Circuit breaker switching-on and switching-off detection method and system for gas insulated switchgear

Abstract

The invention discloses a circuit breaker opening and closing detection method and system for a gas insulated switchgear, and relates to the technical field of circuit breaker opening and closing detection, and the method comprises the following steps: in a circuit breaker opening detection process, firstly carrying out real-time data collection on all circuits in a power grid, and providing initial conditions for subsequent fault simulation and analysis; a target circuit is randomly selected from all circuits, and short circuit faults of the circuit under different conditions are simulated. Through real-time power grid data acquisition, random short-circuit fault simulation and feature extraction in a dynamic monitoring window, in combination with a convolutional neural network and a fuzzy logic algorithm, the short-circuit fault severity degree is intelligently evaluated, the optimal opening speed range is predicted, the actual opening speed is accurately compared, abnormity is timely recognized, the problem of misjudgment in traditional detection is avoided, and the detection accuracy is improved. The high-efficiency response of the circuit breaker under different fault conditions is ensured, and the detection precision and the safety and stability of a power system are effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of circuit breaker opening and closing detection, and in particular to a circuit breaker opening and closing detection method and system for an inflatable cabinet. Background Art

[0002] The opening and closing detection of circuit breakers for inflatable cabinets refers to the testing and monitoring process of the switching operation of the circuit breakers installed in the inflatable cabinets. Specifically, this test is designed to verify that the circuit breaker can reliably realize the functions of opening (disconnecting the circuit) and closing (closing the circuit) in actual operation to ensure the safety and stability of the power system. The test content usually includes checking whether the mechanical action of the circuit breaker is smooth, whether the operation time meets the standards, whether the electrical performance is normal, and the response capability under abnormal conditions such as overload or short circuit. By performing opening and closing detection regularly, potential faults or performance degradation of the circuit breaker can be discovered and eliminated in time, power failures and power outages can be prevented, and the efficient operation of the inflatable cabinet and the entire power system can be guaranteed.

[0003] The main function of the circuit breaker opening speed detection is to evaluate the circuit breaker's ability to quickly disconnect the circuit under fault or operation instructions, thereby ensuring the safety and stability of the power system. The opening speed is one of the key performance indicators of the circuit breaker, which directly affects the interruption time of the fault current, the arc duration, and the protection effect of the equipment and system. Through the opening speed detection, it can be verified whether the mechanical action of the circuit breaker meets the design standards, and abnormal actions caused by mechanical jamming, poor lubrication or aging of components can be discovered in time to prevent the expansion of faults or equipment damage caused by too slow opening speed. At the same time, the test results can be used to guide the maintenance and performance optimization of the circuit breaker, ensuring that it can quickly and reliably complete the opening operation in actual operation, and protect the power grid and load equipment from overcurrent or short circuit.

[0004] The prior art has the following deficiencies: When detecting short-circuit faults in circuit breakers, the prior art usually adopts a unified opening speed detection standard to evaluate short-circuit faults of different severity. However, this unified standard may lead to the following problems: in the case of a minor short circuit, due to the small short-circuit current, the circuit breaker's opening load is light, and the mechanical movement resistance is reduced, resulting in an excessively fast opening speed. This excessively fast opening action may be misjudged as an abnormality in the circuit breaker's mechanical system, such as an overtightened spring or a mechanical structure failure, resulting in an erroneous judgment. On the other hand, in the case of a severe short circuit, although the test results show that the opening speed is qualified, the actual performance may not be able to quickly cut off the high-intensity fault current, posing a serious safety hazard. Therefore, the unified detection standard fails to fully consider the different severity of short-circuit faults, which may lead to inaccurate circuit breaker performance evaluation and affect the safety and stability of the power system.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a circuit breaker opening and closing detection method and system for an inflatable cabinet, which can accurately quantify the severity of the fault by collecting power grid data in real time and randomly selecting target circuits to simulate short-circuit faults, combined with the extraction and analysis of key parameters in the dynamic monitoring window. Intelligent evaluation is performed using a trained convolutional neural network, and the optimal opening speed range is dynamically predicted by a fuzzy logic algorithm to achieve an optimized response of the opening action. By comparing the actual opening speed with the predicted range, the circuit breaker performance can be accurately detected, and an alarm can be triggered in the event of an abnormality, effectively avoiding the misjudgment and missed judgment problems of traditional detection methods. The method ensures that the circuit breaker operates efficiently and reliably under various short-circuit fault conditions through an intelligent and dynamic evaluation mechanism, significantly improving the safety and stability of the power system, so as to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for detecting the opening and closing of a circuit breaker for an inflatable cabinet, comprising the following steps: During the circuit breaker opening detection process, real-time data collection is first performed on all circuits in the power grid to provide initial conditions for subsequent fault simulation and analysis; A target circuit is randomly selected from all circuits, and the short-circuit fault of the circuit is simulated under different conditions; After simulating a short-circuit fault, key parameters that can reflect the fault characteristics are extracted from the collected data, and the extracted characteristics are dynamically analyzed within the set monitoring window to quantify the severity of the fault; The characteristic data obtained by dynamic analysis under the monitoring window is input into the trained convolutional neural network for intelligent evaluation, and the severity of the short-circuit fault of the target circuit is intelligently predicted; According to the output results of the convolutional neural network, the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short-circuit fault of the circuit; The actual measured opening speed is compared with the optimal opening speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual opening speed is not within the recommended range, an abnormal alarm is triggered to improve the detection accuracy of the opening speed.

[0008] Preferably, fault simulation is achieved by setting up a virtual scenario or applying a control signal to the target circuit to ensure coverage of minor, moderate and severe short circuit conditions. The process of randomly selecting and simulating faults can effectively verify the performance of the circuit breaker under a variety of circuits and fault conditions.

[0009] Preferably, key parameters that can reflect the fault characteristics are extracted, wherein the extracted parameters include the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault. The extracted short-circuit current rising speed from zero to the peak value and the duration of the arc in the short-circuit fault are dynamically analyzed within a set monitoring window to generate a short-circuit current rise rate reference value and an arc duration reference value, respectively. The severity of the fault is preliminarily quantified by the short-circuit current rise rate reference value and the arc duration reference value.

[0010] Preferably, a short-circuit current rise rate reference value and an arc duration reference value obtained by dynamically analyzing the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault under the monitoring window are input into a trained convolutional neural network, and a fault intensity assessment index is generated by the convolutional neural network. Based on the fault intensity assessment index, an intelligent assessment and prediction of the severity of the short-circuit fault is performed.

[0011] Preferably, the specific steps of dynamically analyzing the rising speed of the extracted short-circuit current from zero to the peak value within a set monitoring window to generate a short-circuit current rising rate reference value are as follows: In the monitoring window, the data samples of the current signal are first extracted, and the rising speed of the current from zero to the peak value is calculated by signal processing technology. Assuming that in the monitoring window, the function of the current changing with time is , where t represents time, is the current value at time t. Within the monitoring window, the instantaneous growth rate of the short-circuit current is calculated, that is, the exponential expression of the current change rate. The calculation expression is: ,in, represents the instantaneous speed increase of the current, is the decay factor, controlling the effect of time decay; By instantaneous speed Perform time-weighted integration to generate a short-circuit current rise rate reference value. The short-circuit current rise rate reference value is combined with all current growth rate values ​​in the monitoring window. The calculation expression is: ,in, is the reference value of the short-circuit current rise rate, and is the start and end time of the monitoring window, and It is a weighting factor that adjusts the contribution of current growth rate and the attenuation effect of time.

[0012] Preferably, the specific steps of dynamically analyzing the duration of the extracted arc in the short circuit fault within a set monitoring window to generate an arc duration reference value are as follows: When a short circuit fault occurs, the time information of arc occurrence is collected in real time through sensors and monitoring systems; In the monitoring window, based on the collected arc duration data, the arc duration reference value is defined as a comprehensive quantitative indicator reflecting the arc duration characteristics. The generation logic of the arc duration reference value is based on the dynamic characteristics of the arc in the short circuit fault, considering the occurrence, continuation and disappearance process of the arc. The calculation expression is: ,in: is the arc duration reference value, For the i The duration of the arc at a moment, For the i The arc brightness at every moment reflects the change of arc intensity. is the length of the monitoring window, and To adjust the parameters, used to adjust the time length of the monitoring window and the influence of arc intensity, For the i The current intensity value when the arc disappears at the moment, n is the number of arc time points collected within the monitoring window.

[0013] Preferably, according to the output result of the convolutional neural network, a fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short circuit fault of the circuit, and the specific steps are as follows: The fault intensity assessment index output by the convolutional neural network As the input variable of the fuzzy logic algorithm, the input membership function of the fuzzy logic is defined to describe the severity of the short-circuit fault. Specifically, the fault intensity assessment index is divided into three fuzzy sets: "mild", "medium", and "severe", and the corresponding membership functions are: ,in: , , are the center values ​​of minor, moderate and severe fault intensities, respectively. , , are the widths of the slightly, moderately, and severely blurred sets, respectively. is the degree of membership, , , They represent the degree to which the fault intensity assessment index belongs to the fuzzy set of slight, moderate and severe respectively; Based on the membership degree of the fault intensity assessment index and the circuit breaker tripping performance characteristics, a fuzzy rule base is established to associate the severity of the short-circuit fault with the fuzzy set of the optimal tripping speed range. The specific fuzzy rule base is as follows: Rule 1: If the fault intensity assessment index is "mild", the optimal opening speed range is "relatively loose"; Rule 2: If the fault intensity assessment index is "medium", the optimal opening speed range is "moderate"; Rule 3: If the fault intensity assessment index is "serious", the optimal trip speed range is "strict"; The reasoning process is formulated, and the membership of the output fuzzy set is calculated through fuzzy logic reasoning. The calculation expression is: ,in: is the opening speed range, is the fuzzy membership function of the trip speed range, , , Fuzzy membership functions corresponding to the opening speed ranges in the case of slight, medium and severe short circuits; The result of fuzzy reasoning is defuzzified to obtain the specific optimal opening speed range value. The centroid method is used for defuzzification. The defuzzification expression is: ,in: is the optimal opening speed range obtained after defuzzification, and They are the upper and lower limits of the opening speed range respectively.

[0014] Preferably, the actually measured opening speed is compared with the optimal opening speed range predicted by the fuzzy logic algorithm. If the actually measured opening speed is within the optimal opening speed range predicted by the fuzzy logic algorithm, it indicates that the opening speed of the circuit breaker during the opening operation meets the expected standard and no prompt is issued. If the actually measured opening speed is not within the optimal opening speed range predicted by the fuzzy logic algorithm, an abnormal alarm is triggered to notify relevant personnel.

[0015] The circuit breaker opening and closing detection system for the inflatable cabinet includes a real-time data acquisition module, a target circuit selection and fault simulation module, a feature extraction and dynamic analysis module, an intelligent evaluation module, an optimal opening speed prediction module, and an opening speed detection and abnormal alarm module; The real-time data acquisition module first collects real-time data of all circuits in the power grid during the circuit breaker opening detection process to provide initial conditions for subsequent fault simulation and analysis; The target circuit selection and fault simulation module randomly selects a target circuit from all circuits and simulates the short-circuit fault of the circuit under different conditions; The feature extraction and dynamic analysis module extracts key parameters that can reflect the fault characteristics from the collected data after simulating the short-circuit fault, and dynamically analyzes the extracted features within the set monitoring window to quantify the severity of the fault; The intelligent evaluation module inputs the characteristic data obtained from the dynamic analysis under the monitoring window into the trained convolutional neural network for intelligent evaluation, and makes an intelligent prediction of the severity of the short-circuit fault of the target circuit; The optimal tripping speed prediction module uses a fuzzy logic algorithm to calculate and predict the optimal tripping speed range under the short-circuit fault of the circuit according to the output result of the convolutional neural network; The trip speed detection and abnormal alarm module compares the actual measured trip speed with the optimal trip speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual trip speed is not within the recommended range, an abnormal alarm is triggered, effectively improving the detection accuracy of the trip speed.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention collects data from all circuits in the power grid in real time, ensures that the detection process is based on comprehensive and up-to-date operating status information, randomly selects target circuits and simulates multiple short-circuit faults, and extracts and analyzes key parameters in the dynamic monitoring window, so that the quantification of fault severity is more detailed and accurate, and inputs these features into the trained convolutional neural network, using its powerful pattern recognition and prediction capabilities to achieve intelligent evaluation of the severity of short-circuit faults. At the same time, a fuzzy logic algorithm is used to dynamically predict the optimal opening speed range to ensure the optimized response of the opening action under different fault conditions. Finally, by comparing and analyzing the actual opening speed with the predicted optimal range, it is possible to accurately identify whether the performance of the circuit breaker meets the expected standards, and trigger an alarm in time when an abnormality is found, which not only effectively avoids the misjudgment and missed judgment problems caused by the traditional unified detection standard, but also ensures that the circuit breaker can achieve efficient and reliable opening operation under various short-circuit fault conditions through an intelligent and dynamic evaluation mechanism, thereby greatly improving the safety and stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 The present invention is a flow chart of a method for detecting the opening and closing of a circuit breaker for an inflatable cabinet.

[0019] Figure 2 It is a module schematic diagram of the circuit breaker opening and closing detection system for the inflatable cabinet of the present invention. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0021] The present invention provides Figure 1 The circuit breaker opening and closing detection method for the inflatable cabinet shown includes the following steps: During the circuit breaker opening detection process, real-time data collection is first performed on all circuits in the power grid to provide initial conditions for subsequent fault simulation and analysis; The collected data include key parameters such as current, voltage, power, and frequency. These data can be obtained through sensors or monitoring equipment installed on circuit breakers and circuits, and transmitted to the central control system for processing and storage. The collected data should cover the circuit characteristics under normal operation and fault scenarios to ensure the comprehensiveness and accuracy of subsequent analysis. Real-time data acquisition is the basis of the entire detection process and provides the necessary initial conditions for subsequent fault simulation and analysis. Comprehensive real-time data can accurately reflect the operating status and load characteristics of the circuit, laying the foundation for dynamically adjusting the detection strategy.

[0022] Randomly select a target circuit from all circuits and simulate the short-circuit fault of the circuit under different conditions (such as single-phase short circuit, two-phase short circuit or three-phase short circuit); Fault simulation can be achieved by setting up virtual scenarios or applying control signals to the target circuit to ensure coverage of minor, medium and severe short circuits. The process of randomly selecting and simulating faults can effectively verify the performance of circuit breakers under a variety of circuits and fault conditions. By simulating real scenarios, the adaptability and responsiveness of circuit breakers can be tested to ensure their reliability in actual operation.

[0023] After simulating a short-circuit fault, key parameters that can reflect the fault characteristics are extracted from the collected data, and the extracted characteristics are dynamically analyzed within a set monitoring window (i.e., a fixed time range) to quantify the severity of the fault; The key parameters that can reflect the fault characteristics are extracted, wherein the extracted parameters include the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault. The extracted rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault are dynamically analyzed within the set monitoring window to generate a short-circuit current rise rate reference value and an arc duration reference value, respectively. The severity of the fault is preliminarily quantified by the short-circuit current rise rate reference value and the arc duration reference value.

[0024] When the short-circuit current of the target circuit rises very quickly from zero to peak, it usually indicates that the short-circuit fault of the circuit is very serious. This is because a short-circuit fault usually causes a sharp increase in current, especially when the power supply impedance is low or a low-impedance short circuit occurs, the current rise rate will be extremely rapid. The rapid rise of current reflects the strong impact of the short-circuit current source on the circuit, which may cause electrical equipment to be under extremely high pressure, and even the risk of equipment damage or system collapse. On the contrary, if the short-circuit current rises slowly, it may mean that the short-circuit fault is lighter, the current load is smaller, and the impact of the system is weaker. This situation usually occurs when the power supply impedance is high or a high-impedance short circuit occurs, and the circuit fault is relatively mild. Therefore, the speed of the short-circuit current rise can effectively be used as an important indicator to assess the severity of the short-circuit fault. The faster the speed, the more serious the fault, and vice versa.

[0025] The specific steps for dynamically analyzing the rising speed of the extracted short-circuit current from zero to peak value within the set monitoring window to generate a reference value of the short-circuit current rising rate are as follows: In the monitoring window, the data samples of the current signal are first extracted, and the rising speed of the current from zero to the peak value is calculated by signal processing technology. Assuming that in the monitoring window, the function of the current changing with time is , where t represents time, is the current value at time t. Within the monitoring window, the instantaneous growth rate of the short-circuit current is calculated, that is, the exponential expression of the current change rate. The calculation expression is: ,in, represents the instantaneous speed increase of the current, is the decay factor, controlling the effect of time decay (in order to simulate the nonlinear response of the real system); The instantaneous speed increase of the current Describes the instantaneous rate of change of the short-circuit current within the monitoring window, the attenuation factor The hysteresis effect during the control current rise process reflects the electrical inertia of the system. In this way, the temporal characteristics of the sharp rise in current can be captured, which is particularly suitable for simulating the dynamic response of the system. This step can more accurately quantify the nonlinear characteristics of the short-circuit current in the monitoring window by calculating the instantaneous growth rate, reflecting the sharp rise process of the current. The instantaneous growth rate can not only capture the characteristics of the rapid increase in the initial stage of the short-circuit current, but also combine the time factor for a higher-order dynamic description, reflecting the actual response of the system.

[0026] By instantaneous speed Perform time-weighted integration to generate a short-circuit current rise rate reference value. The short-circuit current rise rate reference value is combined with all current growth rate values ​​in the monitoring window. The calculation expression is: ,in, is the reference value of the short-circuit current rise rate, and is the start and end time of the monitoring window, and is the weight factor, which adjusts the contribution of current growth rate and the attenuation effect of time; The weighting factor in this formula This makes the early growth rate change contribute more to the short-circuit current rise rate reference value, and the impact of the growth rate gradually weakens over time. This weighting method can emphasize the impact of sudden faults in the short term, so that the index is more sensitive to the severity of short-circuit faults; through integration and weighting, the short-circuit current rise rate reference value can fully consider the dynamic process of current rise in the monitoring window and quantify the comprehensive impact of the short-circuit current growth rate on the severity of the fault. A high short-circuit current rise rate reference value indicates that the short-circuit current rises very quickly, which is usually associated with severe short-circuit faults, while a low short-circuit current rise rate reference value indicates that the fault current rises slowly, which may indicate a minor fault or a short circuit of lower intensity.

[0027] It can be seen from the short-circuit current rise rate reference value that the larger the performance value of the short-circuit current rise rate reference value generated by dynamically analyzing the rise rate of the extracted short-circuit current from zero to the peak value within the set monitoring window, the more serious the short-circuit fault of the target circuit. This is because when the rise rate of the short-circuit current from zero to the peak value is very fast, it means that the strength and impact of the fault current are extremely large, which is usually related to the low power supply impedance or the short circuit occurring at the key node of the circuit, resulting in a rapid current burst. This situation often indicates that the circuit is under great pressure and may cause equipment damage or system collapse. A smaller short-circuit current rise rate reference value indicates that the current rises slowly, which is usually related to a weak fault current or a high-impedance short circuit, reflecting that the circuit fault is lighter or the short circuit is slower, and the system pressure is relatively small. Therefore, by analyzing the short-circuit current rise rate reference value, the severity of the fault can be effectively quantified. The larger the index, the more serious the fault, and vice versa.

[0028] A longer arc duration usually means a more serious short-circuit fault. The arc is formed when the current passes through the air or other media to form an arc when the circuit breaker fails to cut off the circuit in time. In a short-circuit fault, the arc duration reflects the length of time the current flows and whether the circuit breaker can effectively cut off the fault current in a short time. If the arc duration is long, it usually means that the circuit breaker fails to respond quickly or the short-circuit current is very strong, causing the arc to last too long. This situation often occurs in serious short-circuit faults, which may cause significant power loss, equipment damage, and even fire hazards. If the arc duration is short, it means that the circuit breaker can quickly and effectively cut off the fault current, and the severity of the fault is relatively mild. Therefore, the arc duration is an important indicator for judging the severity of a short-circuit fault. The longer the duration, the more serious the fault, and vice versa.

[0029] The specific steps of dynamically analyzing the duration of the extracted arc in the short-circuit fault within the set monitoring window to generate the arc duration reference value are as follows: When a short circuit fault occurs, the time information of arc occurrence is collected in real time through sensors and monitoring systems; When a short-circuit fault occurs, the sensor and monitoring system capture the occurrence and evolution of the arc by real-time monitoring of the current, voltage, arc brightness and temperature changes. First, the current sensor detects the sudden increase in short-circuit current, and the voltage sensor reflects the sharp fluctuations in the grid voltage. When the short-circuit current reaches a certain threshold, the arc sensor (such as an infrared sensor or a photoelectric sensor) senses the formation of the arc, which is usually accompanied by strong light radiation generated by the arc. The monitoring system records the time points when the arc starts and ends in real time, and obtains multi-dimensional data related to the arc intensity, current waveform and temperature changes. During the whole process, the system not only captures the duration of the arc in real time, but also monitors and analyzes the dynamic characteristics of the arc according to the arc intensity and change trend, providing basic data for subsequent fault diagnosis.

[0030] In the monitoring window, based on the collected arc duration data, the arc duration reference value is defined as a comprehensive quantitative indicator reflecting the arc duration characteristics. The generation logic of the arc duration reference value is based on the dynamic characteristics of the arc in the short circuit fault, considering the occurrence, continuation and disappearance process of the arc. The calculation expression is: ,in: is the arc duration reference value, For the i The duration of the arc at a moment, For the i The arc brightness at every moment reflects the change of arc intensity. is the length of the monitoring window, and To adjust the parameters, used to adjust the time length of the monitoring window and the influence of arc intensity, For the i The current intensity value when the arc disappears at the moment, n is the number of arc time points collected within the monitoring window; The purpose of this step is to dynamically calculate the arc duration reference value by comprehensively considering factors such as arc duration, brightness change, current intensity when the arc disappears, etc. This arc duration reference value can comprehensively reflect the change trend of the arc in the entire monitoring window and effectively evaluate the severity of the short circuit fault.

[0031] It can be seen from the arc duration reference value that the larger the performance value of the arc duration reference value generated by dynamically analyzing the duration of the extracted arc in the short-circuit fault within the set monitoring window, the more serious the short-circuit fault of the target circuit is. In a short-circuit fault, the arc duration directly reflects the duration of the fault current and its impact on the circuit. When the arc duration is long, it means that the current has not been cut off quickly, and the arc is maintained in the circuit for a long time, which usually occurs in more serious short-circuit faults. At this time, the safety of the system is low, which may cause damage to power equipment or even fire and other safety hazards. The situation where the arc duration reference value is large is usually related to factors such as high current, low circuit impedance and slow response of the circuit breaker, which indicate the severity of the fault. On the contrary, if the arc duration is short, it usually indicates that the circuit breaker can respond in time and the fault current is quickly cut off, indicating that the short-circuit fault is light and the system can maintain high safety. Therefore, the larger the arc duration reference value, the higher the severity of the short-circuit fault, and vice versa.

[0032] The characteristic data obtained by dynamic analysis under the monitoring window is input into the trained convolutional neural network for intelligent evaluation, and the severity of the short-circuit fault of the target circuit is intelligently predicted; The short-circuit current rise rate reference value and arc duration reference value obtained by dynamically analyzing the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault under the monitoring window are input into the trained convolutional neural network. The fault intensity assessment index is generated by the convolutional neural network, and the severity of the short-circuit fault is intelligently evaluated and predicted based on the fault intensity assessment index.

[0033] A trained convolutional neural network (CNN) refers to a neural network model that has been trained, optimized, and verified by deep learning, and is usually used to process complex data with spatial or time series characteristics. The trained convolutional neural network is used to process the dynamic feature data of short-circuit faults and generate a fault intensity assessment index. Convolutional neural networks are usually composed of multiple convolutional layers, pooling layers, fully connected layers, and activation functions, which can effectively extract hierarchical features in the input data and classify or regress different fault modes. In this scheme, the main function of the convolutional neural network is to convert the input features of the short-circuit current rise rate reference value and arc duration reference value extracted from the monitoring window into a fault intensity assessment index, thereby realizing an intelligent assessment of the severity of the short-circuit fault.

[0034] During the training process, the convolutional neural network is first supervised through a large amount of historical short-circuit fault data (including short-circuit current rise rate, duration, arc characteristics, etc.). These data are preprocessed and normalized before training to ensure that the model can adapt to various different input features. The convolution layer is used to extract local features (such as the morphological characteristics of the current waveform and the change characteristics of the arc) from the original input data, while the pooling layer further compresses the dimension of the features, reduces the computational complexity and prevents overfitting. The fully connected layer maps high-dimensional features to low-dimensional space and performs deeper nonlinear feature combinations. The network parameters are optimized by the back-propagation algorithm, and the weights are gradually adjusted during the training process to minimize the prediction error, and finally a model that can accurately evaluate the intensity of short-circuit faults is obtained. The trained convolutional neural network can generate an accurate fault intensity assessment index based on the input short-circuit current rise rate reference value and arc duration reference value, and intelligently predict and evaluate the severity of the fault based on the fault intensity assessment index. This method can automatically identify the severity of the fault, avoid errors in manual judgment, and provide a more accurate basis for fault management and early warning of the power system.

[0035] The convolutional neural network is not specifically limited here, and can achieve the reference value of the short-circuit current rise rate and arc duration reference value Comprehensive analysis to generate a fault severity assessment index In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the fault intensity assessment index The resulting calculation formula is: , where , They are short-circuit current rise rate reference values ​​respectively and arc duration reference value The preset scaling factor of , Both are greater than 0.

[0036] It can be seen from the fault intensity assessment index that the greater the performance value of the short-circuit current rise rate reference value generated by dynamically analyzing the rising speed of the extracted short-circuit current from zero to the peak value within the set monitoring window, the greater the performance value of the arc duration reference value generated by dynamically analyzing the duration of the extracted arc in the short-circuit fault within the set monitoring window. That is, the greater the performance value of the fault intensity assessment index generated when the severity of the short-circuit fault of the target circuit is intelligently predicted by the trained convolutional neural network, the more severe the short-circuit fault of the target circuit is, and vice versa.

[0037] According to the output results of the convolutional neural network (the severity of the short-circuit fault), the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short-circuit fault of the circuit; Fuzzy logic algorithms can handle uncertainty and adapt to changes in different fault scenarios. By converting the severity of short-circuit faults into a set of fuzzy rules, fuzzy logic algorithms can generate a range of trip speeds that adapt to different short-circuit scenarios. This method can flexibly adjust the prediction results of the trip speed according to different fault intensities, thereby optimizing the tripping action of the circuit breaker.

[0038] According to the output results of the convolutional neural network, the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short-circuit fault of the circuit. The specific steps are as follows: The fault intensity assessment index output by the convolutional neural network As the input variable of the fuzzy logic algorithm, the input membership function of the fuzzy logic is defined to describe the severity of the short circuit fault. For example, the fault intensity assessment index is divided into three fuzzy sets: "Minor", "Moderate", and "Severe", and the corresponding membership functions are: ,in: , , are the center values ​​of minor, moderate and severe fault intensities, respectively. , , are the widths of the slightly, moderately, and severely blurred sets, respectively. is the degree of membership, , , They represent the degree to which the fault intensity assessment index belongs to the fuzzy set of slight, moderate and severe respectively; By defining fuzzy rules through membership functions, the severity of the fault intensity assessment index can be fuzzily classified, providing diverse decision-making basis for subsequent prediction of the optimal tripping speed range.

[0039] Based on the membership of the fault intensity assessment index and the circuit breaker tripping performance characteristics, a fuzzy rule base is established to associate the severity of the short-circuit fault with the fuzzy set of the optimal tripping speed range. For example: Rule 1: If the fault intensity assessment index is "mild", the optimal opening speed range is "relatively loose"; Rule 2: If the fault intensity assessment index is "medium", the optimal opening speed range is "moderate"; Rule 3: If the fault severity assessment index is “severe”, the optimal tripping speed range is “strict”.

[0040] The reasoning process is formulated, and the membership of the output fuzzy set is calculated through fuzzy logic reasoning. The calculation expression is:

[0041] ,in: is the opening speed range, is the fuzzy membership function of the trip speed range, , , Fuzzy membership functions corresponding to the opening speed ranges in the case of slight, medium and severe short circuits; The fuzzy rule base realizes intelligent reasoning from fault intensity to trip speed by associating the fault intensity assessment index and the trip speed range, providing a basis for dynamic adjustment.

[0042] The result of fuzzy reasoning is defuzzified to obtain the specific optimal opening speed range value. The centroid method is used for defuzzification. The defuzzification expression is: ,in: is the optimal opening speed range obtained after defuzzification, and They are the upper and lower limits of the opening speed range respectively; The defuzzification process converts the fuzzy set obtained by fuzzy logic reasoning into a specific numerical output, making the opening speed range operational and providing a quantitative basis for detecting and adjusting circuit breakers.

[0043] According to the severity of the short-circuit fault output by the convolutional neural network, the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range to achieve precise and intelligent control of the circuit breaker opening action. Short-circuit faults of different severity have different requirements for the opening speed. For example, severe faults require faster opening speeds to quickly cut off the fault current, while minor faults can allow for a slightly slower opening speed to reduce mechanical impact and equipment loss. The fuzzy logic algorithm dynamically calculates the optimal opening speed range suitable for the current short-circuit conditions by processing the fuzzy relationship between the severity of the fault and the opening speed, comprehensively considering the fault level, arc characteristics, and mechanical system limitations, to ensure that the opening action not only meets the fault isolation requirements, but also maximizes the protection of the mechanical structure of the circuit breaker and the safety of the power grid equipment. This can effectively improve the fault handling efficiency of the power system and the service life of the circuit breaker.

[0044] Compare the actual measured opening speed with the optimal opening speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual opening speed is not within the recommended range, an abnormal alarm is triggered, effectively improving the detection accuracy of the opening speed. The actually measured opening speed is compared with the optimal opening speed range predicted by the fuzzy logic algorithm. If the actually measured opening speed is within the optimal opening speed range predicted by the fuzzy logic algorithm, it indicates that the opening speed of the circuit breaker during the opening operation meets the expected standard and no prompt is issued. If the actually measured opening speed is not within the optimal opening speed range predicted by the fuzzy logic algorithm, an abnormal alarm is triggered to notify relevant personnel, thereby improving the detection accuracy of the opening speed.

[0045] Through comparative analysis, it is possible to effectively detect whether the response of the circuit breaker in actual fault conditions meets the expected standards and ensure its normal performance. If the actual opening speed is not within the recommended range, the system will identify potential problems, trigger abnormal alarms, and promptly detect potential performance abnormalities of the circuit breaker to ensure safe and stable operation of the power system. If the actual opening speed exceeds the recommended range, the system will identify possible mechanical failures, electrical performance degradation, or control delays in the circuit breaker, and provide timely early warning signals to operation and maintenance personnel by triggering abnormal alarms. This detection mechanism can not only verify the adaptability of the circuit breaker under different short-circuit conditions, but also prevent fault expansion, equipment damage, or power grid interruption accidents caused by improper opening response, thereby improving the overall reliability and maintenance efficiency of the power system.

[0046] The above-mentioned detection method for the opening and closing of circuit breakers for inflatable cabinets can significantly improve the precision and accuracy of detection. The method collects data from all circuits in the power grid in real time, ensuring that the detection process is based on comprehensive and up-to-date operating status information. The target circuit is randomly selected and multiple short-circuit faults are simulated. Combined with the extraction and analysis of key parameters in the dynamic monitoring window, the quantification of the severity of the fault is more detailed and accurate. These features are input into the trained convolutional neural network, and its powerful pattern recognition and prediction capabilities are used to realize the intelligent evaluation of the severity of the short-circuit fault. At the same time, the fuzzy logic algorithm is used to dynamically predict the optimal opening speed range to ensure the optimized response of the opening action under different fault conditions. Finally, by comparing and analyzing the actual opening speed with the predicted optimal range, it is possible to accurately identify whether the performance of the circuit breaker meets the expected standards, and trigger an alarm in time when an abnormality is found. The integration of this series of steps not only effectively avoids the problems of misjudgment and missed judgment caused by the traditional unified detection standards, but also ensures that the circuit breaker can achieve efficient and reliable opening operation under various short-circuit fault conditions through an intelligent and dynamic evaluation mechanism, thereby greatly improving the safety and stability of the power system.

[0047] The present invention provides Figure 2 The circuit breaker opening and closing detection system for the inflatable cabinet shown includes a real-time data acquisition module, a target circuit selection and fault simulation module, a feature extraction and dynamic analysis module, an intelligent evaluation module, an optimal opening speed prediction module, and an opening speed detection and abnormal alarm module; The real-time data acquisition module first collects real-time data of all circuits in the power grid during the circuit breaker opening detection process to provide initial conditions for subsequent fault simulation and analysis; The target circuit selection and fault simulation module randomly selects a target circuit from all circuits and simulates the short-circuit fault of the circuit under different conditions; The feature extraction and dynamic analysis module extracts key parameters that can reflect the fault characteristics from the collected data after simulating the short-circuit fault, and dynamically analyzes the extracted features within the set monitoring window to quantify the severity of the fault; The intelligent evaluation module inputs the characteristic data obtained from the dynamic analysis under the monitoring window into the trained convolutional neural network for intelligent evaluation, and makes an intelligent prediction of the severity of the short-circuit fault of the target circuit; The optimal tripping speed prediction module uses a fuzzy logic algorithm to calculate and predict the optimal tripping speed range under the short-circuit fault of the circuit according to the output result of the convolutional neural network; The opening speed detection and abnormal alarm module compares the actual opening speed measured with the optimal opening speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual opening speed is not within the recommended range, an abnormal alarm is triggered, effectively improving the detection accuracy of the opening speed; The method for detecting the opening and closing of a circuit breaker for an inflatable cabinet provided in an embodiment of the present invention is realized by the above-mentioned circuit breaker opening and closing detection system for an inflatable cabinet. The specific method and process of the circuit breaker opening and closing detection system for an inflatable cabinet are detailed in the embodiment of the method for detecting the opening and closing of a circuit breaker for an inflatable cabinet, which will not be repeated here.

[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0049] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0050] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for detecting the opening and closing of a circuit breaker for an inflatable cabinet, characterized in that: The following steps are involved: During the circuit breaker opening detection process, real-time data collection is first performed on all circuits in the power grid to provide initial conditions for subsequent fault simulation and analysis; A target circuit is randomly selected from all circuits, and the short-circuit fault of the circuit is simulated under different conditions; After simulating a short-circuit fault, key parameters that can reflect the fault characteristics are extracted from the collected data, and the extracted characteristics are dynamically analyzed within the set monitoring window to quantify the severity of the fault; The characteristic data obtained by dynamic analysis under the monitoring window is input into the trained convolutional neural network for intelligent evaluation, and the severity of the short-circuit fault of the target circuit is intelligently predicted; According to the output results of the convolutional neural network, the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short-circuit fault of the circuit; The actual measured opening speed is compared with the optimal opening speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual opening speed is not within the recommended range, an abnormal alarm is triggered to improve the detection accuracy of the opening speed.

2. The circuit breaker opening and closing detection method for an inflatable cabinet according to claim 1 is characterized in that: Fault simulation is achieved by setting up virtual scenarios or applying control signals to the target circuit to ensure coverage of minor, moderate and severe short circuit conditions. The process of randomly selecting and simulating faults can effectively verify the performance of circuit breakers under a variety of circuits and fault conditions.

3. The circuit breaker opening and closing detection method for an inflatable cabinet according to claim 1 is characterized in that: The key parameters that can reflect the fault characteristics are extracted, wherein the extracted parameters include the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault. The extracted rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault are dynamically analyzed within the set monitoring window to generate a short-circuit current rise rate reference value and an arc duration reference value, respectively. The severity of the fault is preliminarily quantified by the short-circuit current rise rate reference value and the arc duration reference value.

4. The method for detecting the opening and closing of a circuit breaker for an inflatable cabinet according to claim 3, characterized in that: The short-circuit current rise rate reference value and arc duration reference value obtained by dynamically analyzing the rising speed of the short-circuit current from zero to the peak value and the duration of the arc in the short-circuit fault under the monitoring window are input into the trained convolutional neural network. The fault intensity assessment index is generated by the convolutional neural network, and the severity of the short-circuit fault is intelligently evaluated and predicted based on the fault intensity assessment index.

5. The circuit breaker opening and closing detection method for an inflatable cabinet according to claim 3 is characterized in that: The specific steps for dynamically analyzing the rising speed of the extracted short-circuit current from zero to peak value within the set monitoring window to generate a reference value of the short-circuit current rising rate are as follows: In the monitoring window, the data samples of the current signal are first extracted, and the rising speed of the current from zero to the peak value is calculated by signal processing technology. Assuming that in the monitoring window, the function of the current changing with time is , where t represents time, is the current value at time t. Within the monitoring window, the instantaneous growth rate of the short-circuit current is calculated, that is, the exponential expression of the current change rate. The calculation expression is: ,in, represents the instantaneous speed increase of the current, is the decay factor, controlling the effect of time decay; By instantaneous speed Perform time-weighted integration to generate a short-circuit current rise rate reference value. The short-circuit current rise rate reference value is combined with all current growth rate values ​​in the monitoring window. The calculation expression is: ,in, is the reference value of the short-circuit current rise rate, and is the start and end time of the monitoring window, and It is a weighting factor that adjusts the contribution of current growth rate and the attenuation effect of time.

6. The method for detecting the opening and closing of a circuit breaker for an inflatable cabinet according to claim 3, characterized in that: The specific steps of dynamically analyzing the duration of the extracted arc in the short-circuit fault within the set monitoring window to generate the arc duration reference value are as follows: When a short circuit fault occurs, the time information of arc occurrence is collected in real time through sensors and monitoring systems; In the monitoring window, based on the collected arc duration data, the arc duration reference value is defined as a comprehensive quantitative indicator reflecting the arc duration characteristics. The generation logic of the arc duration reference value is based on the dynamic characteristics of the arc in the short circuit fault, considering the occurrence, continuation and disappearance process of the arc. The calculation expression is: ,in: is the arc duration reference value, For the i The duration of the arc at a moment, For the i The arc brightness at every moment reflects the change of arc intensity. is the length of the monitoring window, and To adjust the parameters, used to adjust the time length of the monitoring window and the influence of arc intensity, For the i The current intensity value when the arc disappears at the moment, n is the number of arc time points collected within the monitoring window.

7. The method for detecting the opening and closing of a circuit breaker for an inflatable cabinet according to claim 6, characterized in that: According to the output results of the convolutional neural network, the fuzzy logic algorithm is used to calculate and predict the optimal opening speed range under the short-circuit fault of the circuit. The specific steps are as follows: The fault intensity assessment index output by the convolutional neural network As the input variable of the fuzzy logic algorithm, the input membership function of the fuzzy logic is defined to describe the severity of the short-circuit fault. Specifically, the fault intensity assessment index is divided into three fuzzy sets of "mild", "medium" and "severe", and the corresponding membership functions are: ,in: , , are the center values ​​of minor, moderate and severe fault intensities, respectively. , , are the widths of the slightly, moderately, and severely blurred sets, respectively. is the degree of membership, , , They represent the degree to which the fault intensity assessment index belongs to the fuzzy set of slight, moderate and severe respectively; Based on the membership degree of the fault intensity assessment index and the circuit breaker tripping performance characteristics, a fuzzy rule base is established to associate the severity of the short-circuit fault with the fuzzy set of the optimal tripping speed range. The fuzzy rule base is as follows: Rule 1: If the fault intensity assessment index is "mild", the optimal trip speed range is "relatively loose"; Rule 2: If the fault intensity assessment index is "medium", the optimal opening speed range is "moderate"; Rule 3: If the fault intensity assessment index is "serious", the optimal trip speed range is "strict"; The reasoning process is formulated, and the membership of the output fuzzy set is calculated through fuzzy logic reasoning. The calculation expression is: ,in: is the opening speed range, is the fuzzy membership function of the opening speed range, , , Fuzzy membership functions corresponding to the opening speed ranges in the case of slight, medium and severe short circuits; The result of fuzzy reasoning is defuzzified to obtain the specific optimal opening speed range value. The centroid method is used for defuzzification. The defuzzification expression is: ,in: is the optimal opening speed range obtained after defuzzification, and They are the upper and lower limits of the opening speed range respectively.

8. The method for detecting the opening and closing of a circuit breaker for an inflatable cabinet according to claim 7, characterized in that: The actually measured opening speed is compared with the optimal opening speed range predicted by the fuzzy logic algorithm. If the actually measured opening speed is within the optimal opening speed range predicted by the fuzzy logic algorithm, it indicates that the opening speed of the circuit breaker during the opening operation meets the expected standard and no prompt is issued. If the actually measured opening speed is not within the optimal opening speed range predicted by the fuzzy logic algorithm, an abnormal alarm is triggered to notify relevant personnel.

9. A circuit breaker opening and closing detection system for an inflatable cabinet, used to implement the circuit breaker opening and closing detection method for an inflatable cabinet as described in any one of claims 1 to 8, characterized in that: It includes real-time data acquisition module, target circuit selection and fault simulation module, feature extraction and dynamic analysis module, intelligent evaluation module, optimal opening speed prediction module and opening speed detection and abnormal alarm module; The real-time data acquisition module first collects real-time data of all circuits in the power grid during the circuit breaker opening detection process to provide initial conditions for subsequent fault simulation and analysis; The target circuit selection and fault simulation module randomly selects a target circuit from all circuits and simulates the short-circuit fault of the circuit under different conditions; The feature extraction and dynamic analysis module extracts key parameters that can reflect the fault characteristics from the collected data after simulating the short-circuit fault, and dynamically analyzes the extracted features within the set monitoring window to quantify the severity of the fault; The intelligent evaluation module inputs the characteristic data obtained by dynamic analysis under the monitoring window into the trained convolutional neural network for intelligent evaluation, and makes an intelligent prediction of the severity of the short-circuit fault of the target circuit; The optimal tripping speed prediction module uses a fuzzy logic algorithm to calculate and predict the optimal tripping speed range under the short-circuit fault of the circuit according to the output result of the convolutional neural network; The trip speed detection and abnormal alarm module compares the actual measured trip speed with the optimal trip speed range predicted by the fuzzy logic algorithm to analyze whether it meets the expected standards. If the actual trip speed is not within the recommended range, an abnormal alarm is triggered to improve the detection accuracy of the trip speed.

Images