Electrical equipment insulating material thermal degradation monitoring and early warning method and system based on multi-source data

Abstract

The invention relates to the technical field of thermal degradation monitoring, in particular to an electrical equipment insulating material thermal degradation monitoring and early warning method and system based on multi-source data, and the method mainly comprises the steps: outputting a first monitoring node with a risk at present through a thermal degradation early warning model based on current target data, and detecting a target loop with abnormal current based on the residual electric quantity, acquiring a second monitoring node on the target loop, and judging whether the target gas types of the target monitoring node all belong to the standard gas type or not. According to the method, the possibility of false alarm of the current detection point is reduced by analyzing the gas possibly volatilized by the current monitoring node, and all the current monitoring nodes are evaluated based on the obtained sorting result and the early warning value to obtain a processing sequence for a worker to refer to; therefore, more serious accidents caused by the fact that emergency monitoring nodes are not processed preferentially can be avoided as much as possible.

Description

Technical Field

[0001] This invention relates to the field of thermal degradation monitoring technology, and more specifically, to a method and system for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data. Background Technology

[0002] With the construction of centralized control stations and the advancement of digital transformation, the number of substation maintenance personnel is decreasing. Furthermore, the concentration of power and signal cables in substation cable trenches makes it difficult to promptly detect fire hazards such as cable short circuits, overloads, aging, and poor connections. In addition, abnormal residual current has become a major threat to power supply safety. Therefore, it is urgent to integrate residual current monitoring technology into the existing system to build a dual intelligent early warning system for overheating hazards and electrical insulation faults, thereby achieving an intelligent upgrade of substation safety early warning.

[0003] Currently, existing technologies, such as the self-organizing network-covered cable thermal degradation monitoring method and system disclosed in CN118707240A, collect cable thermal degradation gas data and send it to a server for storage. A gas monitoring model is established at the edge to analyze the gas data, identify signs of cable thermal degradation in real time, and issue early warnings. The server aggregates the data from the edge, analyzes the long-term trend of the gas data, and optimizes the gas monitoring model to achieve long-term monitoring and early warning of cable thermal degradation. This invention's method uses an edge-end self-organizing network to cover the cable area for sampling and detection, enabling real-time analysis of gas data, rapid identification of degradation signs, and timely issuance of early warning signals to prevent the worsening of cable degradation. However, during the detection process, it does not consider whether the detected gas will appear after the current monitoring node undergoes thermal degradation, leading to misjudgment and affecting the processing of other monitoring nodes. Furthermore, current technologies only perform analysis and alarms without providing a reference processing order, causing delays in processing more urgent monitoring nodes. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, so as to solve the above-mentioned problems in the prior art.

[0005] This invention is achieved through the following technical solution:

[0006] In a first aspect, the present invention provides a method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, comprising: Acquire gas detection data from different monitoring nodes, establish a thermal degradation early warning model, and output the first monitoring node with current risk based on the current target data through the thermal degradation early warning model; Obtain the standard gas type generated after thermal degradation of the insulation material at each monitoring node, create a table based on the standard gas type of different monitoring nodes, and add an index value for each monitoring node; The power of each circuit is detected, and the target circuit with abnormal current is obtained based on the power detection. The second monitoring node on the target circuit is then obtained. Determine whether there are duplicate monitoring nodes between the first monitoring node and the second monitoring node. If not, save the first monitoring node as the target monitoring node. If there are duplicate monitoring nodes, save the duplicate monitoring nodes as the target monitoring nodes. Non-duplicate monitoring nodes are ordinary monitoring nodes. The system obtains the warning value and the type of target gas detected by the target monitoring node. Based on the index value of the monitoring node, it indexes the table to obtain the standard gas type of the target monitoring node. It determines whether all the target gas types of the target monitoring node belong to the standard gas type. If so, the warning value of the current target monitoring node is saved. If not, the warning value of the current target monitoring node is corrected. The first result is obtained by sorting the warning values ​​of the current target monitoring nodes. The warning values ​​of ordinary monitoring nodes are then sorted after the last warning value of the first result, and the final sorted result is output.

[0007] Preferred options also include: The gas detection data is preprocessed, the preprocessing including: Gas detection data are grouped by gas type, and within each group, data is sorted chronologically based on the time at which each data point was acquired. The system detects outliers and missing values ​​in each data set, removes and adds outliers, and adds missing values ​​before outputting the processed gas detection data.

[0008] Preferably, after detecting outliers in each data set and removing them, the supplementary data includes: Get the absolute value of the difference between the first data in the adjacent time sequence and the second data in the adjacent time sequence, and set a difference threshold. Determine whether the current absolute value of the difference is greater than the difference threshold. If it is less than or equal to the difference threshold, do not process it. If it is greater than the difference threshold, continue to get the third data after the second data. When the difference between the first and second data is negative, if the third data is greater than or equal to the second data, the second data is considered a normal value. If the third data is less than the second data, the absolute value of the difference between the second and third data is obtained. If the absolute value of the difference between the second and third data is greater than or equal to the difference threshold, the second data is considered an outlier. If it is less than the difference threshold, it is considered a normal value. When the difference between the first and second data is positive, if the third data is less than the second data, the second data is considered a normal value. If the third data is greater than or equal to the second data, the absolute value of the difference between the second and third data is obtained. If the absolute value of the difference between the second and third data is greater than or equal to the difference threshold, the second data is considered an outlier. If it is less than the difference threshold, it is considered a normal value.

[0009] Preferably, the process of removing and supplementing outliers or supplementing missing values ​​includes: Get the missing records of outliers or missing values ​​in the current data, get the data on both sides of the missing record, and write the average of the data on both sides as the fill value to the missing data point. When the data on one or both adjacent sides are also empty record points, the data of the next target record point with existing data is obtained, and the number of record points between the target record point and the empty record point is determined. A selection threshold is set. If the number of record points on only one side is greater than the selection threshold, the data on the other side is used as the fill value. If the number of record points on both sides is greater than the selection threshold, the average value of the current data group is selected as the fill value.

[0010] Preferably, the establishment of the thermal degradation early warning model includes:

[0011] In the formula, Let i be the warning value for the i-th monitoring node. The first monitoring node to exceed the alarm threshold gas concentration, For the first Alarm thresholds for various gas concentrations The temperature of the current monitoring node. This represents the lowest combustion temperature of several types of cables within the current testing point. This represents the average current flowing through all cables within the current monitoring node. The average current flowing through the cables at all testing points. This represents the number of gas types currently exceeding the alarm threshold at the monitoring node. , and The coefficients are calculated, and their sum is 1.

[0012] Preferably, the step of outputting the first monitoring node currently at risk based on the current target data through the thermal degradation early warning model includes: Set a judgment threshold. When the warning value is greater than the judgment threshold, save the monitoring node corresponding to the current warning value as the first monitoring node. The judgment threshold is:

[0013] In the formula, To determine the threshold.

[0014] Preferably, the step of correcting the warning value of the current target monitoring node includes: Establish a correction model, which includes:

[0015] In the formula, This is the corrected warning value. This represents the number of target gas types that are not among the standard gas types.

[0016] Preferably, the final sorted results are also sent in encrypted form. Divide the data into two data packets, construct an elliptic curve, and select points on the curve. , As generators, find the points and points midpoint ; Choose a private key, based on point and Generate two public keys respectively; Encode the plaintext as , For points on the curve, based on two public keys and the midpoint. Generate the first ciphertext, and use the midpoint As a second ciphertext; The first and second ciphertexts are sent to the receiving end respectively, and the receiving end decrypts them to obtain... .

[0017] Preferably, the method is based on two public keys and a midpoint. The generation of the first ciphertext includes:

[0018]

[0019] The second ciphertext includes:

[0020] The receiving end obtains the result after decryption. include: pass Plaintext can be obtained For plaintext Decoding yields the final sorted result; In the formula, This is the first part of the first ciphertext. This is the second part of the first ciphertext. This is the second ciphertext. This is the private key.

[0021] Secondly, the present invention also provides a monitoring and early warning system for thermal degradation of electrical equipment insulation materials based on multi-source data, used to execute the above-mentioned method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, including: The data detection module is configured to include: acquiring gas detection data from different monitoring nodes; establishing a thermal degradation early warning model; outputting the first monitoring node with current risk based on the current target data and the thermal degradation early warning model; acquiring the standard gas types generated after thermal degradation of the insulation material in each monitoring node; establishing a table based on the standard gas types of different monitoring nodes; adding an index value to each monitoring node; detecting the electrical quantity of each circuit; identifying the target circuit with abnormal current based on the electrical quantity detection; and acquiring the second monitoring node on the target circuit. The correction module determines whether there are duplicate monitoring nodes between the first and second monitoring nodes. If not, it saves the first monitoring node as the target monitoring node; if so, it saves the duplicate monitoring node as the target monitoring node and the non-duplicate monitoring node as a normal monitoring node. It obtains the warning value and the detected target gas type of the target monitoring node, indexes it in a table based on the index value of the monitoring node, obtains the standard gas type of the target monitoring node, and determines whether all target gas types of the target monitoring node belong to the standard gas type. If so, it saves the warning value of the current target monitoring node; otherwise, it corrects the warning value of the current target monitoring node. It sorts the warning values ​​of the current target monitoring node to obtain the first result, sorts the warning values ​​of the normal monitoring nodes after the last warning value of the first result, and outputs the final sorted result.

[0022] The technical solution of the present invention has at least the following advantages and beneficial effects: The method provided by this invention mainly includes: outputting the first monitoring node with current risk based on the current target data using a thermal degradation early warning model; identifying the target circuit with abnormal current based on remaining power detection; obtaining the second monitoring node on the target circuit; and determining whether all target gas types of the target monitoring nodes belong to standard gas types. By combining this method with analysis of gases that may be emitted from the current monitoring node, the possibility of false alarms at the current detection point is reduced. Based on the obtained ranking results and early warning values, all current monitoring nodes are evaluated to obtain a processing order for staff reference, thereby minimizing the risk of failing to prioritize more urgent monitoring nodes and causing more serious accidents. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the process of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0026] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not imply that the steps in the method flow must be executed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical objective, as long as the same or similar technical effect is achieved.

[0027] The independently described modules or sub-modules may or may not be physically separated; they may be implemented in software or hardware, and some modules or sub-modules may be implemented in software, with the processor calling the software to implement the function of these modules or sub-modules, while other modules or sub-modules may be implemented in hardware, such as through hardware circuits. Furthermore, some or all of the modules can be selected to achieve the purpose of this application's solution according to actual needs.

[0028] Please refer to Figures 1-2 The present invention provides a method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, comprising: S101: Obtain gas detection data from different monitoring nodes, establish a thermal degradation early warning model, and output the first monitoring node with current risk based on the current target data through the thermal degradation early warning model; In this invention, combustible gas detectors, fiber optic temperature sensors, temperature sensors, smoke detectors, infrared temperature cameras, and other hardware devices can be used to collect gas data. Cloud and fog detection and optical Mie scattering detection technologies can be used, combined with residual current monitoring functions, to achieve integrated detection of key parameters such as nanoscale particles, CO, temperature and humidity, and residual current in electrical systems in the very early stages of a fire, thereby improving the fire early warning and electrical safety capabilities of important safety scenarios in substations.

[0029] S102: Obtain the standard gas type generated after thermal degradation of the insulation material in each monitoring node, create a table based on the standard gas types of different monitoring nodes, and add an index value for each monitoring node. By creating a table for searching information, the gas generated by the thermal degradation of insulation materials at the current monitoring node can be quickly retrieved for subsequent analysis and processing.

[0030] For example, 1-PVC cable-gas: DOP (plasticizer), HCl (hydrogen chloride), 2-epoxy resin-gas VOCs (benzene, formaldehyde, phenol), etc.

[0031] S103: Detect the power of each circuit, identify the target circuit with abnormal current based on the power detection, and obtain the second monitoring node on the target circuit. Voltage measurement is the most basic detection method. It displays the amount of electricity by collecting the current voltage. For example, when the meter voltage is within the rated voltage range of 0.7-0.9, if the current of any phase is less than 0.5% of the rated current and the current of other phases is not less than 5-10% of the rated current, it is judged as an abnormal current loss. This includes the sensor layer: current sensor, voltage sensor, etc.; the data acquisition layer: analog-to-digital converter, signal processing unit; the analysis and judgment layer: microprocessor, algorithm module; and the communication layer: RS485, wireless communication module.

[0032] S104: Determine whether there are duplicate monitoring nodes between the first monitoring node and the second monitoring node. If not, save the first monitoring node as the target monitoring node. If there are duplicate monitoring nodes, save the duplicate monitoring nodes as the target monitoring nodes. Non-duplicate monitoring nodes are ordinary monitoring nodes. The above steps are used to verify whether the current problem at the first monitoring node is caused by an abnormal current at the current monitoring node, in order to reduce the impact of false alarms. If it is determined that the problem is caused by an abnormal current, then it is determined that the current first monitoring node has not caused a false alarm. If it is not caused by an abnormal current, then the next step of analysis is carried out.

[0033] S105: Obtain the warning value and the detected target gas type of the target monitoring node, index the table based on the index value of the monitoring node, obtain the standard gas type of the target monitoring node, determine whether all target gas types of the target monitoring node belong to the standard gas type, if so, save the warning value of the current target monitoring node, if not, correct the warning value of the current target monitoring node. The above steps further refine the reason for the alarm of the first monitoring node. Each monitoring node is generally a closed cabinet structure, but it may be affected by external gases, which may cause false alarms. Therefore, if the alarm is not caused by the gas volatilized by the high temperature of the insulation material inside the monitoring node, the current warning value will be corrected and reduced to lower the priority of the current monitoring node for maintenance. The target gas type is the gas that exceeds the alarm threshold.

[0034] S106: Sort the warning values ​​of the current target monitoring nodes to obtain the first result, sort the warning values ​​of ordinary monitoring nodes after the last warning value of the first result, and output the final sorted result.

[0035] Among the ordinary monitoring nodes, there may be a second monitoring node. The second monitoring node did not pass the calculation of the thermal degradation early warning model. Therefore, when sorting, it is necessary to calculate the monitoring nodes that did not pass the calculation of the thermal degradation early warning model.

[0036] The method provided by this invention mainly includes: outputting a first monitoring node with current risk based on the current target data using a thermal degradation early warning model; identifying a target circuit with abnormal current based on remaining power detection; obtaining a second monitoring node on the target circuit; determining whether all target gas types of the target monitoring nodes belong to standard gas types; if not, correcting the early warning value of the current target monitoring node. By combining this method with analysis of the gases that may be emitted from the current monitoring node, the possibility of false alarms at the current detection point is reduced. Based on the obtained early warning values, all current monitoring nodes are evaluated to obtain a processing order for staff reference, in order to avoid neglecting to address more urgent monitoring nodes and causing more serious accidents.

[0037] An exemplary embodiment of the present invention further includes: The gas detection data is preprocessed, the preprocessing including: Gas detection data are grouped by gas type, and within each group, data is sorted chronologically based on the time at which each data point was acquired. The system detects outliers and missing values ​​in each data set, removes and adds outliers, and adds missing values ​​before outputting the processed gas detection data.

[0038] Specifically, after detecting outliers in each data set and removing them, the remaining data includes: The algorithm retrieves the absolute value of the difference between the first data point (preceding the second data point) and the second data point (following the first data point), sets a difference threshold, and checks if the current absolute value of the difference is greater than the threshold. If it is less than or equal to the threshold, no action is taken; otherwise, it retrieves the third data point following the second data point. When the difference between the first and second data points is negative, if the third data point is greater than or equal to the second data point, the second data point is considered normal. If the third data point is less than the second data point, the algorithm retrieves the absolute value of the difference between the second and third data points. If the absolute value of the difference between the second and third data points is greater than or equal to the difference threshold, the second data point is considered an outlier; otherwise, it is considered normal. Similarly, when the difference between the first and second data points is positive, if the third data point is less than the second data point, the second data point is considered normal. If the third data point is greater than or equal to the second data point, the algorithm retrieves the absolute value of the difference between the second and third data points. If the absolute value of the difference between the second and third data points is greater than or equal to the difference threshold, the second data point is considered an outlier; otherwise, it is considered normal.

[0039] In this embodiment, outliers were identified. Outliers have a significant impact on subsequent analysis during the data acquisition process. Therefore, in this embodiment, outliers were removed and supplemented. Through the above-mentioned identification method, abnormally fluctuating values ​​were deleted as much as possible.

[0040] Specifically, the process of removing and supplementing outliers or supplementing missing values ​​includes: Get the missing records of outliers or missing values ​​in the current data, get the data on both sides of the missing record, and write the average of the data on both sides as the fill value to the missing data point. When the data on one or both adjacent sides are also empty record points, the data of the next target record point with existing data is obtained, and the number of record points between the target record point and the empty record point is determined. A selection threshold is set. If the number of record points on only one side is greater than the selection threshold, the data on the other side is used as the fill value. If the number of record points on both sides is greater than the selection threshold, the average value of the current data group is selected as the fill value.

[0041] In this embodiment, instead of simply using the average of two adjacent data points as the replacement value to replace the missing record point, the specific situation of the data on both sides is considered to determine whether it is suitable for use. For example, if the data on both sides are abnormal, the next data point is collected. However, the data point cannot be too far away from the current missing record point, otherwise it is meaningless to use it. Therefore, a selection threshold is set. The selection threshold is the data that is farthest away in time from the current missing record point. It can be set to 3 or 4.

[0042] In one exemplary embodiment of the present invention, establishing a thermal degradation early warning model includes:

[0043] In the formula, Let i be the warning value for the i-th monitoring node. The first monitoring node to exceed the alarm threshold gas concentration, For the first Alarm thresholds for various gas concentrations The temperature of the current monitoring node. This represents the lowest combustion temperature of several types of cables within the current testing point. This represents the average current flowing through all cables within the current monitoring node. The average current flowing through the cables at all testing points. This represents the number of gas types that exceed the alarm threshold at the current monitoring node, where... Only specific numerical values ​​are taken. , and The coefficients are calculated, and their sum is 1.

[0044] This model considers temperature, gas concentration, and current to evaluate the severity of the current monitoring node from three dimensions. Different weights are assigned to each dimension to reflect the impact of each data point on the final evaluation. , , The higher the warning value, the more urgent the current monitoring node is.

[0045] Specifically, the step of outputting the first monitoring node currently at risk based on the current target data through the thermal degradation early warning model includes: Set a judgment threshold. When the warning value is greater than the judgment threshold, save the monitoring node corresponding to the current warning value as the first monitoring node. The judgment threshold can be set based on historical data, or it can be the judgment threshold of this embodiment, which is set to be floating. The more types of gases that exceed the alarm threshold at the monitoring node, the smaller the threshold, and the easier it is to trigger an alarm.

[0046] In the formula, To determine the threshold.

[0047] Secondly, the correction of the warning value of the current target monitoring node includes: Establish a correction model, which includes:

[0048] In the formula, This is the corrected warning value. This represents the number of target gas types that are not among the standard gas types.

[0049] The current warning value is corrected by combining the relationship between the number of target gas types that are not among the standard gas types and the number of gas types exceeding the alarm threshold at the current monitoring node. Less than or equal to When the values ​​are equal, it means that the gas data at this time has no reference value. The current monitoring node will not have gas exceeding the current alarm threshold. Therefore, the latter two data should be used as a reference.

[0050] Secondly, it also includes encrypting and sending the final sorted results: Divide the data into two data packets, construct an elliptic curve, and select points on the curve. , As generators, find the points and points midpoint ; Choose a private key Based on points and Generate public keys separately and public key ; Among them, the private key From 1 to Random numbers between, where Let be the order of the curve, that is, the total number of points on the elliptic curve that can legally participate in the encryption operation, which is generally a large prime number. , .

[0051] Encode the plaintext as , For points on the curve, based on two public keys and the midpoint. Generate the first ciphertext, and use the midpoint As a second ciphertext; The first and second ciphertexts are sent to the receiving end respectively, and the receiving end decrypts them to obtain... .

[0052] Specifically, based on two public keys and a midpoint The generation of the first ciphertext includes:

[0053]

[0054] The second ciphertext includes:

[0055] The receiving end obtains the result after decryption. include: pass Plaintext can be obtained For plaintext Decoding yields the final sorted result; In the formula, This is the first part of the first ciphertext. This is the second part of the first ciphertext. This is the second ciphertext.

[0056] A system for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, characterized in that, for executing the aforementioned method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, the system comprises: The data detection module is configured to include: acquiring gas detection data from different monitoring nodes; establishing a thermal degradation early warning model; outputting the first monitoring node with current risk based on the current target data and the thermal degradation early warning model; acquiring the standard gas types generated after thermal degradation of the insulation material in each monitoring node; establishing a table based on the standard gas types of different monitoring nodes; adding an index value to each monitoring node; detecting the electrical quantity of each circuit; identifying the target circuit with abnormal current based on the electrical quantity detection; and acquiring the second monitoring node on the target circuit. The correction module determines whether there are duplicate monitoring nodes between the first and second monitoring nodes. If not, it saves the first monitoring node as the target monitoring node; if so, it saves the duplicate monitoring node as the target monitoring node and the non-duplicate monitoring node as a normal monitoring node. It obtains the warning value and the detected target gas type of the target monitoring node, indexes it in a table based on the index value of the monitoring node, obtains the standard gas type of the target monitoring node, and determines whether all target gas types of the target monitoring node belong to the standard gas type. If so, it saves the warning value of the current target monitoring node; otherwise, it corrects the warning value of the current target monitoring node. It sorts the warning values ​​of the current target monitoring node to obtain the first result, sorts the warning values ​​of the normal monitoring nodes after the last warning value of the first result, and outputs the final sorted result.

[0057] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0058] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, characterized in that, include: Acquire gas detection data from different monitoring nodes, establish a thermal degradation early warning model, and output the first monitoring node with current risk based on the current target data through the thermal degradation early warning model; Obtain the standard gas type generated after thermal degradation of the insulation material at each monitoring node, create a table based on the standard gas type of different monitoring nodes, and add an index value for each monitoring node; The power of each circuit is detected, and the target circuit with abnormal current is obtained based on the power detection. The second monitoring node on the target circuit is then obtained. Determine whether there are duplicate monitoring nodes between the first monitoring node and the second monitoring node. If not, save the first monitoring node as the target monitoring node. If there are duplicate monitoring nodes, save the duplicate monitoring nodes as the target monitoring nodes. Non-duplicate monitoring nodes are ordinary monitoring nodes. The system obtains the warning value and the type of target gas detected by the target monitoring node. Based on the index value of the monitoring node, it indexes the table to obtain the standard gas type of the target monitoring node. It determines whether all the target gas types of the target monitoring node belong to the standard gas type. If so, the warning value of the current target monitoring node is saved. If not, the warning value of the current target monitoring node is corrected. The first result is obtained by sorting the warning values ​​of the current target monitoring nodes. The warning values ​​of ordinary monitoring nodes are then sorted after the last warning value of the first result, and the final sorted result is output.

2. The method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 1, characterized in that, Also includes: The gas detection data is preprocessed, the preprocessing including: Gas detection data are grouped by gas type, and within each group, data is sorted chronologically based on the time at which each data point was acquired. The system detects outliers and missing values ​​in each data set, removes and adds outliers, and adds missing values ​​before outputting the processed gas detection data.

3. The method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 2, characterized in that, After detecting outliers in each data set and removing them, the data is supplemented with the following: Get the absolute value of the difference between the first data in the adjacent time sequence and the second data in the adjacent time sequence, and set a difference threshold. Determine whether the current absolute value of the difference is greater than the difference threshold. If it is less than or equal to the difference threshold, do not process it. If it is greater than the difference threshold, continue to get the third data after the second data. When the difference between the first and second data is negative, if the third data is greater than or equal to the second data, the second data is considered a normal value. If the third data is less than the second data, the absolute value of the difference between the second and third data is obtained. If the absolute value of the difference between the second and third data is greater than or equal to the difference threshold, the second data is considered an outlier. If it is less than the difference threshold, it is considered a normal value. When the difference between the first and second data is positive, if the third data is less than the second data, the second data is considered a normal value. If the third data is greater than or equal to the second data, the absolute value of the difference between the second and third data is obtained. If the absolute value of the difference between the second and third data is greater than or equal to the difference threshold, the second data is considered an outlier. If it is less than the difference threshold, it is considered a normal value.

4. The method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 3, characterized in that, The process of removing and supplementing outliers or supplementing missing values ​​includes: Get the missing records of outliers or missing values ​​in the current data, get the data on both sides of the missing record, and write the average of the data on both sides as the fill value to the missing data point. When the data on one or both adjacent sides are also empty record points, the data of the next target record point with existing data is obtained, and the number of record points between the target record point and the empty record point is determined. A selection threshold is set. If the number of record points on only one side is greater than the selection threshold, the data on the other side is used as the fill value. If the number of record points on both sides is greater than the selection threshold, the average value of the current data group is selected as the fill value.

5. A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 4, characterized in that, The establishment of the thermal degradation early warning model includes: In the formula, Let i be the warning value for the i-th monitoring node. The first monitoring node to exceed the alarm threshold gas concentration, For the first Alarm thresholds for various gas concentrations The temperature of the current monitoring node. This represents the lowest combustion temperature of several types of cables within the current testing point. This represents the average current flowing through all cables within the current monitoring node. The average current flowing through the cables at all testing points. This represents the number of gas types currently exceeding the alarm threshold at the monitoring node. , and The coefficients are calculated, and their sum is 1.

6. A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, as described in claim 5, is characterized in that... The first monitoring node that currently poses a risk, output by the thermal degradation early warning model based on the current target data, includes: Set a judgment threshold. When the warning value is greater than the judgment threshold, save the monitoring node corresponding to the current warning value as the first monitoring node. The judgment threshold is: In the formula, To determine the threshold.

7. The method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 6, characterized in that, The correction of the warning value of the current target monitoring node includes: Establish a correction model, which includes: In the formula, This is the corrected warning value. This represents the number of target gas types that are not among the standard gas types.

8. A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data according to claim 7, characterized in that, This also includes encrypting and sending the final sorted results: Divide the data into two data packets, construct an elliptic curve, and select points on the curve. , As generators, find the points and points midpoint ; Choose a private key, based on point and Generate two public keys respectively; Encode the plaintext as , For points on the curve, based on two public keys and the midpoint. Generate the first ciphertext, and use the midpoint As a second ciphertext; The first and second ciphertexts are sent to the receiving end respectively, and the receiving end decrypts them to obtain... .

9. A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, as described in claim 8, is characterized in that... The term is based on two public keys and a midpoint. The generation of the first ciphertext includes: The second ciphertext includes: The receiving end obtains the result after decryption. include: pass Plaintext can be obtained For plaintext Decoding yields the final sorted result; In the formula, This is the first part of the first ciphertext. This is the second part of the first ciphertext. This is the second ciphertext. This is the private key.

10. A monitoring and early warning system for thermal degradation of electrical equipment insulation materials based on multi-source data, characterized in that, A method for monitoring and early warning of thermal degradation of electrical equipment insulation materials based on multi-source data, as described in any one of claims 1-9, includes: The data detection module is configured to include: acquiring gas detection data from different monitoring nodes; establishing a thermal degradation early warning model; outputting the first monitoring node with current risk based on the current target data and the thermal degradation early warning model; acquiring the standard gas types generated after thermal degradation of the insulation material in each monitoring node; establishing a table based on the standard gas types of different monitoring nodes; adding an index value to each monitoring node; detecting the electrical quantity of each circuit; identifying the target circuit with abnormal current based on the electrical quantity detection; and acquiring the second monitoring node on the target circuit. The correction module determines whether there are duplicate monitoring nodes between the first and second monitoring nodes. If not, it saves the first monitoring node as the target monitoring node; if so, it saves the duplicate monitoring node as the target monitoring node and the non-duplicate monitoring node as a normal monitoring node. It obtains the warning value and the detected target gas type of the target monitoring node, indexes it in a table based on the index value of the monitoring node, obtains the standard gas type of the target monitoring node, and determines whether all target gas types of the target monitoring node belong to the standard gas type. If so, it saves the warning value of the current target monitoring node; otherwise, it corrects the warning value of the current target monitoring node. It sorts the warning values ​​of the current target monitoring node to obtain the first result, sorts the warning values ​​of the normal monitoring nodes after the last warning value of the first result, and outputs the final sorted result.

Images