A method and system for judging the degree of pressure leakage of a gas chamber of a gas insulated switchgear

Abstract

The application discloses a kind of gas insulated switchgear gas chamber pressure leakage degree judging method and system, applied to insulating switchgear gas chamber detection technical field, method includes first obtaining the pressure value of the gas chamber to be evaluated in preset time period, constructs pressure value sequence, and then the sequence is weighted average processing, obtains first final pressure value sequence, again to first final pressure value sequence Pressure mutation identification, locates pressure mutation interval and removes it, obtains second final pressure value sequence.Then, construct pressure state space model, input model to predict second final pressure value sequence, obtain optimal estimation pressure value sequence, calculate pressure decay rate according to optimal estimation pressure value sequence, and the pressure decay rate is segmented linear transformation, finally output gas chamber pressure leakage severity value.Through the above method, the accuracy of pressure leakage evaluation is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of gas chamber detection technology for gas-insulated switchgear, and in particular to a method and system for judging the degree of pressure leakage in the gas chamber of gas-insulated switchgear. Background Technology

[0002] With the rapid advancement of ultra-high voltage power grid construction and the large-scale deployment of smart substations, GIS (Gas Insulated Switchgear) equipment, as the core equipment of modern substations, directly affects the safety and stability of the entire power grid due to its operational reliability. In recent years, domestic and foreign power companies have widely deployed online pressure monitoring devices in various gas chambers of GIS, establishing remote pressure data acquisition systems and threshold-based automatic alarm mechanisms, which have improved the automation level of equipment monitoring to a certain extent.

[0003] However, existing monitoring technologies are clearly insufficient in addressing the critical issue of slow pressure decay. Traditional threshold alarm systems can only issue an alarm when the pressure reaches a preset danger threshold, by which time the equipment often already has serious hidden dangers, and the optimal window for maintenance has been missed. More importantly, the pressure changes in GIS gas chambers have their own unique characteristics: on the one hand, normal changes in ambient temperature and equipment load fluctuations can cause periodic fluctuations in pressure data; on the other hand, normal gas replenishment operations during operation and maintenance can cause step changes in pressure data; in addition, leaks caused by aging insulation materials and deterioration of seals often manifest as extremely slow pressure drops. These characteristics make data analysis methods that rely on human experience insufficient to meet the needs of modern smart grids for accurate perception and early warning of equipment status.

[0004] Therefore, improving the accurate sensing of gas chamber pressure in gas-insulated switchgear is a technical problem that urgently needs to be solved in the field of gas chamber detection technology for power equipment. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a method and system for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear, thereby solving the technical problem of low accuracy in assessing the degree of pressure leakage in the gas chamber of a gas-insulated switchgear.

[0006] A first aspect of this invention provides a method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear, the method comprising: Obtain the pressure values ​​of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period to obtain a pressure value sequence; The pressure value sequence is weighted and averaged to obtain the first final pressure value sequence, which includes multiple weighted average pressure values. Pressure mutations are identified in the first final pressure value sequence to obtain pressure mutation intervals. In the first final pressure value sequence, the weighted average pressure values ​​belonging to the pressure mutation intervals are removed to obtain the second final pressure value sequence. A pressure state space model is constructed, and the second final pressure value sequence is input into the pressure state space model for prediction to obtain the optimal estimated pressure value sequence. The pressure decay rate is calculated based on the optimal estimated pressure value sequence. A piecewise linear transformation is then performed on the pressure decay rate to obtain the severity value of the gas chamber pressure leakage in the gas-insulated switchgear to be evaluated.

[0007] In one possible implementation of the first aspect, a weighted average is performed on the pressure value sequence to obtain a first final pressure value sequence, including: Determine the window value, and based on the window value, use the window function to calculate the moving average of the pressure value series to obtain multiple weighted average pressure values; Based on the weighted average pressure values, the first final pressure value sequence is obtained.

[0008] In one possible implementation of the first aspect, pressure abrupt change identification is performed on the first final pressure value sequence to obtain pressure abrupt change intervals, including: Calculate the absolute value of the difference between two adjacent weighted average pressure values ​​in the first final pressure value sequence to obtain the absolute value of the difference sequence; The sequence of absolute difference values ​​is traversed. When a preset number of consecutive absolute difference values ​​are greater than a preset absolute difference value threshold, the first absolute difference value in the preset number is determined to be the mutation start point, and the last absolute difference value is determined to be the mutation end point. The stress mutation interval is obtained based on the mutation start point and mutation end point.

[0009] In one possible implementation of the first aspect, the pressure decay rate is calculated based on the optimal estimated pressure value sequence, including: Obtain the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence to obtain the time point sequence; The mean of the time point series is calculated to obtain the time mean, and the mean of the optimal estimated pressure value series is calculated to obtain the mean of the optimal estimated pressure value. The covariance is obtained from the time mean and the mean of the optimal estimated pressure value, and the time variance is obtained from the time mean. The pressure decay rate is obtained based on the covariance and time variance.

[0010] In one possible implementation of the first aspect, after obtaining the severity value of the chamber pressure leakage of the gas-insulated switchgear chamber to be evaluated, the method further includes: Based on the optimal estimated pressure value sequence, the trend statistical significance confidence level and trend evolution persistence are calculated; The quality of the pressure value sequence is assessed, and a quality assessment score is obtained. The air chamber pressure health index is obtained by weighting and summing the trend statistical significance confidence level, trend evolution persistence, quality assessment score and air chamber pressure leakage severity value.

[0011] In one possible implementation of the first aspect, the statistical significance confidence level of the trend is calculated based on the optimal estimated pressure value sequence, including: Obtain the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence to obtain the time point sequence; Based on the time point series, the optimal estimated pressure value series is filtered to obtain the number of same-order pairs and the number of different-order pairs; Based on the number of identical pairs and the number of disidentical pairs, standardized statistics are obtained; The probability value is obtained by using standardized statistics, and the confidence level of the statistical significance of the trend is obtained based on the probability value.

[0012] In one possible implementation of the first aspect, based on the time point series, the optimal estimated pressure value series is filtered to obtain the number of in-order pairs and the number of out-of-order pairs, including: Compare the magnitudes of any two optimal estimated pressure values ​​in the optimal estimated pressure value sequence. If the optimal estimated pressure value at the later time point is greater than the optimal estimated pressure value at the previous time point, then the two optimal estimated pressure values ​​are out of order. If the optimal estimated pressure value at the later time point is less than the optimal estimated pressure value at the previous time point, then the two optimal estimated pressure values ​​are in the same order. The number of out-of-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of out-of-order pairs. The number of in-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of in-order pairs.

[0013] To address the same technical problem, a second aspect of the present invention provides a system for determining the degree of pressure leakage in a gas-insulated switchgear chamber, comprising: The acquisition module is used to acquire the pressure value of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period, and obtain a pressure value sequence. The weighted average processing module is used to perform weighted average processing on the pressure value sequence to obtain a first final pressure value sequence, wherein the first final pressure value sequence includes multiple weighted average pressure values. The pressure mutation identification module is used to identify pressure mutations in the first final pressure value sequence to obtain pressure mutation intervals. In the first final pressure value sequence, the weighted average pressure values ​​belonging to the pressure mutation intervals are removed to obtain the second final pressure value sequence. The prediction module is used to construct a pressure state space model. The second final pressure value sequence is input into the pressure state space model for prediction to obtain the optimal estimated pressure value sequence. The calculation module is used to calculate the pressure decay rate based on the optimal estimated pressure value sequence, perform piecewise linear transformation on the pressure decay rate, and obtain the severity value of the gas chamber pressure leakage of the gas-insulated switchgear to be evaluated.

[0014] A third aspect of the present invention provides a computer device, comprising: Memory, used to store computer programs; A processor is used to execute computer programs to implement the steps of a method for determining the degree of pressure leakage in a gas-insulated switchgear chamber, as described in the first aspect.

[0015] A fourth aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for determining the degree of pressure leakage in a gas-insulated switchgear chamber as described in the first aspect.

[0016] The technical solution of this invention has the following advantages: The method for judging the degree of pressure leakage in gas-insulated switchgear provided in this invention first obtains the pressure values ​​of the gas chamber to be evaluated within a preset time period, constructing a pressure value sequence. Then, a weighted average is applied to this sequence to obtain a first final pressure value sequence. Next, pressure abrupt changes are identified in the first final pressure value sequence, pressure abrupt change intervals are located and eliminated, resulting in a second final pressure value sequence reflecting a stable trend. Then, a pressure state space model is constructed, and the second final pressure value sequence is input into the model for prediction, obtaining an optimal estimated pressure value sequence, achieving noise filtering and dynamic tracking. Based on this, the pressure decay rate is calculated according to the optimal estimated pressure value sequence, and a piecewise linear transformation is performed on the pressure decay rate to finally output the severity value of the gas chamber pressure leakage. This method effectively improves the accuracy of pressure leakage assessment and provides a reliable basis for condition monitoring and fault early warning of gas-insulated switchgear. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear according to an embodiment of the present invention; Figure 2 This is an overall architecture diagram of the method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear according to an embodiment of the present invention; Figure 3 This is a system block diagram of the gas chamber pressure leakage determination system in an embodiment of the present invention; Figure reference numerals: 200, Gas-insulated switchgear chamber pressure leakage degree judgment system; 201, Acquisition module; 202, Weighted average processing module; 203, Pressure change identification module; 204, Prediction module; 205, Calculation module. Detailed Implementation

[0019] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear provided in this invention embodiment, such as... Figure 1 As shown, Figure 1 The flowchart for determining the degree of pressure leakage in the gas chamber of gas-insulated switchgear includes steps S101 to S105, with each step detailed as follows: S101. Obtain the pressure value of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period to obtain a pressure value sequence.

[0021] In this embodiment, the preset time period refers to collecting the pressure values ​​of the gas chamber of the gas-insulated switchgear to be evaluated within a certain period, such as collecting pressure values ​​over 1 day or 7 days. In practical applications, this can be set according to actual needs. When collecting pressure values, an edge computing-based data acquisition architecture is constructed. Specifically, multiple sensors are placed in the gas chambers of the corresponding gas-insulated switchgear to be evaluated. The pressure values ​​of each gas-insulated switchgear are collected in real time through a standardized interface protocol, and related parameters such as ambient temperature and equipment load are collected simultaneously to provide a data foundation for subsequent analysis. Simultaneously, edge devices are deployed near the sensors to receive the pressure values ​​sent by the sensors, obtaining a pressure value sequence. Environmental data can also be collected simultaneously, and the pressure value sequence data and environmental data are sent to the cloud and stored in a MySQL database. The overall architecture diagram of the gas chamber pressure leakage determination method in this embodiment is shown below. Figure 2 As shown, the system mainly comprises a data foundation layer, a model algorithm layer, an intelligent analysis layer, and a decision application layer. The data foundation layer is responsible for collecting and processing raw pressure data. The model algorithm layer is used to estimate the time-series trend characteristics and dynamic optimal state of the system from the processed pressure data, providing data support for subsequent leakage assessment. The intelligent analysis layer integrates the feature extraction and optimal state estimation results from the model algorithm layer, performing in-depth analysis and feature extraction of the system state to provide directly usable analytical conclusions for the decision layer. The application layer evaluates the conclusions of the intelligent analysis layer and obtains corresponding risk classification warnings, operational decisions, or generates diagnostic reports.

[0022] S102. Perform weighted averaging on the pressure value sequence to obtain the first final pressure value sequence, wherein the first final pressure value sequence includes multiple weighted average pressure values.

[0023] In this embodiment, an improved moving average algorithm is used to smooth the pressure value sequence using multi-scale aggregation analysis within a sliding time window. For example... Figure 2 As shown, specifically, by setting an observation window to perform multi-scale sliding window aggregation, and using a window function to calculate the weighted average of the pressure values ​​within the window, short-term random fluctuations and measurement noise are effectively suppressed, thereby obtaining the first final pressure value sequence.

[0024] In one embodiment, a weighted average is performed on the pressure value sequence to obtain a first final pressure value sequence, including: Determine the window value, and based on the window value, use the window function to calculate the moving average of the pressure value series to obtain multiple weighted average pressure values; Based on the weighted average pressure values, the first final pressure value sequence is obtained.

[0025] In this embodiment, the second final pressure value sequence is obtained by weighted averaging the pressure value sequence. Specifically, a window value is determined, and based on the window value, a moving average is calculated on the pressure value sequence using a window function to obtain multiple weighted average pressure values. The preset division method refers to setting corresponding observation windows, such as 0.5 days, 1 day, 2 days, or 3 days. For example, if the pressure value sequence is collected for 7 days, a 1-day observation window is set, and a weighted average is calculated on the pressure value sequence within 1 day using a window function to obtain the weighted average pressure value of the first window. Then, after sliding one data point to the right, the first data point of the first day is deleted to obtain the data sequence of the second window, which includes the data within the first day plus the first data point of the second day. The weighted average calculation is continued on the data sequence of the second window, and this step is repeated until the last pressure value data is reached to obtain the weighted average pressure value of each window. The weighted average pressure values ​​of each window are sorted according to time to obtain the first final pressure value sequence. The improved moving average algorithm effectively suppresses noise and highlights the long-term, macroscopic variation trajectory inherent in pressure data, laying the foundation for subsequent accurate quantification. This method effectively suppresses short-term random fluctuations and measurement noise. The window function uses a linear weighting form, and the formula for calculating the weight of each pressure value is as follows: In the formula, For window size, For the first in the window The weight of each pressure value.

[0026] This weighting method assigns higher weight to recent data, enhancing sensitivity to trend changes.

[0027] It should be noted that before performing weighted averaging on the pressure value sequence, preprocessing was performed to eliminate noise and handle missing values, providing a high-quality data foundation for subsequent analysis. During data cleaning, the Laida criterion was used to identify and remove gross errors. Specifically, the mean μ and standard deviation σ of the pressure value sequence were calculated, and data points outside the interval [μ-3σ, μ+3σ] were considered outliers and removed. For missing data caused by transmission interruptions, linear interpolation was used to fill in the gaps. Data points with more than 10 consecutive missing data points were marked as invalid for that period. To avoid the influence of different chamber pressure dimensions, a normalization method was used to map the pressure values ​​to the [0,1] interval.

[0028] S103. Perform pressure mutation identification on the first final pressure value sequence to obtain the pressure mutation interval. In the first final pressure value sequence, remove the weighted average pressure value that belongs to the pressure mutation interval to obtain the second final pressure value sequence.

[0029] In this embodiment, the pressure mutation interval refers to the pressure mutation identification obtained from the first final pressure value sequence. The first final pressure value sequence refers to the pure pressure value sequence obtained by removing the pressure mutation interval from the first final pressure value sequence. The pressure mutation is caused by the pressure mutation during the gas filling operation of the gas-insulated switchgear being evaluated. By identifying the pressure mutation interval and removing the data within the pressure mutation interval from the pressure value sequence, a pure pressure sequence without gas filling interference is finally obtained. Specifically, the absolute value of the difference between two adjacent sampling pressure values ​​is calculated point by point for the first final pressure value sequence to obtain the absolute value difference sequence. Then, the pressure mutation interval is determined based on the absolute value difference sequence. In the pressure value sequence, the weighted average pressure value belonging to the pressure mutation interval is removed, and the remaining weighted average pressure values ​​are reassembled in chronological order to obtain the second final pressure value sequence.

[0030] In one embodiment, pressure abrupt change identification is performed on the first final pressure value sequence to obtain pressure abrupt change intervals, including: Calculate the absolute value of the difference between two adjacent weighted average pressure values ​​in the first final pressure value sequence to obtain the absolute value of the difference sequence; The sequence of absolute difference values ​​is traversed. When a preset number of consecutive absolute difference values ​​are greater than a preset absolute difference value threshold, the first absolute difference value in the preset number is determined to be the mutation start point, and the last absolute difference value is determined to be the mutation end point. The stress mutation interval is obtained based on the mutation start point and mutation end point.

[0031] In this embodiment, a preset absolute value threshold for the difference is first defined. This threshold is the minimum instantaneous change in pressure during gas replenishment. It can be calibrated according to the equipment parameters to ensure that only abnormal jumps exceeding the normal fluctuation range are identified as sudden changes. By eliminating these abnormal data points, their interference with the subsequent calculation of the pressure decay rate can be effectively avoided. Specifically, the absolute value of the difference between two adjacent weighted average pressure values ​​is calculated point by point for the first final pressure value sequence. The formula for calculating the absolute value of the difference is: In the formula, The absolute value of the difference. The first final pressure value sequence A weighted average pressure value, The first final pressure value sequence A weighted average pressure value.

[0032] Multiple absolute differences are used to form a pressure change sequence, with the timestamp corresponding to each absolute difference being the midpoint between two adjacent sampling times. This sequence is then iterated through; when multiple consecutive absolute differences exceed a preset threshold, the first absolute difference is identified as the start point of the abrupt change, and the last pressure value as the end point. The start and end points define the pressure abrupt change interval. In practical applications, such abrupt changes are usually caused by external interference, such as gas replenishment operations, sensor transients, or environmental factors. These abrupt changes are characterized by short duration, large amplitude, and do not conform to the slow leakage pattern of the gas chamber. After removal, the remaining data points account for more than 90% of the original data, fully preserving the long-term decay trend of the gas chamber pressure change. Furthermore, the removed data sequence can maintain temporal continuity through interpolation or connecting adjacent points, ensuring no new errors are introduced.

[0033] S104. Construct a pressure state space model, input the second final pressure value sequence into the pressure state space model for prediction, and obtain the optimal estimated pressure value sequence.

[0034] In this embodiment, the pressure state-space model is established by defining the second final pressure value sequence and its rate of change as the state vector of the pressure state-space model, thus creating a complete system model that includes process noise and observation noise. This pressure state-space model includes state transition equations and observation equations. The expression for the state equations is as follows: In the formula, The state vector includes pressure values. and the rate of change of real pressure , Here is the state transition matrix. For process noise, It is the optimal state estimate of the previous moment.

[0035] The expression for the observed equation is: In the formula, For the observation vector, For the observation matrix, It is observation noise.

[0036] like Figure 2As shown, the second final pressure value sequence serves as the observation data basis for state estimation, forming the observation vector in the observation equation. Based on the optimal state estimate and state transition matrix of the previous moment, the prior state estimate for the current moment is predicted. Then, the predicted observation value is extracted from the prior state estimate at the current moment using the observation matrix. Based on the predicted observation value, the optimal estimated pressure value is obtained. Through a prediction-correction loop mechanism, state prediction is performed based on the optimal estimate of the previous moment, and then weighted correction is performed by combining the current observation value to achieve the optimal estimate of the system state. The process noise covariance matrix and the observation noise covariance matrix are trained and optimized using historical data to ensure an optimal balance between system dynamic characteristics and measurement accuracy.

[0037] S105. The pressure decay rate is calculated based on the optimal estimated pressure value sequence. The pressure decay rate is then subjected to piecewise linear transformation to obtain the severity value of the gas chamber pressure leakage in the gas-insulated switchgear to be evaluated.

[0038] In this embodiment, after obtaining the optimal estimated pressure value sequence, as follows: Figure 2 As shown, based on a univariate linear regression model, the least squares method is used to quantitatively analyze the trajectory of the optimal estimated pressure value sequence to obtain the pressure decay rate. Then, a piecewise linear transformation is performed on the pressure decay rate to obtain the severity value of the gas chamber pressure leakage in the gas-insulated switchgear. This severity value accurately reflects the urgency of the gas chamber pressure leakage in the gas-insulated switchgear, enabling relevant personnel to take corresponding adjustment measures. It should be noted that the piecewise linear transformation maps the continuous pressure decay rate to a scoring interval to intuitively express the severity of the leakage. This scoring interval can be determined based on engineering experience; this embodiment does not impose specific limitations.

[0039] In one embodiment, the pressure decay rate is calculated based on the optimal estimated pressure value sequence, including: Obtain the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence to obtain the time point sequence; The mean of the time point series is calculated to obtain the time mean, and the mean of the optimal estimated pressure value series is calculated to obtain the mean of the optimal estimated pressure value. The covariance is obtained from the time mean and the mean of the optimal estimated pressure value, and the time variance is obtained from the time mean. The pressure decay rate is obtained based on the covariance and time variance.

[0040] In this embodiment, the intercept and slope coefficient of the optimal fitted line are solved by minimizing the sum of squared residuals. The slope coefficient is a precise quantitative indicator of the pressure decay rate, and its calculation involves covariance and variance analysis of the time series data to ensure that the obtained trend slope has clear mathematical meaning and statistical reliability. Specifically, the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence are first obtained to obtain the time point sequence. The mean of the time point sequence and the mean of the optimal estimated pressure values ​​are then calculated. The covariance is then calculated based on the mean of the time point sequence and the mean of the optimal estimated pressure values, where the formula for calculating the covariance is: In the formula, To optimally estimate the number of data points in the pressure value sequence or at any given time point, For the first At a certain point in time, For the first The optimal estimated pressure value, The average over time. The mean of the optimal estimated pressure value.

[0041] Then calculate the time variance. The formula for calculating the time variance is: In the formula, For the first At a certain point in time, This is the time average.

[0042] The expression for the pressure decay rate is: In the formula, For covariance, This represents the time variance.

[0043] It should be noted that the mean is calculated using the commonly used mean calculation method, which will not be elaborated upon in this embodiment. Simultaneously, the algorithm also calculates indices such as goodness of fit to evaluate the explanatory power of the best-fit line. The calculation process for goodness of fit is as follows: First, the total sum of squares, regression sum of squares, and residual sum of squares of the estimated stress values ​​are calculated. The expression for the total sum of squares is: In the formula, To obtain the optimal estimated average pressure value, For the first The optimal estimated pressure value, This is the total sum of squares.

[0044] The expression for the regression sum of squares is: In the formula, To obtain the optimal estimated average pressure value, For regression predictions, This is the sum of squares of the regression.

[0045] The expression for the sum of squared residuals is: In the formula, To obtain the optimal estimated average pressure value, These are regression predicted values.

[0046] The expression for goodness of fit is: In the formula, For the total sum of squares, For the regression sum of squares, This is the sum of squared residuals.

[0047] The closer the goodness of fit is to 1, the stronger the ability of the best-fit line to explain the data, that is, the more the trend of pressure change conforms to the linear pattern; conversely, the lower the goodness of fit, the worse the fit of the linear model, and the trend may be non-linear or greatly affected by noise.

[0048] In one embodiment, after obtaining the severity value of the chamber pressure leakage in the gas-insulated switchgear chamber to be evaluated, the method further includes: Based on the optimal estimated pressure value sequence, the trend statistical significance confidence level and trend evolution persistence are calculated; The quality of the pressure value sequence is assessed, and a quality assessment score is obtained. The air chamber pressure health index is obtained by weighting and summing the trend statistical significance confidence level, trend evolution persistence, quality assessment score and air chamber pressure leakage severity value.

[0049] In this embodiment, after obtaining the severity value of gas chamber pressure leakage in the gas-insulated switchgear, a fixed-weight multi-factor fusion decision engine was constructed to transform the analysis results of multiple models into intuitive and operable diagnostic conclusions. For example... Figure 2As shown, this engine generates a gas chamber pressure health index by quantifying and integrating the outputs of four core algorithm modules, achieving accurate risk classification and early warning of faults. Specifically, based on the optimal estimated pressure value sequence, the trend statistical significance confidence level is calculated using a sequence monotonicity statistical verification algorithm, and the trend starting point of the optimal estimated pressure value sequence is identified using a sliding window analysis algorithm, thus obtaining the trend evolution persistence. A quality assessment is performed on the pressure value sequence to obtain a quality assessment score. Weights are set for the trend statistical significance confidence level, trend evolution persistence, quality assessment score, and gas chamber pressure leakage severity value. These weighted sums are then used to obtain the gas chamber pressure health index of the gas-insulated switchgear to be evaluated. The specific calculation formula for the gas chamber pressure health index is as follows: In the formula, These are the weights corresponding to the statistical significance confidence level of the trend, the persistence of the trend evolution, the quality assessment score, and the severity of the air chamber pressure leakage, respectively. For the statistical significance confidence level of the trend, For the duration of trend evolution, For quality assessment scores, This represents the severity of pressure leakage in the gas chamber.

[0050] Based on the air chamber pressure health index, the system employs a four-level early warning mechanism: 0-30 points indicate a steady-state range, where the pressure remains within the normal fluctuation range identified by the algorithm, requiring continued routine monitoring. 31-60 points indicate slight attenuation, where multiple algorithm modules detect consistent risk signals, suggesting an increase in monitoring frequency. 61-80 points indicate moderate attenuation, where statistical tests and trend analysis algorithms both show significant anomalies, triggering an early warning and recommending the development of an investigation plan. 81-100 points indicate severe attenuation, where all algorithm outputs reach the danger threshold, requiring immediate alarm and on-site intervention.

[0051] When the air chamber pressure health index triggers the warning threshold, the system automatically integrates various data, including trend statistical significance confidence level, trend evolution persistence, quality assessment score, air chamber pressure leakage severity value, and duration in days, to generate a comprehensive diagnostic report. By analyzing the pattern characteristics output by each algorithm, the system can further infer potential defect types, providing precise guidance for on-site maintenance.

[0052] In one embodiment, the statistical significance confidence level of the trend is calculated based on the optimal estimated pressure value sequence, including: Obtain the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence to obtain the time point sequence; Based on the time point series, the optimal estimated pressure value series is filtered to obtain the number of same-order pairs and the number of different-order pairs; Based on the number of identical pairs and the number of disidentical pairs, standardized statistics are obtained; The probability value is obtained by using standardized statistics, and the confidence level of the statistical significance of the trend is obtained based on the probability value.

[0053] In this embodiment, the trend statistical significance confidence score is obtained based on the optimal estimated stress value sequence. Specifically, based on the time point sequence, all optimal estimated stress value sequences are traversed to obtain homologous and heterologous pairs, and the number of homologous and heterologous pairs is counted. Based on the number of homologous and heterologous pairs respectively, a standardized statistic is obtained, wherein the formula for calculating the standardized statistic is: In the formula, For standardized statistics, The Mann-Kendall statistic is used. The variance of the Mann-Kendall statistic. This represents the number of identical pairs. This represents the number of out-of-order pairs.

[0054] The probability value is obtained by using standardized statistics. The specific formula for calculating the probability value is as follows: In the formula, This is a probability value. The cumulative distribution function of the standard normal distribution. This is a standard statistic.

[0055] The sigmoid function maps probability values ​​to confidence scores of 0-100, quantifying the statistical significance of a trend.

[0056] In one embodiment, based on the time point series, the optimal estimated pressure value series is filtered to obtain the number of in-order pairs and the number of out-of-order pairs, including: Compare the magnitudes of any two optimal estimated pressure values ​​in the optimal estimated pressure value sequence. If the optimal estimated pressure value at the later time point is greater than the optimal estimated pressure value at the previous time point, then the two optimal estimated pressure values ​​are out of order. If the optimal estimated pressure value at the later time point is less than the optimal estimated pressure value at the previous time point, then the two optimal estimated pressure values ​​are in the same order. The number of out-of-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of out-of-order pairs. The number of in-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of in-order pairs.

[0057] In this embodiment, the optimal estimated pressure values ​​at any two different time points in the sequence are compared. For example, when time point... The corresponding optimal estimated pressure value Greater than the time point corresponding The optimal estimated pressure value is then called the optimal estimated pressure value. and optimal estimated pressure value This is an out-of-order pair. Conversely, if the time point... The corresponding optimal estimated pressure value Less than the time point corresponding The optimal estimated pressure value is then called the optimal estimated pressure value. and optimal estimated pressure value This is a pair of identically ordered values. All values ​​in the optimal estimated pressure value sequence that satisfy this condition... We iterate through the combinations and count the number of out-of-order pairs and same-order pairs. This represents the total number of optimal estimated pressure values ​​in the optimal estimated pressure value sequence. It should be noted that the time points... and time point These represent two adjacent time points. for The moment before, The value is only a time-series index variable, and its specific numerical value is not limited.

[0058] A simulation experiment was conducted using historical data to assess the pressure leakage detection of gas-insulated switchgear chambers proposed in this embodiment. The experiment used multiple sets of chamber pressure data, including normal slow leakage, gas replenishment events, and stable conditions, with a sample size exceeding 500 sets. By applying the method proposed in this embodiment, the system successfully identified all preset slow leakage cases and achieved 95% accurate identification and correct exclusion of gas replenishment events, without generating false alarms. The experiment demonstrates that the technical path provided by this solution is complete and the parameters are clearly defined. The calculation method for the chamber pressure health index achieves 93.5% consistency with manual diagnosis. This method can achieve the goal of early and accurate identification of abnormal pressure decline trends in the chambers.

[0059] The gas chamber pressure leakage determination system for gas-insulated switchgear provided in this embodiment of the invention, such as... Figure 3 As shown, Figure 3 A system block diagram for a gas-insulated switchgear chamber pressure leakage assessment system 200, including: The acquisition module 201 is used to acquire the pressure value of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period, and obtain a pressure value sequence. The weighted average processing module 202 is used to perform weighted average processing on the pressure value sequence to obtain a first final pressure value sequence, wherein the first final pressure value sequence includes multiple weighted average pressure values. The pressure mutation identification module 203 is used to identify pressure mutations in the first final pressure value sequence to obtain pressure mutation intervals. In the first final pressure value sequence, the weighted average pressure values ​​belonging to the pressure mutation intervals are removed to obtain the second final pressure value sequence. Prediction module 204 is used to construct a pressure state space model, input the second final pressure value sequence into the pressure state space model for prediction, and obtain the optimal estimated pressure value sequence. The calculation module 205 is used to calculate the pressure decay rate based on the optimal estimated pressure value sequence, perform piecewise linear transformation on the pressure decay rate, and obtain the severity value of the gas chamber pressure leakage of the gas-insulated switchgear to be evaluated.

[0060] The specific implementation of the system for judging the degree of pressure leakage in the gas chamber of gas-insulated switchgear is basically the same as the specific implementation of the method for judging the degree of pressure leakage in the gas chamber of gas-insulated switchgear described above, and will not be repeated here.

[0061] In one embodiment of this application, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above steps. The implementation principle and technical effects of the computer device provided in this embodiment are similar to those of the above method embodiments, and will not be repeated here.

[0062] In one embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it performs the above steps; the implementation principle and technical effects of the computer-readable storage medium provided in this embodiment are similar to those of the above method embodiments, and will not be repeated here.

[0063] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that 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 for those skilled in the art.

Claims

1. A method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear, characterized in that, include: Obtain the pressure values ​​of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period to obtain a pressure value sequence; The pressure value sequence is weighted and averaged to obtain a first final pressure value sequence, wherein the first final pressure value sequence includes multiple weighted average pressure values; Pressure mutation identification is performed on the first final pressure value sequence to obtain pressure mutation intervals. In the first final pressure value sequence, the weighted average pressure value belonging to the pressure mutation interval is removed to obtain the second final pressure value sequence. A pressure state space model is constructed, and the second final pressure value sequence is input into the pressure state space model for prediction to obtain the optimal estimated pressure value sequence. The pressure decay rate is calculated based on the optimal estimated pressure value sequence. The pressure decay rate is then subjected to a piecewise linear transformation to obtain the severity value of the gas chamber pressure leakage in the gas-insulated switchgear to be evaluated.

2. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 1, characterized in that, The step of performing a weighted average on the pressure value sequence to obtain a first final pressure value sequence includes: Determine a window value, and based on the window value, use a window function to calculate a moving average of the pressure value sequence to obtain multiple weighted average pressure values; Based on the weighted average pressure values, a first final pressure value sequence is obtained.

3. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 1, characterized in that, The step of identifying pressure mutations in the first final pressure value sequence to obtain pressure mutation intervals includes: Calculate the absolute value of the difference between two adjacent weighted average pressure values ​​in the first final pressure value sequence to obtain a sequence of absolute difference values; The sequence of absolute difference values ​​is traversed. When a preset number of consecutive absolute difference values ​​are greater than a preset absolute difference value threshold, the first absolute difference value in the preset number is determined to be the mutation start point, and the last absolute difference value is determined to be the mutation end point. The stress mutation interval is obtained based on the mutation start point and the mutation end point.

4. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 1, characterized in that, The step of calculating the pressure decay rate based on the optimal estimated pressure value sequence includes: Obtain the time points corresponding to each optimal estimated pressure value in the optimal estimated pressure value sequence to obtain the time point sequence; The mean of the time point series is calculated to obtain the time mean, and the mean of the optimal estimated pressure value series is calculated to obtain the mean of the optimal estimated pressure value. The covariance is obtained based on the time mean and the mean of the optimal estimated pressure value; the time variance is obtained based on the time mean. The pressure decay rate is obtained based on the covariance and the time variance.

5. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 1, characterized in that, After obtaining the severity value of the chamber pressure leakage in the gas-insulated switchgear to be evaluated, the following steps are also included: Based on the optimal estimated pressure value sequence, the trend statistical significance confidence level and trend evolution persistence are calculated; The pressure value sequence is subjected to quality assessment to obtain a quality assessment score; The air chamber pressure health index is obtained by weighting and summing the trend statistical significance confidence level, the trend evolution persistence, the quality assessment score, and the air chamber pressure leakage severity value.

6. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 4, characterized in that, The step of calculating the trend statistical significance confidence level based on the optimal estimated pressure value sequence includes: Obtain the time points corresponding to each of the optimal estimated pressure values ​​in the optimal estimated pressure value sequence to obtain the time point sequence; Based on the time point sequence, the optimal estimated pressure value sequence is filtered to obtain the number of identical pairs and the number of disidentical pairs; Based on the number of homologous pairs and the number of heterologous pairs, a standardized statistic is obtained; The probability value is calculated using the standardized statistic, and the trend statistical significance confidence level is obtained based on the probability value.

7. The method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in claim 6, characterized in that, The process of filtering the optimal estimated pressure value sequence based on the time point sequence to obtain the number of identical pairs and the number of disidentified pairs includes: Compare the magnitudes of any two optimal estimated pressure values ​​in the optimal estimated pressure value sequence. If the optimal estimated pressure value corresponding to the later time point is greater than the optimal estimated pressure value corresponding to the earlier time point, then the two optimal estimated pressure values ​​are out of order. If the optimal estimated pressure value corresponding to the later time point is less than the optimal estimated pressure value corresponding to the earlier time point, then the two optimal estimated pressure values ​​are in the same order. The number of all out-of-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of out-of-order pairs. The number of all in-order pairs in the optimal estimated pressure value sequence is counted to obtain the number of in-order pairs.

8. A system for determining the degree of pressure leakage in a gas-insulated switchgear chamber, characterized in that, include: The acquisition module is used to acquire the pressure value of the gas chamber of the gas-insulated switchgear to be evaluated within a preset time period, and obtain a pressure value sequence. A weighted average processing module is used to perform weighted average processing on the pressure value sequence to obtain a first final pressure value sequence, wherein the first final pressure value sequence includes multiple weighted average pressure values. The pressure mutation identification module is used to identify pressure mutations in the first final pressure value sequence to obtain pressure mutation intervals. In the first final pressure value sequence, the weighted average pressure value belonging to the pressure mutation interval is removed to obtain the second final pressure value sequence. The prediction module is used to construct a pressure state space model, input the second final pressure value sequence into the pressure state space model for prediction, and obtain the optimal estimated pressure value sequence. The calculation module is used to calculate the pressure decay rate based on the optimal estimated pressure value sequence, perform piecewise linear transformation on the pressure decay rate, and obtain the severity value of the gas chamber pressure leakage of the gas-insulated switchgear to be evaluated.

9. A computer device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for determining the degree of pressure leakage in the gas chamber of a gas-insulated switchgear as described in any one of claims 1 to 7.

Images