High-voltage cable joint temperature on-line monitoring method based on sensor data fusion

Abstract

The invention discloses a high-voltage cable joint temperature online monitoring method based on sensor data fusion. The method comprises the following steps: data acquisition: acquiring a first temperature data sequence T1i, a second temperature data sequence T2i and an environment temperature data sequence Ei of a plurality of temperature sensors at the position of a high-voltage cable joint; data fusion: fusing the data to generate a fused temperature data sequence Fi; abnormal detection: calculating a temperature change coefficient, a temperature difference coefficient and a temperature change rate of each temperature sensor according to the fused temperature data sequence Fi, and generating an abnormal quantized value Qi of each temperature sensor; and judging result generation: comparing the abnormal quantized value Qi with a preset threshold value Qth, and judging whether each temperature sensor has a temperature abnormal condition or not. According to the invention, by fusing the data from the plurality of temperature sensors and the environment temperature information, the accuracy and reliability of temperature monitoring are improved, and the anti-interference capability and the intelligent level of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and in particular to a method for online monitoring of high-voltage cable joint temperature based on sensor data fusion. Background Art

[0002] With the rapid development of the power system, high-voltage cables, as an important part of power transmission, are crucial to the safe and stable operation of the entire power grid. However, in actual operation, overheating problems caused by material aging, improper construction and other reasons often occur in high-voltage cable joints, becoming one of the main factors affecting the reliability of cable systems. Traditionally, the monitoring of high-voltage cable joint temperature relies on regular manual inspections or monitoring by a single temperature sensor. This method is not only inefficient, but also difficult to detect potential temperature anomalies in a timely manner, and cannot meet the needs of modern power systems for fault warning and preventive maintenance.

[0003] Traditional temperature monitoring technology mainly uses contact or non-contact single-point temperature measurement methods. Although contact temperature sensors such as thermocouples and thermal resistors have high accuracy, they are complex to install, are susceptible to electromagnetic interference, and are difficult to achieve comprehensive monitoring of cable joint temperature. Non-contact temperature sensors such as infrared thermometers are easy to install, but are greatly affected by environmental factors, have limited measurement distances, and cannot effectively monitor temperature changes in all key parts. Therefore, these traditional technical solutions are insufficient in real-time and accuracy, and are difficult to meet the actual needs of high-voltage cable joint temperature monitoring.

[0004] Existing technical solutions have attempted to improve the accuracy and reliability of monitoring by integrating multiple sensors, such as using wireless sensor networks to achieve remote monitoring. However, such technical solutions often ignore the correlation and complementarity between different sensor data and fail to fully utilize the advantages of multi-source data, resulting in the overall performance of the monitoring system still needs to be improved. In addition, most existing monitoring systems lack effective data processing algorithms and are unable to extract valuable information from large amounts of raw data, thus affecting the efficiency and accuracy of fault diagnosis.

[0005] The present invention proposes a method for online monitoring of high-voltage cable joint temperature based on sensor data fusion, aiming to overcome the problems existing in the prior art. By fusing data from multiple temperature sensors and ambient temperature information, the accuracy and reliability of temperature monitoring are improved, the anti-interference ability and intelligence level of the system are enhanced, and strong technical support is provided for the safe and stable operation of the power system. Summary of the invention

[0006] A method for online monitoring of high-voltage cable joint temperature based on sensor data fusion comprises the following steps:

[0007] Data acquisition: Get the first temperature data sequence T of multiple temperature sensors at each high-voltage cable joint position corresponding to the current moment 1i , the second temperature data sequence T 2i And the ambient temperature data series E i , where i represents the i-th temperature sensor;

[0008] Data fusion: The first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i With the ambient temperature data series E i Perform data fusion to generate the fused temperature data sequence F i ;

[0009] Anomaly detection: Based on the fused temperature data sequence F i , calculate the temperature variation coefficient, temperature difference coefficient and temperature change rate of each temperature sensor, and combine these coefficients and change rates to generate the abnormal quantization value Q of each temperature sensor i ;

[0010] Judgment result generation: Based on the abnormal quantification value Q i With the preset threshold Q th Compare and determine whether each temperature sensor has abnormal temperature.

[0011] Preferably, the data fusion comprises the following steps:

[0012] Calculate the first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i The average

[0013] Calculate the ambient temperature data series E i The average

[0014] The first temperature data sequence T 1i , the second temperature data sequence T 2i The average With the ambient temperature data series E i The average Perform weighted averaging to generate the fused temperature data sequence F i :

[0015]

[0016] Among them, α, β, and γ are preset weight coefficients.

[0017] Preferably, the temperature variation coefficient of the temperature sensor includes the following calculation steps:

[0018] At the jth high-voltage cable joint position, calculate the fused temperature data sequence F i The rate of change of adjacent temperature data ΔF i,k , ΔF i,k The formula is as follows:

[0019]

[0020] Among them, k represents the kth temperature data;

[0021] The change rates of all adjacent temperature data at the j-th high-voltage cable joint position are counted in sequence to form the temperature change sequence ΔF at the j-th high-voltage cable joint position. j ;

[0022] The standard deviation calculation formula is used to calculate the temperature change rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j and the second temperature variation coefficient C 2j .

[0023] Preferably, the first temperature variation coefficient is calculated by a standard deviation formula for the temperature variation rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j , C 1j The calculation formula is:

[0024]

[0025] Where n represents the total length of the fused temperature data sequence, is the temperature change rate sequence ΔF from the 1st data point to the n-1th data point j The average value of

[0026] The average value of the temperature change rate series The calculation formula is:

[0027]

[0028] Where n represents the total length of the fused temperature data sequence.

[0029] Preferably, the second temperature variation coefficient is calculated by a standard deviation formula for the temperature variation rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the second temperature variation coefficient C of the jth high-voltage cable joint position2j , C 2j The calculation formula is:

[0030]

[0031] Where n represents the total length of the fused temperature data sequence, is the average value of the temperature change rate sequence from the 2nd data point to the nth data point;

[0032] The average value of the temperature change rate series The calculation formula is:

[0033]

[0034] Where n represents the total length of the fused temperature data sequence.

[0035] Preferably, the temperature difference coefficient of the temperature sensor is specifically calculated as follows:

[0036] Calculate the fused temperature data sequence F of each temperature sensor i The maximum value F imax And the temperature data series F i The maximum value F imin ;

[0037] Use the temperature difference coefficient formula to calculate and obtain the temperature difference coefficient D of each temperature sensor i : The temperature difference coefficient formula is:

[0038]

[0039] Among them, F iavg is the fused temperature data sequence F i The average value of .

[0040] Preferably, the temperature change rate of the temperature sensor is specifically calculated as follows:

[0041] Calculate the fused temperature data sequence F of each temperature sensor i The linear regression slope m i ;

[0042]

[0043] Among them, n i Represents the total data points of the temperature sensor, x i represents the time point of the i-th temperature sensor, y i Represents the temperature data F of the i-th temperature sensor i,k ;

[0044] Use the temperature change rate formula R i =|m i | Perform calculations to obtain the temperature change rate R of each temperature sensor i Preferably, the abnormal quantization value Q of the temperature sensor i The specific calculation is as follows:

[0045] Q i =w1·C 1i +w2·C 2i +w3·D i +w4·R i

[0046] Among them, w1, w2, w3, and w4 are weight coefficients of the first temperature change coefficient, the second temperature change coefficient, the temperature difference coefficient, and the temperature change rate, respectively.

[0047] Preferably, the preset threshold Q th Based on the statistics of historical data;

[0048] The first temperature variation coefficient C of the temperature sensor under the normal working state is collected 1i , the second temperature variation coefficient C 2i , Temperature difference coefficient D i and the temperature change rate R i ;

[0049] Calculate the abnormal quantization value Q under normal conditions i ; The abnormal quantization value Q under the normal state is calculated i The average and standard deviation σ, calculate the threshold Q th ;

[0050]

[0051] Among them, k is 2-3 to ensure that the threshold can cover the abnormal quantization value Q under normal circumstances i .

[0052] Preferably, the abnormal quantization value Q i With the preset threshold Q th The comparison method is:

[0053] The Q i >Q th , determine that the temperature sensor has abnormal temperature;

[0054] The Q i th , determine that the temperature sensor is normal.

[0055] ​Compared with the prior art, the technical solution of this application has the following technical effects:

[0056] The present invention solves the problem that single-point monitoring data in traditional temperature monitoring methods is incomplete and susceptible to interference through a data fusion technical solution, and obtains more accurate and reliable temperature monitoring data. By performing weighted average fusion on the first temperature data sequence, the second temperature data sequence and the ambient temperature data sequence of multiple temperature sensors, a fused temperature data sequence is generated, which effectively improves the accuracy and stability of temperature monitoring.

[0057] The present invention solves the problem of lack of effective means for identifying temperature anomalies in the prior art by introducing a calculation method for parameters such as temperature variation coefficient, temperature difference coefficient and temperature variation rate, and realizes accurate detection of temperature anomalies of high-voltage cable joints. By combining these parameters to calculate the abnormal quantitative value of each temperature sensor, temperature anomalies can be discovered in time, providing a scientific basis for fault warning.

[0058] The present invention solves the problem of false alarms or missed alarms caused by unreasonable threshold setting in traditional technologies by deriving preset thresholds based on historical data statistics, thereby improving the reliability and accuracy of the monitoring system. By collecting relevant data of the temperature sensor under normal working conditions, the average value and standard deviation of the abnormal quantitative values ​​under normal conditions are calculated, and then a reasonable threshold is set to ensure the efficient operation of the monitoring system.

[0059] The present invention solves the problem in the prior art that it is impossible to quickly and accurately determine whether a temperature sensor is abnormal through a comparison mechanism between the abnormal quantization value and the preset threshold, and realizes an instant alarm function for abnormal temperature conditions. According to the comparison result between the abnormal quantization value and the preset threshold, it is automatically determined whether the temperature sensor has an abnormal temperature condition, which helps to take measures in time to prevent accidents and ensure the safe and stable operation of the power system.

[0060] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application so that it can be implemented in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following is a detailed description of the preferred embodiments of the present application in conjunction with the accompanying drawings as follows.

[0061] Based on the detailed description of the specific embodiments of the present application in combination with the accompanying drawings below, those skilled in the art will become more aware of the above and other objects, advantages and features of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions 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 some embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creative work. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0063] Figure 1 This is the temperature detection flow chart;

[0064] Figure 2 It is the data fusion flow chart;

[0065] Figure 3 This is the anomaly detection flow chart. Specific embodiments

[0066] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, rather than all of the embodiments. In the following description, specific details such as specific configuration and components are provided only to help fully understand the embodiments of the present application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, for clarity and brevity, the description of known functions and structures is omitted in the embodiment.

[0067] It should be understood that the references to "one embodiment" or "this embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "one embodiment" or "this embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0068] In addition, the present application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0069] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" in this article describes another type of association object relationship, indicating that there can be two relationships. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0070] The term "at least one" in this article is merely a description of the association relationship of associated objects, indicating that there may be three relationships. For example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0071] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusions.

[0072] Example 1

[0073] This embodiment mainly describes a method for online monitoring of high-voltage cable joint temperature based on sensor data fusion;

[0074] like Figure 1 As shown, a method for online monitoring temperature of a high-voltage cable joint based on sensor data fusion comprises the following steps:

[0075] Data acquisition: Get the first temperature data sequence T of multiple temperature sensors at each high-voltage cable joint position corresponding to the current moment 1i , the second temperature data sequence T 2i And the ambient temperature data series E i , where i represents the i-th temperature sensor;

[0076] Data fusion: The first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i With the ambient temperature data series E i Perform data fusion to generate the fused temperature data sequence F i ;

[0077] Anomaly detection: Based on the fused temperature data sequence F i, calculate the temperature variation coefficient, temperature difference coefficient and temperature change rate of each temperature sensor, and combine these coefficients and change rates to generate the abnormal quantization value Q of each temperature sensor i ;

[0078] Judgment result generation: Based on the abnormal quantification value Q i With the preset threshold Q th Compare and determine whether each temperature sensor has abnormal temperature;

[0079] Through the four steps of data collection, data fusion, anomaly detection and judgment result generation, the temperature of high-voltage cable joints can be effectively monitored. It can monitor the temperature of high-voltage cable joints in real time, discover potential safety hazards in time, and improve the safety and reliability of the power system.

[0080] Further, the data fusion comprises the following steps:

[0081] Calculate the first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i The average

[0082] Calculate the ambient temperature data series E i The average

[0083] The first temperature data sequence T 1i , the second temperature data sequence T 2i The average With the ambient temperature data series E i The average Perform weighted averaging to generate the fused temperature data sequence F i :

[0084]

[0085] Among them, α, β, and γ are preset weight coefficients;

[0086] By performing weighted averaging on multiple temperature data sequences and ambient temperature data sequences to generate a fused temperature data sequence, the accuracy of temperature monitoring is improved, the error that may be caused by single sensor data is reduced, and the monitoring results are more reliable.

[0087] Further, the temperature variation coefficient of the temperature sensor includes the following calculation steps:

[0088] At the jth high-voltage cable joint position, calculate the fused temperature data sequence F i The rate of change of adjacent temperature data ΔF i,k , ΔFi,k The formula is as follows:

[0089]

[0090] Among them, k represents the kth temperature data;

[0091] The change rates of all adjacent temperature data at the j-th high-voltage cable joint position are counted in sequence to form the temperature change sequence ΔF at the j-th high-voltage cable joint position. j ;

[0092] The standard deviation calculation formula is used to calculate the temperature change rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j and the second temperature variation coefficient C 2j ;

[0093] Furthermore, the first temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j , C 1j The calculation formula is:

[0094]

[0095] Where n represents the total length of the fused temperature data sequence, is the temperature change rate sequence ΔF from the 1st data point to the n-1th data point j The average value of

[0096] The average value of the temperature change rate series The calculation formula is:

[0097]

[0098] Where n represents the total length of the fused temperature data sequence.

[0099] Furthermore, the second temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the second temperature variation coefficient C of the jth high-voltage cable joint position 2j , C 2j The calculation formula is:

[0100]

[0101] Where n represents the total length of the fused temperature data sequence, is the average value of the temperature change rate sequence from the 2nd data point to the nth data point;

[0102] The average value of the temperature change rate series The calculation formula is:

[0103]

[0104] Where n represents the total length of the fused temperature data sequence.

[0105] Furthermore, the temperature difference coefficient of the temperature sensor is specifically calculated as follows:

[0106] Calculate the fused temperature data sequence F of each temperature sensor i The maximum value F imax And the temperature data series F i The maximum value F imin ;

[0107] Use the temperature difference coefficient formula to calculate and obtain the temperature difference coefficient D of each temperature sensor i : The temperature difference coefficient formula is:

[0108]

[0109] Among them, F iavg is the fused temperature data sequence F i The average value of

[0110] It can reflect the temperature difference between different temperature sensors, help identify temperature sensor failure or improper installation, and ensure the stable operation of the monitoring system.

[0111] Further, the temperature change rate of the temperature sensor is specifically calculated as follows:

[0112] Calculate the fused temperature data sequence F of each temperature sensor i The linear regression slope m i ;

[0113]

[0114] Among them, n i Represents the total data points of the temperature sensor, x i represents the time point of the i-th temperature sensor, y i Represents the temperature data F of the i-th temperature sensor i,k ;

[0115] Use the temperature change rate formula R i =|m i| Perform calculations to obtain the temperature change rate R of each temperature sensor i ;

[0116] It provides a quantitative indicator of the rate of temperature change, which is crucial for quickly identifying abnormal temperature rise or drop, and helps to take timely measures to avoid accidents.

[0117] Furthermore, the abnormal quantization value Q of the temperature sensor i The specific calculation is as follows:

[0118] Q i =w1·C 1i +w2·C 2i +w3·D i +w4·R i

[0119] Wherein, w1, w2, w3, and w4 are weight coefficients of the first temperature variation coefficient, the second temperature variation coefficient, the temperature difference coefficient, and the temperature variation rate, respectively;

[0120] The abnormal quantitative value of the temperature sensor is calculated according to different coefficients, and multiple factors are comprehensively considered, making the abnormal detection more comprehensive and accurate, and improving the intelligence level and responsiveness of the system.

[0121] Furthermore, the preset threshold Q th Based on the statistics of historical data;

[0122] The first temperature variation coefficient C of the temperature sensor under the normal working state is collected 1i , the second temperature variation coefficient C 2i , Temperature difference coefficient D i and the temperature change rate R i ;

[0123] Calculate the abnormal quantization value Q under normal conditions i ; The abnormal quantization value Q under the normal state is calculated i The average and standard deviation σ, calculate the threshold Q th ;

[0124]

[0125] Among them, k is 2-3 to ensure that the threshold can cover the abnormal quantization value Q under normal circumstances i ;

[0126] The accuracy of anomaly detection is ensured, false positives or negative positives caused by improper threshold settings are avoided, and the practicality and reliability of the system are enhanced.

[0127] Furthermore, the abnormal quantization value Qi With the preset threshold Q th The comparison method is:

[0128] The Q i >Q th , determine that the temperature sensor has abnormal temperature;

[0129] The Q i th , determine that the temperature sensor is normal.

[0130] This embodiment describes in detail a method for online monitoring of high-voltage cable joint temperature based on sensor data fusion. By fusing data from multiple temperature sensors and ambient temperature information, the accuracy and reliability of temperature monitoring are improved, the anti-interference ability and intelligence level of the system are enhanced, and strong technical support is provided for the safe and stable operation of the power system.

[0131] Example 2

[0132] This embodiment is based on embodiment 1. Figure 2 As shown, the specific data fusion is mainly described:

[0133] Data fusion generates a more accurate and reliable temperature data sequence by integrating data from multiple temperature sensors and ambient temperature data. It includes the following steps:

[0134] Acquisition of temperature data sequence: Acquisition of the first temperature data sequence T at the current moment from multiple temperature sensors at each high-voltage cable joint location 1i and the second temperature data sequence T 2i , and also need to obtain the ambient temperature data sequence E i . Assume that the temperature data sequence of the i-th temperature sensor at the current moment is:

[0135] T 1i =[T 1i (1),T 1i (2),…,T 1i (n)]

[0136] T 2i =[T 2i (1),T 2i (2),…,T 2i (n)]

[0137] E i =[E i (1),E i (2),…,E i (n)]

[0138] ​Where n represents the length of the data sequence, that is, the number of temperature data points recorded by each temperature sensor in the current time period;

[0139] Determine whether there is missing data in the temperature data sequence; if there is no missing data, continue the operation; if there is missing data, use the linear interpolation formula to supplement the missing data:

[0140]

[0141] Among them, T missing is the data of missing data points, T prev 、T next is the temperature data of the two known data points before and after the missing data point, t prev ,t next is the time point of the two known data points before and after the missing data point, t missing is the time point where the data point is missing;

[0142] Calculation of the mean of a data series:

[0143] Calculate the average of the first and second temperature data series for each temperature sensor, as well as the average of the ambient temperature data series:

[0144]

[0145] Calculate the weighted average of the average:

[0146] The first temperature data sequence T 1i , the second temperature data sequence T 2i The average With the ambient temperature data series E i The average Perform weighted averaging to generate the fused temperature data sequence F i :

[0147]

[0148] Among them, α, β, and γ are preset weight coefficients, α+β+γ=1;

[0149] This embodiment significantly improves the accuracy, reliability and intelligence level of the high-voltage cable joint temperature online monitoring system through the data fusion process, ensures the efficient operation of the system, timely discovers and handles potential safety hazards, and ensures the safety and stability of the power system.

[0150] Example 3

[0151] This embodiment is based on embodiment 1. Figure 3 As shown, the specific anomaly detection is mainly described:

[0152] Anomaly detection identifies temperature anomalies by analyzing the fused temperature data sequence, discovers potential safety hazards in a timely manner, and improves the safety and reliability of the power system;

[0153] The anomaly detection process mainly includes the following steps:

[0154] Calculate the temperature variation coefficient: The temperature variation coefficient reflects the trend of temperature change over time and can help identify abnormal temperature fluctuations; specifically, it includes:

[0155] Calculate the rate of temperature change:

[0156] At the jth high-voltage cable joint position, calculate the fused temperature data sequence F i The rate of change of adjacent temperature data ΔF i,k , ΔF i,k The formula is as follows:

[0157]

[0158] Among them, k represents the kth temperature data;

[0159] Construct a temperature change sequence:

[0160] The change rates of all adjacent temperature data at the j-th high-voltage cable joint position are counted in sequence to form the temperature change sequence ΔF at the j-th high-voltage cable joint position. j ;

[0161] ΔF j =[ΔF j1 ,ΔF j2 ,…,ΔF j(n-1) ]

[0162] The standard deviation calculation formula is used to calculate the temperature change rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j and the second temperature variation coefficient C 2j ;

[0163] Calculate the temperature coefficient of variation:

[0164] The first temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF at the jth high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j , C 1j The calculation formula is:

[0165]

[0166] Where n represents the total length of the fused temperature data sequence, is the temperature change rate sequence ΔF from the 1st data point to the n-1th data point j The average value of

[0167] Temperature change rate series average The calculation formula is:

[0168]

[0169] Where n represents the total length of the fused temperature data sequence.

[0170] The second temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF at the jth high-voltage cable joint position. j Calculate and obtain the second temperature variation coefficient C of the jth high-voltage cable joint position 2j , C 2j The calculation formula is:

[0171]

[0172] Where n represents the total length of the fused temperature data sequence, is the average value of the temperature change rate sequence from the 2nd data point to the nth data point;

[0173] Temperature change rate series average The calculation formula is:

[0174]

[0175] Where n represents the total length of the fused temperature data sequence.

[0176] Calculate the temperature differential coefficient:

[0177] The temperature difference coefficient reflects the difference between the maximum, minimum and average values ​​of the temperature data, which helps to identify abnormal conditions of the temperature sensor, including the following steps:

[0178] Calculate the maximum, minimum and average values ​​of the fused temperature series;

[0179] F imax =max(F i )

[0180] F imin =min(F i )

[0181]

[0182] Use the temperature difference coefficient formula to calculate and obtain the temperature difference coefficient D of each temperature sensor i : The temperature difference coefficient formula is:

[0183]

[0184] Among them, F iavg is the fused temperature data sequence F i The average value of .

[0185] Calculate the rate of temperature change:

[0186] The temperature change rate reflects the speed at which the temperature changes over time, which helps to quickly identify abnormal temperature rises and falls. The specific steps are:

[0187] Calculate the fused temperature data sequence F of each temperature sensor i The linear regression slope m i ;

[0188]

[0189] Among them, n i Represents the total data points of the temperature sensor, x i represents the time point of the i-th temperature sensor, y i Represents the temperature data F of the i-th temperature sensor i,k ;

[0190] Use the temperature change rate formula R i =|m i | Perform calculations to obtain the temperature change rate R of each temperature sensor i .

[0191] Generate outlier quantization values:

[0192] The temperature variation coefficient, temperature difference coefficient and temperature variation rate are weighted and combined to generate the abnormal quantization value of the temperature sensor; the abnormal quantization value Q of the temperature sensor i The specific calculation is as follows:

[0193] Q i =w1·C 1i +w2·C 2i +w3·D i +w4·R i

[0194] Among them, w1, w2, w3, and w4 are weight coefficients of the first temperature change coefficient, the second temperature change coefficient, the temperature difference coefficient, and the temperature change rate, respectively.

[0195] The preset threshold Q thBased on the statistics of historical data;

[0196] The first temperature variation coefficient C of the temperature sensor under the normal working state is collected 1i , the second temperature variation coefficient C 2i , Temperature difference coefficient D i and the temperature change rate R i ;

[0197] The first temperature variation coefficient C under normal conditions 1i , the second temperature variation coefficient C 2i , Temperature difference coefficient D i and the temperature change rate R i Calculated by the above formula;

[0198] Calculate the abnormal quantization value Q under normal conditions i ; The abnormal quantization value Q under the normal state is calculated i The average and standard deviation σ, calculate the threshold Q th ;

[0199]

[0200] Among them, k is 2-3 to ensure that the threshold can cover the abnormal quantization value Q under normal circumstances i ;

[0201] The outlier quantization value Q i With the preset threshold Q th The comparison method is:

[0202] The Q i >Q th , determine that the temperature sensor has abnormal temperature;

[0203] The Q i th , determine that the temperature sensor is normal.

[0204] This implementation solves the problem in the prior art that it is impossible to quickly and accurately determine whether the temperature sensor is abnormal through a comparison mechanism between the abnormal quantization value and the preset threshold, and realizes the instant alarm function of temperature abnormalities. According to the comparison result between the abnormal quantization value and the preset threshold, it automatically determines whether the temperature sensor has a temperature abnormality, which helps to take timely measures to prevent accidents and ensure the safe and stable operation of the power system.

[0205] ​The above are only preferred embodiments of the present invention, which do not limit the scope of protection of the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any changes, modifications, replacements, integrations and parameter changes to these embodiments within the spirit and principles of the present invention through conventional substitutions or without departing from the principles and spirit of the present invention fall within the scope of protection of the present invention.

Claims

1. A method for online monitoring of high-voltage cable joint temperature based on sensor data fusion, characterized in that: The method comprises the following steps: Data acquisition: Get the first temperature data sequence T of multiple temperature sensors at each high-voltage cable joint position corresponding to the current moment 1i , the second temperature data sequence T 2i And the ambient temperature data series E i , where i represents the i-th temperature sensor; Data fusion: The first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i With the ambient temperature data series E i Perform data fusion to generate the fused temperature data sequence F i ; Anomaly detection: Based on the fused temperature data sequence F i , calculate the temperature variation coefficient, temperature difference coefficient and temperature change rate of each temperature sensor, and combine these coefficients and change rates to generate the abnormal quantization value Q of each temperature sensor i ; Judgment result generation: Based on the abnormal quantification value Q i With the preset threshold Q th Compare and determine whether each temperature sensor has abnormal temperature.

2. A method for online monitoring temperature of high-voltage cable joints based on sensor data fusion according to claim 1, characterized in that: The data fusion comprises the following steps: Calculate the first temperature data sequence T of each temperature sensor 1i , the second temperature data sequence T 2i The average Calculate the ambient temperature data series E i The average The first temperature data sequence T 1i , the second temperature data sequence T 2i The average With the ambient temperature data series E i The average Perform weighted averaging to generate the fused temperature data sequence F i : Among them, α, β, and γ are preset weight coefficients.

3. The method for online monitoring temperature of a high-voltage cable joint based on sensor data fusion according to claim 1 is characterized in that: The temperature variation coefficient of the temperature sensor includes the following calculation steps: At the jth high-voltage cable joint position, calculate the fused temperature data sequence F i The rate of change of adjacent temperature data ΔF i,k , ΔF i,k The formula is as follows: Among them, k represents the kth temperature data; The change rates of all adjacent temperature data at the j-th high-voltage cable joint position are counted in sequence to form the temperature change sequence ΔF at the j-th high-voltage cable joint position. j ; The standard deviation calculation formula is used to calculate the temperature change rate sequence ΔF at the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j and the second temperature variation coefficient C 2j .

4. A method for online monitoring temperature of high-voltage cable joints based on sensor data fusion according to claim 3, characterized in that: The first temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF of the j-th high-voltage cable joint position. j Calculate and obtain the first temperature variation coefficient C of the jth high-voltage cable joint position 1j , C 1j The calculation formula is: Where n represents the total length of the fused temperature data sequence, is the temperature change rate sequence ΔF from the 1st data point to the n-1th data point j The average value of The average value of the temperature change rate series The calculation formula is: Where n represents the total length of the fused temperature data sequence.

5. The method for online monitoring temperature of a high-voltage cable joint based on sensor data fusion according to claim 3 is characterized in that: The second temperature variation coefficient is calculated by the standard deviation formula for the temperature variation rate sequence ΔF of the j-th high-voltage cable joint position. j Calculate and obtain the second temperature variation coefficient C of the jth high-voltage cable joint position 2j , C 2j The calculation formula is: Where n represents the total length of the fused temperature data sequence, is the average value of the temperature change rate sequence from the 2nd data point to the nth data point; The average value of the temperature change rate series The calculation formula is: Where n represents the total length of the fused temperature data sequence.

6. The method for online monitoring temperature of a high-voltage cable joint based on sensor data fusion according to claim 1 is characterized in that: The temperature difference coefficient of the temperature sensor is specifically calculated as follows: Calculate the fused temperature data sequence F of each temperature sensor i The maximum value F imax And the temperature data series F i The maximum value F imin ; Use the temperature difference coefficient formula to calculate and obtain the temperature difference coefficient D of each temperature sensor i : The temperature difference coefficient formula is: Among them, F iavg is the fused temperature data sequence F i The average value of .

7. The method for online monitoring temperature of high-voltage cable joints based on sensor data fusion according to claim 1 is characterized in that: The temperature change rate of the temperature sensor is specifically calculated as follows: Calculate the fused temperature data sequence F of each temperature sensor i The linear regression slope m i ; Among them, n i Represents the total data points of the temperature sensor, x i represents the time point of the i-th temperature sensor, y i Represents the temperature data F of the i-th temperature sensor i,k ; Use the temperature change rate formula R i =|m i | Perform calculations to obtain the temperature change rate R of each temperature sensor i .

8. The method for online monitoring temperature of a high-voltage cable joint based on sensor data fusion according to claim 1 is characterized in that: The abnormal quantization value Q of the temperature sensor i The specific calculation is as follows: Q i =w1·C 1i +w2·C 2i +w3·D i +w4·R i Among them, w1, w2, w3, and w4 are weight coefficients of the first temperature change coefficient, the second temperature change coefficient, the temperature difference coefficient, and the temperature change rate, respectively.

9. The method for online monitoring temperature of high-voltage cable joints based on sensor data fusion according to claim 1, characterized in that: The preset threshold Q th Based on the statistics of historical data; The first temperature variation coefficient C of the temperature sensor under the normal working state is collected 1i , the second temperature variation coefficient C 2i , Temperature difference coefficient D i and the temperature change rate R i ; Calculate the abnormal quantization value Q under normal conditions i ; The abnormal quantization value Q under the normal state is calculated i The average and standard deviation σ, calculate the threshold Q th ; Among them, k is 2-3 to ensure that the threshold can cover the abnormal quantization value Q under normal circumstances i .

10. A method for online monitoring of high-voltage cable joint temperature based on sensor data fusion according to claim 8 or 9, characterized in that: The abnormal quantization value Q i With the preset threshold Q th The comparison method is: The Q i >Q th , determine that the temperature sensor has abnormal temperature; The Q i th , determine that the temperature sensor is normal.​

Images