A method, device, equipment and storage medium for predicting the pollution degree of insulators

Abstract

The present invention discloses a method, apparatus, device, and storage medium for predicting the degree of insulator contamination. The method comprises: obtaining environmental data and leakage current data for overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and leakage current third harmonic / fundamental wave; and inputting the environmental data and leakage current data into a preset insulator contamination degree prediction model to obtain the insulator contamination degree output by the insulator contamination degree prediction model. The present invention considers the effects of operating voltage, relative humidity, and equivalent salt density on insulator leakage current, thereby making the contamination degree of overhead line insulators in coastal salt fog areas predicted by the insulator contamination degree prediction model more accurate and effective.

Description

Technical Field

[0001] The present invention relates to the field of power protection technology, and in particular to a method, device, equipment and storage medium for predicting the pollution degree of an insulator. Background Art

[0002] In areas where transmission lines pass, contaminants such as industrial waste, salt spray from sea breezes, and airborne dust gradually accumulate and adhere to the surfaces of insulators, forming a contamination layer. This contaminant, containing acids, bases, and salts, has poor conductivity when dry, but exhibits a higher conductivity when wet. During adverse weather conditions such as rain, snowmelt, and fog, the dielectric strength of contaminated insulators is significantly reduced, causing insulator flashover at normal operating voltages and widespread power outages. This is known as a pollution flashover incident. Pollution flashover incidents have a significant impact on the safe operation of power systems and can easily cause widespread power outages. With the implementation of the "West-to-East Power Transmission, North-South Power Supply Interconnection, and National Interconnection" power development strategy and the construction of 1000kV UHV AC and ±800kV UHV DC transmission lines, my country's southern, northern, and central transmission corridors are experiencing severe pollution and the combined effects of rain and snow. As my country's power grid construction enters a new phase of development, it is imperative to ensure the stability of the power system under diverse climatic conditions. Harsh environmental conditions such as high altitude, severe cold, and severe air pollution pose new challenges to insulator reliability. Therefore, it is necessary to conduct a scientific and reasonable assessment of the insulator pollution level.

[0003] However, since the leakage current of contaminated insulators is the result of the combined effects of various environmental factors, there is currently no systematic theoretical and experimental research on the relationship between the leakage current of contaminated insulators and various influencing factors, and there is a lack of methods that can accurately and effectively predict the degree of insulator contamination. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, device, equipment and storage medium for predicting the pollution degree of insulators, which takes into account the influence of operating voltage, relative humidity and equivalent salt density on the insulator leakage current, so that the pollution degree of overhead line insulators in coastal salt fog areas predicted according to the insulator pollution degree prediction model is more accurate and effective.

[0005] To achieve the above objectives, an embodiment of the present invention provides a method for predicting the degree of insulator contamination, comprising: obtaining environmental data and leakage current data of overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and leakage current third harmonic / fundamental wave;

[0006] The environmental data and the leakage current data are input into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model.

[0007] As an improvement to the above solution, the training method of the insulator pollution degree prediction model includes:

[0008] Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data;

[0009] Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set;

[0010] A multi-layer pollution flashover index is constructed based on the hierarchical analysis method, a pollution flashover numerical model is determined, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model.

[0011] As an improvement to the above solution, the regression formula of the leakage current data specifically includes:

[0012]

[0013]

[0014]

[0015]

[0016] Among them, I m represents the leakage current amplitude, U represents the operating voltage, RH represents the relative humidity, and ρ represents the equivalent salt density. represents the leakage current phase, THD represents the maximum harmonic distortion of the leakage current, K represents the third harmonic / fundamental wave of the leakage current, and m, n, p, q, a1, a2, a3, a4, c1, b1, b2, and b3 are constants.

[0017] As an improvement to the above solution, the regression analysis is performed based on the regression data set and the regression formula, and the model verification is performed based on the verification data set, specifically including:

[0018] Collecting several sets of training data and dividing the training data into a regression data set and a validation data set according to a preset ratio;

[0019] Performing regression analysis based on the regression data set and the regression formula to calculate the leakage current amplitude, leakage current phase, maximum harmonic distortion of the leakage current, and third harmonic / fundamental wave of the leakage current;

[0020] The model is validated based on the validation dataset, and the calculated results are compared with the experimental results.

[0021] As an improvement to the above solution, the pollution flashover numerical model is specifically:

[0022]

[0023] As an improvement to the above solution, the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model, specifically including:

[0024] The thresholds of pollution flashover with different parameters are obtained, and the parameters in the pollution flashover numerical model are optimized according to the thresholds. The trained insulator pollution degree prediction model is obtained as follows:

[0025]

[0026] Among them, PFI represents the pollution level of the insulator.

[0027] An embodiment of the present invention further provides a device for predicting the degree of insulator pollution, comprising:

[0028] An acquisition module is configured to acquire environmental data and leakage current data of overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental wave of leakage current;

[0029] The prediction module is used to input the environmental data and the leakage current data into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model.

[0030] Furthermore, the training method of the insulator pollution degree prediction model includes:

[0031] Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data;

[0032] Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set;

[0033] A multi-layer pollution flashover index is constructed based on the hierarchical analysis method, a pollution flashover numerical model is determined, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model.

[0034] An embodiment of the present invention further provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any of the above-mentioned methods for predicting the degree of insulator pollution when executing the computer program.

[0035] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute any of the above-mentioned methods for predicting the degree of insulator pollution.

[0036] Compared to existing technologies, the beneficial effects of the insulator contamination degree prediction method, apparatus, device, and storage medium provided by embodiments of the present invention are as follows: Environmental data and leakage current data of overhead line insulators in coastal salt fog areas are obtained; the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental of leakage current; and the environmental data and leakage current data are input into a preset insulator contamination degree prediction model to obtain the insulator contamination degree output by the insulator contamination degree prediction model. The embodiments of the present invention take into account the effects of operating voltage, relative humidity, and equivalent salt density on insulator leakage current, thereby making the contamination degree of overhead line insulators in coastal salt fog areas predicted by the insulator contamination degree prediction model more accurate and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a preferred embodiment of a method for predicting the degree of insulator pollution provided by the present invention;

[0038] Figure 2 It is an equivalent circuit diagram when no partial discharge occurs in the insulator in the method for predicting the degree of insulator pollution provided by the present invention;

[0039] Figure 3 It is an equivalent circuit diagram when partial discharge occurs in an insulator in a method for predicting the degree of insulator pollution provided by the present invention;

[0040] Figure 4 This is a schematic diagram of pollution flashover indicators based on the analytic hierarchy process in a method for predicting the degree of insulator pollution provided by the present invention;

[0041] Figure 5 The leakage current amplitude (I m ) Schematic diagram comparing the experimental and regression results;

[0042] Figure 6 The present invention provides a method for predicting the degree of insulator pollution, wherein the leakage current phase Schematic diagram comparing the experimental and regression results;

[0043] Figure 7 This is a schematic diagram comparing the maximum harmonic distortion (THD) test and regression results of leakage current in a method for predicting the degree of insulator pollution provided by the present invention;

[0044] Figure 8 This is a schematic diagram comparing the leakage current third harmonic / fundamental wave (K) test and regression results in a method for predicting the insulator pollution degree provided by the present invention;

[0045] Figure 9 Schematic diagram of the relationship between PFI, relative humidity RH, and equivalent salt density ρ in a method for predicting the degree of insulator pollution provided by the present invention;

[0046] Figure 10 This is a structural schematic diagram of a preferred embodiment of a device for predicting the degree of insulator pollution provided by the present invention;

[0047] Figure 11 It is a structural diagram of a preferred embodiment of a terminal device provided by the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] See also Figure 1 , Figure 1 The figure is a flow chart of a preferred embodiment of a method for predicting the degree of insulator pollution provided by the present invention. The method for predicting the degree of insulator pollution includes:

[0050] S1, obtaining environmental data and leakage current data of overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental wave of leakage current;

[0051] S2, inputting the environmental data and the leakage current data into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model.

[0052] It should be noted that pollution flashover refers to the phenomenon of intense discharge under the action of an electric field, which occurs when contaminants attached to the insulating surface of electrical equipment gradually dissolve in water under humid conditions, forming a conductive film on the insulation surface. This significantly reduces the insulation level of the insulator. Flashover refers to the phenomenon of discharge along the surface of a solid insulator when the gas or liquid dielectric surrounding it breaks down. Based on a large number of artificial pollution tests, determining the correspondence between the leakage current of contaminated insulators and typical discharge phenomena, exploring the relationship between leakage current and various influencing factors, and establishing a flashover prediction model for contaminated insulators based on leakage current characteristics are of great academic significance and can provide a scientific basis for operation and maintenance in the power sector. Exploring the relationship between the leakage current of contaminated insulators and various influencing factors is also a process of in-depth and systematic research on the development of contaminated insulator discharge. Currently, there is no relatively systematic theoretical and experimental research on the relationship between leakage current and various influencing factors. Since the leakage current of contaminated insulators is the result of the combined effect of various environmental factors, the research on the contaminated insulator safety state prediction model and flashover judgment criteria based on the leakage current characteristic quantity is scientific and feasible. It is also one of the methods that has attracted more attention at present. It will also provide a certain reference for the scientific classification of the contamination level of operating lines.

[0053] Specifically, an embodiment of the present invention provides a method for predicting the degree of insulator contamination in coastal salt fog areas by obtaining environmental data and leakage current data for overhead line insulators in coastal salt fog areas. The environmental data includes humidity (U), relative humidity (RH), and equivalent salt density (ρ). The leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental of leakage current. For example, environmental factor data and leakage current data related to pollution flashover of overhead line insulators in coastal salt fog areas are investigated, collected, and organized. For example, an artificial pollution experiment is conducted to simulate the environment of coastal salt fog areas, and environmental factor data and leakage current data obtained from the experimental test results are obtained for the overhead line insulators set up. The environmental data and leakage current data are input into a preset insulator contamination degree prediction model to obtain the insulator contamination degree output by the insulator contamination degree prediction model.

[0054] When constructing the insulator pollution degree prediction model, this embodiment takes into account the influence of environmental factors such as operating voltage U, relative humidity RH, and equivalent salt density ρ on the insulator leakage current in coastal salt fog areas. This makes the pollution degree of overhead line insulators in coastal salt fog areas predicted by the insulator pollution degree prediction model more accurate and effective.

[0055] In another preferred embodiment, the training method of the insulator pollution degree prediction model includes:

[0056] Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data;

[0057] Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set;

[0058] A multi-layer pollution flashover index is constructed based on the hierarchical analysis method, a pollution flashover numerical model is determined, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model.

[0059] In another preferred embodiment, the regression formula of the leakage current data specifically includes:

[0060]

[0061]

[0062]

[0063]

[0064] Among them, I m represents the leakage current amplitude, U represents the operating voltage, RH represents the relative humidity, and ρ represents the equivalent salt density. represents the leakage current phase, THD represents the maximum harmonic distortion of the leakage current, K represents the third harmonic / fundamental wave of the leakage current, and m, n, p, q, a1, a2, a3, a4, c1, b1, b2, and b3 are constants.

[0065] Specifically, when training the insulator pollution degree prediction model, the embodiment of the present invention analyzes the insulator pollution flashover mechanism based on the partial discharge model and establishes a regression formula for leakage current data. For example, when the relative humidity of the coastal salt fog area is low, the pollution layer of the insulator is not moist enough. At this time, the conductivity of the pollution layer is very small, resulting in a very low leakage current. Since the conductive material dissolved on the surface is limited, the change of the equivalent salt density has little effect on the leakage current. At this time, there is basically no local arc generation. Therefore, the corresponding equivalent circuit model of the contaminated insulator is as follows: Figure 2 As shown, Figure 2 This is the equivalent circuit diagram of the insulator when no partial discharge occurs in the insulator in the method for predicting the degree of insulator pollution provided by the present invention. The average conductivity of the pollution layer is given by the formula Determine; where Y represents the equivalent conductance of the pollution layer, Rp represents the resistance of the pollution layer, and C represents the capacitance of the pollution layer. Meanwhile, the resistance of the pollution layer (Rp) is large, which means that the equivalent conductance of the pollution layer (Y = Rp - jωC) is small. Therefore, the capacitive current accounts for the majority, with a small amount of resistive current.

[0066] As relative humidity increases in coastal salt fog areas, the insulator's contamination layer gradually becomes moist. Moisture in the air causes some of the salt density on the insulator surface to exist as ions. Since the salt density in the contamination layer gradually ionizes with increasing humidity, leakage current also increases. While average conductivity increases, capacitance remains constant. Consequently, the corresponding change in current causes leakage current to gradually decrease.

[0067] When the relative humidity in coastal salt spray areas increases to a high level, the surface of the insulator will be fully wetted, and the leakage current will increase significantly, resulting in a Joule effect, forming a dry area, and partial arcing on the insulator surface. Therefore, the corresponding equivalent circuit model of the contaminated insulator is as follows: Figure 3 As shown, Figure 3 This is the equivalent circuit diagram of the insulator when partial discharge occurs in the method for predicting the degree of insulator pollution provided by the present invention. The average conductivity of the pollution layer is given by the formula Determine; where I represents the leakage current and U represents the operating voltage. At this point, the current waveform is distorted and no longer a regular sine wave. Simultaneously, due to the presence of partial arcing, the leakage current becomes negative. Furthermore, the more pronounced the partial arcing, the greater the leakage current, which lags behind the operating voltage.

[0068] Therefore, based on the above analysis, the leakage current amplitude (I m ), leakage current phase The regression formula for the maximum harmonic distortion (THD) of the leakage current and the third harmonic / fundamental wave (K) of the leakage current is as follows:

[0069]

[0070]

[0071]

[0072]

[0073] Among them, I m represents the leakage current amplitude, U represents the operating voltage, RH represents the relative humidity, and ρ represents the equivalent salt density. represents the leakage current phase, THD represents the maximum harmonic distortion of the leakage current, K represents the third harmonic / fundamental wave of the leakage current, and m, n, p, q, a1, a2, a3, a4, c1, b1, b2, and b3 are constants.

[0074] Regression analysis was performed based on the regression dataset and the aforementioned regression formula, and the model was validated using a validation dataset. A multi-layer pollution flashover index (PFI) was constructed using the analytic hierarchy process (AHP). A numerical model for the PFI pollution flashover was determined, and the parameters in the model were optimized to produce a trained insulator pollution level prediction model. The analytic hierarchy process (AHP) decomposes decision-making elements into a hierarchy of goals, criteria, and options, and then conducts qualitative and quantitative analysis based on these factors. This method, proposed by American operations researcher and professor at the University of Pittsburgh, Professor Satti in the early 1970s while researching the "power allocation based on the contribution of each industrial sector to national welfare" project for the US Department of Defense, employed network system theory and multi-objective comprehensive evaluation methods. Through regression analysis, the impact of environmental factors on leakage current parameters was clarified, thereby constructing the first-level influence relationship. Furthermore, based on the four leakage current parameters, a second-level evaluation indicator was constructed from the perspectives of the leakage current in both the time and frequency domains. It is worth noting that the PFI pollution flashover numerical model is an evaluation model that can be constructed as long as there is a correlation. It has strong subjective factors and users can adjust it according to actual needs. For example, the PFI index based on the hierarchical analysis method is constructed as follows: Figure 4 As shown, Figure 4 The present invention provides a method for predicting the degree of insulator pollution provided by the present invention. The present invention provides a schematic diagram of a pollution flashover index based on the analytic hierarchy process.

[0075] In another preferred embodiment, the performing of regression analysis based on the regression dataset and the regression formula, and performing model validation based on the validation dataset, specifically includes:

[0076] Collecting several sets of training data and dividing the training data into a regression data set and a validation data set according to a preset ratio;

[0077] Performing regression analysis based on the regression data set and the regression formula to calculate the leakage current amplitude, leakage current phase, maximum harmonic distortion of the leakage current, and third harmonic / fundamental wave of the leakage current;

[0078] The model is validated based on the validation dataset, and the calculated results are compared with the experimental results.

[0079] Specifically, when performing regression analysis based on the regression data set and the regression formula, and performing model verification based on the verification data set, the embodiment of the present invention first collects several groups of training data, and divides the training data into a regression data set and a verification data set according to a preset ratio. Then, regression analysis is performed based on the regression data set and the regression formula, and the leakage current amplitude, leakage current phase, leakage current maximum harmonic distortion, and leakage current third harmonic / fundamental wave are calculated. Finally, model verification is performed based on the verification data set, and the calculation results are compared with the experimental results for verification. Exemplarily, literature data can be used for regression analysis and model verification. For example, 120 groups of data are collected, of which 104 groups of data are used as regression data sets for regression analysis, and the remaining 16 groups of data are used as verification data sets for model verification. Four leakage current parameters are calculated by the regression formula, and the calculation results are compared with the experimental results for verification. The verification results are shown in FIG. Figures 5 to 8 supported by experimental data. Figure 5 The leakage current amplitude (I m ) Schematic diagram comparing the experimental and regression results; Figure 6 The present invention provides a method for predicting the degree of insulator pollution, wherein the leakage current phase Schematic diagram comparing the experimental and regression results; Figure 7 This is a schematic diagram comparing the maximum harmonic distortion (THD) test and regression results of leakage current in a method for predicting the degree of insulator pollution provided by the present invention; Figure 8 The present invention provides a schematic diagram of the comparison between the leakage current third harmonic / fundamental wave (K) test and regression results in a method for predicting the degree of insulator pollution.

[0080] In another preferred embodiment, the pollution flashover numerical model is specifically:

[0081]

[0082] In another preferred embodiment, the optimizing the parameters in the pollution flashover numerical model to obtain a trained insulator pollution degree prediction model specifically includes:

[0083] The thresholds of pollution flashover with different parameters are obtained, and the parameters in the pollution flashover numerical model are optimized according to the thresholds. The trained insulator pollution degree prediction model is obtained as follows:

[0084]

[0085] Among them, PFI represents the pollution level of insulators.

[0086] Specifically, during the investigation, it was found that the dangerous leakage current I mIt should be greater than 150mA. According to the test data, the leakage current when the pollution flashover is serious is inferred. The value is approximately -20°. It was also found that when THD exceeds 45%, arcing becomes dense on the insulator surface, making it easy for complete flashover to develop. When the K value approaches 0.4, insulator contamination is already severe. Based on the above investigation, the thresholds for flashover with different parameters were obtained. The parameters in the contamination flashover numerical model were optimized based on the thresholds, resulting in a trained insulator contamination degree prediction model:

[0087]

[0088] Among them, PFI represents the pollution level of the insulator.

[0089] The leakage current amplitude (I m ), leakage current phase The maximum harmonic distortion (THD) of the leakage current and the third harmonic / fundamental wave (K) of the leakage current can be used to output the pollution degree of the overhead line insulator in the coastal salt fog area through the PFI numerical model. The relationship diagram of PFI, relative humidity RH and equivalent salt density ρ is shown in the figure below. Figure 9 As shown, Figure 9 This is a schematic diagram of the relationship between PFI, relative humidity RH, and equivalent salt density ρ in a method for predicting the pollution degree of an insulator provided by the present invention.

[0090] For coastal salt fog areas, the embodiment of the present invention simultaneously considers the influence of environmental factors such as operating voltage U, relative humidity RH and equivalent salt density ρ on the insulator leakage current, converting the qualitative influence into quantitative influence, thereby making the pollution degree of overhead line insulators in coastal salt fog areas predicted by the insulator pollution degree prediction model more accurate and effective. m , leakage current phase Regression analysis of the time-domain and frequency-domain variations of four leakage current parameters, including the maximum harmonic distortion (THD) and the third harmonic / fundamental K, yielded robust regression results with correlation coefficients greater than 0.9. This improved the model's regression performance and facilitated subsequent accurate prediction of the degree of pollution on overhead line insulators in coastal salt fog areas. Based on a three-layer hierarchical analysis, the pollution flashover index (PFI) was introduced, and a severe pollution level criterion (PFI = 1, when the pollution level approaches pollution flashover) was calculated, facilitating a comprehensive assessment of the insulator pollution flashover level. This numerical model of pollution flashover levels provides a theoretical basis for evaluating the pollution flashover level of insulators on site.

[0091] Correspondingly, the present invention also provides a device for predicting the degree of insulator pollution, which can implement all the processes of the method for predicting the degree of insulator pollution in the above embodiment.

[0092] See also Figure 10 , Figure 10 1 is a schematic structural diagram of a preferred embodiment of a device for predicting the degree of insulator pollution provided by the present invention. The device for predicting the degree of insulator pollution comprises:

[0093] An acquisition module 101 is configured to acquire environmental data and leakage current data of overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental wave of leakage current;

[0094] The prediction module 102 is configured to input the environmental data and the leakage current data into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model.

[0095] Preferably, the training method of the insulator pollution degree prediction model includes:

[0096] Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data;

[0097] Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set;

[0098] A multi-layer pollution flashover index is constructed based on the hierarchical analysis method, a pollution flashover numerical model is determined, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model.

[0099] Preferably, the regression formula of the leakage current data specifically includes:

[0100]

[0101]

[0102]

[0103]

[0104] Among them, I m represents the leakage current amplitude, U represents the operating voltage, RH represents the relative humidity, and ρ represents the equivalent salt density. represents the leakage current phase, THD represents the maximum harmonic distortion of the leakage current, K represents the third harmonic / fundamental wave of the leakage current, and m, n, p, q, a1, a2, a3, a4, c1, b1, b2, and b3 are constants.

[0105] Preferably, the performing of regression analysis based on the regression data set and the regression formula, and performing of model validation based on the validation data set, specifically includes:

[0106] Collecting several sets of training data and dividing the training data into a regression data set and a validation data set according to a preset ratio;

[0107] Performing regression analysis based on the regression data set and the regression formula to calculate the leakage current amplitude, leakage current phase, maximum harmonic distortion of the leakage current, and third harmonic / fundamental wave of the leakage current;

[0108] The model is validated based on the validation dataset, and the calculated results are compared with the experimental results.

[0109] Preferably, the pollution flashover numerical model is specifically:

[0110]

[0111] Preferably, the optimizing of the parameters in the pollution flashover numerical model to obtain a trained insulator pollution degree prediction model specifically includes:

[0112] The thresholds of pollution flashover with different parameters are obtained, and the parameters in the pollution flashover numerical model are optimized according to the thresholds. The trained insulator pollution degree prediction model is obtained as follows:

[0113]

[0114] Among them, PFI represents the pollution level of insulators.

[0115] In specific implementation, the working principle, control process and technical effects achieved by the device for predicting the insulator pollution level provided by the embodiment of the present invention are the same as those of the method for predicting the insulator pollution level in the above embodiment, and will not be repeated here.

[0116] See also Figure 11 , Figure 11 1 is a schematic structural diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 1101, a memory 1102, and a computer program stored in the memory 1102 and configured to be executed by the processor 1101. When the processor 1101 executes the computer program, it implements the method for predicting the insulator pollution degree described in any of the above embodiments.

[0117] Preferably, the computer program can be divided into one or more modules / units (e.g., computer program 1, computer program 2, ...), which are stored in the memory 1102 and executed by the processor 1101 to implement the present invention. The one or more modules / units can be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0118] The processor 1101 can be a central processing unit (CPU), or 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 can be a microprocessor, or the processor 1101 can also be any conventional processor. The processor 1101 is the control center of the terminal device, and uses various interfaces and lines to connect the various parts of the terminal device.

[0119] The memory 1102 mainly includes a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function, and the data storage area can store related data. In addition, the memory 1102 can be a high-speed random access memory or a non-volatile memory, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, and a Flash Card. Alternatively, the memory 1102 can be other volatile solid-state memory devices.

[0120] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 11 The structural diagram is only an example of the above-mentioned terminal device and does not constitute a limitation on the above-mentioned terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components.

[0121] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for predicting the insulator pollution degree described in any of the above embodiments.

[0122] Embodiments of the present invention provide a method, apparatus, device, and storage medium for predicting the degree of insulator contamination. These methods obtain environmental data and leakage current data for overhead line insulators in coastal salt fog areas. The environmental data includes operating voltage, relative humidity, and equivalent salt density. The leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion, and third harmonic / fundamental harmonic of the leakage current. These environmental data and leakage current data are then input into a pre-set insulator contamination degree prediction model to obtain the insulator contamination degree output by the insulator contamination degree prediction model. This embodiment of the present invention considers the effects of operating voltage, relative humidity, and equivalent salt density on insulator leakage current, thereby making the contamination degree of overhead line insulators in coastal salt fog areas predicted by the insulator contamination degree prediction model more accurate and effective.

[0123] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across 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 drawings of the system embodiment 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 the present invention without inventive work.

[0124] 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 principles 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 degree of insulator pollution, characterized in that: include: Obtaining environmental data and leakage current data for overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental wave of leakage current; Inputting the environmental data and the leakage current data into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model; The training method of the insulator pollution degree prediction model includes: Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data; Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set; Based on the hierarchical analysis method, a multi-layer pollution flashover index is constructed to determine the pollution flashover numerical model, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model; The regression formula of the leakage current data specifically includes: ； ； ； ； The step of optimizing the parameters in the pollution flashover numerical model to obtain a trained insulator pollution degree prediction model specifically includes: The thresholds of pollution flashover with different parameters are obtained, and the parameters in the pollution flashover numerical model are optimized according to the thresholds. The trained insulator pollution degree prediction model is obtained as follows: ； in, I m represents the leakage current amplitude, U Indicates the operating voltage, RH Relative humidity, ρ Indicates equivalent salt density, represents the leakage current phase, THD Indicates the maximum harmonic distortion of leakage current, K Indicates the leakage current third harmonic / fundamental wave, m 、 n 、 p 、 q 、 a 1. a 2. a 3. a 4. c 1. b 1. b 2. b 3 represents a constant, PFI Indicates the degree of insulator pollution.

2. The method for predicting the degree of insulator pollution according to claim 1, wherein: The regression analysis is performed based on the regression data set and the regression formula, and the model verification is performed based on the verification data set, specifically including: Collecting several sets of training data and dividing the training data into a regression data set and a validation data set according to a preset ratio; Performing regression analysis based on the regression data set and the regression formula to calculate the leakage current amplitude, leakage current phase, maximum harmonic distortion of the leakage current, and third harmonic / fundamental wave of the leakage current; The model is validated based on the validation dataset, and the calculated results are compared with the experimental results.

3. The method for predicting the degree of insulator pollution according to claim 2, wherein: The pollution flashover numerical model is specifically: 。 4. A device for predicting the degree of insulator pollution, used to implement the method for predicting the degree of insulator pollution according to any one of claims 1 to 3, characterized in that: include: An acquisition module is configured to acquire environmental data and leakage current data of overhead line insulators in coastal salt fog areas; wherein the environmental data includes operating voltage, relative humidity, and equivalent salt density; and the leakage current data includes leakage current amplitude, leakage current phase, maximum harmonic distortion of leakage current, and third harmonic / fundamental wave of leakage current; The prediction module is used to input the environmental data and the leakage current data into a preset insulator pollution degree prediction model to obtain the insulator pollution degree output by the insulator pollution degree prediction model.

5. The device for predicting the degree of insulator pollution according to claim 4, wherein: The training method of the insulator pollution degree prediction model includes: Analyze the mechanism of insulator flashover based on the partial discharge model and establish a regression formula for the leakage current data; Performing regression analysis based on the regression data set and the regression formula, and performing model validation based on the validation data set; A multi-layer pollution flashover index is constructed based on the hierarchical analysis method, a pollution flashover numerical model is determined, and the parameters in the pollution flashover numerical model are optimized to obtain a trained insulator pollution degree prediction model.

6. A terminal device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory and configured to be executed by the processor, and wherein the method for predicting the insulator pollution degree according to any one of claims 1 to 3 is implemented when the processor executes the computer program.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for predicting the insulator pollution degree according to any one of claims 1 to 3 is implemented.

Images