Cable temperature measurement early warning method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to a cable temperature measurement early warning method and system. The method comprises the steps of collecting temperature data, obtaining neighborhood data of each temperature data, and obtaining the abnormality of each neighborhood data of each temperature data; correcting the abnormality of each neighborhood data of each temperature data according to the change trend of the temperature data, and obtaining the noise level of each neighborhood data of each temperature data; obtaining noise data according to the noise level of each neighborhood data of each temperature data, and using the COF algorithm to judge abnormal data after removing the noise data. When the COF algorithm is used to detect abnormal data after removing the noise data, the accuracy of the abnormal detection result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a cable temperature measurement and early warning method and system. Background Art

[0002] As the safety and environmental protection requirements of the power system become more stringent, relevant units are required to ensure safety during power transmission and use, reduce environmental pollution and waste of resources. Therefore, the implementation of the cable temperature measurement and early warning system helps to improve the overall operation quality of the power system. By using the cable temperature measurement and early warning system to detect abnormal temperature data of the cable, problems such as cable overload and overheating can be discovered in time, effectively reducing unnecessary energy loss and waste of resources, and improving the operation efficiency and sustainability of the power system.

[0003] The patent application document with the publication number CN116720753A discloses a method, system and readable storage medium for processing hydrological data. By collecting hydrological data and performing data verification, it is determined whether the data verification is passed; if not, subsequent processing is performed on the abnormal data sequence that fails the verification; the data points are detected for abnormality using the One-ClassSVM model to obtain a first index value; the data points are detected for abnormality using the EWMA algorithm, the COF algorithm, and the IsolationForest algorithm respectively, and the second index value is obtained by weighted summation of the weights of each algorithm; the historical data corresponding to the data point is input into the LSTM model to obtain the fitting value, and the abnormal data point is determined based on the variance of the fitting value and the abnormal data sequence to obtain the third index value; the first index value, the second index value and the third index value are input into the hidden Markov model as observation values ​​to obtain the target abnormal data point.

[0004] When collecting temperature data on the cable, the mechanical vibration or impact of the cable itself or the surrounding environment may affect the stability and accuracy of the temperature sensor, resulting in random noise in the collected temperature data. For the COF algorithm mentioned in the above method, for any temperature data, when searching for multiple temperature data closest to it within a certain range, the basis is usually the Euclidean distance between two temperature data. Then, the presence of noise data in the temperature data will affect the accuracy of the Euclidean distance between the two temperature data, which will further cause errors in the selection results of multiple nearest temperature data for the temperature data, resulting in incorrect abnormal detection results. Summary of the invention

[0005] In order to solve the technical problem that the existence of noise data in temperature data affects the accuracy of the Euclidean distance of the temperature data, which in turn causes errors in the selection results of multiple recent temperature data of the COF algorithm, resulting in incorrect abnormal detection results, the present invention provides a cable temperature measurement early warning method and system.

[0006] In a first aspect, the present invention provides a cable temperature measurement early warning method, which adopts the following technical solution:

[0007] A cable temperature measurement and early warning method, comprising the steps of:

[0008] Collect temperature data; obtain neighborhood data of each temperature data; obtain the abnormality degree of each neighborhood data of each temperature data, wherein the abnormality degree represents the prominence degree of the value of each neighborhood data of each temperature data; obtain the noise degree of each neighborhood data of each temperature data:

[0009] ; In the formula, Represents the noise level of the mth neighborhood data of the nth temperature data; Represents the abnormality of the mth neighborhood data of the nth temperature data; Represents the number of extreme points in the surrounding data set of the mth neighborhood data of the nth temperature data; as well as The value of the g+1th extreme point in the surrounding data set of the mth neighborhood data of the nth temperature data and the value of the gth extreme point; The number of representative data sets representing the mth neighborhood data of the nth temperature data; as well as The range of the data in the surrounding data sets of the m-th neighborhood data representing the n-th temperature data and the range of the data in the v-th representative data set; based on the noise level, obtaining noise data; deleting the noise data to obtain an updated temperature data sequence; using the COF algorithm to obtain the COF value of each temperature data in the updated temperature data sequence; judging the abnormality of the current temperature data according to the COF value of each temperature data in the updated temperature data sequence.

[0010] The innovation of the present invention lies in obtaining the noise degree of each neighborhood data of each temperature data, deleting the noise data based on the noise degree, and finally using the COF algorithm to detect abnormal data. The temperature data after the noise data is deleted more accurately reflects the real temperature change trend, effectively reduces the interference of noise data on the abnormal analysis results of the COF algorithm, and improves the accuracy of abnormal data analysis.

[0011] Preferably, the obtaining of neighborhood data of each temperature data includes:

[0012] The number of neighboring data F is preset, and the F temperature data before each temperature data in the temperature data sequence are recorded as the neighboring data of each temperature data.

[0013] This facilitates the subsequent analysis of the noise level of the neighborhood data of each temperature data.

[0014] Preferably, the step of obtaining the abnormality degree of each neighborhood data of each temperature data includes:

[0015] Get the surrounding data sets of each neighborhood data of each temperature data;

[0016] ;

[0017] In the formula, Represents the abnormality of the mth neighborhood data of the nth temperature data; Represents the value of the mth neighboring data of the nth temperature data; Represents the average value of all data in the surrounding data set of the mth neighborhood data of the nth temperature data; The skewness of the surrounding data set representing the mth neighboring data of the nth temperature data; Represents the skewness of the surrounding data set of the m-th neighboring data of the n-th temperature data after removing the m-th neighboring data; || represents the absolute value sign.

[0018] The acquisition of the degree of abnormality takes into account the prominence of the data in the neighborhood, making the acquisition of the degree of abnormality more accurate.

[0019] Preferably, the step of obtaining the surrounding data set of each neighborhood data of each temperature data includes:

[0020] The number of data in the surrounding data set is preset to O, and each neighborhood data of each temperature data and the O temperature data before each neighborhood data of each temperature data in the temperature data sequence are recorded as the surrounding data set of each neighborhood data of each temperature data.

[0021] Preferably, the acquisition of the representative data set includes:

[0022] The surrounding data sets of each neighboring data of each temperature data whose first data in the surrounding data sets of the mth neighboring data of the nth temperature data precedes the temperature data sequence are taken as the representative data sets of the mth neighboring data of the nth temperature data.

[0023] Preferably, the obtaining of noise data includes:

[0024] A noise level threshold T1 is preset. If the noise level of the mth neighborhood data of the nth temperature data is greater than or equal to the noise level threshold, the mth neighborhood data of the nth temperature data is noise data, and all noise data are obtained.

[0025] This makes it easier to perform anomaly detection after deleting the noise data, thus avoiding the impact of noise data on anomaly data detection.

[0026] Preferably, judging the abnormality of the current temperature data according to the COF value of each temperature data in the updated temperature data sequence includes:

[0027] Performing linear normalization processing on the COF values ​​of all temperature data in the updated temperature data sequence to obtain the normalized COF value of each temperature data in the updated temperature data sequence;

[0028] A judgment threshold T2 is preset, and the current temperature data and each temperature data of five minutes before the sampling time of the current temperature data are obtained in the updated temperature data sequence as the data set of the current temperature data, and the number of data with normalized COF values ​​greater than the judgment threshold in the data set of the current temperature data is recorded as the number of representative data; if the number of representative data is greater than 5% of the number of data in the data set of the current temperature data, the current temperature data is abnormal and the system issues an early warning.

[0029] According to the COF value of each temperature data in the updated temperature data sequence, abnormal data judgment is performed, which improves the accuracy of abnormal detection and avoids the influence of noise.

[0030] In a second aspect, the present invention provides a cable temperature measurement early warning system, which adopts the following technical solution:

[0031] A cable temperature measurement and early warning system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned cable temperature measurement and early warning method is implemented.

[0032] By adopting the above technical solution, the above-mentioned cable temperature measurement and early warning method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0033] The present invention has the following technical effects: the purpose of the present invention is to consider the prominence of the values ​​of each neighborhood data of each temperature data and combine the change trend of the temperature data, obtain the noise level of each neighborhood data of each temperature data, based on the noise level, obtain the noise data and delete it, and finally use the COF algorithm to detect abnormal data. The temperature data after the noise data is deleted more accurately reflects the real temperature change trend, effectively reduces the interference of noise data on the abnormal analysis results of the COF algorithm, and improves the accuracy of abnormal data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0035] Figure 1 It is a method flow chart of a cable temperature measurement and early warning method in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0037] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0038] The embodiment of the present invention discloses a cable temperature measurement early warning method, referring to Figure 1 , comprising steps S1 to S3:

[0039] S1: Collect temperature data.

[0040] In an embodiment of the present invention, one second is preset as a sampling time, and a temperature sensor is installed on a cable to collect temperature data. The temperature data is collected for a total of one hour to obtain various temperature data. The collected temperature data are arranged in ascending order according to the sampling time to obtain a temperature data sequence.

[0041] S2: Obtain the neighborhood data of each temperature data, and obtain the abnormality degree of each neighborhood data of each temperature data; correct the abnormality degree of each neighborhood data of each temperature data according to the changing trend of the temperature data, and obtain the noise degree of each neighborhood data of each temperature data.

[0042] It should be noted that when collecting temperature data on the cable, the mechanical vibration or impact of the cable itself or the surrounding environment may affect the stability and accuracy of the temperature sensor, resulting in random noise in the collected temperature data. In the COF algorithm, for any temperature data, when searching for the K temperature data closest to it within a certain range, the basis is usually the Euclidean distance between the two temperature data. Then the existence of noise data in the temperature data will affect the accuracy of the Euclidean distance between the two temperature data, and further cause errors in the selection results of the K nearest temperature data for the temperature data. Therefore, the present invention proposes a cable temperature measurement and early warning method and system, which analyzes the numerical characteristics of the cable temperature data, obtains the noise degree of each neighborhood data of each temperature data, and then obtains the noise data. Finally, the noise data is eliminated, and then the COF value of each temperature data is calculated according to the known steps of the COF algorithm, so as to obtain a more accurate abnormality detection result.

[0043] Step S2 includes steps S20-S21, which are specifically as follows:

[0044] S20: Obtain the neighborhood data of each temperature data, and obtain the abnormality degree of each neighborhood data of each temperature data.

[0045] It should be noted that the present invention needs to calculate the noise level of each neighborhood data of each temperature data, and then eliminate the data points with high noise levels. Therefore, it is necessary to first obtain the neighborhood data of each temperature data. When analyzing the abnormality level of each neighborhood data of each temperature data, the more prominent the numerical value of any neighborhood data of any temperature data, the greater its abnormality level. In addition, the surrounding data sets of the neighborhood data of the temperature data are obtained. The greater the influence of the neighborhood data of the temperature data on the skewness of its surrounding data sets, the greater its abnormality level.

[0046] In the embodiment of the present invention, the number of neighborhood data F is preset, and the F temperature data before each temperature data in the temperature data sequence are recorded as the neighborhood data of each temperature data. It should be noted that when the F temperature data are not satisfied, a 0-filling operation is performed on them. In the embodiment of the present invention, the number of neighborhood data F is preset to 30. In other embodiments, the implementer can preset the value of the number of neighborhood data F according to the specific implementation situation.

[0047] The number of data in the surrounding data set is preset to O, and each neighborhood data of each temperature data and the O temperature data before each neighborhood data of each temperature data in the temperature data sequence are recorded as the surrounding data set of each neighborhood data of each temperature data. It should be noted that when O temperature data are not satisfied, 0-padding operation is performed on them. In an embodiment of the present invention, the number of surrounding data is preset to O=60. In other embodiments, the implementer can preset the value of the number of surrounding data O according to the specific implementation situation.

[0048] Get the degree of abnormality of each neighborhood data for each temperature data:

[0049] ;

[0050] In the formula, Represents the abnormality of the mth neighborhood data of the nth temperature data; Represents the value of the mth neighboring data of the nth temperature data; Represents the average value of all data in the surrounding data set of the mth neighborhood data of the nth temperature data; Represents the skewness of the surrounding data set of the mth neighborhood data of the nth temperature data; || represents the absolute value sign; The skewness after removing the mth neighboring data from the surrounding data set of the mth neighboring data of the nth temperature data; it should be noted that the acquisition of the skewness is an existing technology, which reflects the degree of skewness of the data in the data set;

[0051] The offset of the mth neighboring data of the nth temperature data compared to the average value of all data in the surrounding data set of the mth neighboring data. The larger the value, the more prominent the value of the mth neighboring data of the nth temperature data is, and the more likely it is to be abnormal. It represents the difference between the skewness of the surrounding data set of the mth neighboring data of the nth temperature data and the skewness of the surrounding data set of the mth neighboring data after removing the mth neighboring data. The larger the value, the greater the influence of the numerical value of the mth neighboring data of the nth temperature data on the skewness of the entire surrounding data set, and the greater the abnormality of the mth neighboring data of the nth temperature data itself; The larger the value is, the greater the difference between the skewness of the surrounding data set of the m-th neighborhood data of the n-th temperature data and 0 is. This means that there are more abnormally large or abnormally small data in the surrounding data set of the m-th neighborhood data of the n-th temperature data, that is, the greater the possibility that the m-th neighborhood data is abnormal and affected by noise.

[0052] S21: Correct the abnormality of each neighborhood data of each temperature data according to the change trend of the temperature data to obtain the noise level of each neighborhood data of each temperature data.

[0053] It should be noted that the abnormality degree of each neighborhood data of each temperature data is known, and the analysis of this indicator is only based on the characteristics of the numerical value of the temperature data. In the cable temperature measurement scenario corresponding to this scheme, the abnormal temperature data actually generated by the cable itself will have a similar numerical value to the noise data. Therefore, the noise data cannot be accurately proposed only by the abnormality degree. According to the scenario investigation, the cable material usually has a certain heat capacity and takes a certain amount of time to absorb or release heat, so that the temperature changes slowly. Therefore, the trend of temperature data changes can be analyzed, and the abnormality degree of each neighborhood data of each temperature data can be optimized to obtain its noise degree; among them, the slower the numerical change of the data in the surrounding data set of each neighborhood data of each temperature data point, the less likely the neighborhood data is noise data and the smaller the noise degree.

[0054] In an embodiment of the present invention, the surrounding data sets of each neighboring data of each temperature data whose first data in the surrounding data sets of the mth neighboring data of the nth temperature data precedes the temperature data sequence are used as the representative data sets of the mth neighboring data of the nth temperature data.

[0055] Get the noise level of each neighborhood data for each temperature data:

[0056] ;

[0057] In the formula, Represents the noise level of the mth neighborhood data of the nth temperature data; Represents the abnormality of the mth neighborhood data of the nth temperature data; Represents the number of extreme points in the surrounding data set of the mth neighborhood data of the nth temperature data; Represents the value of the g+1th extreme point in the surrounding data set of the mth neighborhood data of the nth temperature data; Represents the value of the g-th extreme point in the surrounding data set of the m-th neighborhood data of the n-th temperature data; The number of representative data sets representing the mth neighborhood data of the nth temperature data; Represents the range of the data in the surrounding data set of the mth neighborhood data of the nth temperature data; The vth data representing the mth neighborhood data of the nth temperature data represents the range of the data in the data set; norm() represents the normalization function; || represents the absolute value symbol; The larger the value of , the greater the noise level of the mth neighborhood data of the nth temperature data; Represents the numerical difference between all adjacent extreme points in the data set around the mth neighborhood data point of the nth temperature data. The larger the value, the more drastic the numerical change in the data set, and the greater the noise level of the mth neighborhood data; The sum of the differences between the range of the data in the surrounding data sets of the m-th neighborhood data of the n-th temperature data and the range of the data in the v-th representative data set of the m-th neighborhood data of the n-th temperature data. This value represents the relative size of the range of the data in the surrounding data sets of the m-th neighborhood data of the n-th temperature data compared to the range of the data in the data set before its sampling moment. The larger the value, the more drastic the numerical change of the data in the surrounding data sets of the m-th neighborhood data of the n-th temperature data, and the greater the credibility. Then, the greater the possibility that the m-th neighborhood data of the n-th temperature data is affected by noise, and the greater the degree of noise.

[0058] S3: Obtain noise data according to the noise level of each neighborhood data of each temperature data, remove the noise data and use the COF algorithm to judge abnormal data.

[0059] It should be noted that the noise level of each neighborhood data of each temperature data has been obtained, so it is necessary to set a noise level threshold to judge the noise level of the neighborhood data of each temperature data to obtain noise data. Subsequently, the noise data needs to be removed and the COF algorithm is used to judge abnormal data.

[0060] In the embodiment of the present invention, a noise level threshold T1 is preset. If the noise level of the mth neighboring data of the nth temperature data is greater than or equal to the noise level threshold, the mth neighboring data of the nth temperature data is noise data, and all noise data are obtained; the noise data in the temperature data sequence is deleted to obtain an updated temperature data sequence; the COF algorithm is used to obtain the COF value of each temperature data in the updated temperature data sequence, and the COF values ​​of all temperature data in the updated temperature data sequence are linearly normalized to obtain the normalized COF value of each temperature data in the updated temperature data sequence;

[0061] A judgment threshold T2 is preset, and the current temperature data and each temperature data of five minutes before the sampling time of the current temperature data are obtained in the updated temperature data sequence as the data set of the current temperature data, and the number of data with normalized COF values ​​greater than the judgment threshold in the data set of the current temperature data is recorded as the number of representative data; if the number of representative data is greater than 5% of the number of data in the data set of the current temperature data, the current temperature data is abnormal, and the system issues an early warning.

[0062] The purpose of the present invention is to consider the prominence of the values ​​of each neighborhood data of each temperature data and combine the changing trend of the temperature data, obtain the noise degree of each neighborhood data of each temperature data, obtain the noise data based on the noise degree and delete it, and finally use the COF algorithm to detect abnormal data. The temperature data after the noise data is deleted more accurately reflects the real temperature change trend, effectively reduces the interference of noise data on the abnormal analysis results of the COF algorithm, and improves the accuracy of abnormal data analysis.

[0063] An embodiment of the present invention further discloses a cable temperature measurement and early warning system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a cable temperature measurement and early warning method according to the present invention is implemented.

[0064] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0065] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0066] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0067] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A cable temperature measurement early warning method, characterized in that: Includes steps: Collect temperature data; obtain neighboring data of each temperature data; obtain the degree of abnormality of each neighboring data of each temperature data: ; Represents the abnormality of the mth neighborhood data of the nth temperature data; Represents the value of the mth neighboring data of the nth temperature data; Represents the average value of all data in the surrounding data set of the mth neighborhood data of the nth temperature data; as well as Represents the skewness of the surrounding data set of the mth neighboring data of the nth temperature data and the skewness of the surrounding data set after removing the mth neighboring data; obtains the noise level of each neighboring data of each temperature data: , Represents the noise level of the mth neighborhood data of the nth temperature data; Represents the number of extreme points in the surrounding data set of the mth neighborhood data of the nth temperature data; as well as The value of the g+1th extreme point in the surrounding data set of the mth neighborhood data of the nth temperature data and the value of the gth extreme point; The number of representative data sets representing the mth neighborhood data of the nth temperature data; as well as Represents the range of the data in the surrounding data set of the mth neighborhood data of the nth temperature data and the range of the data in the vth representative data set; norm() represents the normalization function; Based on the noise level, acquiring noise data; The noise data is deleted to obtain an updated temperature data sequence; the COF value of each temperature data in the updated temperature data sequence is obtained using the COF algorithm; According to the COF value of each temperature data in the updated temperature data sequence, the abnormality of the current temperature data is judged.

2. A cable temperature measurement and early warning method according to claim 1, characterized in that: The step of obtaining the neighborhood data of each temperature data includes: The number of neighboring data F is preset, and the F temperature data before each temperature data in the temperature data sequence are recorded as the neighboring data of each temperature data.

3. A cable temperature measurement and early warning method according to claim 1, characterized in that: Get the surrounding data set of the mth neighborhood data of the nth temperature data, including: The number of data in the surrounding data set is preset to O, and each neighborhood data of each temperature data and the O temperature data before each neighborhood data of each temperature data in the temperature data sequence are recorded as the surrounding data set of each neighborhood data of each temperature data.

4. A cable temperature measurement and early warning method according to claim 1, characterized in that: The acquisition of the representative data set includes: The surrounding data sets of each neighboring data of each temperature data whose first data in the surrounding data sets of the mth neighboring data of the nth temperature data precedes the temperature data sequence are taken as the representative data sets of the mth neighboring data of the nth temperature data.

5. A cable temperature measurement and early warning method according to claim 1, characterized in that: The obtaining of noise data comprises: A noise level threshold T1 is preset. If the noise level of the mth neighborhood data of the nth temperature data is greater than or equal to the noise level threshold, the mth neighborhood data of the nth temperature data is noise data, and all noise data are obtained.

6. A cable temperature measurement and early warning method according to claim 1, characterized in that: The method of determining the abnormality of the current temperature data according to the COF value of each temperature data in the updated temperature data sequence includes: Performing linear normalization processing on the COF values ​​of all temperature data in the updated temperature data sequence to obtain the normalized COF value of each temperature data in the updated temperature data sequence; A judgment threshold T2 is preset, and the current temperature data and each temperature data of five minutes before the sampling time of the current temperature data are obtained as the data set of the current temperature data. The number of data with normalized COF values ​​greater than the judgment threshold in the data set of the current temperature data is recorded as the number of representative data; if the number of representative data is greater than 5% of the number of data in the data set of the current temperature data, the current temperature data is abnormal and the system issues an early warning.

7. A cable temperature measurement early warning system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a cable temperature measurement and early warning method according to any one of claims 1 to 6 is implemented.

Images