A method for icing warning of transmission lines

Abstract

The present invention provides a method for warning of icing on transmission lines. The method includes: obtaining historical tension data and historical micro-meteorological data of the transmission line, screening out non-icing tension data from the historical tension data, screening out several strongly correlated factors that cause changes in the tension of the transmission line from the historical micro-meteorological data, using the non-icing tension data and the strongly correlated factors to fit and create a tension correction model, substituting the non-icing tension data into the tension correction model to obtain a tension reference value, substituting the real-time tension data into the tension correction model to obtain a tension correction value, and performing icing warning based on the tension reference value and the tension correction value. The icing warning method for transmission lines of the present invention calculates the tension reference value according to changes in environmental factors, so as to obtain the tension when the transmission line is at the icing critical point, which not only improves the accuracy of line icing detection, but also enables the icing warning to respond more quickly and timely.

Description

Technical Field

[0001] The present invention belongs to the technical field of power transmission, and particularly relates to a method for warning of icing on transmission lines. Background Art

[0002] Under the action of meteorological and geographical conditions, icing phenomena such as glaze ice or rime ice may form on the surface of overhead transmission conductors. When icing occurs, the fault risk of the line increases significantly, which may lead to accidents such as insulator flashover, line tripping, wire breakage, tower collapse, conductor galloping, and communication interruption, thus bringing huge economic losses and serious social impacts. In order to improve the safety and reliability of overhead transmission lines, power grid companies everywhere usually monitor the icing conditions of the lines in real time through icing monitoring systems, and issue icing warning signals according to preset reference values, so as to timely grasp the icing state of the lines.

[0003] However, the current reference value of icing tension is usually set based on the average tension during the ice-free period. When the tension exceeds this reference value, it is considered that the line is iced, and the part exceeding the reference value is the ice load. However, in actual monitoring, in addition to the self-weight of the conductor and the weight of the ice, external factors such as internal tension fluctuations caused by temperature changes and wind pressure will also affect the conductor tension. If these changing factors are not considered, it may lead to false icing warnings even when there is no icing or the icing amount does not reach the warning standard, but the line tension increases to a certain extent. Especially during the icing period, false warnings will result in waste of manpower and time, and delay the investigation of potential hazards of truly iced lines.

[0004] In addition, most of the existing methods for setting the reference value of icing tension according to meteorological conditions directly set fixed reference meteorological factors for icing tension calculation, and then establish a prediction model based on historical data and these reference meteorological factors. Due to different environments in different regions, the fixed reference meteorological factors cannot widely adapt to the complex meteorological conditions in various regions. In some regions, the influence of a certain meteorological condition on the reference value of icing tension is small, but in another region, this meteorological condition is quite different from other regions and may instead become an important influencing factor for the reference value of icing tension.

[0005] Therefore, it is necessary to provide a method for warning of icing on transmission lines to improve the accuracy of icing monitoring, reduce the waste of manpower and material resources caused by false warnings, and at the same time improve the response speed of icing warnings to ensure the safer and more stable operation of the power system. Summary of the Invention

[0006] One of the purposes of the present invention is to at least solve one or more of the above problems in the prior art. In other words, one of the purposes of the present invention is to provide a method for warning of icing on transmission lines that meets one or more of the foregoing requirements.

[0007] To achieve the above-mentioned invention objectives, the present invention adopts the following technical solutions:

[0008] In the first aspect, the present invention provides a method for icing warning of a transmission line, and the method includes:

[0009] S1. Obtain the historical tensile force data and historical micro-meteorological data of the transmission line;

[0010] S2. Screen out the non-icing tensile force data from the historical tensile force data, and eliminate the icing tensile force data and abnormal tensile force data;

[0011] S3. Screen out several strongly correlated factors that cause changes in the tensile force of the transmission line from the historical micro-meteorological data;

[0012] S4. Perform multiple linear regression fitting on the non-icing tensile force data and the strongly correlated factors to create a tensile force correction model, and the tensile force correction model is used to normalize the influence of the strongly correlated factors on the tensile force of the transmission line;

[0013] S5. Substitute the non-icing tensile force data and the historical micro-meteorological data into the tensile force correction model to obtain a tensile force reference value;

[0014] S6. Collect real-time tensile force data and real-time micro-meteorological data, and substitute the real-time tensile force data and the real-time micro-meteorological data into the tensile force correction model to obtain a tensile force correction value;

[0015] S7. Perform icing warning according to the tensile force reference value and the tensile force correction value.

[0016] As a preferred implementation manner, performing icing warning according to the tensile force reference value and the tensile force correction value includes:

[0017] Calculate the tensile force increase amount according to the tensile force reference value and the tensile force correction value, and perform icing warning according to the tensile force increase amount.

[0018] As a further preferred implementation manner, perform icing warnings of different levels according to the magnitude of the tensile force increase amount.

[0019] As a preferred implementation manner, in step S2, the following method is used to determine whether each item of micro-meteorological data is a strongly correlated factor of the tensile force data;

[0020] Use the Pearson correlation coefficient method to detect the linear correlation between each item of micro-meteorological data and the tensile force data to determine whether it is a strongly correlated factor;

[0021] Use the Spearman rank correlation coefficient to detect each item of micro-meteorological data that does not conform to the normal distribution or has a non-linear relationship to determine whether it is a strongly correlated factor;

[0022] Use grey relational analysis to detect each item of micro-meteorological data to determine whether it is a strongly correlated factor.

[0023] As a preferred embodiment, step S2 screens out normal tension data and icing tension data from the tension data through the K-shape clustering algorithm, and eliminates abnormal tension data, including:

[0024] S21. Perform standardization processing on the historical tension data using z-standardization;

[0025] S22. Determine the number of clusters K;

[0026] S23. Use the K-shape algorithm to conduct comparative analysis on different time period lengths;

[0027] S24. Compare the trends of the output visual clustering results with each group of data, and divide each group of data into the clusters they belong to;

[0028] S25. Retain the non-icing tension data cluster, and eliminate the icing tension data cluster and abnormal tension data cluster.

[0029] As a preferred embodiment, step S4 includes:

[0030] S41. Import the non-icing tension data and strongly correlated factors into the multiple linear regression model;

[0031] S42. Calculate the regression coefficients of each independent variable in the multiple linear regression model;

[0032] S43. Generate a tension correction model based on the regression coefficients.

[0033] As a preferred embodiment, the micro-meteorological data at least includes air temperature, humidity, air pressure, maximum wind speed, average wind speed, standard wind speed, maximum wind speed wind deflection angle, skew angle, wind direction, and precipitation.

[0034] As a preferred embodiment, before step S2 and after step S1, there is also step S11 of preprocessing the historical tension data and historical micro-meteorological data.

[0035] As a further preferred embodiment, the preprocessing includes: duplicate data deletion, blank data interpolation, and isolated outlier elimination.

[0036] As a preferred embodiment, it further includes:

[0037] S8. Verify the accuracy of the tension correction model through the historical tension data.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] The ice coating warning method for transmission lines of the present invention calculates and fits through linear regression analysis, normalizes and adjusts the influence of micro-meteorological factors on the conductor tension. Both the reference tension value calculated using historical data and the corrected tension value calculated using real-time data contain the influence of the same micro-meteorological factors, making the difference between them only depend on the influence of the ice coating gravity on the tension of the transmission line. Thus, false alarms caused by factors such as wind and temperature increasing the line tension are avoided, the accuracy of line ice coating detection is improved, and the problem of insufficient accuracy faced when detecting the ice coating condition of transmission lines in the prior art is solved. At the same time, the ice coating warning method for transmission lines of the present invention is optimized for data anomalies and missing data. By adding links to process data anomalies and missing data, the problem of inaccurate warning criteria caused by data anomalies is overcome, the warning accuracy of the model is effectively improved, and thus the practicability of the method is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The figure shows the flowchart of the ice coating warning method for transmission lines in an embodiment of the present application;

[0041] Figure 2 The figure shows the flowchart of executing the K-shape clustering algorithm;

[0042] Figure 3 The figure shows the classification diagram of tension data;

[0043] Figure 4 The figure shows the schematic diagram of the influence relationship between the tension of the transmission line and micro-meteorological factors;

[0044] Figure 5 The figure shows the flowchart of judging the ice coating on the transmission line;

[0045] Figure 6 The figure shows the tension data of the experimental line after pretreatment;

[0046] Figure 7 The figure shows the corrected tension data of the experimental line. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0048] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes can be made to the functions and arrangements of the described elements without departing from the scope of the content of the present application. Each example can appropriately omit, substitute, or add various processes or components. For example, the described method can be executed in a different order from the described order, and various steps can be added, omitted, or combined. In addition, the features described in some examples can be combined into other examples.

[0049] The embodiment of the present invention provides a transmission line icing early warning method, the flow chart of which is as follows: Figure 1 As shown, the method comprises the following steps:

[0050] Step S1: Collect historical tension data and historical micro-meteorological data of local power transmission lines. These data are the tension data of power transmission lines and micro-meteorological data corresponding to time and location collected by tension sensors and monitoring equipment. They can be obtained and organized into data sets through historical data saved by local meteorological or power grid units. The organized data sets include ice tension data of transmission lines under different environmental conditions and corresponding time and location marking information.

[0051] In one embodiment of the present application, step S1 further includes step S11 , pre-processing the historical tension data and the historical micro-meteorological data.

[0052] Preprocessing includes deleting duplicate data, using linear interpolation to fill missing values ​​for blank values, and removing isolated outliers in normal waveforms. After preprocessing the original data, the new data set obtained has improved data quality, removed noise, missing values ​​and outliers in the data, corrected potential data errors, deleted unreasonable values, and avoided the accuracy of the calculation model due to erroneous data when the calculation model was generated later, thus improving the credibility of the analysis results.

[0053] Step S2: The tension data of the transmission line during the period without ice cover are screened out by the K-shape clustering algorithm, and the tension data during the period of ice cover and abnormal tension data are eliminated. The K-shape clustering algorithm is a shape-based time series clustering method, which is used to classify similar time series into the same category. The basic idea is to achieve clustering by automatically preprocessing and transforming the time series, and then using the shape-based distance (SBD) to calculate the similarity between time series. Through the clustering algorithm, the distinguishing features between the data can be extracted, so as to identify whether a certain historical tension data was collected when the transmission line was covered with ice.

[0054] The flowchart for executing the K-shape clustering algorithm is as follows Figure 2 As shown, the specific steps are as follows:

[0055] S21. Use z-standardization to standardize the historical tension data.

[0056] First, calculate the mean of each time series and standard deviation , the calculation formula is as follows:

[0057]

[0058]

[0059] wherein is the length of the time series, is the tensile force data at the -th time point.

[0060] Then, each time series is z-normalized, and the calculation formula is as follows:

[0061]

[0062] wherein is the tensile force data at the -th time point after z-normalization; furthermore, it ensures that the contribution of each dimension to the distance calculation is equal, avoiding the influence of different numerical ranges on the distance metric.

[0063] S22. Determine the number of clusters K. Determine the value of K according to the change of the tensile force of the transmission line icing according to manual experience. Take K = 6, that is, divide the tensile force data into 6 categories, as Figure 3 shown, represented by K1 - K6 respectively. The specific descriptions of K1 - K6 are as follows. K1: No data or significantly fewer data points. K2: Rapid periodic changes. K3: Frequent rapid mutations in the waveform. K4: No change in data for a long time. K5: Slow rise and fall of data. K6: Small fluctuations in data.

[0064] S23. Use the K-shape algorithm to conduct a comparative analysis on different time period lengths.

[0065] First, select the time period length to segment the data and form a time series input data set:

[0066]

[0067] wherein is a set of time series composed of , represents the tensile force data at the -th moment, and so on for other groups. After data segmentation, the number of groups is ,

[0068] being the total number of data. and the index sequence , shift the sample time window appropriately to globally align it with for global shape feature comparison of the two sequences. The formula is as follows:

[0069]

[0070] In the formula, is the time series after the time window is shifted. is all possible shift amounts of the time window, where . If , then the time window of is shifted to the right by units; if , then the time window of

[0071] is shifted to the left by units. Thus, the cross-correlation sequence

[0072]

[0073] of length is obtained and defined as follows: The calculation of

[0074]

[0075] The goal of the above calculation is to find the position of such that the cross-correlation sequence is maximized. In this way, relative to , the optimal displacement of is

[0076]

[0077] Then, normalization is performed to eliminate the inherent distortion so that its fluctuation range is between -1 and 1. Among them, the larger the cross-correlation sequence coefficient value, the higher the positive correlation degree of the two sequences. The specific calculation is as follows: is the cross-correlation coefficient value corresponding to the case where the completely similar time series does not have a relative displacement.

[0078] Then, the time series similarity judgment distance measure is calculated, and its normalized calculation formula is as follows:

[0079]

[0080] In the formula: The distance value representing the similarity between two time series ranges from 0 to 2, where 0 represents that the time series samples are completely similar. For each time series, find the corresponding minimum value in the distance value, find the time series closest to the cluster center, and assign the time series to the cluster corresponding to the minimum distance;

[0081] Then calculate the average shape of all members of each cluster, calculate the average value of all cluster members at each time point, and get a time series of average shape. The calculated average shape is used as the updated cluster center of all time series in the cluster. There are k clusters of time series, each with a length of m. For each time point t, calculate the value of the average shape as follows:

[0082]

[0083] In the formula, Indicates The cluster members at time The value at

[0084] Finally, the distance between each time series and the new cluster center is recalculated, and the time series is reallocated to the nearest cluster according to the minimum distance; the cluster center is updated again; step S23 is repeated, and the iteration is performed until the convergence condition is met, that is, the cluster center no longer changes or the predetermined number of iterations is reached;

[0085] S24, comparing the output visual clustering results with the trends of each group of data, and dividing each group of data into its corresponding cluster.

[0086] S25, retaining the non-icing tension data cluster, and eliminating the ice-covered tension data cluster and the abnormal tension data cluster. Specifically, K1-K4 are abnormal tension data, K5 is ice-covered tension data, and K6 is non-icing tension data.

[0087] Existing methods rely on collected data to evaluate the icing condition of transmission lines, but do not consider the anomalies and missing data collected. The online monitoring system of transmission lines is affected by events such as strong winds, ice shedding, and uncertain factors such as sunshine fluctuations and sensor failures. The monitoring data will have singular points, outliers, noise and data missing, which directly affect the accuracy of the pre-set reference meteorological factors and the prediction results of the model. The above steps remove abnormal data through a clustering algorithm, and divide normal data into tension data in the icing state and tension data in the non-icing state, so that the tension data in the non-icing state is used alone for linear regression analysis in the subsequent steps.

[0088] Step S3: Select several strongly correlated factors that cause changes in the tension of local transmission lines from historical micro-meteorological data. The strongly correlated factors can be obtained by using the correlation analysis method to analyze the micro-meteorological data based on the tension data, and finding the data items with strong correlation with the tension data from among the numerous data items in the micro-meteorological data, and then selecting these data items as the strongly correlated factors affecting the tension data.

[0089] Specifically, in step S3, the Pearson correlation coefficient method, the Spearman rank correlation coefficient detection method, and the grey relational analysis method are used to determine whether each item of micro-meteorological data is a strongly correlated factor of the tension data.

[0090] Among them, the Pearson correlation coefficient is used to measure the correlation (linear correlation) between two variables X and Y, and its value ranges from -1 to 1. The Pearson correlation coefficient between two variables is defined as the quotient of the covariance and the standard deviation between the two variables. The formula defines the population correlation coefficient, and the commonly used Greek lowercase letter ρ is used as the representative symbol. The calculation formula is as follows:

[0091]

[0092] In the formula, and are the expectations of the random variables X and Y respectively, and are their standard deviations respectively, is their covariance.

[0093] The value range of the Pearson correlation coefficient is between -1 and 1. The closer the value is to 1 or -1, the stronger the linear correlation, and 0 indicates no correlation.

[0094] If the historical tension data and the micro-meteorological data do not conform to the normal distribution or there is a non-linear relationship, the Spearman rank correlation coefficient can be used. Pearson correlation is a statistical measure of the strength of the linear relationship between two random variables, while Spearman correlation examines the strength of the monotonic relationship between the two, that is, to what extent they keep in step in the trend of increasing or decreasing, even if there is no proportional relationship. When calculating the Pearson correlation coefficient, the data sample values themselves are used, while when calculating the Spearman correlation coefficient, the ranked position values of the data samples are used. The calculation formula of the Spearman correlation coefficient is as follows:

[0095]

[0096] In the formula, represents the difference in the ranked position values of the i-th data pair, and n is the total number of observed samples.

[0097] The value range of the Spearman rank correlation coefficient is also between -1 and 1, and its meaning is the same as that of the Pearson correlation coefficient, but it is applicable to data with non-normal distribution or non-linear relationship.

[0098] If the historical tension data or micro-meteorological data is incomplete or the information is incomplete, the grey correlation degree, that is, the degree of tightness of the connection between the curves, is used to determine the relationship between them. The basic steps of using grey correlation analysis method to analyze the influencing factors of icing comprehensive load in transmission lines are as follows:

[0099] First, determine the analysis sequence. According to the analysis target, determine the comprehensive load of the transmission line as the reference sequence, denoted as , , is the sample size. The influencing factors of tension are the comparison sequences, denoted as , is the number of characteristic quantities.

[0100] Then, perform data normalization. The orders of magnitude and units of the reference sequence and the comparison sequences are usually different. For the convenience of analysis, it is necessary to normalize each sequence. The formula is as follows:

[0101]

[0102] In the formula: is the original value of a certain characteristic quantity; and are the maximum value and the minimum value of a certain characteristic quantity respectively; is the normalized value of a certain characteristic quantity.

[0103] Then, calculate the correlation coefficient. The correlation coefficient refers to the degree of association between the comparison sequence and the reference sequence at each moment. The correlation coefficient between and at the th moment is:

[0104]

[0105] In the formula: is the resolution coefficient, , usually take = 0.5, is the minimum value of the absolute difference between all comparison sequences and the reference sequence, is the maximum value of the absolute difference between all comparison sequences and the reference sequence. , when < 0.5, it indicates a weak correlation; when 0.5 ≤ < 0.7, it indicates a strong correlation; ≥ 0.7, it indicates a very strong correlation.

[0106] Finally, the grey correlation degree is determined according to the above correlation coefficient. The grey correlation degree refers to the overall correlation degree between the comparison sequence and the reference sequence, that is, the average value of the correlation coefficients at each moment. The calculation formula is as follows:

[0107]

[0108] In the formula: is the grey correlation degree, and its value and meaning are the same as .

[0109] Figure 4 shows the influence relationship between each data item in the micro-meteorological data and the historical tensile force data after the correlation analysis is carried out according to the three methods in the above step S3. After the above correlation analysis, it is determined that the comprehensive tensile force load has a relatively strong correlation with four factors: temperature, humidity, air pressure, and maximum wind speed; it has a moderate correlation with average wind speed, standard wind speed, maximum wind speed wind deviation angle, and skew angle; it has a weak correlation with wind direction and precipitation intensity. Among them, the relationship between temperature and the comprehensive tensile force load is negative correlation, that is, when the temperature rises, the wire expands and contracts thermally, and the tensile force increases; the relationship between wind speed and the comprehensive tensile force load is positive correlation, that is, the greater the wind speed, the greater the tensile force.

[0110] S4. Perform multiple linear regression fitting on the non-icing tensile force data screened in step S2 and several strongly correlated factors to create a tensile force correction model.

[0111] Multiple linear regression is a statistical method used to analyze the relationship between two or more independent variables (explanatory variables) and a dependent variable (response variable). In the multiple linear regression model, the dependent variable Y is assumed to be related to the linear combination of the independent variables X, and there is a random error term ϵ at the same time, which represents the part that the model cannot explain.

[0112] This embodiment provides a specific method for fitting and analyzing the non-icing tensile force data and strongly correlated factors through a multiple linear regression model and creating a tensile force correction model, including the following steps:

[0113] S41. Import the non-icing tensile force data and strongly correlated factors into the multiple linear regression model, and fit the non-icing tensile force data and strongly correlated factors. The formula is as follows:

[0114]

[0115] Among them, Y is the tensile force, X1, X2,..., Xn are the strongly correlated factors of the tensile force data, β0 is the intercept term, which represents the expected value of the dependent variable when all independent variables are zero. β1, β2,..., βn are the regression coefficients, which represent the slopes corresponding to the strongly correlated factors, that is, the average change in the tensile force expected for each unit change in the strongly correlated factors. is the error term, representing the influence of other factors on the tensile force except for the strongly correlated factors.

[0116] S42. Calculate the regression coefficients β1, β2, …, βn of each independent variable in the multiple linear regression model.

[0117] S43. Substitute the regression coefficients of each independent variable into the multiple linear regression model to obtain the final tensile force correction model.

[0118] The method of this embodiment further includes step S44. Substitute the non-icing tensile force data and strongly correlated factors again to evaluate the tensile force correction model to ensure the accuracy of the tensile force correction model.

[0119] Specifically, step S44 comprehensively evaluates the tensile force correction model using four evaluation indicators: Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). Among them, MAPE provides the percentage form of the prediction error and is sensitive to outliers; RMSE considers the magnitude of the prediction error but is not as intuitive as MAPE; MAE is similar to RMSE but does not consider the direction of the error and is less sensitive to outliers; R² measures the explanatory ability of the model, and the closer the value is to 1, the stronger the explanatory power of the model. The formulas are as follows:

[0120] ;

[0121] ;

[0122] ;

[0123] .

[0124] Among them, is the true value, is the sample mean, is the predicted value.

[0125] Step S5. Substitute the non-icing tensile force data and historical micro-meteorological data into the tensile force correction model to obtain the tensile force reference value.

[0126] In the above step S4, a linear relationship between strong correlation factors and the tension of the transmission line has been established in the tension correction model. Therefore, by controlling the strong correlation factors to a specified value through the tension correction model, the influence of the strong correlation factors on the tension of the transmission line can be normalized, so that the difference in the tension of the transmission line under different meteorological conditions only includes the part affected by the ice coating weight.

[0127] Specifically, since the intercept represents the expected value of the dependent variable when all independent variables are zero. Therefore, in step S5, after taking the non-ice-coated tension data as Y in the linear model and substituting the historical micro-meteorological data as X1, X2,..., Xn in the linear model into the tension correction model, the new intercept of the tension correction model is taken as the tension reference value after normalization adjustment of the strong correlation factors under non-ice-coated conditions.

[0128] In step S6, real-time tension data and real-time micro-meteorological data are collected, and the real-time tension data and real-time micro-meteorological data are substituted into the tension correction model to obtain a tension correction value. Similarly to the above step S5, by controlling the strong correlation factors to a specified value through the tension correction model, the influence of the strong correlation factors on the tension of the transmission line can be normalized. Therefore, after taking the real-time tension data as Y in the linear model and substituting the real-time micro-meteorological data as X1, X2,..., Xn in the linear model into the tension correction model, the new intercept β0 of the tension correction model is taken as the tension correction value after normalization adjustment of the strong correlation factors under real-time conditions. Compared with the tension reference value, the part affected by the strong correlation factors of this tension correction value has been normalized, so the difference between the two is the part affected by the ice coating weight.

[0129] In step S7, according to the tension reference value and the tension correction value obtained in steps S5 and S6, the tension increase caused by ice coating is calculated, so as to judge the ice coating state and give a suitable warning signal. When the tension correction value exceeds the tension reference value, it means that the line has started to ice. When the tension correction value reaches 120% of the tension reference value and the tension increase exceeds 20% of the tension reference value, it means that the line is severely iced, and the system can issue an alarm to notify the relevant departments to take ice melting measures in time.

[0130] Figure 5 The figure shows the process of judging the ice coating of the transmission line after calculating the tension reference value.

[0131] This embodiment is illustrated by taking the ice coating data monitored by a certain transmission line in the south as an example. According to the method of the above embodiment, the data is first preprocessed, that is, the repeated data is deleted, the blank values are filled with linear interpolation to fill the missing values, and the isolated abnormal values of the normal waveform are removed. The preprocessed data is as Figure 6 shown.

[0132] Substitute the non-icing tensile force data of the experimental line into the multiple linear regression model, and the final tensile force correction model is obtained as follows:

[0133] Y = 22799 - 13.1 + 2.43 + 5.55 + 703.94 - 126.03

[0134] Where Y is the tensile force, is the air temperature data, is the humidity data, is the average wind speed data, is the wind deflection angle data, is the skew angle data.

[0135] The evaluation results of the tensile force correction model are shown in Table 1.

[0136] Table 1

[0137]

[0138] From the perspective of the MAPE index, the MAPE of the experimental line is 0.001, and the low prediction error of the line indicates that the prediction is very close to the actual value. From the perspectives of the RMSE and MAE indices, the RMSE and MAE of the experimental line are 33.58 and 21.62 respectively, indicating that the prediction results of the model are relatively accurate. The R² index shows the ability of the model to explain the data variability. The R² of the experimental line is 0.985, indicating that the model can explain most of the data variability.

[0139] Obtain the tensile force data of the experimental line and substitute it into the tensile force correction model to obtain the corrected tensile force correction value, as Figure 7 shown.

[0140] Take the tensile force value after excluding the influence of strongly correlated factors as the tensile force reference value, that is, the tensile force value 22799 is used as the tensile force reference value. When the tensile force correction value of the transmission line exceeds 120% of this value, that is, 27358.8, an alarm is issued.

[0141] This embodiment also provides a verification step S8 to ensure the accuracy of the tensile force correction model. After calculating the tensile force reference value and the tensile force correction value according to the historical tensile force data, verify the accuracy of the tensile force correction model according to the icing records of a certain period. The steps are as follows:

[0142] S71. Calculate the confusion matrix TP, TN, FP, FN.

[0143] TP: The number of samples that are actually iced and predicted to be iced;

[0144] TN: The number of samples that are actually not ice-covered and predicted not to be ice-covered;

[0145] FP: The number of samples that are actually not ice-covered but predicted to be ice-covered;

[0146] FN: The number of samples that are actually ice-covered but predicted not to be ice-covered.

[0147] S72. Calculate the evaluation metrics:

[0148] Accuracy = (TP + TN) / Total number of samples;

[0149] Precision = TP / (TP + FP);

[0150] Recall = TP / (TP + FN);

[0151] F1 score = 2 × (Precision × Recall) / (Precision + Recall).

[0152] Taking the ice-covering data monitored by a certain transmission line in the south as an example above, verify the accuracy of the tensile reference value according to step S7. TP = 136, TN = 194, FP = 6, FN = 1.

[0153] Accuracy = (136 + 194) / 337 = 97.9%;

[0154] Precision = 136 / (136 + 6) = 95.8%;

[0155] Recall = 136 / (136 + 1) = 99.3%;

[0156] F1 score = 2 × (0.958 × 0.993) / (0.958 + 0.993) = 0.975.

[0157] It shows that the set tensile reference value can accurately identify the ice-covering situation of the transmission line.

[0158] The ice accretion warning method for transmission lines of the present invention uses the method of fitting through linear regression analysis to normalize and adjust the influence of micro-meteorological factors on the conductor tension. Both the reference tension value calculated using historical data and the corrected tension value calculated using real-time data include the influence of the same micro-meteorological factors, making the difference between the two only depend on the influence of the ice accretion gravity on the tension of the transmission line. Thus, false alarms caused by factors such as wind force and temperature increasing the line tension are avoided, the accuracy of line ice accretion detection is improved, and the problem of insufficient accuracy faced when detecting the ice accretion condition of transmission lines in the prior art is solved. At the same time, the ice accretion warning method for transmission lines of the present invention is optimized for data anomalies and missing problems. By adding links to process data anomalies and missing data, the problem of inaccurate warning criteria caused by data anomalies is overcome, the warning accuracy of the model is effectively improved, and thus the practicability of the method is enhanced.

[0159] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0160] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0161] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will readily think of other embodiments of the present disclosure. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A transmission line icing early warning method, characterized in that: include: S1. Obtain historical tension data and historical micro-meteorological data of the transmission line; S2, filtering out non-icing tension data from the historical tension data, and removing ice-covered tension data and abnormal tension data; S3, selecting several strongly correlated factors causing the change of transmission line tension from the historical micro-meteorological data; S4, performing multivariate linear regression fitting on the non-icing tension data and the strongly correlated factors to create a tension correction model, wherein the tension correction model is used to normalize the influence of the strongly correlated factors on the tension of the transmission line; S5, substituting the non-icing tension data and the historical micro-meteorological data into the tension correction model to obtain a tension reference value; S6, collecting real-time tension data and real-time micro-meteorological data, substituting the real-time tension data and the real-time micro-meteorological data into the tension correction model to obtain a tension correction value; S7: Perform ice cover warning according to the tension reference value and the tension correction value.

2. A power transmission line icing early warning method according to claim 1, characterized in that: The step of providing an ice warning according to the tension reference value and the tension correction value includes: The tension increase amount caused by icing is calculated according to the tension reference value and the tension correction value, and an icing warning is issued according to the tension increase amount.

3. A power transmission line icing early warning method as claimed in claim 2, characterized in that: According to the magnitude of the tension increase, different levels of ice cover warning are issued.

4. A power transmission line icing early warning method according to claim 1, characterized in that: The step S2 determines whether each micro-meteorological data is a strong correlation factor of the tension data by the following method; The Pearson correlation coefficient method is used to detect the linear correlation between each micro-meteorological data and the tension data to determine whether it is a strong correlation factor; The Spearman rank correlation coefficient was used to detect various micrometeorological data that did not conform to the normal distribution or had nonlinear relationships to determine whether they were strong correlation factors; Grey correlation analysis is used to detect various micrometeorological data to determine whether they are strong correlation factors.

5. The power transmission line icing early warning method according to claim 1, characterized in that: The step S2 selects normal tension data and ice-covered tension data from the tension data by using a K-shape clustering algorithm, and removes abnormal tension data, including: S21, performing standardization processing on the historical tension data by adopting z standardization; S22, determining the number of clusters K; S23, using K-shape algorithm to compare and analyze the lengths of different time periods; S24, comparing the output visual clustering results with the trends of each group of data, and dividing each group of data into its corresponding cluster; S25. Retain the non-icing tension data clusters, and remove the ice-covered tension data clusters and abnormal tension data clusters.

6. A power transmission line icing early warning method according to claim 1, characterized in that: The step S4 comprises: S41, importing the non-icing tension data and the strongly correlated factors into a multiple linear regression model; S42, calculating the regression coefficient of each independent variable in the multivariate linear regression model; S43: generating a tension correction model according to the regression coefficient.

7. The power transmission line icing early warning method according to claim 1, characterized in that: The micrometeorological data at least include temperature, humidity, air pressure, maximum wind speed, average wind speed, standard wind speed, maximum wind speed wind angle, deflection angle, wind direction, and precipitation.

8. The power transmission line icing early warning method according to claim 1, characterized in that: After step S1 and before step S2, the method further includes step S11 of preprocessing the historical tension data and historical micro-meteorological data.

9. A power transmission line icing early warning method as claimed in claim 8, characterized in that: The preprocessing includes: deleting duplicate data, interpolating blank data, and eliminating isolated outliers.

10. The power transmission line icing early warning method according to claim 1, characterized in that: The method also includes: S8. Verifying the accuracy of the tension correction model through the historical tension data.

Images