A method and system for monitoring and warning abnormal conditions of a measuring switch

Abstract

The present invention relates to the technical field of measuring electrical variables, and specifically to a method and system for monitoring and warning the abnormal state of a measuring switch, comprising: obtaining historical measurement data such as mechanical state, electrical characteristics, and environmental conditions, and preprocessing the data to construct a measurement switch data set; extracting key features of the measurement switch, constructing monitoring rules and an abnormal state monitoring model based on these features and expert experience, and packaging the rules and importing them into an expert knowledge base; then, predicting future measurement parameters through a machine learning model, combining the measurement parameters obtained in real time, and generating primary and secondary judgment results using an expert knowledge base; comparing the judgment results with the actual operating conditions of the measurement switch, and calculating the comprehensive false alarm rate and missed alarm rate; finally, based on the false alarm rate and missed alarm rate, optimizing the expert knowledge base using a genetic algorithm, thereby improving the intelligence and accuracy of abnormal state monitoring of the measurement switch and providing a strong guarantee for the safety and stability of power grid operation.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electrical variables, and in particular to a method and system for monitoring and warning of abnormal conditions of a measuring switch. Background Art

[0002] Measuring switches are low-voltage switchgear equipped with high-precision current sensors and measurement units. They are widely used to monitor and manage power usage in power grids, supporting remote communication and data exchange to improve grid management. However, abnormal conditions in measuring switches can cause grid monitoring systems to fail or generate false alarms, impacting grid stability and maintenance efficiency. Therefore, effective monitoring and early warning of abnormal conditions in measuring switches are crucial.

[0003] Current measurement switch monitoring technology uses sensors to collect electrical parameters in real time and monitors common faults based on a simple threshold judgment mechanism. If a fault occurs, an alarm device notifies the operation and maintenance personnel to perform maintenance. Although most existing measurement switch solutions have basic monitoring and protection functions, they still have shortcomings in terms of intelligence and fault judgment accuracy. On the one hand, existing solutions mainly rely on fixed threshold rules, which cannot adapt to large fluctuations in grid parameters and are prone to false alarms or missed alarms. On the other hand, existing solutions mostly process data at the collection and transmission level, lacking in-depth analysis and trend prediction functions for historical data, and cannot provide forward-looking guidance for grid operation. Therefore, the intelligence level of measurement switches needs to be further improved to improve the accuracy of abnormal status monitoring and early warning of measurement switches.

[0004] To this end, a method and system for monitoring and warning abnormal status of a measuring switch are proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for monitoring and early warning of abnormal conditions of measuring switches. The method obtains historical measurement data such as mechanical status, electrical characteristics and environmental conditions, and preprocesses them to construct a measurement switch data set; extracts key features of the measurement switch, and constructs monitoring rules and abnormal condition monitoring models based on these features and expert experience, which are then packaged and imported into an expert knowledge base; then, a machine learning model is used to predict future measurement parameters, and the expert knowledge base is used to generate primary and secondary judgment results in combination with the measurement parameters obtained in real time; the judgment results are compared with the actual operating conditions of the measurement switch, and the comprehensive false alarm rate and missed alarm rate are calculated; finally, based on the false alarm rate and missed alarm rate, a genetic algorithm is used to optimize the expert knowledge base, thereby improving the intelligence and accuracy of abnormal condition monitoring of the measurement switch, and providing a strong guarantee for the safety and stability of power grid operation.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The first part is a method for monitoring and warning abnormal status of a measuring switch, comprising:

[0008] Acquiring historical measurement switch parameters, the historical measurement switch parameters including mechanical state parameters, electrical characteristic parameters, environmental parameters, and data integrity parameters; preprocessing the historical measurement switch parameters to obtain a measurement switch data set;

[0009] Extracting features from the measurement switch data set to obtain measurement switch features by calculation;

[0010] Constructing a monitoring rule based on the measurement switch characteristics and expert experience, wherein the monitoring rule is used to set a corresponding feature threshold for each measurement switch characteristic;

[0011] Establishing an abnormal state monitoring model, wherein the abnormal state monitoring model is used to determine whether the measuring switch is in an abnormal state;

[0012] Encapsulating the feature threshold and the abnormal state monitoring model and importing them into an expert knowledge base;

[0013] Acquire real-time measurement switch parameters, and predict future measurement parameters using a machine learning model based on the historical measurement switch parameters and the real-time measurement switch parameters;

[0014] Using the expert knowledge base to predict the real-time measurement switch parameters and the future measurement parameters, and outputting a primary judgment result and a secondary judgment result;

[0015] Acquiring the actual operating status of the measuring switch at predetermined time intervals, and comparing the actual operating status with the first-level judgment result and the second-level judgment result to obtain a comprehensive false alarm rate and a comprehensive missed alarm rate;

[0016] According to the comprehensive false alarm rate and the comprehensive missed alarm rate, a genetic algorithm is used to optimize the expert knowledge base to obtain an updated expert knowledge base.

[0017] Furthermore, the historically measured switch parameters specifically include:

[0018] the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter;

[0019] The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state;

[0020] The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance;

[0021] The environmental parameters include temperature, humidity, dust concentration and air pressure;

[0022] The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

[0023] Furthermore, the feature extraction process includes:

[0024] Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters;

[0025] Calculate measurement switch characteristics based on the historical measurement switch parameters; the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics, and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics, and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics, and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics, and abnormal signal quality characteristics;

[0026] The calculation process of the measured switch characteristics includes:

[0027] Calculating the mean, maximum, and standard deviation of the switch action time to obtain the time anomaly characteristics;

[0028] Calculating the frequency spectrum characteristics of the contact vibration frequency using Fourier transform, and extracting the main frequency from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics;

[0029] Calculating the proportion of the switch in the incompletely closed state in the positioning state to obtain abnormal characteristics of the positioning state;

[0030] Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic; calculating the current imbalance rate according to the current to obtain the current imbalance characteristic;

[0031] Calculating a root mean square current based on the current, and obtaining the line loss characteristic based on the root mean square current and contact resistance;

[0032] Calculating the mean values ​​of temperature, humidity, dust concentration, and air pressure, and performing weighted summation of the mean values ​​to obtain the comprehensive environmental characteristics;

[0033] Calculating the time synchronization anomaly feature according to the signal acquisition time;

[0034] The data loss rate abnormality feature and the signal quality abnormality feature are respectively calculated based on the data loss amount, signal power and noise power.

[0035] Furthermore, the predetermined time interval increases as the number of optimization times of the expert knowledge base increases, which is expressed as:

[0036] ;

[0037] in, For the suboptimal said predetermined time interval, is the initial predetermined time interval, is an exponential function, is the attenuation coefficient, is the number of optimizations.

[0038] Furthermore, the optimization step of the expert knowledge base includes:

[0039] S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals;

[0040] S62: Setting a fitness function, which is expressed as:

[0041] ;

[0042] in, is the fitness value, 、 and is the weight coefficient, is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor;

[0043] S63: Evaluate the initial population according to the fitness function to obtain the fitness value;

[0044] S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals;

[0045] S65: updating the initial population according to the new threshold individuals;

[0046] S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

[0047] The second part is a monitoring and early warning system for abnormal status of a measuring switch, including:

[0048] a parameter preprocessing module, configured to obtain historical measurement switch parameters, preprocess the historical measurement switch parameters, and obtain a measurement switch data set;

[0049] A feature extraction module, configured to extract features from the measurement switch data set and calculate measurement switch features;

[0050] An expert knowledge base establishment module constructs monitoring rules based on the measurement switch characteristics and expert experience, wherein the monitoring rules are used to set corresponding feature thresholds for each measurement switch characteristic; establishes an abnormal state monitoring model, wherein the abnormal state monitoring model is used to determine whether the measurement switch is in an abnormal state; and encapsulates the feature thresholds and the abnormal state monitoring model and imports them into the expert knowledge base;

[0051] an abnormality monitoring module that obtains real-time measurement switch parameters, and uses a machine learning model to predict future measurement parameters based on the historical measurement switch parameters and the real-time measurement switch parameters; uses the expert knowledge base to predict the real-time measurement switch parameters and the future measurement parameters, and outputs a primary judgment result and a secondary judgment result;

[0052] The expert knowledge base optimization module obtains the actual operating status of the measuring switch at predetermined time intervals, and compares the actual operating status with the first-level judgment result and the second-level judgment result to obtain a comprehensive false alarm rate and a comprehensive missed alarm rate; based on the comprehensive false alarm rate and the comprehensive missed alarm rate, a genetic algorithm is used to optimize the expert knowledge base to obtain an updated expert knowledge base.

[0053] Furthermore, the historically measured switch parameters specifically include:

[0054] Mechanical state parameters, electrical characteristic parameters, environmental parameters and data integrity parameters;

[0055] the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter;

[0056] The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state;

[0057] The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance;

[0058] The environmental parameters include temperature, humidity, dust concentration and air pressure;

[0059] The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

[0060] Furthermore, the feature extraction process includes:

[0061] Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters;

[0062] Calculate measurement switch characteristics based on the historical measurement switch parameters; the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics, and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics, and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics, and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics, and abnormal signal quality characteristics;

[0063] The calculation process of the measured switch characteristics includes:

[0064] Calculating the mean, maximum, and standard deviation of the switch action time to obtain the time anomaly characteristics;

[0065] Calculating the frequency spectrum characteristics of the contact vibration frequency using Fourier transform, and extracting the main frequency from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics;

[0066] Calculating the proportion of the switch in the incompletely closed state in the positioning state to obtain abnormal characteristics of the positioning state;

[0067] Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic; calculating the current imbalance rate according to the current to obtain the current imbalance characteristic;

[0068] Calculating a root mean square current based on the current, and obtaining the line loss characteristic based on the root mean square current and contact resistance;

[0069] Calculating the mean values ​​of temperature, humidity, dust concentration, and air pressure, and performing weighted summation of the mean values ​​to obtain the comprehensive environmental characteristics;

[0070] Calculating the time synchronization anomaly feature according to the signal acquisition time;

[0071] The data loss rate abnormality feature and the signal quality abnormality feature are respectively calculated based on the data loss amount, signal power and noise power.

[0072] Furthermore, the predetermined time interval increases as the number of optimization times of the expert knowledge base increases, which is expressed as:

[0073] ;

[0074] in, For the suboptimal said predetermined time interval, is the initial predetermined time interval, is an exponential function, is the attenuation coefficient, is the number of optimizations.

[0075] Furthermore, the optimization step of the expert knowledge base includes:

[0076] S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals;

[0077] S62: Setting a fitness function, which is expressed as:

[0078] ;

[0079] in, is the fitness value, 、 and is the weight coefficient, is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor;

[0080] S63: Evaluate the initial population according to the fitness function to obtain the fitness value;

[0081] S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals;

[0082] S65: updating the initial population according to the new threshold individuals;

[0083] S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

[0084] Compared with the prior art, the present invention has the following beneficial effects:

[0085] 1. This invention refines the key characteristic indicators of measurement switches by extracting multidimensional features from parameters such as mechanical state, electrical characteristics, environmental parameters, and data integrity, improving the ability to capture abnormal conditions and making the monitoring process more comprehensive. Furthermore, by combining expert experience with a data-driven approach to construct monitoring rules and setting feature thresholds based on historical parameter calculations, the adaptability of the rules is enhanced and the subjective interference of single threshold setting in traditional methods is reduced, thereby improving the accuracy of abnormal state monitoring of measurement switches.

[0086] 2. This invention uses monitoring rules to establish an abnormal state monitoring model, encapsulates characteristic thresholds and the abnormal state monitoring model, and imports them into an expert knowledge base. This knowledge can automatically apply to abnormality judgments, enabling real-time monitoring based on historical data and experience. Furthermore, the introduction of a machine learning prediction model predicts future monitoring parameters based on real-time parameters. These parameters are then combined with future monitoring parameters to output separate judgment results. This allows for timely identification of potential anomalies and rapid response to different types of abnormal situations, thereby improving the accuracy of abnormal state monitoring of measurement switches.

[0087] 3. This invention uses a genetic algorithm to optimize the expert knowledge base, constructing a closed-loop optimization process and reducing the problems of false positives and false negatives caused by deviations in feature threshold settings. Furthermore, by incorporating false positive and false negative rates into the fitness function, the optimization strategy can be continuously improved based on actual operating conditions, making the optimization target more aligned with actual application requirements and thus improving the accuracy of abnormal state monitoring. Furthermore, a dynamic time interval mechanism is introduced into the optimization process, enabling the expert knowledge base to adapt to changes in the actual operating environment, thus ensuring effective monitoring while effectively reducing resource consumption caused by frequent calculations. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 A flow chart of a method for monitoring and warning abnormal conditions of a measuring switch proposed in an embodiment of the present invention;

[0089] Figure 2 A schematic diagram of the structure of a measurement switch feature proposed in an embodiment of the present invention;

[0090] Figure 3 This is a structural diagram of a system for monitoring and warning abnormal conditions of a measuring switch proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0091] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0092] See also Figures 1 to 3 The present invention provides a method and system for monitoring and warning abnormal conditions of a measuring switch. The technical solution is as follows:

[0093] Example 1 is as follows:

[0094] As grid loads gradually increase, power systems are increasingly demanding monitoring accuracy and real-time response capabilities. Measuring switches, as a crucial component of grid monitoring and management, help dispatch centers and managers maintain a timely understanding of grid status. However, as grid loads increase and measuring switchgear age, they can face a range of potential anomaly risks. For example, communication modules can lose signals due to electromagnetic interference or connection issues, or even aging equipment can cause delayed or ineffective switch responses. If these anomalies go undetected, the monitoring system will not accurately reflect the grid's true condition, potentially leading to false alarms or missed alerts, ultimately impacting grid stability and operational efficiency.

[0095] While some existing solutions can provide basic monitoring of measuring switches, they still lack intelligence and fault diagnosis accuracy. For example, in certain environmental interference situations, solutions based on pre-set rules are prone to misjudgment, making it difficult for grid managers to promptly detect potential faults or hidden dangers. Therefore, further improving the accuracy of abnormal monitoring and early warning for measuring switches has become an urgent issue to ensure reliable grid operation.

[0096] Figure 1 The figure is a flow chart of a method for monitoring and warning abnormal status of a measuring switch proposed in an embodiment of the present invention.

[0097] like Figure 1 As shown, a method for monitoring and warning abnormal status of a measuring switch includes:

[0098] Step S10: Acquire historical measurement switch parameters, wherein the historical measurement switch parameters include mechanical state parameters, electrical characteristic parameters, environmental parameters, and data integrity parameters; pre-process the historical measurement switch parameters to obtain a measurement switch data set;

[0099] In this embodiment, according to the normal operation of the measurement switch, the operation status of the measurement switch is recorded in real time, and different types of parameter data are obtained from multiple sensors to form historical measurement switch parameters.

[0100] Furthermore, the historically measured switch parameters specifically include:

[0101] the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter;

[0102] The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state;

[0103] The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance;

[0104] The environmental parameters include temperature, humidity, dust concentration and air pressure;

[0105] The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

[0106] Specifically, in this embodiment, the switch action time is obtained by collecting control signal feedback, and the vibration of the contact can be monitored in real time by a vibration sensor installed at the contact position. The open or closed state of the switch can be detected by a position sensor, and poor contact problems caused by wear or aging can be discovered in time, thereby avoiding the occurrence of electrical failures.

[0107] Electrical characteristic parameters are obtained by measuring the current and voltage sensors installed on the measuring switch. Electrical parameters such as current, voltage, active power, and reactive power directly reflect the operating status of the power system and are important indicators for determining whether the measuring switch is abnormal. These parameters can be used to further infer the operating efficiency of the measuring switch and the health of its internal components.

[0108] Environmental parameters are obtained by sensors such as ambient temperature and humidity installed around the measuring switch. Environmental factors such as temperature, humidity, dust concentration and air pressure directly affect the performance of the switch. For example, a sharp drop in temperature may cause the performance of the measuring switch to deteriorate. Monitoring these environmental parameters can help evaluate the operating status of the measuring switch and provide early warning.

[0109] Data integrity parameters can be obtained by analyzing data transmission records between the measurement switch and the monitoring system. The monitoring data from the measurement switch must ensure high integrity and stability. In particular, metrics such as signal power, data loss, and noise power can help assess problems during data transmission and help detect communication anomalies in a timely manner.

[0110] By acquiring multi-dimensional data, a comprehensive analysis of the operating status of the measuring switch can be conducted from multiple perspectives, including mechanical status, electrical characteristics, environmental impact, and data integrity. This allows not only accurate determination of whether the measuring switch is abnormal, but also pinpointing the specific cause of the abnormality. For example, mechanical status parameters can reflect changes in the physical properties of the measuring switch, helping to achieve comprehensive anomaly monitoring, thereby improving the accuracy of abnormal status monitoring of the measuring switch.

[0111] Furthermore, the historical measured switch parameters are de-noised and missing values ​​filled to obtain a measured switch data set, which can remove noise data caused by electromagnetic interference or hardware failure, ensuring data integrity and facilitating subsequent analysis.

[0112] Step S20: extracting features from the measurement switch data set and calculating measurement switch features;

[0113] Furthermore, the feature extraction process includes:

[0114] Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters;

[0115] Among them, in this embodiment, the generation interval of the timestamp of the mechanical state parameter is 1 second, the generation interval of the timestamp of the electrical characteristic parameter is 10 seconds, the generation interval of the timestamp of the environmental parameter is 30 minutes, and the generation interval of the timestamp of the data integrity parameter is 10 minutes, and a total of 10 days of historical measurement switch parameters are obtained.

[0116] The measured switch characteristics are calculated based on the historical measured switch parameters.

[0117] Figure 2 This is a schematic diagram of the structure of measuring switch characteristics proposed in an embodiment of the present invention.

[0118] like Figure 2 As shown, the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics and abnormal signal quality characteristics;

[0119] The calculation process of the measured switch characteristics includes:

[0120] The mean, maximum, and standard deviation of the switch action time are calculated to obtain the time anomaly characteristics, which are expressed as:

[0121] ;

[0122] ;

[0123] ;

[0124] in, is the mean switching time, is the total number of switching actions, For the The time interval between switching actions, is the standard deviation of the switching time, is the maximum value of the switch action time, is the maximum value function, It is the serial number of the number of switch actions.

[0125] The frequency spectrum characteristics of the contact vibration frequency are calculated using Fourier transform, and the main frequency is extracted from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics, which are expressed as:

[0126] ;

[0127] in, is the main frequency, is the spectrum value obtained by Fourier transform, is the frequency value, The maximum function is used to return the spectrum value Maximum frequency value .

[0128] The proportion of the incompletely closed state in the switch positioning state is calculated to obtain the abnormal characteristics of the positioning state, which can be expressed as:

[0129] ;

[0130] in, is the proportion of the incompletely closed state, is the number of incomplete closures, is the total number of switches.

[0131] Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic;

[0132] The current imbalance rate is calculated according to the current to obtain the current imbalance characteristic, which is expressed as:

[0133] ;

[0134] in, is the current unbalance rate, is the three-phase current value, is the mean value of the three-phase current, is the maximum value function, is the minimum function.

[0135] Calculating three-phase current typically involves the current values ​​of phases A, B, and C. Three-phase imbalance can lead to equipment overload, damage, or energy waste. By calculating the current imbalance rate, faults in the power system can be promptly identified, thereby determining whether the operating status of the measurement switch is abnormal. Furthermore, in this embodiment, the current loss characteristics and RMS current are monitored for a single phase.

[0136] The root mean square current is calculated based on the current, and the line loss characteristic is obtained based on the root mean square current and the contact resistance, which is expressed as:

[0137] ;

[0138] ;

[0139] in, is the root mean square current, reflecting the comprehensive intensity of the current; For the Current value; is the total number of sampling points; is the contact resistance; is the line loss power; It is the serial number of the current sampling point.

[0140] The mean values ​​of temperature, humidity, dust concentration and air pressure are calculated and weighted summed to obtain the comprehensive environmental characteristics, which can be expressed as:

[0141] ;

[0142] in, For comprehensive environmental characteristics, are the mean values ​​of temperature, humidity, dust concentration and air pressure, respectively. is the weight of each parameter;

[0143] In this embodiment, temperature has the greatest impact on the measurement switch, so the weights of the parameters are set to 0.4, 0.3, 0.2, and 0.1, respectively, and can be adjusted according to the actual operating environment.

[0144] According to the signal acquisition time, the time synchronization anomaly feature is calculated and expressed as:

[0145] ;

[0146] in, It is a time synchronization anomaly feature. is the number of signals, For the The timestamp of signal acquisition, For the The actual acquisition time of the signal, is the serial number of the signal sampling point.

[0147] According to the data loss amount, signal power and noise power, the data loss rate abnormality feature and the signal quality abnormality feature are calculated respectively and expressed as:

[0148] ;

[0149] ;

[0150] in, is the abnormal characteristic of data loss rate, is the number of lost packets, is the total number of packages, Abnormal signal quality characteristics, is the signal power, is the noise power, It is the logarithm with base 10.

[0151] Mechanical state characteristics calculated from historically measured switch parameters can proactively detect anomalies in the switch's mechanical components, reducing downtime. Electrical characteristics and line loss characteristics can assess circuit anomalies, providing data support for optimizations such as load distribution. Combining environmental and data signal characteristics can identify data collection issues, ensuring the timeliness and accuracy of monitoring data. Furthermore, the calculated results of these characteristics can aid in the establishment of monitoring rules. For example, thresholds for contact vibration frequency or current imbalance ratio can be set based on historical data, forming targeted anomaly identification criteria, thereby improving the accuracy of abnormal switch status monitoring.

[0152] Step S30: constructing a monitoring rule based on the measurement switch characteristics and expert experience, wherein the monitoring rule is used to set a corresponding feature threshold for each measurement switch characteristic;

[0153] Establishing an abnormal state monitoring model, wherein the abnormal state monitoring model is used to determine whether the measuring switch is in an abnormal state;

[0154] The characteristic threshold and the abnormal state monitoring model are encapsulated and imported into an expert knowledge base.

[0155] Specifically, taking the current imbalance rate as an example, the average current imbalance characteristic is calculated to be 20.63% based on historical measurement of switch parameters. Combined with expert experience, the characteristic threshold of the current imbalance rate is set as:

[0156] Abnormal state: greater than 20%;

[0157] Warning status: greater than 10% and less than or equal to 20%;

[0158] Normal state: less than or equal to 10%.

[0159] The warning state is intended to identify potential fault risks in advance so that necessary measures can be taken for inspection or prevention. The abnormal state indicates that the operation of the measuring switch has deviated from the normal range, which may have a serious impact on the operating efficiency or safety of the power grid. Therefore, the threshold of the abnormal state will be further optimized in the later stage to improve the accuracy of monitoring the abnormal state of the measuring switch.

[0160] The current imbalance ratio is used as an input feature and compared with the characteristic threshold. If the calculated current imbalance ratio is greater than 20%, the output status is "abnormal." If the calculated current imbalance ratio is greater than 10% and less than or equal to 20%, the output status is "warning." If the calculated current imbalance ratio is less than or equal to 10%, the output status is "normal." The current imbalance ratio calculation formula, characteristic threshold, and abnormal status monitoring model are encapsulated and imported into the expert knowledge base for real-time monitoring of the measurement switch.

[0161] Step S40: obtaining real-time measurement switch parameters, and using a machine learning model to predict future measurement parameters based on the historical measurement switch parameters and the real-time measurement switch parameters;

[0162] Among them, the machine learning model can be a random forest model, a decision tree model, a support vector machine model, and a long short-term memory network (LSTM) model, etc.

[0163] The expert knowledge base is used to predict the real-time measurement switch parameters and the future measurement parameters, and a first-level judgment result and a second-level judgment result are output.

[0164] Specifically, the LSTM model is good at processing time series data and can learn the dynamic pattern of historical data. Therefore, in this embodiment, the LSTM model is selected to predict the measurement parameters. Taking the current imbalance rate as an example, the three-phase current (phase A current) within 10 days is collected. , B phase current , C phase current ), input into the LSTM model, the LSTM model outputs the three-phase current at the next moment (future phase A current , B phase current , C phase current ). The current three-phase current ( =100, =95, =80), the three-phase current at the next moment ( =105, =85, =90) is input into the expert knowledge base, resulting in a first-level judgment of "abnormal" and a second-level judgment of "warning." The second-level judgment triggers an alarm and advises maintenance personnel to take action before more serious problems occur in the future.

[0165] Step S50: obtaining the actual operating status of the measuring switch at predetermined time intervals, and comparing the actual operating status with the first-level judgment result and the second-level judgment result to obtain a comprehensive false alarm rate and a comprehensive missed alarm rate;

[0166] The actual operating status refers to the actual state of the measured switch during operation. Anomalies such as the switch not closing and contact sticking are recorded by manual inspection and self-test functions. By collecting the system judgment results, including the first-level judgment results and the second-level judgment results, and comparing them with the actual operating status, a confusion matrix is ​​formed. Based on the data in the confusion matrix, the false alarm rate and missed alarm rate are calculated, which is expressed as:

[0167] ;

[0168] ;

[0169] in, is the false alarm rate; is the underreporting rate; For the expert knowledge base to determine anomalies, the situation is actually abnormal; The expert knowledge base determines that the situation is abnormal, but it is actually normal; This is a situation where the expert knowledge base determines that it is normal, but it is actually abnormal.

[0170] Furthermore, the predetermined time interval increases as the number of optimization times of the expert knowledge base increases, which is expressed as:

[0171] ;

[0172] in, For the suboptimal said predetermined time interval, is the initial predetermined time interval, is an exponential function, is the attenuation coefficient, is the number of optimizations.

[0173] Specifically, as the number of knowledge base optimizations increases, monitoring rules become more complete, model prediction accuracy improves, and false positives and false negatives of measurement switch abnormalities decrease, the collection time interval can be appropriately extended, reducing system resource consumption. Set to 5 minutes, the decay coefficient is 0.2, and after the first optimization, the scheduled time interval The scheduled time interval is about 6 minutes after the second optimization. About 7 minutes and 30 seconds, after the fifth optimization, the scheduled time interval The total time is about 12 minutes and 15 seconds, thus avoiding redundant calculations caused by oversampling. It not only improves the intelligence level and accuracy of measurement switch monitoring, but also strikes a balance between optimizing performance and reducing resource consumption.

[0174] Step S60: Optimizing the expert knowledge base using a genetic algorithm based on the comprehensive false alarm rate and the comprehensive omission rate to obtain an updated expert knowledge base.

[0175] Furthermore, the optimization step of the expert knowledge base includes:

[0176] S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals;

[0177] S62: Setting a fitness function, which is expressed as:

[0178] ;

[0179] in, is the fitness value, is the weight coefficient, is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor;

[0180] S63: Evaluate the initial population according to the fitness function to obtain the fitness value;

[0181] S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals;

[0182] S65: updating the initial population according to the new threshold individuals;

[0183] S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

[0184] Specifically, in this embodiment, the initial population size is 50 individuals. The feature threshold in the expert knowledge base is obtained, and the other 49 individuals are randomly generated within the corresponding interval. The weight coefficients are set to 0.4, 0.4 and 0.2 respectively, and the smoothing factor is set to 1. The fitness values ​​of all 50 individuals are calculated and sorted according to the fitness value. The individuals with the top 20% fitness values ​​are selected to generate new individuals by cross-pollination, and 10% of the individuals are mutated to obtain new threshold individuals. The new threshold individuals replace the individuals with low fitness values, and the initial population is updated. When the predetermined number of iterations reaches 100 times, the optimal threshold is output. By optimizing the feature threshold, after the fifth optimization, the false alarm rate is effectively reduced by 3% and the missed alarm rate is effectively reduced by 2%, thereby improving the accuracy of the measurement switch monitoring. It can also adapt to the feature changes under different operating environments, ensuring the stable operation of the measurement switch.

[0185] The present invention comprehensively analyzes and extracts features from historical measurement switch parameters, combines expert experience to construct monitoring rules and define feature thresholds, effectively reducing the subjectivity of threshold setting and improving the sensitivity of abnormal state monitoring. The introduction of a machine learning model accurately predicts future measurement parameters, achieving early warning of abnormal states, thereby reducing safety hazards caused by sudden abnormalities. Based on the dual judgment of real-time measurement parameters and predicted parameters, the comprehensive false alarm rate and missed alarm rate are obtained, further improving the reliability and accuracy of monitoring. By optimizing the expert knowledge base through genetic algorithms and using fitness functions for evaluation and optimization iterations, the monitoring rules and monitoring models are continuously optimized in long-term operation and adapt to the dynamic changes of the actual operating environment, thereby improving the accuracy of measurement switch monitoring and building an efficient and reliable measurement switch abnormal state monitoring system.

[0186] The second embodiment is as follows:

[0187] A power supply company manages a large number of measuring switches, which operate in a complex workshop environment characterized by high humidity and dust concentrations. The company discovered that some measuring switches were not fully closed, resulting in reduced grid efficiency and potential safety hazards. To address this issue, the application of this invention can improve the accuracy of measuring switch monitoring, reduce the missed detection rate of abnormal conditions, and provide early warning of abnormal conditions.

[0188] Figure 3 A schematic diagram of the structure of a system for monitoring and warning abnormal conditions of a measuring switch proposed in an embodiment of the present invention;

[0189] like Figure 3 As shown, a system for monitoring and warning abnormal status of a measuring switch includes:

[0190] a parameter preprocessing module, configured to obtain historical measurement switch parameters, preprocess the historical measurement switch parameters, and obtain a measurement switch data set;

[0191] A feature extraction module, configured to extract features from the measurement switch data set and calculate measurement switch features;

[0192] An expert knowledge base establishment module constructs monitoring rules based on the measurement switch characteristics and expert experience, wherein the monitoring rules are used to set corresponding feature thresholds for each measurement switch characteristic; establishes an abnormal state monitoring model, wherein the abnormal state monitoring model is used to determine whether the measurement switch is in an abnormal state; and encapsulates the feature thresholds and the abnormal state monitoring model and imports them into the expert knowledge base;

[0193] an abnormality monitoring module that obtains real-time measurement switch parameters, and uses a machine learning model to predict future measurement parameters based on the historical measurement switch parameters and the real-time measurement switch parameters; uses the expert knowledge base to predict the real-time measurement switch parameters and the future measurement parameters, and outputs a primary judgment result and a secondary judgment result;

[0194] In this embodiment, the machine learning model uses an LSTM model, and the measurement switch data set is divided into 80% and 20% for training and testing of the LSTM model.

[0195] Specifically, the LSTM model has two hidden layers, 64 LSTM units in each layer, a ReLU activation function, a learning rate of 0.001, and a batch size of 64. After 100 training rounds, all parameters are predicted and the average accuracy is taken. The obtained accuracy meets the requirements. The ARIMA model and the SVR model are used as comparison models. The results are shown in Table 1. It can be seen that the LSTM model has the highest prediction accuracy and the lowest error in both the training and testing phases.

[0196] Table 1 Comparison of model results

[0197] The expert knowledge base optimization module obtains the actual operating status of the measuring switch at predetermined time intervals, and compares the actual operating status with the first-level judgment result and the second-level judgment result to obtain a comprehensive false alarm rate and a comprehensive missed alarm rate; based on the comprehensive false alarm rate and the comprehensive missed alarm rate, a genetic algorithm is used to optimize the expert knowledge base to obtain an updated expert knowledge base.

[0198] Furthermore, the historically measured switch parameters specifically include:

[0199] Mechanical state parameters, electrical characteristic parameters, environmental parameters and data integrity parameters;

[0200] the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter;

[0201] The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state;

[0202] The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance;

[0203] The environmental parameters include temperature, humidity, dust concentration and air pressure;

[0204] The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

[0205] Furthermore, the feature extraction process includes:

[0206] Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters;

[0207] Calculate measurement switch characteristics based on the historical measurement switch parameters; the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics, and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics, and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics, and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics, and abnormal signal quality characteristics;

[0208] Furthermore, the calculation process of measuring the switch characteristics includes:

[0209] Calculating the mean, maximum, and standard deviation of the switch action time to obtain the time anomaly characteristics;

[0210] Calculating the frequency spectrum characteristics of the contact vibration frequency using Fourier transform, and extracting the main frequency from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics;

[0211] Calculating the proportion of the switch in the incompletely closed state in the positioning state to obtain abnormal characteristics of the positioning state;

[0212] Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic; calculating the current imbalance rate according to the current to obtain the current imbalance characteristic;

[0213] Calculating a root mean square current based on the current, and obtaining the line loss characteristic based on the root mean square current and contact resistance;

[0214] Calculating the mean values ​​of temperature, humidity, dust concentration, and air pressure, and performing weighted summation of the mean values ​​to obtain the comprehensive environmental characteristics;

[0215] Calculating the time synchronization anomaly feature according to the signal acquisition time;

[0216] The data loss rate abnormality feature and the signal quality abnormality feature are respectively calculated based on the data loss amount, signal power and noise power.

[0217] Furthermore, the predetermined time interval increases as the number of optimization times of the expert knowledge base increases, which is expressed as:

[0218] ;

[0219] in, For the suboptimal said predetermined time interval, is the initial predetermined time interval, is an exponential function, is the attenuation coefficient, is the number of optimizations.

[0220] Furthermore, the optimization step of the expert knowledge base includes:

[0221] S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals;

[0222] S62: Setting a fitness function, which is expressed as:

[0223] ;

[0224] in, is the fitness value, is the weight coefficient, is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor;

[0225] S63: Evaluate the initial population according to the fitness function to obtain the fitness value;

[0226] S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals;

[0227] S65: updating the initial population according to the new threshold individuals;

[0228] S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

[0229] Table 2 First optimization results

[0230] Table 3 Optimization result example

[0231] Specifically, in this embodiment, the predetermined number of iterations is set to 40. The results of the first optimization are shown in Table 2. It can be seen that when the number of iterations is 1 to 10, the maximum fitness value is 0.92, that is, the feature threshold set according to expert experience performs well. However, as the number of iterations increases, the fitness value gradually increases, and the genetic algorithm tends to converge. It stops after the 40th optimization, and the final average fitness value reaches 0.95, and the maximum individual fitness value is 0.96, indicating that the threshold optimization effect is significant.

[0232] In this example, the optimization was completed 10 times, and the results are shown in Table 3. It can be seen that the threshold amplitude gradually decreases with each optimization, and the feature threshold eventually stabilizes and achieves the optimal effect. Furthermore, limiting the number of optimizations to 10 times also avoids unnecessary complexity caused by excessive adjustments.

[0233] To demonstrate the effectiveness of the present invention, the optimized feature threshold is compared with a company's original solution. Table 4 shows the optimization comparison results of the missed alarm rate and false alarm rate. It can be seen that the present invention reduces the missed alarm and false alarm rates by optimizing the feature threshold, which also verifies the superiority of the present invention in measuring switch anomaly detection.

[0234] Table 4 Comparison results of optimization of missed alarm rate and false alarm rate

[0235] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring and warning abnormal status of a measuring switch, characterized in that: include: Obtain historical measurement switch parameters, including mechanical state parameters, electrical characteristic parameters, environmental parameters, and data integrity parameters; Preprocessing historical measurement switch parameters to obtain a measurement switch data set; Feature extraction is performed on the measurement switch data set to calculate measurement switch features. The measurement switch features include mechanical state features, electrical characteristics, line loss features, comprehensive environmental features, and data signal features. The mechanical state features include abnormal action time features, abnormal contact vibration features, and abnormal positioning state features. The electrical characteristics include pressure loss features, current loss features, and current imbalance features. The data signal features include abnormal time synchronization features, abnormal data loss rate features, and abnormal signal quality features. Construct monitoring rules based on measurement switch features and expert experience. The monitoring rules are used to set corresponding feature thresholds for each measurement switch feature. Establish an abnormal state monitoring model, which is used to determine whether the measuring switch is in an abnormal state; Encapsulate the feature threshold and abnormal state monitoring model and import them into the expert knowledge base; Obtain real-time measurement switch parameters, and use machine learning models to predict future measurement parameters based on historical measurement switch parameters and real-time measurement switch parameters; Use the expert knowledge base to predict real-time measurement switch parameters and future measurement parameters, and output first-level judgment results and second-level judgment results; The actual operating status of the measuring switch is obtained at predetermined time intervals, and the actual operating status is compared with the first-level judgment result and the second-level judgment result to obtain the comprehensive false alarm rate and the comprehensive missed alarm rate; According to the comprehensive false alarm rate and the comprehensive missed alarm rate, the expert knowledge base is optimized using a genetic algorithm to obtain an updated expert knowledge base. The optimization steps of the expert knowledge base include: S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals; S62: Setting a fitness function, which is expressed as: ； in, is the fitness value, 、 and is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor; S63: Evaluate the initial population according to the fitness function to obtain the fitness value; S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals; S65: updating the initial population according to the new threshold individuals; S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

2. The abnormal state monitoring and early warning method of a measuring switch according to claim 1 is characterized in that: The historical measurement switch parameters specifically include: the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter; The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state; The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance; The environmental parameters include temperature, humidity, dust concentration and air pressure; The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

3. The abnormal state monitoring and early warning method of a measuring switch according to claim 1 is characterized in that: The feature extraction process includes: Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters; Calculate measurement switch characteristics based on the historical measurement switch parameters; the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics, and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics, and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics, and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics, and abnormal signal quality characteristics; The calculation process of the measured switch characteristics includes: Calculating the mean, maximum, and standard deviation of the switch action time to obtain the time anomaly characteristics; Calculating the frequency spectrum characteristics of the contact vibration frequency using Fourier transform, and extracting the main frequency from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics; Calculating the proportion of the switch in the incompletely closed state in the positioning state to obtain abnormal characteristics of the positioning state; Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic; calculating the current imbalance rate according to the current to obtain the current imbalance characteristic; Calculating a root mean square current based on the current, and obtaining the line loss characteristic based on the root mean square current and contact resistance; Calculating the mean values ​​of temperature, humidity, dust concentration, and air pressure, and performing weighted summation of the mean values ​​to obtain the comprehensive environmental characteristics; Calculating the time synchronization anomaly feature according to the signal acquisition time; The data loss rate abnormality feature and the signal quality abnormality feature are respectively calculated based on the data loss amount, signal power and noise power.

4. A monitoring and early warning system for abnormal status of a measuring switch, characterized in that: A method for monitoring and warning abnormal conditions of a measuring switch according to any one of claims 1 to 3, comprising: a parameter preprocessing module, configured to obtain historical measurement switch parameters, preprocess the historical measurement switch parameters, and obtain a measurement switch data set; a feature extraction module, configured to extract features from the measurement switch data set and calculate measurement switch features; the measurement switch features include mechanical state features, electrical characteristic features, line loss features, comprehensive environmental features, and data signal features; An expert knowledge base establishment module constructs monitoring rules based on the measurement switch characteristics and expert experience, wherein the monitoring rules are used to set corresponding feature thresholds for each measurement switch characteristic; establishes an abnormal state monitoring model, wherein the abnormal state monitoring model is used to determine whether the measurement switch is in an abnormal state; and encapsulates the feature thresholds and the abnormal state monitoring model and imports them into the expert knowledge base; an abnormality monitoring module that obtains real-time measurement switch parameters, and uses a machine learning model to predict future measurement parameters based on the historical measurement switch parameters and the real-time measurement switch parameters; uses the expert knowledge base to predict the real-time measurement switch parameters and the future measurement parameters, and outputs a primary judgment result and a secondary judgment result; an expert knowledge base optimization module, which obtains actual operating conditions of the measurement switch at predetermined time intervals, and compares the actual operating conditions with the primary judgment result and the secondary judgment result to obtain a comprehensive false alarm rate and a comprehensive missed alarm rate; and optimizes the expert knowledge base using a genetic algorithm based on the comprehensive false alarm rate and the comprehensive missed alarm rate to obtain an updated expert knowledge base; The predetermined time interval is expressed as: ； in, For the suboptimal said predetermined time interval, is the initial predetermined time interval, is an exponential function, is the attenuation coefficient, The number of optimizations.

5. The abnormal state monitoring and early warning system of a measuring switch according to claim 4, characterized in that: The historical measurement switch parameters specifically include: Mechanical state parameters, electrical characteristic parameters, environmental parameters and data integrity parameters; the mechanical state parameter, the electrical characteristic parameter, the environmental parameter, and the data integrity parameter; The mechanical state parameters include switch action time, contact vibration frequency and switch positioning state; The electrical characteristic parameters include current, voltage, active power, reactive power and contact resistance; The environmental parameters include temperature, humidity, dust concentration and air pressure; The data integrity parameters include signal power, signal acquisition time, data loss amount and noise power.

6. The abnormal state monitoring and early warning system for a measuring switch according to claim 4, characterized in that: The feature extraction process includes: Setting a timestamp, wherein the timestamp is used to obtain the historical measurement switch parameters; Calculate measurement switch characteristics based on the historical measurement switch parameters; the measurement switch characteristics include mechanical state characteristics, electrical characteristics, line loss characteristics, comprehensive environmental characteristics, and data signal characteristics; the mechanical state characteristics include abnormal action time characteristics, abnormal contact vibration characteristics, and abnormal positioning state characteristics; the electrical characteristics include pressure loss characteristics, current loss characteristics, and current imbalance characteristics; the data signal characteristics include abnormal time synchronization characteristics, abnormal data loss rate characteristics, and abnormal signal quality characteristics; The calculation process of the measured switch characteristics includes: Calculating the mean, maximum, and standard deviation of the switch action time to obtain the time anomaly characteristics; Calculating the frequency spectrum characteristics of the contact vibration frequency using Fourier transform, and extracting the main frequency from the frequency spectrum characteristics to obtain the abnormal contact vibration characteristics; Calculating the proportion of the switch in the incompletely closed state in the positioning state to obtain abnormal characteristics of the positioning state; Extracting the minimum values ​​of current and voltage respectively to obtain the current loss characteristic and the voltage loss characteristic; calculating the current imbalance rate according to the current to obtain the current imbalance characteristic; Calculating a root mean square current based on the current, and obtaining the line loss characteristic based on the root mean square current and contact resistance; Calculating the mean values ​​of temperature, humidity, dust concentration, and air pressure, and performing weighted summation of the mean values ​​to obtain the comprehensive environmental characteristics; Calculating the time synchronization anomaly feature according to the signal acquisition time; The data loss rate abnormality feature and the signal quality abnormality feature are respectively calculated based on the data loss amount, signal power and noise power.

7. The abnormal state monitoring and early warning system of a measuring switch according to claim 4, characterized in that: The optimization steps of the expert knowledge base include: S61: Setting an initial population, wherein the initial population includes the characteristic threshold and randomly generated threshold individuals; S62: Setting a fitness function, which is expressed as: ； in, is the fitness value, 、 and is the weight coefficient, is the false alarm rate, is the omission rate, is an exponential function, is the current threshold obtained during the optimization process, is the feature threshold, is the smoothing factor; S63: Evaluate the initial population according to the fitness function to obtain the fitness value; S64: According to the fitness value, select individuals whose fitness value is greater than a preset threshold value for crossover and mutation to obtain new threshold individuals; S65: updating the initial population according to the new threshold individuals; S66: If the number of optimization times reaches the predetermined number of iterations, the optimization is terminated and a new feature threshold is output; otherwise, S63 to S66 are repeated.

Images