High-voltage switch cabinet fault monitoring method and system

Abstract

The invention provides a high-voltage switch cabinet fault monitoring method and system, and belongs to the technical field of power equipment monitoring, and the method comprises the steps: obtaining the temperature data of each temperature monitoring point in a high-voltage switch cabinet; the concentration data of the characteristic gas in a target area is obtained, and the target area is a circular target area determined with each temperature monitoring point in the high-voltage switch cabinet as the center and the preset distance as the radius; determining an incidence relation between each temperature data and the concentration data of the characteristic gas according to the temperature data and the concentration data of the characteristic gas; and determining the change trend of the concentration data of the characteristic gas according to the association relationship, and monitoring the fault trend of the high-voltage switch cabinet according to the change trend. According to the high-voltage switch cabinet fault monitoring method and system provided by the invention, the accuracy and timeliness of high-voltage switch cabinet fault monitoring can be improved, and stable operation of a power system is ensured.

Description

Technical Field

[0001] This application belongs to the field of power equipment monitoring technology, and more specifically, relates to a method and system for monitoring faults in high-voltage switchgear. Background Technology

[0002] High-voltage switchgear, as a crucial electrical device in the power system, plays an irreplaceable core role in the distribution, control, and protection of power lines. It is one of the key devices to ensure the safe, stable, and reliable operation of the power system, and its operating status is directly related to the power supply quality and security of the entire power network.

[0003] However, during long-term operation, high-voltage switchgear is highly susceptible to failure due to factors such as aging of internal electrical components, poor contact, and deterioration of insulation performance. Traditional fault monitoring methods often rely on single monitoring parameters, which cannot comprehensively and accurately reflect the actual operating conditions inside the high-voltage switchgear. For example, relying solely on temperature monitoring may overlook potential faults indicated by characteristic gases produced due to the decomposition of insulating materials, leading to delayed fault detection and potentially even serious power accidents, posing a significant threat to the safe operation of the power system. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for monitoring faults in high-voltage switchgear, so as to improve the accuracy and timeliness of fault monitoring in high-voltage switchgear and ensure the stable operation of the power system.

[0005] A first aspect of this application provides a method for fault monitoring of high-voltage switchgear, comprising: Acquire temperature data from various temperature monitoring points inside the high-voltage switchgear; Acquire the concentration data of characteristic gases within the target area. The target area is a circular target area defined by taking each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius. The correlation between temperature data and the concentration data of characteristic gases is determined based on temperature data and the concentration data of characteristic gases. The trend of characteristic gas concentration data is determined based on the correlation, and the fault trend of high-voltage switchgear is monitored based on the trend.

[0006] A second aspect of this application provides a high-voltage switchgear fault monitoring system, comprising: The temperature data acquisition module is used to acquire temperature data from various temperature monitoring points inside the high-voltage switchgear. The gas concentration acquisition module is used to acquire the concentration data of characteristic gases in the target area. The target area is a circular target area defined by taking each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius. The correlation determination module is used to determine the correlation between temperature data and the concentration data of characteristic gases based on temperature data and the concentration data of characteristic gases. The fault monitoring module is used to determine the changing trend of the concentration data of characteristic gases based on the correlation, and to monitor the fault trend of the high-voltage switchgear based on the changing trend.

[0007] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described high-voltage switchgear fault monitoring method.

[0008] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described high-voltage switchgear fault monitoring method.

[0009] The beneficial effects of the high-voltage switchgear fault monitoring method and system provided in this application are as follows: By combining the temperature data inside the high-voltage switchgear with the concentration data of characteristic gases in the corresponding area, the correlation between the two is determined. Based on the correlation between the temperature data and the concentration data of characteristic gases, the changing trend of characteristic gases is determined. This can comprehensively capture possible faults inside the high-voltage switchgear, making up for the fact that when relying solely on single temperature data for monitoring, potential faults indicated by characteristic gases generated due to the decomposition of insulating materials are ignored. Thus, the actual operating conditions inside the high-voltage switchgear are accurately reflected, the accuracy of fault monitoring is improved, and the safe and stable operation of the power system is ensured. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a high-voltage switchgear fault monitoring method provided in an embodiment of this application; Figure 2 This is a structural block diagram of a high-voltage switchgear fault monitoring system provided in an embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0014] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a high-voltage switchgear fault monitoring method according to an embodiment of this application. The method may include: S101: Obtain temperature data from various temperature monitoring points inside the high-voltage switchgear.

[0015] In this embodiment, multiple monitoring points are installed inside the high-voltage switchgear based on its structure and heat-prone areas (e.g., busbar joints, circuit breaker contacts, cable terminals, and other critical connection points). These monitoring points cover different electrical component areas to ensure a clear reflection of the overall temperature distribution and potential heat sources within the high-voltage switchgear. The number of monitoring points can be determined according to the specifications of the high-voltage switchgear (e.g., single cabinet, combined cabinet).

[0016] Sensors suitable for high-voltage environments should be used, with priority given to wireless passive sensors (such as surface acoustic wave sensors) or fiber optic sensors to avoid electromagnetic interference affecting data accuracy. For auxiliary monitoring in low-voltage areas, thermocouples or PT100 resistance temperature detectors (RTD) sensors can be selected to ensure a temperature measurement range of -40℃ to 150℃, meeting the temperature monitoring needs of high-voltage switchgear under normal and fault conditions. The sensor should be fixed to the surface of the monitoring point using magnetic attraction or screws to ensure good contact between the sensor and the measured part of the high-voltage switchgear. Simulate temperature points of 0℃, 50℃, and 100℃ in the laboratory, compare the sensor readings with the standard thermometer readings, and correct the error to within ±0.5℃ to ensure data accuracy.

[0017] Temperature data is collected in real time by sensors, with a sampling frequency set to once per minute, which can be increased to once per 10 seconds when a fault warning is issued. The collected temperature data is transmitted wirelessly or via wired cable to a data acquisition terminal outside the high-voltage switchgear. The terminal performs preliminary filtering on the raw data, removing obvious outliers (such as erroneous data exceeding the sensor's range), and then stores the filtered temperature data in the background database.

[0018] Regularly check the data transmission status of each monitoring point (e.g., once per hour). If no data is received from a monitoring point for three consecutive times, trigger a communication failure alarm. The operation and maintenance personnel will then investigate sensor connection or transmission problems to ensure continuous and complete data transmission.

[0019] S102: Obtain the concentration data of characteristic gases within the target area. The target area is a circular target area defined by taking each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius.

[0020] In this embodiment, the characteristic gases that need to be monitored are determined. The characteristic gases may include hydrogen (H2), carbon monoxide (CO), methane (CH4), ethylene (C2H4), and acetylene (C2H5). The concentration data of each characteristic gas is obtained, and the concentration data of each characteristic gas reflects different fault types of the high-voltage switchgear.

[0021] Using the established temperature monitoring points as centers, and based on the internal space dimensions and gas diffusion characteristics of the high-voltage switchgear, a preset distance is set as the radius. For compact areas such as busbar joints and circuit breaker contacts, the preset distance can be set to 5-10cm; for relatively open areas such as cable terminals, the preset distance can be set to 10-15cm. This ensures that the target area can cover the main gas diffusion range, while avoiding excessive overlap of target areas of different monitoring points (for example, controlling the overlap rate of different monitoring points to ≤20%).

[0022] Select a gas sensor suitable for high-pressure, confined environments, prioritizing infrared gas sensors capable of simultaneously detecting the aforementioned characteristic gases. The measurement range should meet the following requirements: H2 (0-1000ppm), CO (0-500ppm), CH4 (0-1000ppm), C2H4 (0-500ppm), C2H2 (0-100ppm), with an accuracy error ≤ ±5% FS (full scale). Install the infrared gas sensor at the radius boundary of each corresponding temperature monitoring point, ensuring the sensor probe is directly facing the center of the target area, and the straight-line distance between the sensor and the monitoring point equals the radius. After installation, calibrate the distance using a laser rangefinder, controlling the error within ±1cm to ensure accurate coverage of the target area.

[0023] The infrared gas sensor and temperature sensor are configured to use the same sampling frequency to collect real-time concentration data of characteristic gases within the target area. During acquisition, gas data is synchronized with the corresponding temperature monitoring point's temperature data via timestamps to ensure a one-to-one correspondence in time. The collected raw concentration data is preprocessed to remove outliers caused by infrared gas sensor drift (e.g., concentrations suddenly exceeding the measurement range), and data fluctuations are smoothed by averaging three consecutive samples. If the gas sensor in a target area fails to collect valid data for five consecutive times, a sensor fault alarm is triggered, prompting maintenance personnel to check the equipment connection or replace the infrared gas sensor.

[0024] S103: Determine the correlation between temperature data and the concentration data of characteristic gases based on temperature data and the concentration data of characteristic gases.

[0025] In this embodiment, step S103 includes: The regression model was determined based on temperature data and the corrected concentration data of the characteristic gas. Multiple temperature ranges are determined based on temperature data; The correlation between temperature data and the concentration data of characteristic gases is determined based on each temperature range and the regression model. Before determining the correlation between temperature data and the concentration data of characteristic gases, the process also includes: correcting the concentration data of characteristic gases based on ambient humidity data.

[0026] In this embodiment, the concentration data of the characteristic gas is corrected based on the ambient humidity data to eliminate the influence of humidity on the detection results of the concentration data of the characteristic gas.

[0027] A regression model is determined based on the preprocessed temperature data and the corrected characteristic gas concentration data. This regression model is used to quantify the relationship between temperature changes and characteristic gas concentration changes. Temperature data of the high-voltage switchgear under different operating conditions, as well as characteristic gas concentration data corrected for ambient humidity, are obtained, and a model is constructed using linear regression or multinomial regression methods.

[0028] Based on the relationship between the concentration data of each characteristic gas and the temperature data, the change curve of each characteristic gas with temperature is determined, the concentration change rate of each characteristic gas is determined, the corresponding peak point is determined based on the concentration change rate of each characteristic gas, the temperature value corresponding to each peak point is determined based on each peak point, and the temperature range is divided based on each temperature value.

[0029] For each temperature range, the growth rate of the concentration data of the characteristic gas in that temperature range as a function of temperature data is determined by combining a regression model, and the correlation between the temperature data and the concentration data of the characteristic gas is determined based on the growth rate.

[0030] S104: Determine the trend of characteristic gas concentration data based on the correlation, and monitor the fault trend of high-voltage switchgear based on the trend of change.

[0031] In this embodiment, based on the correlation between temperature data and the concentration data of each characteristic gas, the law of the concentration of each characteristic gas changing with temperature is analyzed. If there is a correlation between temperature data and the concentration data of each characteristic gas, the growth rate of the concentration of each characteristic gas (e.g., the increase in concentration corresponding to a unit temperature change) is calculated by regression model, and its change curve is fitted by combining historical data to determine the change trend of the concentration of the characteristic gas. This change trend is the growth trend of the concentration of the characteristic gas.

[0032] Based on the corresponding characteristics of different characteristic gases and fault types (for example, acetylene corresponds to arc discharge faults, and ethylene corresponds to high temperature overheating faults), and combined with the concentration growth trend of different characteristic gases, the following judgments are made: if the acetylene concentration increases exponentially and the temperature rises rapidly in the 60-80℃ range, it is determined that there may be a local arc discharge fault; if the ethylene concentration increases linearly with temperature and the temperature remains above 80℃, it is determined that there may be a contact overheating fault; if the concentrations of multiple gases increase slowly but do not exceed the threshold and the growth trend is stable, it is determined to be a slight gas release under normal operating conditions, in which case the high-voltage switchgear is fault-free.

[0033] As can be seen from the above, the embodiments of this application combine the temperature data inside the high-voltage switchgear with the concentration data of characteristic gases in the corresponding area to determine the correlation between the two. Based on the correlation between the temperature data and the concentration data of characteristic gases, the changing trend of characteristic gases can be determined. This can comprehensively capture possible faults inside the high-voltage switchgear, making up for the fact that when relying solely on single temperature data for monitoring, potential faults indicated by characteristic gases generated by the decomposition of insulating materials are ignored. Thus, it accurately reflects the actual operating conditions inside the high-voltage switchgear, improves the accuracy of fault monitoring, and ensures the safe and stable operation of the power system.

[0034] In one embodiment of this application, determining multiple temperature ranges based on temperature data includes: Based on the relationship between the concentration of each characteristic gas and temperature data, the peak point of the concentration change rate of each characteristic gas is determined. The temperature sequence is determined based on the temperature corresponding to each peak point; Multiple temperature ranges are determined based on the temperature sequence.

[0035] In this embodiment, based on the acquired temperature data of the high-voltage switchgear and the concentration data of each characteristic gas corresponding to different temperatures of the high-voltage switchgear, multiple sets of sample pairs (temperature T, concentration C) between temperature and concentration are formed. The concentration-temperature curve between the concentration data and temperature data of each characteristic gas is plotted using a data visualization tool to intuitively present the change law of the concentration of the characteristic gas with temperature.

[0036] Differentiate the concentration-temperature curves for each gas to obtain the relationship curve between the concentration change rate and temperature for each characteristic gas. Based on the relationship curves of the concentration change rate and temperature for each characteristic gas, determine the maximum point (i.e., the inflection point where the rate of change changes from increasing to decreasing) in each curve, and determine the peak point of the concentration change rate for each characteristic gas.

[0037] Extract the temperature values ​​corresponding to the peak values ​​of all characteristic gas concentration change rates, remove duplicate values, and sort them in ascending order to form a temperature sequence. Using the temperature sequence as the dividing point, and combining it with the normal operating temperature range of the high-voltage switchgear (e.g., -10℃ to 120℃), divide the overall temperature range of the high-voltage switchgear into multiple continuous intervals, thereby determining multiple temperature intervals of the temperature data.

[0038] For example, taking CO, CH4, and C2H4 as examples, sample pairs between different temperature data and the concentrations of CO, CH4, and C2H4 were obtained. Specifically, the sample pairs between temperature and concentration data for CO were: (30℃, 10ppm), (40℃, 15ppm), (50℃, 30ppm), (60℃, 40ppm), and (70℃, 45ppm); the sample pairs between temperature and concentration data for CH4 were: (30℃, 5ppm), (40℃, 8ppm), (50℃, 10ppm), (60℃, 25ppm), and (70℃, 30ppm); and the sample pairs between temperature and concentration data for C2H4 were: (30℃, 0ppm), (40℃, 2ppm), (50℃, 5ppm), (60℃, 15ppm), and (70℃, 40ppm).

[0039] Based on the sample pairs corresponding to the aforementioned characteristic gases, the concentration change rate of each characteristic gas is determined. Taking the concentration change rate of CO as an example, the concentration change rate of CO is determined based on adjacent concentration data and adjacent temperature data: (15-10) / (40-30) = 0.5 ppm / ℃, (30-15) / (50-40) = 1.5 ppm / ℃, (40-30) / (60-50) = 1.0 ppm / ℃, (45-40) / (70-60) = 0.5 ppm / ℃. Based on the above change rates, the peak point of the CO concentration change rate is determined to be at 50℃, corresponding to a concentration change rate of 1.5 ppm / ℃. Using the same calculation method, the peak point of the CH4 concentration change rate is determined to be at 60℃, corresponding to a concentration change rate of 1.5 ppm / ℃; the peak point of the C2H4 concentration change rate is at 70℃, corresponding to a concentration change rate of 2.5 ppm / ℃.

[0040] The peak temperatures of CO, CH4, and C2H4 are 50℃, 60℃, and 70℃, respectively, so the temperature sequence is [50℃, 60℃, 70℃]. Considering the operating range of the high-voltage switchgear (-10℃~120℃), the temperature ranges are determined as [-10℃, 50℃), [50℃, 60℃), [60℃, 70℃), [70℃, 120℃].

[0041] In one embodiment of this application, the correlation between temperature data and the concentration data of a characteristic gas is determined based on each temperature range and the corresponding regression model, including: The growth rate of the concentration data of the characteristic gas within each temperature range as a function of temperature data is determined based on the regression model corresponding to each temperature range. If the growth rate is less than or equal to the preset growth rate threshold within the temperature range, and the concentration data of each characteristic gas within the temperature range does not exceed the preset concentration threshold, then it is determined that there is a correlation between the temperature data and the concentration data of the characteristic gas within the temperature range. If the growth rate is greater than the preset growth rate threshold within the temperature range, or if the concentration data of at least one characteristic gas within the temperature range exceeds the preset concentration threshold, it is determined that there is no correlation between the temperature data and the concentration data of the characteristic gas within the temperature range.

[0042] In this embodiment, based on the pre-defined temperature intervals, a regression model is determined for each temperature interval according to the temperature data and the concentration data of the characteristic gas within each interval. For each temperature interval, the growth rate corresponding to the concentration of the characteristic gas in each temperature interval is determined using the parameter values ​​of the regression model corresponding to each temperature interval. For linear models, the growth rate is the slope k of the regression equation within that interval (i.e., the concentration change value corresponding to a unit temperature change); for nonlinear models, the average growth rate is calculated by differentiation or by the ratio of the concentration change to the temperature change within the interval.

[0043] Based on historical fault data and safe operation standards of high-voltage switchgear, preset growth rate thresholds and preset concentration thresholds for characteristic gas concentrations are set for each temperature range. For example, within the temperature range of [-10℃, 50℃), the preset growth rate threshold for CO is set to 1.2ppm / ℃, and the preset concentration threshold is set to 30ppm; within the temperature range of [50℃, 60℃), the preset growth rate threshold for CO is set to 1.5ppm / ℃, and the preset concentration threshold is set to 40ppm.

[0044] If the growth rate of the concentration data of a characteristic gas with temperature within a certain temperature range is less than or equal to a preset growth rate threshold for that temperature range, and the concentration data of all characteristic gases within that temperature range are less than or equal to their respective preset concentration thresholds, then it is determined that there is a correlation between the temperature data and the concentration data of the characteristic gases within that temperature range. If the growth rate of the concentration data of a characteristic gas with temperature within a certain temperature range is greater than the preset growth rate threshold for that temperature range, or the concentration data of at least one characteristic gas is greater than its preset concentration threshold, then it is determined that there is no correlation between the temperature data and the concentration data of the characteristic gases within that temperature range.

[0045] For example, taking the monitoring results of CO gas in a 10kV high-voltage switchgear within the temperature range of [50℃, 60℃) as an example, the temperature data in this temperature range are 50℃, 55℃, and 60℃, and the corresponding corrected CO concentration data are 30ppm, 38ppm, and 45ppm. The regression model for this temperature range is determined to be C=1.3T-35 (k=1.3), where C is the CO gas concentration, T is the temperature, and k is the slope. The growth rate of CO concentration with temperature data in this temperature range is the slope of the regression model, 1.3ppm / ℃. Within the [50℃, 60℃) temperature range, the preset growth rate threshold for CO is set to 1.5ppm / ℃, and the preset concentration threshold is set to 40ppm. At this point, the growth rate of CO concentration with temperature data is less than the preset growth rate threshold for CO, and the CO concentration at 60℃ in this temperature range is 45ppm, which is greater than the preset concentration threshold. Therefore, it is determined that within the [50℃, 60℃) temperature range, there is no correlation between the temperature data and the CO concentration data.

[0046] Taking the monitoring results of CH4 gas in the high-voltage switchgear within the temperature range of [-10℃, 50℃) as an example, the regression model within this temperature range is C1=0.8T+5 (k=0.8), where C1 is the concentration of CH4 gas. The preset growth rate threshold for CH4 within this temperature range is set to 1.0ppm / ℃, and the preset concentration threshold is set to 20ppm. At this point, the growth rate of CH4 concentration with temperature data is less than the preset growth rate threshold for CH4, and the highest concentration of CH4 within this temperature range is 18ppm, which is less than the preset concentration threshold. Therefore, it is determined that there is a correlation between temperature data and CH4 concentration data within the temperature range of [-10℃, 50℃).

[0047] In one embodiment of this application, determining the growth rate of the concentration data of a characteristic gas within a temperature range as a function of temperature data, based on each temperature range and a regression model, includes: Based on the concentration data of the characteristic gas in each temperature range and the corresponding regression model, the parameter values ​​in the corresponding regression model are determined by the least squares method, and the growth rate of the concentration data of the characteristic gas in each temperature range is determined based on the parameter values.

[0048] In this embodiment, a regression model is determined for each temperature range. The regression model includes a linear regression model and a nonlinear regression model. The linear regression model can be C=kT+b, where b is the intercept; the nonlinear regression model can be C=aT. 2 +dT+c, where a is the coefficient of the quadratic term, d is the coefficient of the linear term, and c is the constant term.

[0049] Substitute the temperature and concentration data within the temperature range into the regression model, and calculate the parameter values ​​of the regression model using the least multiplication method. For the linear regression model, solve for the slope and intercept that minimize the sum of squared errors. The slope is the growth rate of the concentration data of the characteristic gas with temperature data. For the nonlinear regression model, solve for the corresponding coefficients, differentiate the nonlinear regression model, and substitute the temperature data within the temperature range into the differentiation formula to obtain the average growth rate within that temperature range.

[0050] For example, consider the monitoring of CO gas in a high-voltage switchgear within the temperature range of [50℃, 60℃). The temperature data within this range are 50℃, 52℃, 55℃, 58℃, and 60℃, with corresponding corrected CO concentration data of 30ppm, 33ppm, 38ppm, 42ppm, and 45ppm. The linear regression model for this temperature range is determined to be C=kT+b. Substituting the temperature data and corresponding concentration data into this linear regression model, the sum of squared errors is determined. This sum of squared errors is the sum of the squares of the differences between the actual concentration at each monitoring point and the concentration predicted by the model. Partial derivatives are calculated with respect to the slope and intercept, and then set to zero. This determines the slope k to be 1.25 and the intercept b to be -32.5, thus determining the linear regression model as C=1.25T-32.5. That is, within the temperature range of [50℃, 60℃), the CO concentration increases with temperature at a rate of 1.25ppm / ℃.

[0051] In one embodiment of the application, after determining the growth rate of the concentration data of the characteristic gas within each temperature range based on the parameter values, the method further includes: Based on the pre-trained multi-label classification model and the growth rate of the concentration data of the characteristic gas in each temperature range, obtain the set of fault types output by the multi-label classification model; If the number of elements in the fault type set is greater than 1, then the growth rate is determined to correspond to multiple fault types. If the number of elements in the fault type set is zero, then the growth rate is considered to correspond to no faults.

[0052] In this embodiment, the pre-trained multi-label classification model is trained as follows: historical data of the high-voltage switchgear under different states is acquired. This historical data includes the growth rate of the concentration of the characteristic gas with temperature in each temperature range, and the actual fault type corresponding to each growth rate. The fault types are then encoded. Each fault type is converted into a label, and the multi-label training dataset is determined. In the actual fault types corresponding to each growth rate, one growth rate may correspond to multiple fault types, or one growth rate may correspond to no fault.

[0053] Choose a multi-label classification algorithm, such as multi-label K-nearest neighbors or decision tree-based multi-label classification. Train the multi-label classification model using training data from the prepared multi-label training dataset, optimize the model parameters, and enable the multi-label classification model to learn the correspondence between the growth rate and the set of fault types, thus obtaining a pre-trained multi-label classification model.

[0054] The growth rate of the characteristic gas concentration with temperature within the current temperature range is used as input to the multi-label classification model. Based on the input growth rate, the model outputs a set of corresponding fault types. The number of elements in this set is then determined. If the number of elements is greater than 1, the growth rate is considered to correspond to multiple fault types; if the number of elements is 0, the growth rate is considered to correspond to no fault.

[0055] For example, suppose the fault types of a high-voltage switchgear may include slight contact overheating, mild insulation aging, arc discharge, or severe contact overheating. Each fault type is coded as 1, 2, 3, and 4, respectively, to determine a multi-label training dataset. In this example, when the growth rate is 1.2 ppm / ℃, the corresponding fault types are slight contact overheating and mild insulation aging; when the growth rate is 2.5 ppm / ℃, the corresponding fault types are arc discharge and severe contact overheating; and when the growth rate is 0.5 ppm / ℃, the corresponding high-voltage switchgear has no faults.

[0056] The concentration of a certain characteristic gas within the current temperature range is determined to increase at a rate of 2.3 ppm / ℃ with temperature. This rate is input into a trained multi-label classification model. The multi-label classification model outputs a set of fault types as {3,4}. Since the number of elements in this set is greater than 1, it is determined that this rate corresponds to multiple fault types, namely, arc discharge and severe overheating of contacts.

[0057] In one embodiment of this application, the degree of failure of the high-voltage switchgear is determined based on the concentration growth rate of the characteristic gas, and corresponding countermeasures are taken based on the degree of failure of the high-voltage switchgear.

[0058] In this embodiment, the fault index characterizes the fault severity of the high-voltage switchgear. The fault index formula is determined by the concentration growth rate of the characteristic gas, a preset safety threshold, and a fault acceleration coefficient. The fault index formula is as follows: ,in, F The failure index, r The concentration growth rate of the characteristic gas. To preset a safety threshold, m This is the fault acceleration factor. This represents the critical failure rate. In this failure index formula, This indicates no fault. Indicates the fault development stage. This indicates a serious malfunction.

[0059] The degree of fault in the high-voltage switchgear is determined based on this fault index. F If the concentration is 0, the high-voltage switchgear is considered to have a stable concentration and no fault; if 0 < FIf the concentration of the characteristic gas is ≤0.3, it is determined that there is a slight leakage, and the high-voltage switchgear is in a state of minor fault. In this case, it is necessary to determine the monitoring point corresponding to the leakage location, adjust the operating parameters of the high-voltage switchgear, increase the sampling frequency, and suppress the leakage of the characteristic gas concentration; if 0.3 < F If the concentration of the characteristic gas is less than 1, it is determined that there is a medium-level leak, and the high-voltage switchgear is in a medium-level fault state. In this case, the power supply to the high-voltage switchgear must be cut off, local ventilation must be activated, the monitoring point corresponding to the medium-level leak location must be determined, and the faulty equipment must be switched off. F If the value is 1, it indicates a serious leak in the concentration of the characteristic gas, and the high-voltage switchgear is in a state of serious fault. In this case, it is necessary to remotely cut off all power sources, evacuate maintenance personnel, and activate the fire sprinkler system.

[0060] In one embodiment of this application, determining the trend of concentration data of a characteristic gas based on correlation, and monitoring faults in a high-voltage switchgear based on the trend of change, includes: The growth trend of concentration data for each characteristic gas was determined based on the correlation. The fault trend of high-voltage switchgear is monitored based on the concentration data of each characteristic gas and its corresponding growth trend.

[0061] In this embodiment, from the established correlation between temperature and the concentration of characteristic gases, the correlation status (including whether there is a correlation or not), corresponding concentration data and growth rate of each characteristic gas in each temperature range are extracted to form a single gas correlation dataset.

[0062] For temperature ranges where there are correlations in the associated dataset of a single gas, the growth rate and concentration change curves within that temperature range are combined to determine the type of growth trend of the characteristic gas concentration. If the growth rate is stable and the concentration increases proportionally with temperature, it is determined to be a linear growth trend; if the growth rate increases significantly with temperature (for example, the growth rate is a quadratic function of temperature), it is determined to be an accelerating growth trend; if the growth rate fluctuates within a preset fluctuation range and the concentration changes slowly, it is determined to be a slow growth trend.

[0063] The fault trend of high-voltage switchgear is monitored by the concentration growth trend of characteristic gases. For characteristic gases with a linear growth trend but whose concentration is far below the preset concentration threshold, it is determined that the high-voltage switchgear has a slight change trend under normal operation. For characteristic gases with an accelerating growth trend and whose concentration is close to or exceeds the preset concentration threshold, it is determined that the fault risk of the high-voltage switchgear is increasing and requires close attention. When multiple characteristic gases show an accelerating growth trend at the same time, it is determined that the high-voltage switchgear has a complex fault risk trend and requires urgent investigation.

[0064] For example, CO gas exhibits a correlation within the temperature range of [40℃, 50℃]. At this temperature, the CO concentration is 25ppm (the preset concentration threshold is 40ppm), with a growth rate of 0.8ppm / ℃. The concentration increases steadily with temperature, indicating a linear growth trend. Since the CO concentration does not exceed the preset concentration threshold and the growth is gradual, the monitoring indicates that the high-voltage switchgear is in normal operation with no significant risk of failure.

[0065] Corresponding to the high-voltage switchgear fault monitoring method in the above embodiment, Figure 2 This is a structural block diagram of a high-voltage switchgear fault monitoring system provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The high-voltage switchgear fault monitoring system 20 includes: a temperature data acquisition module 21, a gas concentration acquisition module 22, a correlation determination module 23, and a fault monitoring module 24.

[0066] Among them, the temperature data acquisition module 21 is used to acquire temperature data of each temperature monitoring point inside the high-voltage switchgear; The gas concentration acquisition module 22 is used to acquire the concentration data of characteristic gases in the target area. The target area is a circular target area defined with each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius. The correlation determination module 23 is used to determine the correlation between each temperature data and the concentration data of the characteristic gas based on the temperature data and the concentration data of the characteristic gas. The fault monitoring module 24 is used to determine the changing trend of the concentration data of the characteristic gas based on the correlation, and to monitor the fault trend of the high-voltage switchgear based on the changing trend.

[0067] In one embodiment of this application, before the correlation determination module 23 determines the correlation between each temperature data and the concentration data of the characteristic gas, the high-voltage switchgear fault monitoring system 20 further includes a gas concentration correction module. The gas concentration correction module is used to correct the concentration data of characteristic gases based on ambient humidity data.

[0068] The correlation determination module 23 is further used to determine the regression model based on the temperature data and the corrected concentration data of the characteristic gas; Multiple temperature ranges are determined based on temperature data; The correlation between temperature data and the concentration data of characteristic gases is determined based on each temperature range and the regression model.

[0069] In one embodiment of this application, the correlation determination module 23 is further used to determine the peak point of the concentration change rate of each characteristic gas based on the relationship between the concentration of each characteristic gas and the temperature data. The temperature sequence is determined based on the temperature corresponding to each peak point; Multiple temperature ranges are determined based on the temperature sequence.

[0070] In one embodiment of this application, the correlation determination module 23 is further configured to determine the growth rate of the concentration data of the characteristic gas within each temperature range as a function of the temperature data, based on each temperature range and the regression model. If the growth rate is less than or equal to the preset growth rate threshold within the temperature range, and the concentration data of each characteristic gas within the temperature range does not exceed the preset concentration threshold, then it is determined that there is a correlation between the temperature data and the concentration data of the characteristic gas within the temperature range. If the growth rate is greater than the preset growth rate threshold within the temperature range, or if the concentration data of at least one characteristic gas within the temperature range exceeds the preset concentration threshold, it is determined that there is no correlation between the temperature data and the concentration data of the characteristic gas within the temperature range.

[0071] In one embodiment of this application, the correlation determination module 23 is further specifically used to determine the parameter value in the regression model by least squares method based on the concentration data of the characteristic gas in the corresponding temperature range in each temperature range and the corresponding temperature range in the regression model, and to determine the growth rate of the concentration data of the characteristic gas in each temperature range based on the parameter value.

[0072] In one embodiment of this application, after the correlation determination module 23 determines the growth rate of the concentration data of the characteristic gas in each temperature range, it is further used to... Based on the pre-trained multi-label classification model and the growth rate of the concentration data of the characteristic gas in each temperature range, obtain the set of fault types output by the multi-label classification model; If the number of elements in the fault type set is greater than 1, then the growth rate is determined to correspond to multiple fault types. If the number of elements in the fault type set is zero, then the growth rate is considered to correspond to no faults.

[0073] In one embodiment of this application, the fault monitoring module 24 is further configured to determine the growth trend of the concentration data of each characteristic gas based on the correlation relationship; The fault trend of high-voltage switchgear is monitored based on the concentration data of each characteristic gas and its corresponding growth trend.

[0074] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application.Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above system embodiments, for example... Figure 2 The functions of the temperature data acquisition module 21, gas concentration acquisition module 22, correlation determination module 23, and fault monitoring module 24 are shown.

[0075] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0076] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0077] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store temperature data of various temperature monitoring points inside the high-voltage switchgear, concentration data of characteristic gases in various target areas, and the correlation between the temperature data and the concentration data of characteristic gases.

[0078] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the high-voltage switchgear fault monitoring method provided in the embodiments of this application, or they can execute the implementation method of the electronic equipment described in the embodiments of this application, which will not be repeated here.

[0079] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or system capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0080] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0081] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0082] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0083] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0084] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0085] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0086] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for fault monitoring in high-voltage switchgear, characterized in that, include: Acquire temperature data from various temperature monitoring points inside the high-voltage switchgear; Acquire the concentration data of characteristic gases within the target area, wherein the target area is a circular target area defined with each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius; The correlation between each temperature data point and the concentration data of the characteristic gas is determined based on the temperature data and the concentration data of the characteristic gas. The trend of the concentration data of the characteristic gas is determined based on the correlation, and the fault trend of the high-voltage switchgear is monitored based on the trend of the change.

2. The high-voltage switchgear fault monitoring method as described in claim 1, characterized in that, Before determining the correlation between each temperature data point and the concentration data of the characteristic gas based on the temperature data and the concentration data of the characteristic gas, the method further includes: The concentration data of the characteristic gas is corrected based on the ambient humidity data; The step of determining the correlation between each temperature data point and the concentration data of the characteristic gas based on the temperature data and the concentration data of the characteristic gas includes: The regression model is determined based on the temperature data and the corrected concentration data of the characteristic gas. Multiple temperature ranges are determined based on the temperature data; The correlation between temperature data and the concentration data of characteristic gases is determined based on each temperature range and the regression model.

3. The high-voltage switchgear fault monitoring method as described in claim 2, characterized in that, The step of determining multiple temperature ranges based on the temperature data includes: Based on the relationship between the concentration of each characteristic gas and the temperature data, the peak point of the concentration change rate of each characteristic gas is determined. The temperature sequence is determined based on the temperature corresponding to each peak point; Multiple temperature ranges are determined based on the temperature sequence.

4. The high-voltage switchgear fault monitoring method as described in claim 2, characterized in that, The step of determining the correlation between temperature data and the concentration data of characteristic gases based on each temperature range and the regression model includes: The growth rate of the concentration data of the characteristic gas within each temperature range as a function of the temperature data is determined based on the regression model for each temperature range. If the growth rate is less than or equal to the preset growth rate threshold within the temperature range, and the concentration data of each characteristic gas within the temperature range does not exceed the preset concentration threshold corresponding to the concentration data of each characteristic gas, then it is determined that there is a correlation between the temperature data and the concentration data of the characteristic gas within the temperature range. If the growth rate is greater than the preset growth rate threshold within the temperature range, or if the concentration data of at least one characteristic gas within the temperature range exceeds the corresponding preset concentration threshold, it is determined that there is no correlation between the temperature data and the concentration data of the characteristic gas within the temperature range.

5. The high-voltage switchgear fault monitoring method as described in claim 4, characterized in that, The step of determining the growth rate of the concentration data of the characteristic gas within each temperature range as a function of the temperature data, based on each temperature range and the regression model, includes: Based on the concentration data of the characteristic gas in each temperature range and the corresponding temperature range in the regression model, the parameter values ​​in the regression model are determined by the least squares method, and the growth rate of the concentration data of the characteristic gas in each temperature range is determined based on the parameter values.

6. The high-voltage switchgear fault monitoring method as described in claim 5, characterized in that, After determining the growth rate of the concentration data of the characteristic gas within each temperature range based on the parameter value, the method further includes: Based on the pre-trained multi-label classification model and the growth rate of the concentration data of the characteristic gas in each temperature range, the set of fault types output by the multi-label classification model is obtained. If the number of elements in the fault type set is greater than 1, then the growth rate is determined to correspond to multiple fault types; If the number of elements in the fault type set is zero, then the growth rate is determined to correspond to no fault.

7. The method as described in claim 1, characterized in that, The step of determining the trend of concentration data of the characteristic gas based on the correlation, and monitoring the fault trend of the high-voltage switchgear based on the trend of the correlation, includes: The growth trend of the concentration data for each characteristic gas is determined based on the aforementioned correlation; The fault trend of high-voltage switchgear is monitored based on the concentration data of each characteristic gas and its corresponding growth trend.

8. A fault monitoring system for high-voltage switchgear, characterized in that, include: The temperature data acquisition module is used to acquire temperature data from various temperature monitoring points inside the high-voltage switchgear. The gas concentration acquisition module is used to acquire the concentration data of characteristic gases in the target area, wherein the target area is a circular target area defined with each temperature monitoring point inside the high-voltage switchgear as the center and a preset distance as the radius. The correlation determination module is used to determine the correlation between each temperature data and the concentration data of the characteristic gas based on the temperature data and the concentration data of the characteristic gas. The fault monitoring module is used to determine the changing trend of the concentration data of the characteristic gas based on the correlation, and to monitor the fault trend of the high-voltage switchgear based on the changing trend.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images