An intelligent vacuum circuit breaker monitoring system

Abstract

The present invention relates to the field of vacuum circuit breaker monitoring technology, and specifically to an intelligent vacuum circuit breaker monitoring system, the system comprising: a vibration trend analysis module collects vibration data of the vacuum circuit breaker equipment during operation, performs frequency analysis and amplitude analysis, and constructs a wear trend prediction result in combination with historical maintenance records. In the present invention, by maintaining the GM (1, 1) model of the historical comparison submodule, the system can effectively combine the real-time vibration data of the vacuum circuit breaker with the historical maintenance records to predict the wear trend and identify early fault signals. Therefore, the system can not only identify the current equipment status, but also accurately predict the wear progress of key components such as contacts through in-depth analysis of historical data, thereby achieving more accurate maintenance plan formulation. Ensuring that the vacuum circuit breaker equipment is properly maintained or replaced before reaching the critical point of wear greatly reduces the failure rate caused by unexpected wear.

Description

Technical Field

[0001] The present invention relates to the technical field of vacuum circuit breaker monitoring, and in particular to an intelligent vacuum circuit breaker monitoring system. Background Art

[0002] The vacuum circuit breaker monitoring field uses vacuum media to disconnect current and prevent arcing. Vacuum circuit breakers are favored for their high reliability, long life and low maintenance requirements. In the field, through monitoring, the status of circuit breakers can be tracked in real time and maintenance requirements can be predicted, thereby reducing the failure rate and improving the stability and efficiency of the power system.

[0003] Among them, the intelligent vacuum circuit breaker monitoring system is a system that uses sensor technology, data processing and communication technology to achieve real-time monitoring and analysis of the vacuum circuit breaker status. The purpose is to prevent potential failures, optimize maintenance plans, and improve the overall operating efficiency of the power system by providing accurate and real-time data. By monitoring key parameters such as current, voltage, and temperature, the system can detect abnormal conditions in a timely manner, so that preventive measures can be taken before the problem becomes a serious failure.

[0004] Although the existing technology has certain effects in real-time monitoring and data analysis, it is still insufficient in identifying subtle wear and early fault signals of equipment. For example, in a vacuum circuit breaker, the contacts are responsible for connecting and disconnecting the current, and it is difficult for traditional systems to accurately predict the contact wear caused by subtle vibration changes in vacuum circuit breaker equipment, which makes it difficult to optimize the maintenance plan in a targeted manner, causing the contacts to fail before reaching the scheduled maintenance cycle. In addition, although a certain degree of fault prevention is achieved through the monitoring of key parameters, the dynamic adjustment capability of the fault detection threshold also shows limitations. When the vacuum circuit breaker equipment ages or the environmental conditions change, the fixed fault detection threshold is no longer applicable. For example, when operating in a high temperature environment, the normal vibration range of the vacuum circuit breaker equipment will change due to the expansion of the metal material. The threshold setting of the traditional system is difficult to accurately reflect the state change, which easily increases the risk of false alarms or missed alarms. Summary of the invention

[0005] The present application provides an intelligent vacuum circuit breaker monitoring system to solve the problem that although the existing technology has certain effects in real-time monitoring and data analysis, it still has deficiencies in identifying subtle wear and early fault signals of equipment. For example, in a vacuum circuit breaker, the contacts are responsible for connecting and disconnecting the current, and it is difficult for traditional systems to accurately predict the contact wear caused by subtle vibration changes in vacuum circuit breaker equipment, which makes it difficult to optimize the maintenance plan in a targeted manner, causing the contacts to fail before reaching the scheduled maintenance cycle. In addition, although a certain degree of fault prevention is achieved through the monitoring of key parameters, it also shows limitations in the ability to dynamically adjust the fault detection threshold. When the vacuum circuit breaker equipment ages or the environmental conditions change, the fixed fault detection threshold is no longer applicable. For example, when operating in a high temperature environment, the normal vibration range of the vacuum circuit breaker equipment will change due to the expansion of the metal material. The threshold setting of the traditional system is difficult to accurately reflect the state change, which easily increases the risk of false alarms or missed alarms.

[0006] In view of the above problems, the present application provides an intelligent vacuum circuit breaker monitoring system.

[0007] The present application provides an intelligent vacuum circuit breaker monitoring system, wherein the system comprises:

[0008] The vibration trend analysis module collects vibration data of the vacuum circuit breaker during operation, performs frequency analysis and amplitude analysis, and builds wear trend prediction results based on historical maintenance records;

[0009] The wear diagnosis and early warning module uses the wear trend prediction results to predict the wear development trend of the mechanical parts of the vacuum circuit breaker, identify the wear accelerating parts, and generate early warning information of the key wear parts;

[0010] The micro-change analysis and identification module analyzes abnormal fluctuations in the vibration data based on the early warning information of the wear key components, identifies the state changes of the vacuum circuit breaker equipment, and forms equipment change analysis results;

[0011] The fault detection threshold optimization module dynamically adjusts the fault detection threshold according to the equipment change analysis result to match the current operating state of the vacuum circuit breaker equipment and environmental changes to obtain the adjusted fault detection threshold;

[0012] The operating status real-time monitoring module uses the adjusted fault detection threshold to monitor the vacuum circuit breaker device in real time, feeds back the current operating status of the device, and generates real-time status monitoring results;

[0013] The equipment fault response module triggers a fault warning immediately based on the real-time status monitoring result, indicates the fault type and location, and forms a fault warning and response strategy when the monitoring data exceeds the adjusted fault detection threshold.

[0014] Preferably, the wear trend prediction results include vibration frequency change trends, vibration amplitude abnormality indicators and historical maintenance cycle comparisons; the wear key component warning information includes key contact wear speed, drive component wear status and insulating material aging rate; the equipment change analysis results include frequency fluctuation sensitivity within the cycle, amplitude abnormality fluctuation index and vibration mode change characteristics; the adjusted fault detection threshold includes a frequency threshold that matches environmental changes, an amplitude abnormality threshold and a vibration mode recognition threshold; the real-time status monitoring results include current operating current monitoring values, voltage fluctuation data and real-time analysis of vibration characteristics; the fault warning and response strategy includes fault type emergency level classification, fault location positioning and predetermined fault response measures.

[0015] Preferably, the vibration trend analysis module includes:

[0016] The vibration signal collection submodule collects multiple vibration data of key mechanical parts of the vacuum circuit breaker during operation, including contacts, operating rods and insulating brackets, and generates a vibration signal data set;

[0017] The vibration mode recognition submodule performs signal processing based on the vibration signal data set, analyzes frequency distribution and amplitude, recognizes multiple vibration modes, including normal operation modes and abnormal vibration modes caused by various reasons such as wear or looseness, and generates vibration mode difference analysis results;

[0018] The maintenance history comparison submodule compares and analyzes the vibration mode difference analysis results with the historical maintenance records of the vacuum circuit breaker equipment, identifies the association between the vibration trend and the wear or failure mode that occurred in the past through the GM (1, 1) model, and constructs the wear trend prediction result.

[0019] Preferably, the GM (1, 1) model is in accordance with the improved formula I:

[0020]

[0021] Perform trend prediction and error analysis, calibrate model parameters to match current vibration data, and generate wear trend prediction results;

[0022] in, represents the original data sequence, represents the cumulative generation sequence, represents the step size of the time series, represents the development coefficient, represents the adjustment factor based on the age of the device, represents the gray action amount, represents the temperature deviation weight coefficient, represents the average temperature during the monitoring period, Indicates the optimal operating temperature of the device. represents the load deviation weight coefficient, Indicates the current load, Indicates normal operating load.

[0023] Preferably, the wear diagnosis and warning module includes:

[0024] The wear progress assessment submodule analyzes the wear data of multiple mechanical parts such as contacts and operating rods in the vacuum circuit breaker based on the wear trend prediction results, calculates the wear speed and wear degree, analyzes the wear progress of each part, and generates a wear state analysis result;

[0025] The key component monitoring submodule uses the wear state analysis results to continuously monitor the components with increasing wear speed in the vacuum circuit breaker equipment, identifies the key components of wear development by comparing the time series changes of the vibration data, and generates the key component wear records;

[0026] The maintenance demand prediction submodule combines the key component wear records and the past maintenance history of the vacuum circuit breaker equipment to predict future maintenance needs, including the time point for contact replacement or operating rod adjustment, and generates early warning information for worn key components.

[0027] Preferably, the microvariation analysis and identification module includes:

[0028] The fluctuation abnormality detection submodule performs time series analysis on the vibration data based on the warning information of the wear key components, marks the vibration frequency and amplitude points in the vacuum circuit breaker equipment that deviate from the normal operating mode, reflects potential equipment wear or failure, and generates a vibration abnormality mark;

[0029] The device status tracking submodule uses the vibration abnormality mark to track and record the changes in key operating parameters of the vacuum circuit breaker device, including the current and voltage changes in the operation cycle, and multiple data of temperature trends, plots the evolution of the device status over time, and generates a device operation status trajectory;

[0030] The change index summarization submodule synthesizes the equipment operation status trajectory, extracts key operation indicators reflecting the overall health status of the vacuum circuit breaker equipment, including equipment performance fluctuations and potential fault warning signals, and obtains equipment change analysis results.

[0031] Preferably, the fault detection threshold optimization module includes:

[0032] The environmental adaptability analysis submodule determines the changes in the operating environment of the vacuum circuit breaker equipment based on the equipment change analysis results, calculates multiple statistical indicators through moment estimation method, analyzes the impact of environmental changes on fault detection sensitivity, and generates environmental factor impact analysis results;

[0033] The threshold adjustment decision submodule uses the environmental factor impact analysis result to evaluate whether the current fault detection threshold can reflect the current operating state of the vacuum circuit breaker device, combines the device's operating data and fault history, determines the fault detection threshold that needs to be adjusted, and generates a fault detection threshold adjustment plan;

[0034] The update threshold setting submodule resets the fault detection threshold according to the fault detection threshold adjustment scheme to obtain an adjusted fault detection threshold.

[0035] Preferably, the moment estimation method is according to the improved formula II:

[0036]

[0037] Calculate multiple statistical indicators, analyze the impact of environmental changes on fault detection sensitivity, and generate environmental factor impact analysis results;

[0038] in, is the adjusted mean, is the adjusted variance, is the adjusted skewness, is the adjusted kurtosis, , , is the environmental impact adjustment factor, are weight coefficients, representing the influence of temperature, humidity, and load on mean, variance, skewness, and kurtosis, respectively. , The temperature, humidity and load values ​​in the current environment. , It is the temperature, humidity, load value under reference environment conditions, as well as the average value of temperature and humidity.

[0039] Preferably, the operating status real-time monitoring module includes:

[0040] The operating parameter recording submodule captures the current key operating parameters of the vacuum circuit breaker device in real time based on the adjusted fault detection threshold, reflects the immediate working status of the device, and forms a real-time key parameter data set;

[0041] The operating status real-time analysis submodule uses the real-time key parameter data set to continuously monitor the operating status of the vacuum circuit breaker equipment, analyze the relationship between parameters and deviations from predetermined thresholds, identify changes or abnormal trends in the operating status, and generate abnormal analysis results of the operating status;

[0042] The monitoring feedback summary submodule integrates all the data of the abnormal operation status analysis results, determines the overall health status of the vacuum circuit breaker equipment operation, and classifies and prioritizes the monitored issues to obtain real-time status monitoring results.

[0043] Preferably, the device failure response module includes:

[0044] The fault identification triggering submodule monitors the key operating parameters of the vacuum circuit breaker device in real time based on the real-time status monitoring results, including current, voltage, temperature and vibration level. If the parameters exceed the preset threshold range, they are immediately identified as potential fault signals and generate potential fault signals;

[0045] The fault point location submodule utilizes the potential fault signal, combines the wiring diagram and mechanical structure diagram of the vacuum circuit breaker device, compares the characteristics and location of the fault signal, identifies the fault location, and generates a fault location analysis result;

[0046] The emergency measures formulation submodule plans emergency measures for the identified fault type and location based on the fault location analysis results, including immediate power outage, local isolation of the fault location, or activation of backup plans, to form a fault warning and response strategy.

[0047] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0048] By maintaining the GM (1, 1) model of the history comparison submodule, the system can effectively combine the real-time vibration data of the vacuum circuit breaker with the historical maintenance records to predict the wear trend and identify early fault signals. Therefore, the system can not only identify the current equipment status, but also accurately predict the wear progress of key components such as contacts through in-depth analysis of historical data, thereby achieving more accurate maintenance planning. It ensures that the vacuum circuit breaker equipment is maintained or replaced in time before reaching the critical point of wear, greatly reducing the failure rate caused by unexpected wear. At the same time, through the moment estimation method of the environmental adaptability analysis submodule, the system can dynamically adjust the fault detection threshold to match the current operating status and environmental changes of the vacuum circuit breaker equipment. By referring to the real-time operating conditions of the equipment, such as material expansion caused by temperature changes, etc., the fault detection threshold is accurately matched with the actual situation of the equipment. It not only improves the accuracy of fault detection and reduces the risk of false alarms or missed alarms, but also ensures that the monitoring system can sensitively respond to slight changes in the equipment status, effectively improving the stability and reliability of the entire power system.

[0049] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A module diagram of an intelligent vacuum circuit breaker monitoring system is proposed for the present invention;

[0051] Figure 2 A system framework diagram of an intelligent vacuum circuit breaker monitoring system is proposed for the present invention;

[0052] Figure 3 The present invention proposes a specific flow chart of a vibration trend analysis module in an intelligent vacuum circuit breaker monitoring system;

[0053] Figure 4 A specific flow chart of a wear diagnosis and early warning module in an intelligent vacuum circuit breaker monitoring system is proposed for the present invention;

[0054] Figure 5 The present invention proposes a specific flow chart of a micro-change analysis and identification module in an intelligent vacuum circuit breaker monitoring system;

[0055] Figure 6 The present invention proposes a specific flow chart of a fault detection threshold optimization module in an intelligent vacuum circuit breaker monitoring system;

[0056] Figure 7 The present invention proposes a specific flow chart of a real-time monitoring module for operating status in an intelligent vacuum circuit breaker monitoring system;

[0057] Figure 8 The present invention proposes a specific flow chart of a device fault response module in an intelligent vacuum circuit breaker monitoring system. DETAILED DESCRIPTION

[0058] The present application provides an intelligent vacuum circuit breaker monitoring system.

[0059] Application Overview

[0060] The existing technology has certain effects in real-time monitoring and data analysis, but it is still insufficient in identifying subtle wear and early fault signals of equipment. For example, in a vacuum circuit breaker, the contacts are responsible for connecting and disconnecting the current, and it is difficult for traditional systems to accurately predict the contact wear caused by subtle vibration changes in vacuum circuit breaker equipment, which makes it difficult to optimize the maintenance plan in a targeted manner, causing the contacts to fail before reaching the scheduled maintenance cycle. In addition, although a certain degree of fault prevention is achieved through the monitoring of key parameters, the dynamic adjustment capability of the fault detection threshold also shows limitations. When the vacuum circuit breaker equipment ages or the environmental conditions change, the fixed fault detection threshold is no longer applicable. For example, when operating in a high temperature environment, the normal vibration range of the vacuum circuit breaker equipment will change due to the expansion of the metal material. The threshold setting of the traditional system is difficult to accurately reflect these state changes, which easily increases the risk of false alarms or missed alarms.

[0061] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0062] like Figure 1 As shown, the present application provides an intelligent vacuum circuit breaker monitoring system, wherein the system includes;

[0063] The vibration trend analysis module collects vibration data of the vacuum circuit breaker during operation, performs frequency analysis and amplitude analysis, and builds wear trend prediction results based on historical maintenance records;

[0064] The wear diagnosis and early warning module uses the wear trend prediction results to predict the wear development trend of the mechanical parts of the vacuum circuit breaker, identify the wear accelerating parts, and generate early warning information for the key wear parts;

[0065] The micro-change analysis and identification module analyzes abnormal fluctuations in vibration data based on early warning information of key wear components, identifies changes in the state of vacuum circuit breaker equipment, and forms equipment change analysis results;

[0066] The fault detection threshold optimization module dynamically adjusts the fault detection threshold according to the equipment change analysis results to match the current operating status of the vacuum circuit breaker equipment and environmental changes to obtain the adjusted fault detection threshold;

[0067] The operation status real-time monitoring module uses the adjusted fault detection threshold to monitor the vacuum circuit breaker equipment in real time, feedback the current operation status of the equipment, and generate real-time status monitoring results;

[0068] The equipment fault response module is based on the real-time status monitoring results. When the monitoring data exceeds the adjusted fault detection threshold, it immediately triggers a fault warning, indicates the fault type and location, and forms a fault warning and response strategy.

[0069] The wear trend prediction results include the vibration frequency change trend, vibration amplitude abnormality index and historical maintenance cycle comparison. The warning information of key wear components includes the wear speed of key contacts, the wear status of drive components and the aging rate of insulating materials. The equipment change analysis results include the frequency fluctuation sensitivity within the cycle, the amplitude abnormal fluctuation index and the vibration mode change characteristics. The adjusted fault detection threshold includes the frequency threshold that matches the environmental changes, the amplitude abnormality threshold and the vibration mode recognition threshold. The real-time status monitoring results include the current operating current monitoring value, voltage fluctuation data and real-time analysis of vibration characteristics. The fault warning and response strategy includes the classification of fault type emergency level, fault location positioning and predetermined fault response measures.

[0070] like Figure 2 and Figure 3 As shown, the vibration trend analysis module includes:

[0071] The vibration signal collection submodule collects multiple vibration data of key mechanical parts of the vacuum circuit breaker during operation, including contacts, operating rods and insulating brackets. The specific process of generating the vibration signal data set is as follows:

[0072] The vibration signal collection submodule is based on the operating status of the vacuum circuit breaker. It uses acceleration sensors to capture the vibration data of key mechanical parts such as contacts, operating rods and insulating brackets, and uses an analog-to-digital converter to convert the analog signal into a digital format. The sampling rate is set to 1024 Hz and the sampling depth is set to 16 bits to ensure high-precision and high-resolution acquisition of vibration signals and generate a vibration signal dataset.

[0073] The vibration pattern recognition submodule performs signal processing based on the vibration signal data set, analyzes the frequency distribution and amplitude, and identifies multiple vibration patterns, including normal operation patterns and abnormal vibration patterns caused by wear or looseness. The specific process of generating vibration pattern difference analysis results is as follows;

[0074] The vibration pattern recognition submodule uses the Fourier transform algorithm to perform spectrum analysis on the vibration signal based on the vibration signal data set, converts the time series data into frequency domain data, and uses the peak detection algorithm to identify the main vibration frequency and its amplitude. It further uses clustering algorithms such as K-means to classify the vibration patterns according to frequency distribution and amplitude size, identifies multiple vibration patterns including normal operation patterns and abnormal vibration patterns caused by wear or looseness, and generates vibration pattern difference analysis results.

[0075] The maintenance history comparison submodule compares and analyzes the vibration mode difference analysis results with the historical maintenance records of the vacuum circuit breaker equipment, identifies the association between the vibration trend and the wear or failure mode that occurred in the past through the GM (1, 1) model, and constructs the specific process of the wear trend prediction result as follows;

[0076] The maintenance history comparison submodule is based on the vibration mode difference analysis results and uses the GM (1, 1) algorithm in the grey prediction model to compare the wear and failure mode data in the historical maintenance records. By setting the initial conditions and development coefficients of the grey prediction model and using the linear difference equation to fit the model, the time series prediction of the wear trend is calculated. The model parameters are further corrected through error analysis to improve the prediction accuracy and reliability, and the wear trend prediction results are generated.

[0077] The GM(1,1) model is based on the improved formula I:

[0078]

[0079] Perform trend prediction and error analysis, calibrate model parameters to match current vibration data, and generate wear trend prediction results;

[0080] in, Represents the original data sequence, that is, the vibration data of the key mechanical parts of the vacuum circuit breaker without any processing. It represents the cumulative generation sequence, which is a new sequence generated by accumulating the original data sequence once, and is used for data processing in the grey prediction model. Represents the step size of the time series, which is used to indicate the interval between data points in time series analysis. It represents the development coefficient, which reflects the growth rate of the data series. Indicates the adjustment factor based on the age of the equipment, used to adjust the development factor In order to consider the impact of performance changes caused by the increase in equipment usage time on the prediction model, it is determined by analyzing the equipment's service life and historical maintenance records, considering the trend of equipment wear and performance degradation. Represents the grey action, and the development coefficient Together we determine the changing trend of the data series. Represents the temperature deviation weight coefficient, which is used to adjust the estimated impact of temperature changes on equipment wear. It is determined by analyzing the correlation between historical temperature records and equipment failure rates and evaluating the impact of temperature changes on the probability of failure. Indicates the average temperature during the monitoring period, which is used to reflect the average operating temperature of the equipment during the monitoring period. Indicates the optimal operating temperature of the equipment, that is, the ideal temperature at which the equipment operates most stably and efficiently. Represents the load deviation weight coefficient, which is used to adjust the estimate of the impact of load changes on equipment wear. It is determined by evaluating the performance change data of the equipment under different load conditions and analyzing the sensitivity of load fluctuations to equipment wear. Indicates the current load, that is, the actual load of the device at the current or specific moment. Indicates normal operating load, which is the standard load level when the equipment is designed or normally operated.

[0081] The execution process is as follows:

[0082] Collect historical maintenance records, operating data (including vibration data), temperature data, and load data of vacuum circuit breaker equipment.

[0083] The collected data are preprocessed, including data cleaning and normalization, to ensure the quality and consistency of the data.

[0084] Using the original vibration data series , perform an accumulation to generate a new sequence , to prepare for the subsequent grey prediction model analysis.

[0085] The least squares method is used to analyze the cumulative generation sequence and estimate the development coefficient and gray action .

[0086] Analyze the equipment age and historical maintenance records, and calculate the adjustment factor based on the equipment aging trend . Perform regression analysis on historical temperature records and equipment failure rates to calculate the temperature deviation weight coefficient Analyze the performance data of the equipment under different load conditions and calculate the load deviation weight coefficient through regression analysis .

[0087] Substitute all the calculated parameter values ​​into Formula I to predict the wear trend of the vacuum circuit breaker.

[0088] Compare the predicted results with the actual wear data, analyze the prediction error, and adjust the model parameters (such as , , to improve the prediction accuracy.

[0089] Finally, the wear trend prediction results are obtained after error analysis and parameter correction, which provides a basis for the maintenance and fault prevention of vacuum circuit breakers.

[0090] like Figure 2 and Figure 4 As shown, the wear diagnosis and warning module includes:

[0091] The wear progress assessment submodule analyzes the wear data of multiple mechanical parts such as contacts and operating rods in the vacuum circuit breaker based on the wear trend prediction results, calculates the wear speed and wear degree, and analyzes the wear progress of each part. The specific process of generating the wear status analysis results is as follows;

[0092] The wear progress assessment submodule is based on the wear trend prediction results and uses linear regression analysis method. By setting the independent variable as time and the dependent variable as wear depth, the wear speed and degree of wear of each mechanical component such as contacts and operating rods are calculated. The Python SciPy library is used for data fitting, and the fitting parameter is set to 0.95 to ensure the accuracy of the prediction. The wear progress of each component is further analyzed to generate the wear status analysis results.

[0093] The key component monitoring submodule uses the wear status analysis results to continuously monitor the components with increasing wear speed in the vacuum circuit breaker equipment. By comparing the time series changes of vibration data, the key components of wear development are identified. The specific process of generating the wear records of key components is as follows;

[0094] The key component monitoring submodule uses the wear status analysis results and time series analysis technology to identify components with increasing wear rates by comparing vibration data at consecutive time points. The time window is set to collect data every 7 days, and Python's Pandas library is used to process time series data. The sliding average calculation of the wear rate is performed to smooth short-term fluctuations, identify key components with significantly increased wear development rates, and generate key component wear records.

[0095] The maintenance demand prediction submodule combines the key component wear records and the past maintenance history of the vacuum circuit breaker equipment to predict future maintenance needs, including the time point for contact replacement or operating rod adjustment. The specific process of generating early warning information of key wear components is as follows;

[0096] The maintenance demand prediction submodule combines the wear records of key components and the past maintenance history of the vacuum circuit breaker equipment, and adopts a decision tree classification algorithm to predict future maintenance needs based on the wear rate and component replacement history. The decision tree model is constructed using Python's Sklearn library with a depth of 5 layers to ensure the generalization ability of the model and avoid overfitting. The time point for contact replacement or operating rod adjustment is predicted, and early warning information for key wear components is generated.

[0097] like Figure 2 and Figure 5 As shown, the micro-variation analysis and identification module includes:

[0098] The fluctuation anomaly detection submodule performs time series analysis on vibration data based on the early warning information of key wear components, marks the vibration frequency and amplitude points in the vacuum circuit breaker equipment that deviate from the normal operating mode, reflects potential equipment wear or failure, and generates the specific process of vibration anomaly marking as follows;

[0099] The fluctuation anomaly detection submodule uses the autoregressive moving average model to perform time series analysis on vibration data based on the warning information of key wear components. By setting the autoregressive term to 2 and the moving average term to 2, the expected value and standard deviation of the current data point are calculated using historical vibration data. For each data point, its deviation from the expected value is calculated. If the deviation exceeds 2 times the standard deviation, the point is marked as abnormal, reflecting potential equipment wear or failure, and generating a vibration anomaly mark.

[0100] The equipment status tracking submodule uses vibration anomaly markers to track and record changes in key operating parameters of vacuum circuit breaker equipment, including current and voltage changes during the operation cycle, as well as temperature trend data, and plots the evolution of equipment status over time. The specific process of generating equipment operating status trajectory is as follows;

[0101] The equipment status tracking submodule uses vibration anomaly markers and digital filtering technology, such as Kalman filter, to filter key operating parameters such as current, voltage and temperature. By setting the Kalman gain to minimize the estimation error, the changes of these parameters over time are tracked to chart the evolution of the equipment status. The noise variance and process variance in the filtering process are set to adapt to different environmental noises and equipment change speeds, and the equipment operating status trajectory is generated.

[0102] The change index summary submodule integrates the equipment operation status trajectory and extracts key operation indicators that reflect the overall health status of the vacuum circuit breaker equipment, including equipment performance fluctuations and potential fault warning signals. The specific process of obtaining the equipment change analysis results is as follows;

[0103] The change index summary submodule integrates the equipment operation status trajectory and uses the principal component analysis method to reduce the dimension of multiple indicators such as current, voltage, and temperature, and extracts the main components that reflect the overall health status of the equipment. The number of components in the PCA model is set to the number when the proportion of variance explained by the main components exceeds 80% to reduce the impact of data redundancy and noise. The extracted main components are used as key operation indicators to obtain the equipment change analysis results.

[0104] like Figure 2 and Figure 6 As shown, the fault detection threshold optimization module includes:

[0105] The environmental adaptability analysis submodule determines the changes in the operating environment of the vacuum circuit breaker equipment based on the equipment change analysis results, calculates multiple statistical indicators through the moment estimation method, analyzes the impact of environmental changes on fault detection sensitivity, and generates the specific process of environmental factor impact analysis results as follows;

[0106] The environmental adaptability analysis submodule is based on the equipment change analysis results and uses the moment estimation method to quantify the changes in the operating environment of the vacuum circuit breaker. By collecting environmental parameters such as temperature and humidity data, calculating their mean, variance, skewness and kurtosis, and using Python's NumPy library for numerical calculations, the impact of environmental changes on fault detection sensitivity is analyzed. The statistical significance level is set to 0.05, and hypothesis testing is performed to confirm whether environmental changes significantly affect fault detection performance, generating environmental factor impact analysis results.

[0107] The moment estimation method is based on the improved formula II:

[0108]

[0109] Calculate multiple statistical indicators, analyze the impact of environmental changes on fault detection sensitivity, and generate environmental factor impact analysis results;

[0110] in, It is the adjusted mean, representing the average level of equipment operating parameters under specific environmental conditions. It is the adjusted variance, which measures the fluctuation range of equipment operating parameters under adjusted environmental conditions. is the adjusted skewness, which describes the asymmetry of the data distribution after adjustment. is the adjusted kurtosis, a measure of how sharp or flat the distribution of the data is after adjustment. , , are environmental impact adjustment coefficients, which are used to adjust the mean, skewness and kurtosis respectively. are weight coefficients, representing the influence of temperature, humidity, and load on mean, variance, skewness, and kurtosis, respectively. Through regression analysis of historical data on the relationship between temperature changes and equipment performance, Determined through historical data analysis of the impact of humidity changes on equipment operating conditions, By analyzing the relationship between load changes and equipment failure rates, The impact of temperature fluctuations on fault detection accuracy was determined by analyzing historical data. Determined through statistical analysis of the relationship between humidity fluctuations and equipment operating efficiency, Determined through data regression analysis of the impact of load fluctuations on equipment performance stability, By analyzing the effect of temperature change on the degree of data distribution skewness, The effect of humidity changes on the kurtosis of the data distribution was quantitatively determined by analyzing the effect of humidity changes on the kurtosis of the data distribution. , It is the temperature, humidity and load value in the current environment. , It is the temperature, humidity, load value under reference environment conditions, as well as the average value of temperature and humidity.

[0111] The execution process is as follows:

[0112] Collect real-time environmental data (temperature) of vacuum circuit breakers ,humidity ,load ) and equipment operating status data.

[0113] Determine the temperature, humidity, and load values ​​under reference environmental conditions ( , , and the average value ( ,

[0114] Calculate the difference between the current environmental parameters and the reference values, such as , , .

[0115] Determine the weight coefficient, where The β, γ weight coefficients are determined by regression analysis of historical data on the relationship between temperature, humidity, load changes and equipment performance. , , The weight coefficient is determined by analyzing historical data that examines the impact of environmental fluctuations on fault detection accuracy. , The weight coefficients were determined through a detailed analysis of the effects of changes in environmental parameters on the skewness and kurtosis of the data distribution.

[0116] Calculate the adjusted mean using Formula II ,variance , skewness and Kurtosis .

[0117] Evaluate environmental impact adjustment factors based on historical data and expert experience , , , reasonably reflects the actual impact of environmental changes on fault detection.

[0118] The adjusted statistical parameters are applied to the fault detection model to optimize the fault detection threshold to improve the accuracy and adaptability of detection.

[0119] Through simulation or actual operation data, the fault detection effect after the threshold is adjusted by Formula II is evaluated, and the weight coefficient and adjustment coefficient are further adjusted according to the evaluation results when necessary.

[0120] The threshold adjustment decision submodule uses the environmental factor impact analysis results to evaluate whether the current fault detection threshold can reflect the current operating status of the vacuum circuit breaker equipment, and combines the equipment's operating data and fault history to determine the fault detection threshold that needs to be adjusted. The specific process of generating a fault detection threshold adjustment plan is as follows;

[0121] The threshold adjustment decision submodule uses the environmental factors to influence the analysis results and adopts the logistic regression analysis method to evaluate whether the current fault detection threshold can reflect the current operating status of the vacuum circuit breaker equipment. It combines the equipment's operating data and fault history, such as the relationship between fault frequency and environmental parameters, and uses Python's Sklearn library to build a logistic regression model. The independent variables are set as environmental parameters and operating data, and the dependent variable is the probability of fault occurrence. The optimal fault detection threshold is calculated and a fault detection threshold adjustment plan is generated.

[0122] The updating threshold setting submodule resets the fault detection threshold according to the fault detection threshold adjustment scheme, and the specific process of obtaining the adjusted fault detection threshold is as follows:

[0123] The updated threshold setting submodule resets the fault detection threshold according to the fault detection threshold adjustment scheme using a dynamic programming method, uses a Python script to automatically update the threshold parameters in the configuration file, sets a new fault detection threshold to adapt to environmental changes and the latest equipment operating status, and tests the effectiveness of the new threshold by simulating fault conditions to ensure that the new threshold can more accurately reflect the health status of the equipment and obtain the adjusted fault detection threshold.

[0124] like Figure 2 and Figure 7 As shown, the real-time monitoring module for operating status includes:

[0125] The operating parameter recording submodule captures the current key operating parameters of the vacuum circuit breaker equipment in real time based on the adjusted fault detection threshold, reflects the immediate working status of the equipment, and forms a real-time key parameter data set. The specific process is as follows;

[0126] The operating parameter recording submodule uses real-time data acquisition technology based on the adjusted fault detection threshold. Through sensors installed on the vacuum circuit breaker, such as temperature sensors, current sensors and voltage sensors, it continuously captures the current key operating parameters of the equipment, including but not limited to the temperature, current and voltage of the equipment. It uses a serial communication interface such as RS-485 for data transmission, sets the transmission rate to 9600 baud, and uses the Modbus protocol for data encoding to ensure the real-time and accuracy of the data, forming a real-time key parameter data set.

[0127] The operation status real-time analysis submodule uses real-time key parameter data sets to continuously monitor the operation status of the vacuum circuit breaker equipment, analyze the relationship between parameters and deviations from predetermined thresholds, identify changes or abnormal trends in the operation status, and generate the specific process of abnormal analysis results of the operation status as follows;

[0128] The operating status real-time analysis submodule adopts real-time key parameter data sets and continuously monitors the operating status of vacuum circuit breaker equipment through time series analysis techniques, such as the moving average method. The moving average window is set to 5 minutes to smooth short-term fluctuations, analyze the relationship between parameters and their deviations from predetermined thresholds, and use threshold comparison algorithms, such as the simple threshold judgment method, to set specific threshold ranges for each operating parameter, identify operating status changes or abnormal trends that exceed the threshold range, and generate operating status abnormality analysis results.

[0129] The monitoring feedback summary submodule integrates all the data of the abnormal operation status analysis results, determines the overall health status of the vacuum circuit breaker equipment, and classifies and prioritizes the monitored issues. The specific process of obtaining the real-time status monitoring results is as follows;

[0130] The monitoring feedback summary submodule integrates all data of the abnormal operation status analysis results, and uses a rule-based reasoning engine to analyze the overall health status of the equipment operation. By setting specific rules, such as "if the current exceeds the threshold three times in a row, it is judged as a current abnormality", the monitored issues are classified and prioritized. According to the severity and frequency of the abnormality, the processing priority of each issue is determined to obtain real-time status monitoring results.

[0131] like Figure 2 and Figure 8 As shown, the device fault response module includes:

[0132] The fault identification trigger submodule monitors the key operating parameters of the vacuum circuit breaker equipment in real time based on the real-time status monitoring results, including current, voltage, temperature and vibration level. If the parameters exceed the preset threshold range, they are immediately identified as potential fault signals. The specific process of generating potential fault signals is as follows;

[0133] The fault identification trigger submodule is based on the real-time status monitoring results and adopts threshold comparison technology to monitor the key operating parameters of the vacuum circuit breaker equipment in real time, including current, voltage, temperature and vibration level. By setting the specific threshold range of each parameter, the Python script is used to read the sensor data in real time and compare the current reading with the preset threshold. If any parameter exceeds its threshold range, the logical judgment statement is immediately used to identify the reading as a potential fault signal and generate a potential fault signal.

[0134] The fault location submodule uses potential fault signals, combined with the wiring diagram and mechanical structure diagram of the vacuum circuit breaker equipment, to identify the fault location by comparing the characteristics and location of the fault signals, and generates the specific process of fault location analysis results as follows;

[0135] The fault point location submodule uses potential fault signals, combined with the wiring diagram and mechanical structure diagram of the vacuum circuit breaker equipment, and analyzes the source and characteristics of the fault signals through spatial analysis algorithms. It uses GIS (geographic information system) software to match and analyze spatial data, compares the location information of the fault signal with the equipment layout, identifies the specific location of the fault, and generates fault location analysis results.

[0136] The emergency measures formulation submodule plans emergency measures for the identified fault type and location based on the fault location analysis results, including immediate power outage, local isolation of the fault location, or activation of backup plans. The specific process of forming a fault warning and response strategy is as follows;

[0137] The emergency measures formulation submodule uses a decision tree algorithm to plan emergency measures for the identified fault type and location based on the fault location analysis results. It uses Python's Sklearn library to build a decision tree model and calculates the optimal emergency response plan based on the fault type, location, and historical processing case database, including immediate power outages, local isolation of the fault site, or initiation of backup plans, to minimize equipment damage and operation interruption risks and form a fault warning and response strategy.

[0138] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. An intelligent vacuum circuit breaker monitoring system, characterized in that: The system comprises: The vibration trend analysis module collects vibration data of the vacuum circuit breaker during operation, performs frequency analysis and amplitude analysis, and builds wear trend prediction results based on historical maintenance records; The wear diagnosis and early warning module uses the wear trend prediction results to predict the wear development trend of the mechanical parts of the vacuum circuit breaker, identify the wear accelerating parts, and generate early warning information of the key wear parts; The micro-change analysis and identification module analyzes abnormal fluctuations in the vibration data based on the early warning information of the wear key components, identifies the state changes of the vacuum circuit breaker equipment, and forms equipment change analysis results; The fault detection threshold optimization module dynamically adjusts the fault detection threshold according to the equipment change analysis result to match the current operating state of the vacuum circuit breaker equipment and environmental changes to obtain the adjusted fault detection threshold; The operating status real-time monitoring module uses the adjusted fault detection threshold to monitor the vacuum circuit breaker device in real time, feeds back the current operating status of the device, and generates real-time status monitoring results; The equipment fault response module triggers a fault warning immediately based on the real-time status monitoring result, indicates the fault type and location, and forms a fault warning and response strategy when the monitoring data exceeds the adjusted fault detection threshold.

2. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The wear trend prediction results include vibration frequency change trends, vibration amplitude abnormality indicators and historical maintenance cycle comparisons; the wear key component warning information includes key contact wear speed, drive component wear status and insulation material aging rate; the equipment change analysis results include frequency fluctuation sensitivity within the cycle, amplitude abnormality fluctuation index and vibration mode change characteristics; the adjusted fault detection threshold includes a frequency threshold that matches environmental changes, an amplitude abnormality threshold and a vibration mode recognition threshold; the real-time status monitoring results include current operating current monitoring values, voltage fluctuation data and real-time analysis of vibration characteristics; the fault warning and response strategy includes fault type emergency level classification, fault location positioning and predetermined fault response measures.

3. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The vibration trend analysis module includes: The vibration signal collection submodule collects multiple vibration data of key mechanical parts of the vacuum circuit breaker during operation, including contacts, operating rods and insulating brackets, and generates a vibration signal data set; The vibration mode recognition submodule performs signal processing based on the vibration signal data set, analyzes frequency distribution and amplitude, recognizes multiple vibration modes, including normal operation modes and abnormal vibration modes caused by various reasons such as wear or looseness, and generates vibration mode difference analysis results; The maintenance history comparison submodule compares and analyzes the vibration mode difference analysis results with the historical maintenance records of the vacuum circuit breaker equipment, identifies the association between the vibration trend and the wear or failure mode that occurred in the past through the GM (1, 1) model, and constructs the wear trend prediction result.

4. The intelligent vacuum circuit breaker monitoring system according to claim 3, characterized in that: The GM (1, 1) model is based on the improved formula I: ； Perform trend prediction and error analysis, calibrate model parameters to match current vibration data, and generate wear trend prediction results; in, represents the original data sequence, represents the cumulative generation sequence, represents the step size of the time series, represents the development coefficient, represents the adjustment factor based on the age of the device, represents the gray action amount, represents the temperature deviation weight coefficient, represents the average temperature during the monitoring period, Indicates the optimal operating temperature of the device. represents the load deviation weight coefficient, Indicates the current load, Indicates normal operating load.

5. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The wear diagnosis and early warning module comprises: The wear progress assessment submodule analyzes the wear data of multiple mechanical parts such as contacts and operating rods in the vacuum circuit breaker based on the wear trend prediction results, calculates the wear speed and wear degree, analyzes the wear progress of each part, and generates a wear state analysis result; The key component monitoring submodule uses the wear state analysis results to continuously monitor the components with increasing wear speed in the vacuum circuit breaker equipment, identifies the key components of wear development by comparing the time series changes of the vibration data, and generates the key component wear records; The maintenance demand prediction submodule combines the key component wear records and the past maintenance history of the vacuum circuit breaker equipment to predict future maintenance needs, including the time point for contact replacement or operating rod adjustment, and generates early warning information for worn key components.

6. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The micro-variation analysis and identification module includes: The fluctuation abnormality detection submodule performs time series analysis on the vibration data based on the warning information of the wear key components, marks the vibration frequency and amplitude points in the vacuum circuit breaker equipment that deviate from the normal operating mode, reflects potential equipment wear or failure, and generates a vibration abnormality mark; The device status tracking submodule uses the vibration abnormality mark to track and record the changes in key operating parameters of the vacuum circuit breaker device, including the current and voltage changes in the operation cycle, and multiple data of temperature trends, plots the evolution of the device status over time, and generates a device operation status trajectory; The change index summarization submodule synthesizes the equipment operation status trajectory, extracts key operation indicators reflecting the overall health status of the vacuum circuit breaker equipment, including equipment performance fluctuations and potential fault warning signals, and obtains equipment change analysis results.

7. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The fault detection threshold optimization module includes: The environmental adaptability analysis submodule determines the changes in the operating environment of the vacuum circuit breaker equipment based on the equipment change analysis results, calculates multiple statistical indicators through moment estimation method, analyzes the impact of environmental changes on fault detection sensitivity, and generates environmental factor impact analysis results; The threshold adjustment decision submodule uses the environmental factor impact analysis result to evaluate whether the current fault detection threshold can reflect the current operating state of the vacuum circuit breaker device, combines the device's operating data and fault history, determines the fault detection threshold that needs to be adjusted, and generates a fault detection threshold adjustment plan; The update threshold setting submodule resets the fault detection threshold according to the fault detection threshold adjustment scheme to obtain an adjusted fault detection threshold.

8. The intelligent vacuum circuit breaker monitoring system according to claim 7, characterized in that: The moment estimation method is based on the improved formula II: ； Calculate multiple statistical indicators, analyze the impact of environmental changes on fault detection sensitivity, and generate environmental factor impact analysis results; in, is the adjusted mean, is the adjusted variance, is the adjusted skewness, is the adjusted kurtosis, , , is the environmental impact adjustment factor, are weight coefficients, representing the influence of temperature, humidity, and load on mean, variance, skewness, and kurtosis, respectively. , The temperature, humidity and load values ​​in the current environment. , It is the temperature, humidity, load value under reference environment conditions, as well as the average value of temperature and humidity.

9. The intelligent vacuum circuit breaker monitoring system according to claim 1, characterized in that: The running status real-time monitoring module includes: The operating parameter recording submodule captures the current key operating parameters of the vacuum circuit breaker device in real time based on the adjusted fault detection threshold, reflects the immediate working status of the device, and forms a real-time key parameter data set; The operating status real-time analysis submodule uses the real-time key parameter data set to continuously monitor the operating status of the vacuum circuit breaker equipment, analyze the relationship between parameters and deviations from predetermined thresholds, identify changes or abnormal trends in the operating status, and generate abnormal analysis results of the operating status; The monitoring feedback summary submodule integrates all the data of the abnormal operation status analysis results, determines the overall health status of the vacuum circuit breaker equipment operation, and classifies and prioritizes the monitored issues to obtain real-time status monitoring results.

Images