salt density or the above-mentioned carbon particle size, the construction of the correction relationship corresponding to the above-mentioned contamination parameter includes:

[0086] For each contamination parameter, obtaining a first flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes;

[0087] According to the first flashover voltage measurement value and the corresponding contamination parameter, the equivalent contamination degree corresponding to the contamination parameters of different sizes is calculated;

[0088] According to the above-mentioned contamination parameters and the corresponding equivalent degree of contamination, the correction coefficient of the contamination parameters is calculated;

[0089] The above-mentioned contamination parameters and the correction coefficients of the above-mentioned contamination parameters are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0090] Specifically, based on the artificial pollution test, by changing the pollution degree of the composite insulator, the pollution accumulation of the insulator after the wildfire in different pollution degree areas is simulated, and then the flashover voltage under different salt density and other conditions are the same is studied. According to the relationship between different salt density and flashover voltage and the pollution withstand voltage formula, the equivalent pollution degree at this time is inferred, and compared with the pollution degree, the correction coefficient of different salt density to the equivalent pollution degree is obtained, and the correction relationship between salt density and correction coefficient is obtained by fitting.

[0091] Specifically, based on the artificial pollution test, by changing the particle size of the smeared carbon particles, the pollution accumulation of composite insulators after the burning of different vegetation is simulated, and the insulation performance of the composite insulators after forest fires in different vegetation distribution areas is obtained. According to the relationship between different carbon particle sizes and the flashover voltage and the pollution withstand voltage formula, the equivalent pollution degree at this time is deduced and compared with the pollution degree. The correction coefficients of the equivalent pollution degree corresponding to different carbon particle sizes after the burning of different vegetation are obtained, and the correction relationship between different carbon particle sizes and the correction coefficients is obtained by fitting.

[0092] In this preferred embodiment, when the contamination parameter is the salt density or the carbon particle size mentioned above, a correction relationship is constructed based on the first flashover voltage measurement value and the corresponding contamination parameter.

[0093] In another preferred embodiment, when the above-mentioned smearing parameter is relative humidity, the above-mentioned ash density or the above-mentioned ash distribution area, the construction of the correction relationship corresponding to the above-mentioned smearing parameter includes:

[0094] For each contamination parameter, obtaining a second flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes;

[0095] According to the second flashover voltage measurement value and the corresponding contamination parameter, the equivalent salt density of the contamination parameters of different sizes is calculated;

[0096] According to the above-mentioned smearing parameters and the corresponding equivalent salt density, the correction coefficient of the smearing parameters is calculated;

[0097] The above-mentioned contamination parameters and the correction coefficients of the above-mentioned contamination parameters are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0098] Specifically, based on the artificial pollution test, an artificial fog chamber was used to control the relative humidity of the test environment, simulating the composite insulators under different relative humidity after a wildfire, and then studying the flashover voltage of the composite insulator. According to the relationship between different relative humidity and flashover voltage and the pollution withstand voltage formula, the equivalent salt density at this time was deduced, and the correction coefficients for different relative humidity were obtained. The correction relationship between relative humidity and correction coefficient was obtained by fitting.

[0099] Specifically, based on the artificial pollution test, carbon particles of different densities were applied to the composite insulators after pre-pollution to simulate the pollution accumulation of composite insulators under different ash densities after wildfire. According to the relationship between different ash densities and flashover voltage and the pollution withstand voltage formula, the equivalent salt density at this time was inferred and compared with the pre-coating pollution degree to obtain the correction coefficient under different ash densities, and the correction relationship between ash density and correction coefficient was obtained by fitting.

[0100] Specifically, based on the artificial pollution test, carbon particles with different distribution areas are applied to the composite insulators after pre-pollution. According to the relationship between different ash distribution areas and flashover voltage and the pollution withstand voltage formula, the equivalent salt density at this time is deduced and compared with the pre-coating contamination degree to obtain the correction coefficient under different ash distribution areas, and the correction relationship between the ash distribution area and the correction coefficient is obtained by fitting.

[0101] In this preferred embodiment, when the contamination parameter is relative humidity, ash density or ash distribution area, the equivalent salt density is calculated based on the measured second flashover voltage measurement value and the corresponding contamination parameter, and then the correction coefficient is obtained based on the contamination parameter and the corresponding equivalent salt density, and then the correction relationship is obtained.

[0102] In another preferred embodiment, when the above-mentioned smear parameter is the above-mentioned voltage type, the construction of the correction relationship corresponding to the above-mentioned smear parameter includes:

[0103] Obtaining the third flashover voltage measurement value of the composite insulator under different voltage types;

[0104] Calculate the correction coefficient of the voltage type according to the third flashover voltage measurement value;

[0105] According to the voltage types and the correction coefficients corresponding to the voltage types, the correction relationship corresponding to the contamination parameters is calculated.

[0106] Specifically, based on the artificial pollution test, in order to study the influence of AC and DC voltage on the surface flashover characteristics of composite insulators, AC and DC power supplies were used to apply pressure under the same conditions such as pre-coating pollution degree and ash density on the surface of the insulator. According to the relationship between different types of voltages and flashover voltages, based on the previous experiments, the correction coefficient between the flashover voltage under DC conditions and the flashover voltage under AC conditions was obtained, and then the corresponding correction relationship was obtained.

[0107] In this preferred embodiment, the third flashover voltage measurement value of the composite insulator under different voltage types is measured, and the correction coefficient is calculated based on the third flashover voltage value, and then the correction relationship is fitted according to the voltage type and the correction coefficient.

[0108] In another preferred embodiment, when the above-mentioned contamination parameter is the above-mentioned hydrophobic value, the construction of the correction relational expression corresponding to the above-mentioned contamination parameter includes:

[0109] Obtaining first hydrophobic values ​​of a composite insulator with a completely clean surface at different heating times and different heating temperatures, and fourth flashover voltage measurement values ​​corresponding to each first hydrophobic value;

[0110] Calculating each first hydrophobicity correction coefficient according to each first hydrophobicity value and the corresponding fourth flashover voltage measurement value;

[0111] The correction coefficients of the above-mentioned first hydrophobic values ​​and the corresponding first hydrophobic values ​​are fitted to obtain the correction relationship corresponding to the above-mentioned contamination parameters.

[0112] Specifically, based on the artificial smearing test, in order to study the influence of high temperature of wildfire on the hydrophobicity of composite insulators, the first hydrophobic value of the surface of the composite insulator was measured before and after high-temperature heating when the surface was completely clean. By changing the heating time and heating temperature, the change of the first hydrophobic value on the surface of the composite insulator after wildfire burning in different situations and the influence on the flashover voltage were simulated and photographed, and the correction coefficient of the first hydrophobic value for the flashover voltage was obtained. Then, according to the correction coefficient of the first hydrophobic value and the corresponding fitting result of the first hydrophobic value, the correction relationship of the hydrophobic value was obtained.

[0113] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0114] like Figure 3 As shown, an embodiment of the present invention provides a device for predicting the surface flashover voltage of a composite insulator after a wildfire, comprising:

[0115] Data acquisition module and flashover voltage prediction module;

[0116] The data acquisition module is used to obtain the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and average surface temperature of the composite insulators in the test area;

[0117] The above-mentioned flashover voltage prediction module is used to input the above-mentioned contamination parameters and model factors into a preset flashover voltage prediction model, so that the above-mentioned preset flashover voltage prediction model can calculate the predicted flashover voltage of the composite insulator in the above-mentioned test area according to the above-mentioned contamination parameters, model factors and the correction relationship corresponding to each contamination parameter; wherein the correction relationship corresponding to each contamination parameter is constructed according to the correction coefficient corresponding to the contamination parameter of the composite insulator under different contamination tests.

[0118] It should be noted that the device embodiments described above are merely schematic, wherein the modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without creative work. The above schematic diagram is only an example of a device for predicting the surface flashover voltage of a composite insulator after a wildfire, and does not constitute a limitation on a device for predicting the surface flashover voltage of a composite insulator after a wildfire, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0119] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.

[0120] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for predicting the surface flashover voltage of a composite insulator after a wildfire described in any embodiment of the present invention.

[0121] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more module elements may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the device;

[0122] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The device may include, but is not limited to, a processor, a memory;

[0123] The processor referred to herein may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), 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. The above-mentioned processor is the control center of the above-mentioned device, and uses various interfaces and lines to connect various parts of the entire device;

[0124] The above-mentioned memory can be used to store the above-mentioned computer programs and / or modules. The above-mentioned processor realizes various functions of the above-mentioned device by running or executing the computer programs and / or modules stored in the above-mentioned memory, and calling the data stored in the memory. The above-mentioned memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; in addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0125] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0126] Another embodiment of the present invention provides a storage medium, the storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the method for predicting the surface flashover voltage of a composite insulator after a wildfire described in any embodiment of the present invention.

[0127] In this embodiment, the storage medium is a computer-readable storage medium, the computer program includes computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0128] Compared with the prior art, by implementing the above embodiments of the present invention, on the basis of considering the salt density and ash density, the effect of the carbon particle size parameter on the predicted value of the final flashover voltage is also considered, so that the final calculation result is more accurate and in line with the actual situation.

[0129] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for predicting the surface flashover voltage of a composite insulator after a wildfire, characterized in that: include: Obtaining the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and average surface temperature of the composite insulators in the test area; Inputting the contamination parameters and model factors into a preset flashover voltage prediction model, so that the preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the test area according to the contamination parameters, model factors and the correction relationship corresponding to each contamination parameter; The correction relation corresponding to each pollution parameter is constructed according to the correction coefficient corresponding to the pollution parameter of the composite insulator under different pollution tests.

2. The method for predicting the surface flashover voltage of a composite insulator after a wildfire according to claim 1 is characterized in that: The hydrophobicity value is calculated based on the burning time and the average surface temperature of the composite insulator in the test area, including: The experimental hydrophobicity values ​​of composite insulators at different experimental burning times and experimental surface average temperatures were measured; According to the experimental combustion time, the experimental surface average temperature and the experimental hydrophobicity value, a relationship between the experimental hydrophobicity value, the experimental combustion time and the experimental surface average temperature is obtained; The hydrophobicity value is calculated according to the combustion time, the average surface temperature and the relationship.

3. The method for predicting the surface flashover voltage of composite insulators after wildfire according to claim 2 is characterized in that: The training of the preset flashover voltage prediction model includes: Acquire several groups of samples and the actual flashover voltage corresponding to each group of samples; wherein the samples include: smear parameter samples and model factor samples; Inputting each group of samples and the corresponding actual flashover voltage into the flashover voltage prediction model to be trained, so that the flashover voltage prediction model calculates a first correction coefficient corresponding to each contamination parameter sample according to the contamination parameter sample and the corresponding correction relationship; Calculating a first predicted flashover voltage according to each first correction coefficient and the model factor sample; Calculating a prediction error according to the first predicted flashover voltage and the actual flashover voltage; If the prediction error is less than the preset error threshold, the training of the flashover voltage prediction model is completed; otherwise, after adjusting the parameters in the flashover voltage prediction model according to the prediction error, the training of the flashover voltage prediction model continues.

4. The method for predicting the surface flashover voltage of a composite insulator after a wildfire according to claim 3 is characterized in that: When the contamination parameter is salt density or carbon particle size, the construction of the correction relationship corresponding to the contamination parameter includes: For each contamination parameter, obtaining a first flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes; According to the first flashover voltage measurement value and the corresponding contamination parameter, the equivalent contamination degree corresponding to the contamination parameters of different sizes is calculated; Calculate the correction coefficient of the contamination parameter according to the contamination parameter and the corresponding equivalent degree of contamination; The smear parameter and the correction coefficient of the smear parameter are fitted to obtain a correction relationship corresponding to the smear parameter.

5. The method for predicting the surface flashover voltage of composite insulators after wildfire according to claim 4 is characterized in that: When the smear parameter is relative humidity, the ash density or the ash distribution area, the construction of the correction relationship corresponding to the smear parameter includes: For each contamination parameter, obtaining a second flashover voltage measurement value of the composite insulator under contamination parameters of different magnitudes; According to the second flashover voltage measurement value and the corresponding contamination parameter, the equivalent salt density of the contamination parameters of different sizes is calculated; According to the smearing parameter and the corresponding equivalent salt density, a correction coefficient of the smearing parameter is calculated; The smear parameter and the correction coefficient of the smear parameter are fitted to obtain a correction relationship corresponding to the smear parameter.

6. The method for predicting the surface flashover voltage of composite insulators after wildfire according to claim 5 is characterized in that: When the smear parameter is the voltage type, the construction of the correction relationship corresponding to the smear parameter includes: Obtaining a third flashover voltage measurement value of the composite insulator under different voltage types; Calculating a correction coefficient for the voltage type according to the third flashover voltage measurement value; According to the voltage type and the correction coefficient corresponding to the voltage type, a correction relationship corresponding to the smear parameter is calculated.

7. The method for predicting the surface flashover voltage of composite insulators after wildfire according to claim 6 is characterized in that: When the contamination parameter is the hydrophobic value, the construction of the correction relationship corresponding to the contamination parameter includes: Obtaining first hydrophobic values ​​of a composite insulator with a completely clean surface at different heating times and different heating temperatures, and fourth flashover voltage measurement values ​​corresponding to each first hydrophobic value; Calculating each first hydrophobicity correction coefficient according to each first hydrophobicity value and the corresponding fourth flashover voltage measurement value; The correction coefficients of the first hydrophobic values ​​and the corresponding first hydrophobic values ​​are fitted to obtain a correction relationship corresponding to the contamination parameter.

8. A device for predicting the surface flashover voltage of composite insulators after wildfire, characterized in that: include: Data acquisition module and flashover voltage prediction module; The data acquisition module is used to obtain the contamination parameters and model factors of the composite insulators in the test area after the wildfire; wherein the contamination parameters include: salt density, carbon particle size, relative humidity, ash density, ash distribution area, voltage type and hydrophobicity, and the hydrophobicity is calculated according to the burning time and the average surface temperature of the composite insulators in the test area; The flashover voltage prediction module is used to input the contamination parameters and model factors into a preset flashover voltage prediction model, so that the preset flashover voltage prediction model calculates the predicted flashover voltage of the composite insulator in the test area according to the contamination parameters, model factors and the correction relationship corresponding to each contamination parameter; wherein the correction relationship corresponding to each contamination parameter is constructed according to the correction coefficient corresponding to the contamination parameter of the composite insulator under different contamination tests.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for predicting the surface flashover voltage of a composite insulator after a wildfire as claimed in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the method for predicting the surface flashover voltage of a composite insulator after a wildfire as described in any one of claims 1 to 7.

Images