Lightning arrester temperature compensation method and system based on DSA-CTCM network

Abstract

The invention discloses a lightning arrester temperature compensation method based on a DSA-CTCM network. The lightning arrester temperature compensation method comprises the following steps: acquiring historical environment data of a lightning arrester; performing data preprocessing on the historical environment data of the lightning arrester; the method comprises the following steps: constructing and training to obtain a temperature compensation model through historical environment data after data preprocessing based on a dual-stage self-attention and MambaNet time sequence convolutional network; inputting real-time environment data of the lightning arrester into the temperature compensation model to obtain predicted temperature data, and calculating a temperature deviation value between the real-time temperature data and the predicted temperature data; a dynamic feedback mechanism is established, a compensation coefficient of the temperature compensation model is dynamically generated according to the temperature deviation value, the compensation coefficient is fed back to the temperature compensation model so as to adjust parameters of the temperature compensation model, and performance evaluation is conducted on the temperature compensation model; according to the lightning arrester temperature compensation method based on the construction of the DSA-CTCM network, environmental data of different time steps can be accurately identified and weighted, and the accuracy of temperature compensation is improved.

Description

Technical Field

[0001] This invention relates to the field of surge arrester testing technology, and in particular to a surge arrester temperature compensation method and system based on a DSA-CTCM network. Background Art

[0002] In the operation and maintenance of power systems, the health status of substation equipment is crucial. With increasing power load, the demand for monitoring substation equipment is growing. Infrared thermography, due to its non-contact and rapid measurement characteristics, has become a common method for monitoring the thermal condition of substation equipment. This technology analyzes the infrared radiation on the equipment surface to detect temperature distribution, thereby assessing whether the equipment has faults. However, infrared thermography mainly relies on manual inspection, using handheld infrared imagers to capture two-dimensional infrared images for fault diagnosis. This method suffers from problems such as missed detections, strong subjective judgment, and time lag, especially in complex environments, such as substations with complex structures and equipment blocking each other, leading to unsatisfactory infrared detection results. Furthermore, environmental factors such as climate and light radiation can also affect the accuracy of infrared thermography; therefore, effective real-time compensation measures are needed to ensure the accuracy of temperature detection.

[0003] As a critical protection device in power systems, surge arresters are significantly affected by temperature changes. During long-term operation and in harsh environments, temperature variations can increase leakage current, and prolonged high temperatures can accelerate the degradation of zinc oxide materials, impacting the arrester's electrical characteristics and lifespan. Although the internal temperature of a surge arrester is closely related to its electrical performance, current temperature monitoring methods largely rely on localized contact temperature sensors, which cannot comprehensively reflect the internal temperature distribution. Furthermore, the installation of these sensors may affect the structural integrity of the arrester, increasing maintenance difficulty. Moreover, existing temperature compensation methods are relatively simple, typically based on temperature feedback control systems, lacking a comprehensive response to complex temperature fields and struggling to adapt to rapid changes in ambient temperature. These limitations are particularly pronounced under complex meteorological conditions and strong electromagnetic environments, severely affecting the accuracy of infrared thermography in substation equipment, and consequently impacting the reliability and lifespan of surge arresters. Summary of the Invention

[0004] In response to the above-mentioned problems in the prior art, the purpose of the present invention is to provide a lightning arrester temperature compensation method and system based on the DSA-CTCM network. By constructing a lightning arrester temperature compensation model based on the DSA-CTCM network, the accurate value of the lightning arrester temperature after temperature compensation is obtained, and through dynamic correction and real-time feedback mechanism, it is ensured that the temperature compensation model can provide high-precision temperature compensation results when the external environment changes rapidly.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a surge arrester temperature compensation method based on a DSA-CTCM network, comprising:

[0007] S1: Obtain historical environmental data of the surge arrester;

[0008] The environmental data includes the temperature data of the surge arrester and the climate data of the environment in which the surge arrester is located;

[0009] S2: Perform data preprocessing on the historical environmental data of the surge arrester;

[0010] S3: A temperature compensation model is constructed and trained based on a temporal convolutional network combining two-stage self-attention and MambaNet, using preprocessed historical environmental data.

[0011] S4: Obtain the real-time environmental data of the surge arrester, input the real-time environmental data into the temperature compensation model to obtain the predicted temperature data, and calculate the temperature deviation value between the real-time temperature data and the predicted temperature data.

[0012] S5: Establish a dynamic feedback mechanism to dynamically generate compensation coefficients for the temperature compensation model based on the temperature deviation value, feed the compensation coefficients back to the temperature compensation model to adjust the parameters of the temperature compensation model, and evaluate the performance of the temperature compensation model.

[0013] Optionally, S2 includes the following specific steps:

[0014] S201: Acquire historical environmental data of the arrester and synchronize the historical environmental data;

[0015] The data synchronization is to add a timestamp to each historical environmental data record and align the historical environmental data at different times;

[0016] S202: performing data cleaning processing on the historical environmental data;

[0017] S203: Smooth the historical environmental data based on the Kalman filter algorithm;

[0018] S204: Extract the mean and standard deviation of the historical environmental data, and normalize the historical environmental data;

[0019] S205: Perform Z-Score standardization on the historical environmental data.

[0020] Optionally, the Kalman filter algorithm in S203 includes a prediction process and an update process;

[0021] The functional expression for the prediction process is:

[0022]

[0023]

[0024] Where, Let be the system state vector at time k. Let k be the system state vector at time k-1; is the state transfer matrix; is the control matrix; For control input; for The transpose of the matrix, and They are state vectors and The uncertainty covariance matrix, Here is the noise covariance matrix;

[0025] The function expression for the update process is:

[0026]

[0027]

[0028]

[0029] Where, is the Kalman gain, is the forecast error covariance, is a column vector of prior estimates, for The transpose of the matrix, is the sensor noise covariance matrix; is the best estimate for this forecast update, These are the observations from the system's sensors; This is the optimal covariance matrix after the prediction update;

[0030] The function expression for the normalization process in S204 is:

[0031]

[0032] In the formula, x' represents the normalized historical environmental data; x represents the historical environmental data; min(x) represents the minimum value of the historical environmental data; and max(x) represents the maximum value of the historical environmental data.

[0033] The Z-Score normalized function expression in S205 is as follows:

[0034]

[0035] In the formula, X represents standardized historical environmental data; μ represents the mean of historical environmental data; and σ represents the standard deviation of historical environmental data.

[0036] Optionally, step S3 includes the following specific steps:

[0037] S301: Establishing an environmental data set based on the historical environmental data after data preprocessing; the environmental data set includes a training set and a test set;

[0038] S302: A temperature compensation model for a surge arrester is constructed based on a temporal convolutional network combining two-stage self-attention and MambaNet; the temperature compensation model includes an encoder, a Mamba module, and a decoder.

[0039] S303: Input the training set data into the encoder, extract the feature sequence of the input data based on the encoder, calculate the importance weight of the feature sequence to generate a weighted hidden state, and send the encoded hidden state to the Mamba module.

[0040] S304: Based on the Mamba module, the encoder output is integrated, the dimensions are transformed and key time series information is dynamically selected to enhance the model's time series modeling capability and generate appropriate feature sequences to be sent to the decoder.

[0041] S305: The decoder decodes the hidden state using classification information and adaptively selects the importance weight of the hidden state to generate a new hidden state. It then combines the new hidden state with the feature sequence output by the Mamba module to calculate the temperature-compensated predicted temperature data.

[0042] S306: Calculate the temperature difference between historical temperature data and its corresponding predicted temperature data, and adjust the parameters of the temperature compensation model based on the temperature difference, and continuously iterate the training.

[0043] S307: When the number of training iterations of the temperature compensation model reaches the preset number of tests, the performance of the temperature compensation model is tested based on the test set; if the model performance is qualified, the training of the temperature compensation model is completed; if the model performance is unqualified, step S308 is executed.

[0044] S308: Determine whether the number of iterations has reached the preset number of iterations. If yes, complete the training of the temperature compensation model; otherwise, return to step S303.

[0045] Optionally, step S4 includes the following specific steps:

[0046] S401: Obtain real-time environmental data of the surge arrester;

[0047] S402: Inputting the real-time environmental data into the trained temperature compensation model to obtain predicted temperature data;

[0048] The formula for calculating the predicted temperature data is:

[0049]

[0050] Where, To predict temperature data, For real-time climate data, Historical temperature data;

[0051] S403: Calculating the temperature deviation between the real-time temperature data and the predicted temperature data;

[0052] The formula for calculating the temperature deviation value is:

[0053]

[0054] Where, b represents the real-time temperature data, and b represents the temperature deviation value.

[0055] Optionally, step S5 includes the following specific steps:

[0056] S501: Establish a dynamic feedback mechanism; the dynamic feedback mechanism includes a dynamic correction algorithm and a real-time feedback mechanism; S502: Based on a preset abnormal deviation threshold, determine whether the temperature deviation value is greater than the abnormal deviation threshold; if so, record the temperature deviation value and execute step S503; otherwise, output the predicted temperature data.

[0057] S503: Based on the dynamic correction algorithm, dynamically generate an adjustment coefficient of the temperature compensation model according to the temperature deviation value;

[0058] S504: Generates feedback signals based on temperature deviation values ​​and climate data;

[0059] S505: Based on the real-time feedback mechanism, adjust the temperature compensation model parameters according to the adjustment coefficient and feedback signal;

[0060] S506: Based on the temperature deviation values ​​recorded in step 502, generate a deviation dataset and calculate the mean and variance of the deviation dataset to evaluate the performance of the temperature compensation model and ensure the continuous optimization and normal operation of the model.

[0061] Optionally, the function expression of the dynamic correction algorithm in S503 is:

[0062]

[0063] Where, is the new compensation coefficient, The old compensation coefficient, To adjust the rate;

[0064] The functional expression of the feedback signal is:

[0065]

[0066] Where, As a feedback signal, For deviation weights, Weighting of climate data changes The amount of change in climate data;

[0067] The function expression for the real-time feedback mechanism is:

[0068]

[0069] Where, This is the adjusted compensation coefficient. For feedback adjustment coefficients;

[0070] The mean and variance of the deviation data set are calculated as follows:

[0071]

[0072]

[0073] Where, The mean of the deviation, For the deviation variance, is the temperature deviation value in the deviation data set, and N is the number of samples in the deviation data set.

[0074] Optionally, the encoder includes a convolutional neural network layer, an input multi-head self-attention layer, and a temporal convolutional network layer connected in sequence;

[0075] The Mamba module includes a splicing layer, a flattening layer, a linear mapping layer, a selective state space model layer, and a one-dimensional convolutional layer connected in sequence.

[0076] The encoder comprises a temporal multi-head self-attention layer and a temporal convolutional network layer connected in sequence.

[0077] Optionally, the process of cleaning the historical environmental data in step S202 includes one or more of the following:

[0078] Check the integrity and consistency of historical environmental data, remove noise, fill in missing data, and delete invalid data.

[0079] Secondly, embodiments of the present invention provide a surge arrester temperature compensation method based on a DSA-CTCM network, comprising:

[0080] The data acquisition module is used to acquire historical environmental data of the surge arrester;

[0081] The environmental data includes the temperature data of the surge arrester and the climate data of the environment in which the surge arrester is located;

[0082] The data preprocessing module is used to preprocess the historical environmental data of the surge arrester;

[0083] The model building module is used to build and train a temperature compensation model based on a temporal convolutional network combining two-stage self-attention and MambaNet, using preprocessed historical environmental data.

[0084] a deviation calculation module for obtaining real-time environmental data of the arrester, inputting the real-time environmental data into a temperature compensation model to obtain predicted temperature data, and calculating a temperature deviation value between the real-time temperature data and the predicted temperature data;

[0085] The dynamic correction module is used to establish a dynamic feedback mechanism, dynamically generate a compensation coefficient of the temperature compensation model according to the temperature deviation value, feed the compensation coefficient back to the temperature compensation model to adjust the temperature compensation model parameters, and perform performance evaluation on the temperature compensation model.

[0086] The beneficial effects of the embodiments provided by the present invention include:

[0087] By integrating a temporal convolutional network with a two-stage self-attention mechanism, the present invention significantly improves the temporal data processing capability and feature attention accuracy of the temperature compensation model. It can effectively capture long-term dependencies in environmental data to accurately identify and weight environmental data at different time steps, thereby increasing the model's sensitivity to time series changes and improving the accuracy of temperature compensation.

[0088] By integrating a temporal convolutional network with a two-stage self-attention mechanism, the present invention enables the temperature compensation model to learn on different time scales, adapt to temperature change patterns in different time periods, and improve the temperature prediction accuracy of the model.

[0089] By combining convolutional neural networks and selective state-space models, the present invention significantly enhances the feature extraction capability of the temperature compensation model, effectively extracting spatial and local features from environmental data, and helping the model perform temperature compensation more accurately.

[0090] This invention establishes a dynamic feedback mechanism to ensure that the temperature compensation model can still provide high-precision temperature compensation results even when the external environment of the surge arrester changes rapidly. Attached Figure Description

[0091] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0092] Figure 1 A flowchart of a surge arrester temperature compensation method based on a DSA-CTCM network according to an embodiment of this specification is shown;

[0093] Figure 2 A schematic diagram of the structure of a surge arrester according to an embodiment of this specification is shown;

[0094] Figure 3 A schematic diagram of the framework of the temperature compensation model according to an embodiment of this specification is shown;

[0095] Figure 4 A block diagram of a surge arrester temperature compensation system based on a DSA-CTCM network according to an embodiment of this specification is shown. Detailed Implementation

[0096] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0097] However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0098] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The term "comprising" used herein indicates the presence of features, steps, operations, but does not exclude the presence or addition of one or more other features. It should be noted that all terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used here should be interpreted as having meanings consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0099] Example 1

[0100] Figure 1 A flowchart of a surge arrester temperature compensation method based on a DSA-CTCM network according to an embodiment of this specification is shown;

[0101] like Figure 1 As shown, this embodiment provides a surge arrester temperature compensation method based on a DSA-CTCM network, including:

[0102] S1: Obtain historical environmental data of the surge arrester;

[0103] For example, environmental data includes the temperature data of the surge arrester and the climate data of the environment in which the surge arrester is located;

[0104] The climate data includes environmental factors that affect infrared thermometry, such as wind speed, humidity, and solar radiation.

[0105] Figure 2 A schematic diagram of the surge arrester according to an embodiment of this specification is shown; wherein, (a) is a cross-sectional view of a single-section surge arrester; and (b) is a front view of a single-section surge arrester.

[0106] like Figure 2 As shown, in some embodiments, this embodiment uses high-precision temperature sensors and environmental sensors, and arranges them reasonably on the porcelain sleeve of the surge arrester according to the structure and environment of the surge arrester, which can ensure that the monitoring area fully covers the surge arrester, so as to collect temperature data of the surge arrester surface and climate data of the environment where the surge arrester is located at regular intervals.

[0107] S2: Perform data preprocessing on the historical environmental data of the surge arrester;

[0108] For example, S2 includes the following specific steps:

[0109] S201: Acquire historical environmental data of the arrester and synchronize the historical environmental data;

[0110] Data synchronization involves adding a timestamp to each historical environmental data record and aligning historical environmental data from different times in time.

[0111] S202: performing data cleaning processing on the historical environmental data;

[0112] In some embodiments, the data cleaning process includes one or more of the following: checking the integrity and consistency of historical environmental data, removing noise, filling in missing data, and deleting invalid data.

[0113] Specifically, the historical environmental data obtained in this embodiment may contain noise and outliers. The data is cleaned using the Z-score method. The Z-score of each environmental data point is calculated. If the Z-score exceeds the threshold, it is marked as an outlier and deleted.

[0114] Specifically, the historical environmental data obtained in this embodiment may contain missing values, which are filled in by linear interpolation.

[0115] S203: Smooth the historical environmental data based on the Kalman filter algorithm;

[0116] In some embodiments, this embodiment uses the Kalman filter algorithm to smooth environmental data, which can remove random fluctuations and improve data availability; wherein, based on the prediction and update processes in the Kalman filter algorithm, the results of measurement and prediction can be combined to obtain more accurate prediction results.

[0117] Specifically, the functional expression for the prediction process is:

[0118]

[0119] In the formula,

[0120] Specifically, the function expression for the update process is:

[0121]

[0122]

[0123] In the formula, is the Kalman gain, For the prediction error covariance;

[0124] S204: Extract the mean and standard deviation of the historical environmental data, and normalize the historical environmental data;

[0125] In this embodiment, historical environmental data is normalized to adjust environmental data acquired by different sensors to the same scale, thereby facilitating subsequent processing.

[0126] Specifically, the function expression for normalization is:

[0127]

[0128] In the formula, x' represents the normalized historical environmental data; x represents the historical environmental data; min(x) represents the minimum value of the historical environmental data; and max(x) represents the maximum value of the historical environmental data.

[0129] S205: Perform Z-Score standardization on the historical environmental data.

[0130] Specifically, the Z-Score standardized function expression is:

[0131]

[0132] In the formula, X represents standardized historical environmental data; μ represents the mean of historical environmental data; and σ represents the standard deviation of historical environmental data.

[0133] S3: A temperature compensation model is constructed and trained based on a temporal convolutional network combining two-stage self-attention and MambaNet, using preprocessed historical environmental data.

[0134] Figure 3 A schematic diagram of the framework of the temperature compensation model according to an embodiment of this specification is shown;

[0135] like Figure 3 As shown, for example, S3 includes the following specific steps:

[0136] S301: Establish an environmental dataset based on preprocessed historical environmental data;

[0137] In some embodiments, the environmental dataset is divided into a training set and a test set in a ratio of 7:3;

[0138] The dataset includes multiple samples and a label for each sample. The sample is the actual climate data of each arrester temperature compensation point at each historical moment in the historical time period, and the label is the actual measured temperature of each temperature compensation point.

[0139] S302: A lightning arrester temperature compensation model is constructed based on a temporal convolutional network combining two-stage self-attention and MambaNet.

[0140] In this embodiment, the DSA-CTCM network refers to a temporal convolutional network based on dual-stage self-attention combined with MambaNet.

[0141] In some embodiments, the surge arrester temperature compensation model based on the DSA-CTCM network adopts an encoder-MambaNet-decoder structure. Considering that surge arrester temperature compensation has the characteristics of strong coupling and large hysteresis, the temperature compensation model sets the input to the real environmental data of k temperature measuring points from time T to time T+t, and sets the output to the compensated temperature data of the k temperature measuring points at time T+t.

[0142] Specifically, the encoder includes a convolutional neural network (CNN) layer, an input multi-head self-attention layer, and a temporal convolutional network (TCN) layer connected in sequence.

[0143] Specifically, the Mamba module consists of a concatenated layer (Concat), a flattened layer (Flatten), a linear mapping layer (Linear), a selective state space model layer (Selective SSM), and a one-dimensional convolutional layer (Conv1d) connected in sequence.

[0144] Specifically, the encoder consists of a multi-head self-attention layer and a temporal convolutional network layer connected in sequence;

[0145] S303: After inputting the training set data into the encoder, the feature sequence of the input data is extracted through the convolutional neural network layer. The importance weight of the feature sequence is calculated using the input multi-head self-attention layer, and the feature sequence is weighted and summed to generate the hidden state. The hidden state is encoded based on the temporal convolutional network layer and then sent to the Mamba module.

[0146] S304: Based on the Mamba module, the encoder output is integrated through splicing and flattening layers, and dimensional transformation is performed. The encoded information is passed through the Linear layer, Selective SSM layer, Conv1d layer and Linear layer respectively to dynamically select time series information and enhance the ability to model time series. Finally, the two are multiplied and input into the decoder.

[0147] Specifically, the encoder extracts features from the input environmental data, extracting the spatial and preliminary temporal relationships between different temperature measurement points. The Mamba model receives the encoder output and integrates features from different time steps using the Concat and Flatten layers. It also performs dimensionality transformation, flattening the multidimensional features output by the encoder into a single dimension and concatenating features from different time steps. This allows these feature representations to be processed uniformly, enabling more efficient feature calculation and temporal information extraction.

[0148] The Linear layer then further adjusts the feature dimensions to make the data structure more suitable for subsequent time series modeling operations. The Selective State-Space Model (SSM) module can be seen as a dynamic time series information extraction mechanism. By selectively modeling features at different time steps, it can flexibly adjust the focus on specific time steps according to the temporal changes of the input data, extracting the most representative time series features. In addition, the Conv1d layer captures the relationships between local time steps. This combination allows the Mamba model to not only identify global time series patterns but also extract key local time series features. Furthermore, the Selective State-Space Model and the Conv1d layer enhance the model's understanding of time series data. This enhancement is manifested in the model's ability to capture long-term and short-term dependencies in the input data and find a balance between global and local time series patterns, thereby generating more effective time series feature representations.

[0149] Finally, after the Mamba module performs timing modeling and feature extraction, the generated feature sequence contains the integrated timing information and dynamic features of key time steps, which is convenient for further processing by the decoder.

[0150] S305: The decoder decodes the hidden state through classification information and adaptively selects the importance weight of the hidden state through temporal multi-head self-attention to generate a new hidden state. It combines the new hidden state with the feature sequence output by the Mamba module and finally calculates the temperature-compensated predicted temperature data through a temporal convolutional network layer.

[0151] S306: Calculate the temperature difference between historical temperature data and its corresponding predicted temperature data, and adjust the parameters of the temperature compensation model based on the temperature difference, and continuously iterate the training.

[0152] S307: When the number of training iterations of the temperature compensation model reaches the preset number of tests, the performance of the temperature compensation model is tested based on the test set; if the model performance is qualified, the training of the temperature compensation model is completed; if the model performance is unqualified, step S308 is executed; wherein, the preset number of tests is 100 and the preset number of tests is always less than the preset number of iterations.

[0153] Specifically, the temperature compensation model is tested every 100 iterations. After the test set is input into the model, the temperature difference between the historical temperature data and the corresponding predicted temperature data is calculated. It is then determined whether the temperature difference is less than the preset temperature difference accuracy. If it is, the temperature compensation model passes the test and its temperature compensation effect is good; otherwise, the temperature compensation model fails the test.

[0154] S308: Determine whether the number of iterations has reached the preset number of iterations. If yes, complete the training of the temperature compensation model; otherwise, return to step S303.

[0155] In some embodiments, the model iteration training cutoff condition in S308 further includes determining whether the temperature difference between historical temperature data and its corresponding predicted temperature data reaches a preset compensation accuracy.

[0156] S4: Obtain the real-time environmental data of the surge arrester, input the real-time environmental data into the temperature compensation model to obtain the predicted temperature data, and calculate the temperature deviation value between the real-time temperature data and the predicted temperature data.

[0157] For example, S4 includes the following specific steps:

[0158] S401: Obtain real-time environmental data of the surge arrester;

[0159] S402: Inputting the real-time environmental data into the trained temperature compensation model to obtain predicted temperature data;

[0160] The formula for calculating the predicted temperature data is:

[0161]

[0162] Where, To predict temperature data, For real-time climate data, Historical temperature data;

[0163] S403: Calculating the temperature deviation between the real-time temperature data and the predicted temperature data;

[0164] The formula for calculating the temperature deviation value is:

[0165]

[0166] Where, b represents the real-time temperature data, and b represents the temperature deviation value.

[0167] S5: Establish a dynamic correction and real-time feedback mechanism, dynamically generate an adjustment coefficient of the temperature compensation model according to the temperature deviation value, feed the adjustment coefficient back to the temperature compensation model to adjust the temperature compensation model parameters, and perform a performance evaluation on the temperature compensation model.

[0168] For example, S5 includes the following specific steps:

[0169] S501: Establish a dynamic feedback mechanism; the dynamic correction and real-time feedback mechanism includes a dynamic correction algorithm and a real-time feedback mechanism;

[0170] S502: Based on the preset abnormal deviation threshold, determine whether the temperature deviation value is greater than the abnormal deviation threshold; if so, record the temperature deviation value and execute step S503; otherwise, output the predicted temperature data.

[0171] S503: Based on the dynamic correction algorithm, dynamically generate an adjustment coefficient of the temperature compensation model according to the temperature deviation value;

[0172] S504: Generates feedback signals based on temperature deviation values ​​and climate data;

[0173] S505: Based on the real-time feedback mechanism, adjust the temperature compensation model parameters according to the adjustment coefficient and feedback signal;

[0174] S506: Based on the temperature deviation values ​​recorded in step 502, generate a deviation dataset and calculate the mean and variance of the deviation dataset to evaluate the performance of the temperature compensation model and ensure the continuous optimization and normal operation of the model.

[0175] Specifically, the function expression of the dynamic correction algorithm in S503 is:

[0176]

[0177] Where, is the new compensation coefficient, The old compensation coefficient, To adjust the rate;

[0178] The functional expression for the feedback signal is:

[0179]

[0180] Where, As a feedback signal, For deviation weights, Weighting of climate data changes The amount of change in climate data;

[0181] The function expression for the real-time feedback mechanism is as follows:

[0182]

[0183] Where, This is the adjusted compensation coefficient. For feedback adjustment coefficients;

[0184] The mean and variance of the bias dataset are calculated as follows:

[0185]

[0186]

[0187] In the formula, The mean of the deviation. For the deviation variance, denoted as , where is the temperature deviation value in the deviation dataset, and N is the number of samples in the deviation dataset.

[0188] In this embodiment, a dataset is constructed by acquiring real environmental data of the surge arrester. The training data in the dataset is used to iteratively train the deep learning-based nonlinear temperature compensation model. An independent test set is used to test the performance of the trained temperature compensation model in order to evaluate the compensation effect of the model. In addition, this embodiment also establishes a dynamic feedback mechanism to ensure that the temperature compensation model can still provide high-precision temperature compensation results even when the external environment of the surge arrester changes rapidly.

[0189] Example 2

[0190] Figure 4 A structural block diagram of a surge arrester temperature compensation system based on a DSA-CTCM network according to an embodiment of this specification is shown.

[0191] like Figure 4 As shown, this embodiment provides a surge arrester temperature compensation system 100 based on a DSA-CTCM network, including:

[0192] Data acquisition module 101 is used to acquire historical environmental data of the surge arrester;

[0193] The environmental data includes the temperature data of the surge arrester and the climate data of the environment in which the surge arrester is located;

[0194] The data preprocessing module 102 is used to preprocess the historical environmental data of the surge arrester;

[0195] The model building module 103 is used to build and train a temperature compensation model based on a temporal convolutional network combining two-stage self-attention and MambaNet, using preprocessed historical environmental data.

[0196] The deviation calculation module 104 is used to obtain real-time environmental data of the surge arrester, input the real-time environmental data into the temperature compensation model to obtain predicted temperature data, and calculate the temperature deviation value between the real-time temperature data and the predicted temperature data.

[0197] The dynamic correction module 105 is used to establish a dynamic feedback mechanism, dynamically generate the compensation coefficient of the temperature compensation model based on the temperature deviation value, feed the compensation coefficient back to the temperature compensation model to adjust the parameters of the temperature compensation model, and evaluate the performance of the temperature compensation model.

[0198] Example 3

[0199] This embodiment provides an electronic device, including at least one control processor and a memory for communicatively connecting to the at least one control processor;

[0200] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0201] The non-transient software program and instructions required to implement the surge arrester temperature compensation method based on a DSA-CTCM network in the above embodiments are stored in memory. When executed by the processor, the surge arrester temperature compensation method based on a DSA-CTCM network in the above embodiments is executed. For example, the above-described surge arrester temperature compensation method is executed. Figure 1 The method steps S1 to S5.

[0202] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Example 4

[0204] This embodiment provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a surge arrester temperature compensation method based on a DSA-CTCM network as described in Embodiment 1.

[0205] It should be noted that the computer-readable storage medium in this embodiment can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0206] In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this embodiment, the computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0207] The computer-readable storage medium described above can be used to write computer programs for executing this embodiment in one or more programming languages ​​or combinations thereof. These programming languages ​​include object-oriented programming languages ​​such as Python, Java, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0208] In summary, this embodiment can effectively capture long-term dependencies in environmental data through the time series convolutional network, which is crucial for analyzing temperature changes with time series characteristics. It significantly improves the model's ability to process time series data of temperature measurement data and improves the accuracy and reliability of temperature compensation.

[0209] This embodiment introduces a two-stage self-attention mechanism, enhancing the model's ability to focus on important features in the input data. This allows the model to flexibly identify and weight temperature data at different time steps, thereby improving its sensitivity to time series changes and further enhancing the temperature compensation effect. Simultaneously, the combination of temporal convolutional networks and the self-attention mechanism enables the model to learn at multiple time scales, allowing it to adapt to temperature change patterns across different time periods, improving prediction accuracy, and making temperature compensation more flexible and accurate.

[0210] This embodiment effectively improves the feature extraction capability of the temperature compensation model by combining the convolutional neural network and the selective state space model, so that the temperature compensation model can more accurately extract the spatial and local features in the temperature data, providing strong support for more accurate temperature compensation.

[0211] This embodiment enhances the flexibility of the model structure through the design of the Concat layer, the Flatten layer, and the linear layer, so that the DSA-CTCM network can be adjusted according to the characteristics of the actual data, optimizing the model performance to adapt to different temperature compensation scenarios.

[0212] This embodiment improves the generalization ability of the model through the application of the self-attention mechanism, so that the model can better understand and remember important patterns in the input data, reduce the risk of overfitting, improve the generalization ability of the model on new data, and ensure the stability and effectiveness of the temperature compensation model in different environments and conditions.

[0213] The above description is merely a preferred embodiment of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects. The scope of the present invention is defined by the appended claims rather than the foregoing description, and thus all variations falling within the meaning and scope of the equivalents of the claims are intended to be included within the present invention.

Claims

1. A lightning arrester temperature compensation method based on DSA-CTCM network, characterized in that: include: S1: Obtain historical environmental data of lightning arrester; The environmental data include temperature data of the arrester and climate data of the environment in which the arrester is located; S2: preprocess the historical environmental data of the arrester; S3: Based on the dual-stage self-attention combined with the temporal convolutional network of MambaNet, the temperature compensation model is constructed and trained through the historical environmental data after data preprocessing; S4: acquiring real-time environmental data of the arrester, inputting the real-time environmental data into a temperature compensation model to acquire predicted temperature data, and calculating a temperature deviation value between the real-time temperature data and the predicted temperature data; S5: Establish a dynamic feedback mechanism to dynamically generate a compensation coefficient of the temperature compensation model according to the temperature deviation value, feed back the compensation coefficient to the temperature compensation model to adjust the temperature compensation model parameters, and perform a performance evaluation on the temperature compensation model.

2. The method according to claim 1, characterized in that The S2 comprises the following specific steps: S201: Acquire historical environmental data of the arrester and synchronize the historical environmental data; The data synchronization is to add a timestamp to each historical environmental data record and to time-align the historical environmental data at different times; S202: performing data cleaning processing on the historical environment data; S203: Smoothing the historical environmental data based on a Kalman filter algorithm; S204: extracting the mean and standard deviation of the historical environmental data, and performing normalization processing on the historical environmental data; S205: Perform Z-Score standardization processing on the historical environmental data.

3. The method according to claim 2, characterized in that: The Kalman filter algorithm in S203 includes a prediction process and an update process; The functional expression of the prediction process is: ； ； In the formula, is the system state vector at time k, is the system state vector at time k-1; is the state transfer matrix; is the control matrix; is the control input; for The transposed matrix of and The state vectors are and The uncertainty covariance matrix of is the noise covariance matrix; The function expression of the update process is: ； ； ； In the formula, is the Kalman gain, is the forecast error covariance, is a column vector of prior estimates, for The transposed matrix of is the sensor noise covariance matrix; is the best estimate for this forecast update, is the system sensor observation value; is the optimal covariance matrix after updating for this prediction; The function expression of the normalization process in S204 is: ； In the formula, x' is the normalized historical environmental data; x is the historical environmental data; min(x) is the minimum value of the historical environmental data, and max(x) is the maximum value of the historical environmental data; The function expression of Z-Score standardization in S205 is: ； Where X is the standardized historical environmental data; μ is the mean of the historical environmental data, and σ is the standard deviation of the historical environmental data.

4. The method according to claim 1, characterized in that The S3 comprises the following specific steps: S301: Establishing an environmental data set based on the historical environmental data after data preprocessing; the environmental data set includes a training set and a test set; S302: Construct a lightning arrester temperature compensation model based on a dual-stage self-attention combined with MambaNet temporal convolutional network; The temperature compensation model includes an encoder, a Mamba module and a decoder; S303: Input the data in the training set to the encoder, extract the feature sequence of the input data based on the encoder, calculate the importance weight of the feature sequence to generate a weighted hidden state, and encode the hidden state and send it to the Mamba module; S304: Integrate the encoder output based on the Mamba module, transform the dimension and dynamically select key timing information to enhance the time series modeling capability of the model, and generate a suitable feature sequence to send to the decoder; S305: The decoder decodes the hidden state through the classification information, and adaptively selects the importance weight of the hidden state to generate a new hidden state, combines it with the feature sequence output by the Mamba module, and calculates the predicted temperature data after temperature compensation; S306: Calculate the temperature difference between the historical temperature data and the corresponding predicted temperature data, and adjust the parameters of the temperature compensation model based on the temperature difference, and continue iterative training; S307: When the number of training iterations of the temperature compensation model reaches the preset number of test times, a performance test is performed on the temperature compensation model based on the test set; if the model performance is qualified, the training of the temperature compensation model is completed; if the model performance is unqualified, step S308 is executed; S308: Determine whether the number of iterations reaches a preset number of iterations. If so, complete the training of the temperature compensation model; otherwise, return to step S303.

5. The method according to claim 1, characterized in that The S4 comprises the following specific steps: S401: Acquire real-time environmental data of the arrester; S402: Inputting the real-time environmental data into the trained temperature compensation model to obtain predicted temperature data; The calculation formula for the predicted temperature data is: ； In the formula, To predict temperature data, For real-time climate data, is the historical temperature data; S403: Calculating a temperature deviation value between the real-time temperature data and the predicted temperature data; The calculation formula of the temperature deviation value is: ； In the formula, is the real-time temperature data, and b is the temperature deviation value.

6. The method according to claim 1, characterized in that The S5 comprises the following specific steps: S501: Establishing a dynamic feedback mechanism; the dynamic feedback mechanism includes a dynamic correction algorithm and a real-time feedback mechanism; S502: Based on a preset abnormal deviation threshold, determine whether the temperature deviation value is greater than the abnormal deviation threshold; if so, record the temperature deviation value and execute step S503; otherwise, output the predicted temperature data; S503: Based on a dynamic correction algorithm, dynamically generate an adjustment coefficient of a temperature compensation model according to the temperature deviation value; S504: generating a feedback signal according to the temperature deviation value and the climate data; S505: Based on the real-time feedback mechanism, adjusting the temperature compensation model parameters according to the adjustment coefficient and the feedback signal; S506: Generate a deviation data set according to the temperature deviation value recorded in step 502, and calculate the mean and variance of the deviation data set to evaluate the performance of the temperature compensation model to ensure continuous optimization and normal operation of the model.

7. The method according to claim 6, characterized in that: The function expression of the dynamic correction algorithm in S503 is: ； In the formula, is the new compensation coefficient, is the old compensation coefficient, To adjust the rate; The function expression of the feedback signal is: ； In the formula, is the feedback signal, is the bias weight, is the change weight of climate data, is the change in climate data; The function expression of the real-time feedback mechanism is: ； In the formula, is the adjusted compensation coefficient, is the feedback adjustment coefficient; The mean and variance of the calculated deviation data set are as follows: ； ； In the formula, is the mean deviation, is the deviation variance, is the temperature deviation value in the deviation data set, and N is the number of samples in the deviation data set.

8. The method according to claim 4, characterized in that The encoder includes a convolutional neural network layer, an input multi-head self-attention layer, and a temporal convolutional network layer connected in sequence; The Mamba module includes a concatenation layer, a flattening layer, a linear mapping layer, a selective state space model layer and a one-dimensional convolution layer connected in sequence; The encoder includes a temporal multi-head self-attention layer and a temporal convolutional network layer connected in sequence.

9. The method according to claim 2, characterized in that: The process of performing data cleaning on the historical environment data in step S202 includes one or more of the following: Check the integrity and consistency of historical environmental data, remove noise, fill in missing data, and delete invalid data.

10. A lightning arrester temperature compensation method based on DSA-CTCM network, characterized in that: include: A data acquisition module is used to obtain historical environmental data of the lightning arrester; The environmental data include temperature data of the arrester and climate data of the environment in which the arrester is located; A data preprocessing module is used to preprocess the historical environmental data of the arrester; The model building module is used to build and train a temperature compensation model based on the temporal convolutional network of dual-stage self-attention combined with MambaNet through historical environmental data after data preprocessing; A deviation calculation module, used to obtain real-time environmental data of the arrester, input the real-time environmental data into a temperature compensation model to obtain predicted temperature data, and calculate a temperature deviation value between the real-time temperature data and the predicted temperature data; The dynamic correction module is used to establish a dynamic feedback mechanism, dynamically generate a compensation coefficient of the temperature compensation model according to the temperature deviation value, feed back the compensation coefficient to the temperature compensation model to adjust the temperature compensation model parameters, and perform performance evaluation on the temperature compensation model.

Images