A method and system for monitoring the status of a shielded data cable shielding layer

Abstract

The present application relates to the technical field of electrical variable measurement, and specifically to a method and system for monitoring the status of a cable shielding layer of a shielded data cable. The method includes: obtaining parameter values ​​at the current moment and the historical moment, and obtaining the corrected capacitance value at the historical moment; determining the number of overall clusters by the number of clusters in each dimension; clustering the dimension of each environmental factor separately to obtain the influence coefficient of the environmental factor on the capacitance; selecting adjacent moments, and obtaining the reference coefficient according to the parameter difference between the adjacent moment and the current moment; in the FCM algorithm, determining the distribution uniformity of the fuzzy class and the clustering result correction coefficient according to the membership degree; determining the environmental impact factor according to the parameter difference between the current moment and the fuzzy class center, and obtaining the final corrected membership of the data point at the current moment in combination with all the above indicators; and correcting the capacitance value according to the final corrected membership degree to complete the status monitoring. The present application improves the reliability and accuracy of judging the status of the cable shielding layer.

Description

Technical Field

[0001] The present application relates to the technical field of electrical variable measurement, and in particular to a method and system for monitoring the status of a cable shielding layer of a shielded data cable. Background Art

[0002] The existing method for determining and analyzing the status of the cable shielding layer is to use the capacitance between the cable shielding layer and the core at the measurement detection point to judge the status of the cable shielding layer according to the change of capacitance. However, when measuring the capacitance, due to different measurement environments, the measurement results may be affected by temperature and humidity, which in turn affects the measurement results, resulting in inaccurate judgment results of the cable shielding layer status. Therefore, it is necessary to provide a method for accurately measuring the capacitance data of the cable shielding layer and the center layer in the process of cable shielding layer status monitoring.

[0003] When using capacitance to determine the status of a cable shield, environmental factors may cause inaccurate capacitance measurement. This application corrects the capacitance measurement results in combination with historical data, and uses the FCM clustering algorithm when selecting historical data. However, this clustering algorithm uses random initial seeds for clustering, which may result in poor clustering effects. Therefore, it is necessary to correct the clustering results and obtain reliable historical reference data, thereby correcting the capacitance value according to the historical correction method to obtain an accurate capacitance value, thereby accurately monitoring the status of the cable shield. Summary of the invention

[0004] In order to solve the technical problem of the influence of the environment on the measurement results, the present application provides a cable shielding layer status monitoring method and system for a shielded data cable. The technical solution adopted is as follows:

[0005] In a first aspect, the present application proposes a method for monitoring the status of a cable shielding layer of a shielded data cable, the method comprising the following steps:

[0006] Collect the temperature, humidity and capacitance values ​​of all monitoring points at the current time and historical time, and obtain the corrected capacitance values ​​at historical time;

[0007] The temperature value, humidity value and capacitance value form a three-dimensional data point, cluster each dimension, and determine the number of clusters in the FCM algorithm based on the number of clusters of all dimensions; cluster all data points using the FCM algorithm;

[0008] The humidity clustering clusters are segmented according to the difference value of the capacitance value before and after correction in the clustering clusters of the humidity value clustering, and the temperature mean of the class with the smallest difference value mean after segmentation is calculated. The thermoelectric ratio is obtained according to the difference between the temperature value at the historical moment and the temperature mean and the difference between the capacitance value before and after correction, and the temperature influence coefficient is determined according to the variance of the thermoelectric ratio; the humidity-electric ratio is obtained by clustering the temperature value separately, and the humidity influence coefficient is determined according to the variance of the humidity-electric ratio;

[0009] Select adjacent moments, determine the temperature weight and humidity weight according to the temperature influence coefficient and the humidity influence coefficient, and obtain the reference coefficient of the adjacent moments by combining the temperature, humidity, capacitance and time differences between the adjacent moments and the current moment;

[0010] In the FCM algorithm, each class is recorded as a fuzzy class, and the distribution uniformity of the fuzzy class is obtained based on the capacitance difference before and after the correction of the historical data point and the membership degree of each fuzzy class; the clustering result correction coefficient is determined based on the distribution uniformity of the fuzzy class;

[0011] The temperature weight and humidity weight are combined with the temperature, humidity and capacitance difference between the current data point and the center point of the fuzzy class to obtain the environmental impact factor; the final corrected membership of the current data point is obtained according to the clustering result correction coefficient, the current data point, the membership of the adjacent data point in the fuzzy class, the environmental impact factor and the reference coefficient of the adjacent time;

[0012] The capacitance value at the current moment is corrected according to the final corrected membership, and the state monitoring is completed by detecting the abnormality of the corrected capacitance value.

[0013] In the above scheme, the present application monitors the capacitance data of the cable shielding layer, monitors the capacitance of the cable shielding layer and its surrounding environment data, clusters the capacitance data based on the FCM algorithm combined with historical data, selects a correction method based on the clustering result, and analyzes the impact of environmental data on the capacitance detection result, thereby correcting the clustering result to obtain a more accurate clustering result. In this process, the impact of temperature and humidity environment on capacitance detection is considered. In addition, the impact of adjacent data on current data is analyzed. Based on these two considerations, the clustering cluster that best matches the current data is selected from all clustering clusters to correct the capacitance value. Further obtain accurate capacitance correction measurement values ​​to improve the reliability and accuracy of judging the status of the cable shielding layer.

[0014] In one embodiment, the product of the number of clusters after clustering all dimensions is used as the number of clusters in the FCM algorithm.

[0015] In one embodiment, the method of obtaining the thermoelectric ratio according to the difference between the temperature value at the historical moment and the temperature average and the difference between the capacitance values ​​before and after correction, and determining the temperature influence coefficient according to the variance of the thermoelectric ratio is:

[0016] The ratio of the absolute value of the difference between each temperature value and the temperature mean to the absolute value of the difference between the capacitance values ​​before and after correction is recorded as the thermoelectric ratio;

[0017] The variance of the thermoelectric ratio of each humidity cluster is calculated, the mean of the variances of all thermoelectric ratios is calculated, and the normalized value of the variance means of all thermoelectric ratios is negatively mapped as the temperature influence coefficient.

[0018] In one embodiment, the method of determining the temperature weight and the humidity weight according to the temperature influence coefficient and the humidity influence coefficient, and obtaining the reference coefficient of the adjacent moment by combining the temperature, humidity, capacitance and time difference between the adjacent moment and the current moment is:

[0019] The sum of the temperature influence coefficient and the humidity influence coefficient is recorded as the first sum value;

[0020] Let the ratio of the temperature influence coefficient to the first sum value be recorded as the temperature weight, and let the ratio of the humidity influence coefficient to the first sum value be recorded as the humidity weight;

[0021] The temperature weight and humidity weight are used as the weights of the temperature difference and humidity difference between the adjacent time and the current time, respectively;

[0022] The reference coefficients of adjacent moments are negatively correlated with the weighted temperature difference, weighted humidity difference, capacitance difference, and time difference.

[0023] In one embodiment, the method for obtaining the distribution uniformity of the fuzzy class based on the capacitance difference before and after the correction of the historical moment data point and the membership degree of each fuzzy class is:

[0024] , represents the corrected capacitance difference of the jth historical data point, Indicates the membership of the data point at the jth historical moment to the dth fuzzy class, Represents the number of data points at historical moments, represents the distribution uniformity of the d-th fuzzy class, Represents an exponential function with a natural constant as its base.

[0025] In one embodiment, the method for determining the clustering result correction coefficient according to the distribution uniformity of the fuzzy class is:

[0026] The mean of the distribution uniformity of all fuzzy classes is calculated, and the normalized value after negative mapping of the distribution uniformity of all fuzzy classes is used as the clustering result correction coefficient.

[0027] In one embodiment, the method of combining the temperature weight and humidity weight with the temperature, humidity and capacitance difference between the current data point and the fuzzy class center point to obtain the environmental impact factor is:

[0028] , Represents the temperature difference between the current data point r and the cluster center of the dth fuzzy class, Represents the humidity difference between the current data point r and the cluster center of the dth fuzzy class, represents the capacitance difference between the current data point r and the cluster center of the dth fuzzy class, represents the temperature weight, represents the humidity weight, represents the linear normalization function, Represents environmental impact factors.

[0029] In one embodiment, the method for obtaining the final corrected membership of the data point at the current moment according to the clustering result correction coefficient, the data point at the current moment, the membership of the data point at the adjacent moments in the fuzzy class, the environmental impact factor, and the reference coefficient at the adjacent moments is:

[0030] , represents the membership of the data point r in the dth fuzzy class at the current moment, represents the clustering result correction coefficient, represents the membership of the data point at the oth neighboring moment in the dth fuzzy class, represents the reference coefficient of the oth adjacent time, represents the environmental impact factor, Indicates the corrected membership of the data point at the current moment;

[0031] The ratio of the corrected membership of the data point at the current moment to each fuzzy class to the sum of the corrected membership of the data point at the current moment to all fuzzy classes is taken as the final corrected membership of the data point at the current moment to the fuzzy class.

[0032] In one embodiment, the method for correcting the capacitance value at the current moment according to the final corrected membership is:

[0033] The fuzzy class with the maximum final corrected membership is recorded as the fuzzy class to which the data point belongs;

[0034] Get the fuzzy class where the data point at the current moment belongs, get all the historical data points in the fuzzy class and their corresponding corrected capacitance values, calculate the average of the difference between the capacitance values ​​of all historical data points and the corrected capacitance values, use this value as the corrected value at the current moment, and use the sum of the capacitance value measured at the current moment and the corrected value as the corrected capacitance value.

[0035] In the second aspect, an embodiment of the present application also provides a cable shielding layer status monitoring system for a shielded data cable, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods for monitoring the cable shielding layer status of a shielded data cable when executing the computer program.

[0036] The beneficial effects of this application are:

[0037] This application monitors the capacitance data of the cable shielding layer, monitors the capacitance of the cable shielding layer and its surrounding environment data, clusters the capacitance data based on the FCM algorithm combined with historical data, selects a correction method based on the clustering results, and analyzes the impact of environmental data on the capacitance detection results, thereby correcting the clustering results to obtain more accurate clustering results. In this process, the impact of temperature and humidity environment on capacitance detection is considered. In addition, the impact of adjacent data on current data is analyzed. Based on these two considerations, the clustering cluster that best matches the current data is selected from all clustering clusters to correct the capacitance value. Further obtain accurate capacitance correction measurement values ​​to improve the reliability and accuracy of judging the status of the cable shielding layer. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a method for monitoring the status of a cable shielding layer of a shielded data cable provided in one embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the cable shielding layer status monitoring method and system of a shielded data cable proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0042] A method for monitoring the status of a shielded data cable shield layer:

[0043] The specific scheme of the cable shielding layer status monitoring method of a shielded data cable provided by the present application is described in detail below with reference to the accompanying drawings.

[0044] See also Figure 1 , which shows a flow chart of a method for monitoring the status of a shielded data cable shield layer provided by an embodiment of the present application, the method comprising the following steps:

[0045] Step S001, collecting the temperature value, humidity value and capacitance value of all monitoring points at the current time and the historical time, and obtaining the corrected capacitance value at the historical time.

[0046] Multiple monitoring points are set in the cable, and the temperature value, humidity value and corresponding capacitance value of each monitoring point are collected. In this embodiment, the temperature value, humidity value and corresponding capacitance value of each monitoring point are collected once every 10 minutes, that is, for the current moment, the temperature value, humidity value and capacitance value of each monitoring point at the current moment are obtained and recorded as the data information at the current moment.

[0047] Obtain historical sample data of each monitoring point, where each historical data includes temperature value, humidity value, capacitance value and corrected capacitance value, which are recorded as historical data information. And record the collection time of each data collection.

[0048] At this point, the data information of the current moment and the data information of the historical sample data have been obtained.

[0049] Step S002, the temperature value, humidity value and capacitance value constitute a three-dimensional data point, cluster each dimension, and determine the number of clusters in the FCM algorithm according to the number of clustered dimensions; cluster all three-dimensional data points using the FCM algorithm.

[0050] Since the capacitance value measured by the existing method may be affected by the monitoring environment, especially by the temperature and humidity, the present application corrects the capacitance data obtained by the measurement, wherein the correction method is to analyze and correct the detection result at the current moment based on the historical scene measurement results. When using the FCM clustering algorithm, the clustering results may not be ideal when using random initial seed points for clustering analysis, which in turn leads to poor clustering effect, resulting in a relatively inaccurate capacitance correction result, affecting the final judgment of the cable shielding layer status. Therefore, the present application requires the distance result obtained by the clustering algorithm to be corrected.

[0051] For the analysis of a monitoring point, first of all, for the data information of the current moment and the data information of all historical data, the temperature value, humidity value and capacitance value corresponding to each moment are taken as a three-dimensional data point, and all the three-dimensional data points are clustered by the FCM algorithm, where the clustering distance is the Euclidean distance between data points at different moments. The number of clusters is determined by the three dimensions, and the Euclidean distance is calculated by the difference in temperature value, humidity value and capacitance value.

[0052] To obtain the number of clusters in the FCM algorithm, the historical data of the three dimensions of temperature, capacitance and humidity at all times are clustered by DBSCAN respectively, and different numbers of clusters are obtained, which are recorded as N, M, and Q clusters. In this embodiment, r=3 and minpts=3 for DBSCAN clustering. The product of the number of clusters obtained in the three dimensions is used as the K value of the FCM algorithm, that is, the number of clusters in the FCM algorithm, that is, , K is the number of clusters in the FCM algorithm. The purpose of this is to reflect the characteristics of all data points. The same data point may be divided into three different categories in different dimensions. When clustering in three dimensions at the same time, in order to fully express its characteristics, all three categories need to be reflected. Therefore, the number of K in the FCM algorithm is the product of the three, including the possibility of each pixel being classified into each category. The characteristics of each pixel are expressed more accurately and the classification is more precise.

[0053] At this point, all three-dimensional data points at each monitoring point at each moment are clustered.

[0054] Step S003, clustering is performed with humidity value and temperature value as dimensions, and each category is segmented, and the thermoelectric ratio and the wet-electric ratio are obtained according to the capacitance difference before and after correction after segmentation and the corresponding temperature difference and humidity difference, so as to obtain the temperature influence coefficient and the humidity influence coefficient;

[0055] Since both humidity information and temperature information will affect the capacitance measurement value, the present application performs analysis based on the temperature information and humidity information to obtain the degree of influence of the humidity information and temperature information on the capacitance measurement value.

[0056] For all historical data of the same monitoring point, first, for the humidity values ​​of all historical data, use the DBSCAN clustering algorithm to classify them, and then record each cluster as a humidity cluster. For any humidity cluster, calculate the difference between the capacitance value corresponding to each historical data in the humidity cluster and the corrected capacitance value and record it as the capacitance difference. The specific calculation method of the capacitance difference is the absolute value of the difference between the capacitance values.

[0057] For all the capacitance differences in the humidity clustering cluster, all the historical data in the humidity clustering cluster are divided into two categories using threshold segmentation, the mean of the capacitance difference in each category is calculated, the category with the lowest mean is selected, the temperature mean of all the historical data therein is calculated and recorded as the category average temperature, the difference between each historical data in the humidity clustering cluster and the category average temperature is calculated and recorded as the temperature difference, and the specific calculation method of the temperature difference is the absolute value of the difference between the temperature value of the historical data and the category average temperature, wherein the threshold segmentation method used in this embodiment is the Otsu threshold method.

[0058] The ratio of the temperature difference to the capacitance difference is recorded as the thermoelectric ratio, and the variance of the thermoelectric ratio of all historical data in the humidity cluster is calculated.

[0059] If the temperature change has a greater impact on the capacitance measurement result, then the corresponding temperature change is greater, the capacitance difference is also greater, and the thermoelectric ratio fluctuates less. Therefore, when the variance of the required thermoelectric ratio is smaller, it means that the capacitance difference caused by temperature change has a greater impact on the capacitance measurement result. Conversely, it means that the temperature change has a smaller impact on the capacitance measurement result.

[0060] The temperature influence coefficient is determined according to the variance of the thermoelectric ratio in all humidity clusters. The temperature influence coefficient is negatively correlated with the variance of the thermoelectric ratio.

[0061] Preferably, in this embodiment, the expression of the temperature influence coefficient is:

[0062] , represents the variance of the thermoelectric ratio of the Sth humidity cluster, represents the number of humidity clusters, represents an exponential function with a natural constant as base, Represents the temperature influence coefficient. The smaller the variance of the temperature-to-electricity ratio is, the greater the impact of temperature change on the capacitance measurement results in the humidity cluster.

[0063] Preferably, in another embodiment of the present application, the expression of the temperature influence coefficient is:

[0064] , represents the variance of the thermoelectric ratio of the Sth humidity cluster, represents the number of humidity clusters, represents the linear normalization function, Represents the temperature influence coefficient. The smaller the variance of the temperature-to-electricity ratio is, the greater the impact of temperature change on the capacitance measurement results in the humidity cluster.

[0065] Similarly, for the temperature values ​​of all historical data, use the DBSCAN clustering algorithm to classify them and obtain temperature clusters, and calculate the capacitance difference of each historical data in the temperature cluster. According to the capacitance difference, all historical data in the temperature cluster are divided into two categories, and the humidity mean of the category with the lowest capacitance difference mean is calculated as the class average humidity, and the humidity difference of each historical data is obtained based on this. Let the ratio of humidity difference and capacitance difference be recorded as the wet-to-electric ratio, and obtain its variance. According to the variance of the wet-to-electric ratio in all temperature clusters, the humidity influence coefficient is obtained, which is recorded as .

[0066] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the two variables change in the same direction. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0067] At this point, the temperature influence coefficient and humidity influence coefficient are obtained.

[0068] Step S004, select an adjacent moment, determine the temperature weight and humidity weight according to the temperature influence coefficient and the humidity influence coefficient, and obtain the reference coefficient of the adjacent moment by combining the temperature difference, humidity difference, capacitance difference and time difference between the adjacent moment and the current moment.

[0069] Since the status monitoring of the cable shielding layer is continuous, the monitoring data obtained is also time-series, and for environmental data, such as temperature and humidity, the corresponding data is also continuous, so the capacitance data obtained at the current acquisition moment is also similar to the capacitance data obtained at the previous few moments. Therefore, the clustering results of the capacitance data at the current moment can be corrected based on the clustering analysis results of the capacitance data obtained at the previous few moments.

[0070] In this embodiment, the three moments before the current moment are recorded as adjacent moments, and the implementer can select different numbers of moments as adjacent moments.

[0071] There are temperature values, humidity values ​​and capacitance values ​​at each moment, and this application considers the influence of different influencing factors on capacitance. Therefore, the weights of temperature values ​​and humidity values ​​are calculated according to the temperature influence coefficient and humidity influence coefficient obtained in the above steps. The calculation method is:

[0072] , , represents the temperature influence coefficient, represents the humidity influence coefficient, represents the temperature weight, Represents the moisture weight.

[0073] The temperature difference and humidity difference between the adjacent time and the current time are weighted based on the temperature weight and humidity weight, and the reference coefficient of the adjacent time is obtained by combining the capacitance difference and the time difference.

[0074] The reference coefficients at adjacent moments are negatively correlated with the temperature difference, humidity difference, capacitance difference, and time difference.

[0075] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0076] Preferably, in this embodiment, the expression of the reference coefficient is:

[0077] , represents the temperature difference between the oth adjacent moment and the current moment, represents the humidity difference between the oth adjacent moment and the current moment, represents the capacitance difference between the oth adjacent moment and the current moment, represents the time difference between the oth adjacent moment and the current moment, represents an exponential function with a natural constant as base, Represents the reference coefficient of the oth adjacent time.

[0078] Preferably, in another embodiment of the present application, the expression of the reference coefficient is:

[0079] , represents the temperature difference between the oth adjacent moment and the current moment, represents the humidity difference between the oth adjacent moment and the current moment, represents the capacitance difference between the oth adjacent moment and the current moment, represents the time difference between the oth adjacent moment and the current moment, represents the reference coefficient of the oth adjacent time, represents the linear normalization function.

[0080] The smaller the difference between the temperature, humidity, capacitance value and data collection time obtained at the desired collection time and the data collected at the adjacent time o, the larger the reference coefficient of the data at the adjacent time.

[0081] At this point, the reference coefficients for each adjacent moment are obtained.

[0082] Step S005, in the FCM algorithm, each class is recorded as a fuzzy class, and the distribution uniformity of the fuzzy class is obtained according to the capacitance difference before and after the correction of the historical data point and the membership degree of each fuzzy class; the clustering result correction coefficient is determined according to the distribution uniformity of the fuzzy class.

[0083] After clustering the three-dimensional data points of a monitoring point at all times through the FCM algorithm, K clusters are obtained, and the clusters obtained through the FCM algorithm are recorded as fuzzy classes. The FCM algorithm can obtain the membership of each three-dimensional data point to each fuzzy class, record the three-dimensional data points of historical data as historical moment data points, and record the three-dimensional data points corresponding to the data points at the current moment as the data points at the current moment.

[0084] For any fuzzy class, the data except the current data are analyzed, and the difference between the capacitance value of the data point at the historical moment and the corrected capacitance value is recorded as the corrected capacitance difference; the distribution uniformity of each fuzzy class is obtained according to the membership of all the data points at the historical moment in the fuzzy class and the corrected capacitance difference of each data point at the historical moment.

[0085] Preferably, in this embodiment, the expression for the distribution uniformity of the fuzzy class is:

[0086] , represents the corrected capacitance difference of the jth historical data point, Indicates the membership of the data point at the jth historical moment to the dth fuzzy class, Represents the number of data points at historical moments, represents the distribution uniformity of the dth fuzzy class.

[0087] First, the membership degree and corrected capacitance difference of each historical data point are weighted, and then the difference is subtracted from the mean of the weighted values ​​of all historical data points, which reflects the up and down volatility of each historical data point based on the mean. Then, the mean of the volatility of all historical data points is calculated to reflect the volatility of all historical data points under this fuzzy class. The smaller the difference, that is, the closer to the mean, the stronger the distribution uniformity of the fuzzy class.

[0088] The stronger the distribution uniformity of the capacitance correction value obtained by clustering each fuzzy class according to temperature, humidity and capacitance, the smaller the influence of the poor clustering effect caused by the initial seed point in the clustering process, and the smaller the necessity of correcting the final clustering result, so the clustering result correction coefficient can be obtained accordingly.

[0089] The clustering result correction coefficient is negatively correlated with the distribution uniformity of the fuzzy classes.

[0090] Preferably, the expression of this embodiment is:

[0091] , represents the distribution uniformity of the d-th fuzzy class, represents the number of fuzzy classes, Represents the clustering result correction coefficient.

[0092] Preferably, in another embodiment of the present application:

[0093] , represents the distribution uniformity of the d-th fuzzy class, represents the number of fuzzy classes, Represents the clustering result correction coefficient.

[0094] At this point, the clustering result correction coefficient is obtained.

[0095] Step S006, combining the temperature weight and humidity weight with the temperature difference, humidity difference and capacitance difference between the data point at the current moment and the center point of the fuzzy class to obtain the environmental impact factor; obtaining the final corrected membership of the data point at the current moment according to the clustering result correction coefficient, the data point at the current moment, the membership of the data point at the adjacent moments in the fuzzy class, the environmental impact factor and the reference coefficient at the adjacent moments.

[0096] Since different environmental factors have an impact on the measurement of capacitance values, and the weights of different factors are the same when using the FCM algorithm for clustering, the membership of the current data point to the fuzzy class does not take into account the impact of different environmental factors on capacitance monitoring. Therefore, the Euclidean distance between the current data point and the corresponding cluster center is calculated in combination with the weights of different environmental factors as the environmental influencing factor.

[0097] The expression of environmental impact factor is:

[0098] , Represents the temperature difference between the current data point r and the cluster center of the dth fuzzy class, Represents the humidity difference between the current data point r and the cluster center of the dth fuzzy class, represents the capacitance difference between the current data point r and the cluster center of the dth fuzzy class, represents the temperature weight, represents the humidity weight, represents the linear normalization function, Represents environmental impact factors.

[0099] The greater the temperature difference, humidity difference, and capacitance difference between the current data point and the fuzzy class cluster center, the less the data point belongs to this fuzzy class. The greater the environmental impact factor obtained by combining the weights under different environments, the less the data point belongs to this fuzzy class.

[0100] The corrected membership of the data point at the current moment is obtained according to the clustering result correction coefficient, the membership of the data point at the current moment in the fuzzy class, the environmental impact factor, the reference coefficient at the adjacent moment, and the membership of the data point at the adjacent moment in the fuzzy class. The expression is as follows:

[0101] , represents the membership of the data point r in the dth fuzzy class at the current moment, represents the clustering result correction coefficient, represents the membership of the data point at the oth neighboring moment in the dth fuzzy class, represents the reference coefficient of the oth adjacent time, represents the environmental impact factor, Indicates the corrected membership of the data point at the current moment.

[0102] when When it is a negative number, it means that the membership of the current data point in the fuzzy class is greater than the membership of the adjacent data point in the fuzzy class. At this time, the corrected membership should be reduced. When it is a positive number, it means that the membership of the current data point in the fuzzy class is less than the membership of the adjacent data point in the fuzzy class. At this time, the corrected membership should be increased. As the clustering result correction coefficient, the membership degree is scaled. The larger the correction coefficient is, the more correction is needed, and the more the correction results of the subsequent formulas need to be amplified. The larger it is, the larger the reference coefficient of the adjacent moment is, and the more worthy it is to be referred to. Therefore, the larger it is, the greater the impact on the correction. It represents the environmental impact factor. The larger its value is, the less the data point belongs to this fuzzy class. Therefore, it is used as the overall denominator to adjust the corrected membership degree.

[0103] According to the above steps, the revised membership of the data point at the current moment to each fuzzy class is obtained. Since the sum of the membership of each data point to all fuzzy classes is 1, the ratio of the revised membership of the data point at the current moment to each fuzzy class to the sum of the revised membership of the data point at the current moment to all fuzzy classes is taken as the final revised membership of the data point at the current moment to the fuzzy class.

[0104] At this point, the final corrected membership of the data point to the fuzzy class at the current moment is obtained.

[0105] Step S007, correcting the capacitance value at the current moment according to the final corrected membership, and completing the state monitoring by detecting the abnormality of the corrected capacitance value.

[0106] The fuzzy class with the maximum final corrected membership value is recorded as the fuzzy class to which the data point belongs; the current data points of each monitoring point are clustered to obtain the fuzzy class to which each current data point belongs, all historical data points in the fuzzy class and their corresponding corrected capacitance values ​​are obtained, the average value of the difference between the capacitance values ​​of all historical data points and the corrected capacitance values ​​is calculated, and this value is used as the corrected value at the current moment, and the capacitance value measured at the current moment is added to the corrected value to obtain the corrected capacitance value.

[0107] In this way, the corrected capacitance value of each monitoring point at the current moment is obtained, and the corrected capacitance value and the corrected capacitance value at the historical moment are used as input. The LOF anomaly detection algorithm is used to monitor all corrected capacitance values. If the anomaly value at the current moment is greater than 1, then the corresponding cable shielding layer at the current moment has an abnormality and an alarm needs to be issued.

[0108] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a cable shielding layer status monitoring system for a shielded data cable, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned cable shielding layer status monitoring methods for a shielded data cable when executing the computer program.

[0109] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0110] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring the status of a cable shielding layer of a shielded data cable, characterized in that: The method comprises the following steps: Collect the temperature, humidity and capacitance values ​​of all monitoring points at the current time and historical time, and obtain the corrected capacitance values ​​at historical time; The temperature value, humidity value and capacitance value form a three-dimensional data point, cluster each dimension, and determine the number of clusters in the FCM algorithm based on the number of clusters of all dimensions; cluster all data points using the FCM algorithm; The humidity clustering clusters are segmented according to the difference value of the capacitance value before and after correction in the clustering clusters of the humidity value clustering, and the temperature mean of the class with the smallest difference value mean after segmentation is calculated. The thermoelectric ratio is obtained according to the difference between the temperature value at the historical moment and the temperature mean and the difference between the capacitance value before and after correction, and the temperature influence coefficient is determined according to the variance of the thermoelectric ratio; the humidity-electric ratio is obtained by clustering the temperature value separately, and the humidity influence coefficient is determined according to the variance of the humidity-electric ratio; Select adjacent moments, determine the temperature weight and humidity weight according to the temperature influence coefficient and the humidity influence coefficient, and obtain the reference coefficient of the adjacent moments by combining the temperature, humidity, capacitance and time differences between the adjacent moments and the current moment; In the FCM algorithm, each class is recorded as a fuzzy class, and the distribution uniformity of the fuzzy class is obtained based on the capacitance difference before and after the correction of the historical data point and the membership degree of each fuzzy class; the clustering result correction coefficient is determined based on the distribution uniformity of the fuzzy class; The temperature weight and humidity weight are combined with the temperature, humidity and capacitance difference between the current data point and the center point of the fuzzy class to obtain the environmental impact factor; the final corrected membership of the current data point is obtained according to the clustering result correction coefficient, the current data point, the membership of the adjacent data point in the fuzzy class, the environmental impact factor and the reference coefficient of the adjacent time; The capacitance value at the current moment is corrected according to the final corrected membership, and the state monitoring is completed by detecting the abnormality of the corrected capacitance value; The method for correcting the capacitance value at the current moment according to the final corrected membership is: The fuzzy class with the maximum final corrected membership is recorded as the fuzzy class to which the data point belongs; Obtain the fuzzy class to which the data point at the current moment belongs, obtain all historical data points in the fuzzy class and their corresponding corrected capacitance values, calculate the average value of the difference between the capacitance values ​​of all historical data points and the corrected capacitance values, use the average value of the difference as the corrected value at the current moment, and use the sum of the capacitance value measured at the current moment and the corrected value as the corrected capacitance value.

2. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 1, characterized in that: The product of the number of clusters after clustering all dimensions is taken as the number of clusters in the FCM algorithm.

3. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 1, characterized in that: The method of obtaining the thermoelectric ratio according to the difference between the temperature value at the historical moment and the temperature average and the difference between the capacitance values ​​before and after correction, and determining the temperature influence coefficient according to the variance of the thermoelectric ratio is as follows: The ratio of the absolute value of the difference between each temperature value and the temperature mean to the absolute value of the difference between the capacitance values ​​before and after correction is recorded as the thermoelectric ratio; The variance of the thermoelectric ratio of each humidity cluster is calculated, the mean of the variances of all thermoelectric ratios is calculated, and the normalized value of the variance means of all thermoelectric ratios is negatively mapped as the temperature influence coefficient.

4. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 1, characterized in that: The method of determining the temperature weight and humidity weight according to the temperature influence coefficient and the humidity influence coefficient, and obtaining the reference coefficient of the adjacent moment by combining the temperature, humidity, capacitance and time difference between the adjacent moment and the current moment is: The sum of the temperature influence coefficient and the humidity influence coefficient is recorded as the first sum value; Let the ratio of the temperature influence coefficient to the first sum value be recorded as the temperature weight, and let the ratio of the humidity influence coefficient to the first sum value be recorded as the humidity weight; The temperature weight and humidity weight are used as the weights of the temperature difference and humidity difference between the adjacent time and the current time, respectively; The reference coefficients of adjacent moments are negatively correlated with the weighted temperature difference, weighted humidity difference, capacitance difference, and time difference.

5. The method for monitoring the status of a shielded data cable shield layer according to claim 1, characterized in that: The method for obtaining the distribution uniformity of the fuzzy class based on the capacitance difference before and after the correction of the historical data point and the membership degree of each fuzzy class is: , represents the corrected capacitance difference of the jth historical data point, Indicates the membership of the data point at the jth historical moment to the dth fuzzy class, Represents the number of data points at historical moments, represents the distribution uniformity of the d-th fuzzy class, Represents an exponential function with a natural constant as its base.

6. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 5, characterized in that: The method for determining the clustering result correction coefficient according to the distribution uniformity of the fuzzy class is: The mean of the distribution uniformity of all fuzzy classes is calculated, and the normalized value after negative mapping of the distribution uniformity of all fuzzy classes is used as the clustering result correction coefficient.

7. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 1, characterized in that: The method of combining the temperature weight and humidity weight with the temperature, humidity and capacitance difference between the current data point and the fuzzy class center point to obtain the environmental impact factor is: , Represents the temperature difference between the current data point r and the cluster center of the dth fuzzy class, Represents the humidity difference between the current data point r and the cluster center of the dth fuzzy class, represents the capacitance difference between the current data point r and the cluster center of the dth fuzzy class, represents the temperature weight, represents the humidity weight, represents the linear normalization function, Represents environmental impact factors.

8. A method for monitoring the status of a shielded data cable shield layer as claimed in claim 1, characterized in that: The method for obtaining the final corrected membership of the data point at the current moment according to the clustering result correction coefficient, the data point at the current moment, the membership of the data point at the adjacent moments in the fuzzy class, the environmental impact factor, and the reference coefficient at the adjacent moments is: , represents the membership of the data point r in the dth fuzzy class at the current moment, represents the clustering result correction coefficient, represents the membership of the data point at the oth neighboring moment in the dth fuzzy class, represents the reference coefficient of the oth adjacent time, represents the environmental impact factor, Indicates the corrected membership of the data point at the current moment; The ratio of the corrected membership of the data point at the current moment to each fuzzy class to the sum of the corrected membership of the data point at the current moment to all fuzzy classes is taken as the final corrected membership of the data point at the current moment to the fuzzy class.

9. A cable shielding layer condition monitoring system for a shielded data cable, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the processor implements the steps of a method for monitoring the status of a cable shielding layer of a shielded data cable as described in any one of claims 1-8.

Images