Real-time monitoring system for high-voltage circuit breaker

Abstract

The invention relates to the technical field of circuit breaker monitoring data analysis, and relates to a real-time monitoring system for a high-voltage circuit breaker. According to the invention, temperature and humidity data and partial discharge pulse signals of the high-voltage circuit breaker insulating sleeve are monitored in real time through the distributed sensors, surface dew point temperature distribution and partial discharge characteristics are analyzed through the data processing module, and a condensation high-risk area is accurately positioned. And an insulating medium performance attenuation index is generated based on an energy entropy change curve of the partial discharge pulse signal, and the fault probability of the high-voltage circuit breaker is compared and output in combination with a historical monitoring database, so that early warning of the fault of the high-voltage circuit breaker is realized, and a powerful guarantee is provided for stable operation of a power system. When the fault probability exceeds a threshold value, the system executes circuit breaking control, and the contact state is deduced by collecting an arcing spectrum and an arc extinguish chamber pressure waveform, so that accurate monitoring, fault diagnosis and control deduction of the high-voltage circuit breaker are realized, and the reliability and the safety of the high-voltage circuit breaker are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breaker monitoring data analysis, in particular to a high-voltage circuit breaker real-time monitoring system. Background Art

[0002] High-voltage circuit breakers, as core protection devices in power systems, have a direct impact on grid security. Condensation on the surface of insulating bushings caused by temperature and humidity fluctuations in the operating environment is a major cause of partial discharge, accelerated insulation degradation, and even flashover failures. Existing monitoring technologies often focus on single data points, such as partial discharge or temperature, but lack dynamic environmental coupling analysis of condensation formation mechanisms, making it difficult to provide early warning of faults.

[0003] For example, Chinese patent publication No. CN107478988A discloses a circuit breaker anomaly identification method and system based on an imprecise Bayesian model. Based on fault recording data obtained by a fault recorder, the time parameters of circuit breakers of the same type are statistically analyzed. The time parameters of the circuit breakers are evaluated for anomalies according to the confidence level. Using historical data, an imprecise Bayesian model for estimating the probability of circuit breaker anomalies is established. Furthermore, a Bayesian network is constructed to perform probabilistic reasoning on whether the circuit breaker is abnormal given given time parameters. This method can determine state anomalies based solely on electrical measurement information, making it simpler to operate and less expensive than existing technologies.

[0004] However, the existing technology has the following problems: (1) The existing technology mainly relies on fault recording data and time parameters, and the real-time operating status monitoring of the circuit breaker is not comprehensive enough, especially the monitoring of insulation performance related parameters is insufficient. It does not consider the dynamic impact of ambient temperature and humidity on the performance of the insulating sleeve, and cannot quantify the temporal and spatial correlation between micro-water accumulation and active discharge. As a result, the positioning accuracy of high-risk areas for condensation is insufficient, and it is impossible to give early warning of insulation breakdown failures caused by condensation, which in turn causes a high rate of missed reporting of circuit breaker failures.

[0005] (2) Existing technologies rely solely on the time parameters of fault recording data for probabilistic reasoning, lacking quantitative characterization of insulation medium performance degradation. Fault probability analysis relies solely on historical data comparison and does not incorporate the dynamic evolution laws of real-time physical quantities. This makes it difficult to accurately judge the failure risk of a circuit breaker before a fault occurs, and it is impossible to take timely measures to prevent the occurrence of a fault, which affects the reliability of the high-voltage power system. Summary of the Invention

[0006] The present invention aims to address the deficiencies of the prior art and provide a real-time monitoring system for high-voltage circuit breakers. By real-time monitoring and comprehensive analysis of multiple parameters such as temperature, humidity, and partial discharge pulse signals of high-voltage circuit breakers, the system can achieve early warning of high-voltage circuit breaker faults and evaluate their operating status, thereby improving the reliability of the power system.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a real-time monitoring system for high-voltage circuit breakers, comprising a surface feature data monitoring module, a surface feature data processing module, a condensation high-risk area positioning module, a circuit breaker failure probability analysis module, a circuit breaker control deduction module, and a historical monitoring database. The modules are connected as follows: the surface feature data monitoring module is connected to the surface feature data processing module; the condensation high-risk area positioning module is connected to the surface feature data processing module and the circuit breaker failure probability analysis module, respectively; the circuit breaker control deduction module is connected to the circuit breaker failure probability analysis module; and the historical monitoring database is connected to the condensation high-risk area positioning module and the circuit breaker failure probability analysis module, respectively.

[0008] The surface feature data monitoring module is used to monitor the temperature and humidity data of different monitoring points in real time through distributed temperature and humidity sensors evenly covered on the surface of the insulating bushing of the high-voltage circuit breaker, and synchronously collect the partial discharge pulse signal on the surface of the insulating bushing.

[0009] The surface feature data processing module is used to generate the surface dew point temperature distribution characteristics of the insulating sleeve based on the temperature and humidity data of different monitoring points. Based on the surface dew point temperature distribution characteristics, the area with a tendency to accumulate micro-water is screened. The phase analysis of the partial discharge pulse signal is performed to obtain the partial discharge pulse phase distribution characteristics and identify the active partial discharge area.

[0010] The condensation high-risk area positioning module is used to conduct spatiotemporal coupling analysis between areas prone to micro-water accumulation and areas with active partial discharge to locate high-risk areas for condensation.

[0011] The circuit breaker failure probability analysis module is used to generate the insulation medium performance attenuation index based on the energy entropy change curve of the partial discharge pulse signal corresponding to the high-risk condensation area, and output the failure probability of the high-voltage circuit breaker by comparing the high-risk condensation area with the historical monitoring database.

[0012] The circuit breaker control deduction module is used to perform operation control according to the failure probability of the high-voltage circuit breaker, collect the arcing spectrum and arc extinguishing chamber pressure transient waveform of the high-voltage circuit breaker during the control process, and deduce the circuit breaker contact state.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention monitors the surface temperature and humidity of the insulating bushing of the high-voltage circuit breaker and the partial discharge pulse signal in real time, adopts the inverse distance weighted interpolation method to construct a continuous temperature and humidity distribution field, and performs cluster analysis to screen the areas with a tendency to accumulate micro-water. At the same time, the phase analysis of the partial discharge pulse signal is performed to identify the active areas of partial discharge, thereby solving the problem that the monitoring parameters of the prior art are not comprehensive enough, reflecting the operating status of the high-voltage circuit breaker more comprehensively, and improving the accuracy of fault warning.

[0014] (2) The present invention analyzes the micro-water accumulation tendency area and the local discharge active area through time-space coupling, locates the high-risk area of ​​condensation, and generates the insulation medium performance attenuation index based on the energy entropy change curve of the local discharge pulse signal. Combined with the historical monitoring database, the output high-voltage circuit breaker failure probability is compared and output, achieving early warning of high-voltage circuit breaker failure, providing a strong guarantee for the stable operation of the power system.

[0015] (3) The present invention performs operation control according to the fault probability, collects the arc spectrum and the transient waveform of the arc extinguishing chamber pressure to deduce the state of the circuit breaker contact, and triggers a replacement warning when the contact is in the ablation state, thereby improving the accuracy of the circuit breaker operation status assessment, being able to timely detect the abnormal state of the circuit breaker contact, avoiding further expansion of the fault, and improving the operation reliability and maintenance efficiency of the high-voltage circuit breaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of system module connections of the present invention.

[0018] Figure 2 Schematic diagram of the flow chart of the surface dew point temperature calculation steps in the present invention.

[0019] Figure 3 Schematic diagram of the flow of steps for generating the insulation medium performance attenuation index in the present invention.

[0020] Figure 4 This is a schematic diagram of the specific analysis process of the circuit breaker control deduction module in the present invention. DETAILED DESCRIPTION

[0021] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions, and numerical values ​​described in these embodiments do not limit the scope of the present invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn to scale.

[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and is not intended to limit the invention, its application, or uses. Technologies, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the specification.

[0023] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0024] The present invention uses distributed sensors to monitor the temperature and humidity data and partial discharge pulse signals of the high-voltage circuit breaker insulation bushing in real time. A data processing module analyzes the surface dew point temperature distribution and partial discharge characteristics, accurately locating high-risk areas for condensation. The system then generates an insulation dielectric performance attenuation index based on the energy entropy curve of the partial discharge pulse signal. This is combined with a historical monitoring database to compare and output the failure probability of the high-voltage circuit breaker, providing early warning of high-voltage circuit breaker failures and providing a strong guarantee for the stable operation of the power system. When the failure probability exceeds a threshold, the system executes circuit breaker control and, by collecting arcing spectra and arc extinguishing chamber pressure waveforms, deduces the contact state, enabling precise monitoring, fault diagnosis, and control deduction of the high-voltage circuit breaker, improving its reliability and safety.

[0025] See also Figure 1 As shown, the present invention provides a real-time monitoring system for high-voltage circuit breakers, comprising a surface feature data monitoring module, a surface feature data processing module, a condensation high-risk area positioning module, a circuit breaker failure probability analysis module, a circuit breaker control deduction module, and a historical monitoring database. The modules are connected as follows: the surface feature data monitoring module is connected to the surface feature data processing module; the condensation high-risk area positioning module is connected to the surface feature data processing module and the circuit breaker failure probability analysis module, respectively; the circuit breaker control deduction module is connected to the circuit breaker failure probability analysis module; and the historical monitoring database is connected to the condensation high-risk area positioning module and the circuit breaker failure probability analysis module, respectively.

[0026] The surface feature data monitoring module is used to monitor temperature and humidity data at different monitoring points in real time using distributed temperature and humidity sensors evenly distributed across the surface of the high-voltage circuit breaker's insulating bushing. This module also simultaneously collects partial discharge pulse signals from the bushing's surface. For example, these signals can be collected synchronously using ultrasonic sensors.

[0027] The surface feature data processing module is used to generate the surface dew point temperature distribution characteristics of the insulating sleeve based on the temperature and humidity data of different monitoring points. Based on the surface dew point temperature distribution characteristics, the area with a tendency to accumulate micro-water is screened. The phase analysis of the partial discharge pulse signal is performed to obtain the partial discharge pulse phase distribution characteristics and identify the active partial discharge area.

[0028] It should be noted that the specific content of the surface feature data processing module includes: constructing a continuous temperature and humidity distribution field on the surface of the high-voltage circuit breaker insulating bushing by using the inverse distance weighted interpolation method for the temperature and humidity data of each monitoring point monitored in real time.

[0029] The continuous temperature and humidity distribution field is divided into grid areas, and the surface dew point temperature is calculated based on the average temperature and humidity of each grid area. The temperature difference between the surface average temperature of each grid area and the corresponding surface dew point temperature is obtained.

[0030] The grid division method divides the surface area into equal areas according to the set surface area, so that the surface temperature and humidity distribution can be covered more comprehensively and detailedly, ensuring that each grid area can be analyzed separately and capturing local subtle changes, avoiding the omission of important information due to insufficient distribution of monitoring points, and improving the perception accuracy of surface temperature and humidity distribution characteristics.

[0031] The temperature difference is compared with the set temperature threshold of micro-water accumulation tendency, and the grid areas with temperature difference less than the set temperature threshold of micro-water accumulation tendency are screened as micro-water accumulation tendency areas.

[0032] The surface dew point temperature is compared with the surface temperature of the insulation layer. If the surface temperature of the insulation layer is lower than the dew point temperature, condensation may occur because water vapor in the air will condense on the surface of the insulation layer with a lower temperature, thereby causing partial discharge, accelerating insulation degradation, and even flashover failure.

[0033] In a specific embodiment, the inverse distance weighted interpolation method converts discrete temperature and humidity data from each monitoring point into a continuous surface temperature and humidity field distribution. Inverse distance weighted interpolation is a distance-based interpolation method in which known points closer to the interpolated point have a greater influence on it and receive a greater weight. Because inverse distance weighted interpolation is an existing technology, it will not be further described in detail in this disclosure.

[0034] like Figure 2 As shown, the surface dew point temperature calculation steps are: S1, according to the average temperature of each grid area, substitute it into the Magnus-Tetens formula to calculate the saturated water vapor pressure at the temperature of each grid area.

[0035] The Magnus-Tetens formula is an existing technology and is an approximate formula for estimating saturated water vapor pressure. Saturated water vapor pressure refers to the water vapor partial pressure when water vapor and liquid water are in equilibrium at a specific temperature. Its formula is , where is the saturated water vapor pressure, are empirical constants, for example, in liquid water, , , , is the surface temperature.

[0036] S2. Calculate the actual water vapor pressure of each grid area through the saturated water vapor pressure and average humidity at the temperature of each grid area.

[0037] The calculation formula for the actual water vapor pressure in each grid area is: , where is the actual water vapor pressure, is the surface humidity. This formula is obtained by modifying the definition of relative humidity.

[0038] S3. Using the inverse Magnus-Tetens formula Get the surface dew point temperature of each grid area.

[0039] It should be noted that the specific contents of the surface feature data processing module also include: waveform phase analysis of the partial discharge pulse signal on the surface of the high-voltage circuit breaker insulating bushing, statistics of the discharge peak value of the partial discharge pulse signal in each phase window, the number of discharges per unit cycle, and the amplitude difference between the positive and negative half-wave discharge pulses.

[0040] The discharge peak value of the partial discharge pulse signal in each phase window, the number of discharges in a unit cycle, and the amplitude difference between the positive and negative half-wave discharge pulses are used to judge the characteristics of the discharge active area and identify the partial discharge active area.

[0041] In a specific embodiment, after waveform phase analysis of the partial discharge pulse signal, the distribution of the signal in different phase windows is obtained. For example, one cycle is usually divided into multiple phase windows, such as each phase window is 10 degrees. This allows for a more detailed study of the relationship between partial discharge and phase.

[0042] The discharge peak is the maximum discharge value within the phase window. A phase window with a high discharge peak means that local discharge is more intense near this phase. The number of discharges per unit cycle can reflect the frequency of discharge. The amplitude difference between the positive and negative half-wave discharge pulses is the amplitude difference between the positive half-wave and negative half-wave discharge pulses. This difference reflects the difference in discharge intensity of local discharge under different polarity conditions. The phase window with a larger amplitude difference between the positive and negative half-wave discharge pulses may correspond to an active local discharge area.

[0043] In a specific embodiment, the rule for judging the characteristics of the discharge active area is: screening the phase window with the largest difference in the discharge peak value, the number of discharges per unit cycle, and the amplitude of the positive and negative half-wave discharge pulses; if the phase windows are the same, the area corresponding to the phase window is used as the discharge active area; if the phase windows are different, the areas corresponding to different phase windows are integrated to obtain the discharge active area.

[0044] The present invention monitors the surface temperature and humidity of the insulating bushing of a high-voltage circuit breaker and the partial discharge pulse signal in real time, uses the inverse distance weighted interpolation method to construct a continuous temperature and humidity distribution field, performs cluster analysis to screen areas prone to micro-water accumulation, and simultaneously performs phase analysis on the partial discharge pulse signal to identify active partial discharge areas. This solves the problem of incomplete monitoring parameters in the prior art, can more comprehensively reflect the operating status of the high-voltage circuit breaker, and improves the accuracy of fault warning.

[0045] The condensation high-risk area positioning module is used to conduct spatiotemporal coupling analysis between areas prone to micro-water accumulation and areas with active partial discharge to locate high-risk areas for condensation.

[0046] It should be noted that the method for locating the high-risk condensation area is to spatially overlap the area prone to micro-water accumulation with the active area of ​​partial discharge to obtain a spatial overlap area.

[0047] The surface temperature and ambient temperature of the spatially overlapping area at each historical time point within the historical time period are retrieved from the historical monitoring database. Based on the surface temperature and ambient temperature at each historical time point, the surface temperature change rate and ambient temperature change rate are analyzed to obtain the surface temperature change rate and ambient temperature change rate. The historical time period can be the time period from the current time to the previous day.

[0048] If the surface temperature change rate of the spatial overlap area exceeds the ambient temperature change rate during the historical time period, the spatial overlap area will be regarded as a high-risk area for condensation.

[0049] In a specific embodiment, the surface temperature change rate and the ambient temperature change rate are analyzed as follows: based on the surface temperature of the overlapping area at each historical time point within the historical time period, a linear regression equation is constructed with time as the independent variable and the surface temperature as the dependent variable, and the data is fitted by the least squares method to obtain the slope of the regression equation, which is used as the surface temperature change rate; similarly, the ambient temperature change rate is obtained through the surface temperature change rate analysis method.

[0050] The circuit breaker failure probability analysis module is used to generate the insulation medium performance attenuation index based on the energy entropy change curve of the partial discharge pulse signal corresponding to the high-risk condensation area, and output the failure probability of the high-voltage circuit breaker by comparing the high-risk condensation area with the historical monitoring database.

[0051] like Figure 3 As shown, the insulating medium performance attenuation index is generated as follows: W1. Extract the partial discharge pulse signal corresponding to the high-risk condensation area from the partial discharge pulse signal on the surface of the insulating sleeve, and screen out the continuous pulse signal sequence in the high-risk condensation area within the set time domain.

[0052] W2. Calculate the energy value based on the pulse voltage and pulse current of each partial discharge pulse in the continuous pulse signal sequence to form a continuous pulse signal energy value sequence.

[0053] The energy value calculation formula is: , where is the energy value, and are the starting and stopping times of the partial discharge pulse, is the pulse voltage, is a pulse current.

[0054] W3. Use the continuous pulse signal energy value sequence as a sample to construct the probability distribution of each partial discharge pulse. Substitute the probability distribution into the information entropy formula to calculate the entropy value of the partial discharge energy in the high-risk area of ​​condensation within the set time domain.

[0055] The probability distribution of each partial discharge pulse is the ratio of the energy value to the total energy value of all partial discharge pulses.

[0056] The information entropy formula is: , where It is the entropy value of the partial discharge energy in the high-risk condensation area within the set time domain, reflecting the disorder of the energy distribution. For the The probability distribution of partial discharge pulses, , is the number of partial discharge pulses.

[0057] W4. With time as the horizontal axis and the energy entropy values ​​in different time domains as the vertical axis, an energy entropy change curve that changes with time is formed. The mean entropy value, entropy change slope and entropy value fluctuation variance in the energy entropy change curve are extracted, and the fusion feature analysis is performed to obtain the insulation medium performance attenuation index.

[0058] In a specific embodiment, the insulating medium performance attenuation index is analyzed by a fusion feature analysis method: the entropy mean, entropy change slope and entropy fluctuation variance in the energy entropy change curve are normalized to obtain the normalized entropy mean, entropy change slope and entropy fluctuation variance.

[0059] A historical data set is constructed based on multiple groups of historical monitoring data corresponding to high-voltage circuit breakers obtained from the historical monitoring database. The weight coefficients of the entropy mean, entropy change slope and entropy fluctuation variance are obtained through training based on the historical data set.

[0060] The normalized entropy mean, entropy change slope, and entropy fluctuation variance are multiplied and accumulated with the corresponding weight coefficient to obtain the insulation medium performance attenuation index.

[0061] The training method for the weight coefficients of the mean entropy value, the slope of the entropy change and the variance of the entropy value fluctuation is as follows: multiple groups of historical monitoring data corresponding to high-voltage circuit breakers are obtained from the historical monitoring database, and the mean entropy value, the slope of the entropy change and the variance of the entropy value fluctuation of the energy entropy change curve and the performance attenuation index of the insulating medium in the multiple groups of historical monitoring data are extracted to construct a historical data set. The historical data set is input into the random forest regression model for training. The random forest regression model outputs the prediction results through voting of multiple decision trees. During the training process, the model automatically calculates the contribution of the mean entropy value, the slope of the entropy change and the variance of the entropy value fluctuation to the prediction accuracy of each decision tree, and takes the sum of the contribution of each decision tree to the prediction accuracy as the feature importance score, and takes the ratio of the feature importance score to the total feature importance score as the weight coefficient.

[0062] The present invention uses random forest regression to train the weight coefficients of the entropy mean, entropy change slope, and entropy fluctuation variance, and calculates the insulation medium performance attenuation index. This improves the intelligence level and monitoring accuracy of the monitoring system, can more accurately evaluate the insulation performance and fault risk of high-voltage circuit breakers, and provide a more reliable basis for power system operation and maintenance decisions.

[0063] It should be noted that the failure probability output method of the high-voltage circuit breaker is: obtaining the area and position coordinates of the high-risk condensation area, and forming a real-time feature vector with the area and position coordinates of the area and the insulation medium performance attenuation index.

[0064] Abstract: In order to solve the problem of high-voltage circuit breaker failure, a novel fault characterization method based on the real-time feature vector and the historical feature vector is proposed. The historical feature vectors corresponding to multiple groups of historical monitoring data of high-voltage circuit breakers in the historical monitoring database are constructed. The Euclidean distance between the real-time feature vector and the historical feature vector is analyzed. The fault characterization value corresponding to each historical feature vector whose Euclidean distance is less than the set Euclidean distance is retrieved. The failure probability of the high-voltage circuit breaker is determined based on the fault characterization value. The experimental results show that the proposed method can be applied to the fault characterization of high-voltage circuit breakers in the historical monitoring database. The proposed method can be applied to the fault characterization of high-voltage circuit breakers in the historical monitoring database.

[0065] In a specific embodiment, the specific method of determining the failure probability of a high-voltage circuit breaker based on the fault characterization value is: screening the number of historical feature vectors whose fault characterization values ​​represent faults from each historical feature vector whose Euclidean distance is less than the set Euclidean distance, and using the ratio of the historical feature vectors whose fault characterization values ​​represent faults to the total number of historical feature vectors whose Euclidean distance is less than the set Euclidean distance as the failure probability of the high-voltage circuit breaker.

[0066] When the fault characterization value is 1, it means that the high-voltage circuit breaker has a fault, and when the fault characterization value is 0, it means that the high-voltage circuit breaker has no fault.

[0067] The present invention analyzes the areas prone to micro-water accumulation and active partial discharge areas through spatiotemporal coupling, locates high-risk areas for condensation, and generates an insulation medium performance attenuation index based on the energy entropy change curve of the partial discharge pulse signal. Combined with the historical monitoring database, the present invention compares and outputs the failure probability of the high-voltage circuit breaker, thereby achieving early warning of high-voltage circuit breaker failures and providing strong protection for the stable operation of the power system.

[0068] The circuit breaker control deduction module is used to perform operation control according to the failure probability of the high-voltage circuit breaker, collect the arcing spectrum and arc extinguishing chamber pressure transient waveform of the high-voltage circuit breaker during the control process, and deduce the circuit breaker contact state.

[0069] like Figure 4 As shown, the specific analysis process of the circuit breaker control deduction module is as follows: when the failure probability of the high-voltage circuit breaker is greater than the set failure probability threshold, the high-voltage circuit breaker is controlled to perform circuit breaking control.

[0070] An ultraviolet fiber optic sensor is used to collect the arcing spectrum of the high-voltage circuit breaker during the circuit breaking control process. The peak wavelength offset is analyzed based on the arcing spectrum. The pressure transient waveform of the arc extinguishing chamber is monitored by a pressure transmitter. The pressure recovery rate is obtained according to the pressure transient waveform of the arc extinguishing chamber.

[0071] When the peak wavelength offset exceeds the set threshold of the circuit breaker material and the pressure recovery rate is lower than the standard pressure recovery rate, the circuit breaker contact is in a burnt state and a contact replacement warning is triggered.

[0072] The present invention performs operational control according to the fault probability, collects arcing spectra and arc extinguishing chamber pressure transient waveforms to deduce the circuit breaker contact status, and triggers a replacement warning when the contacts are in the ablation state, thereby improving the accuracy of circuit breaker operation status assessment, being able to promptly detect abnormal conditions of circuit breaker contacts, avoiding further expansion of faults, and improving the operational reliability and maintenance efficiency of high-voltage circuit breakers.

[0073] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0074] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0075] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0076] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0077] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0078] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A high voltage circuit breaker real-time monitoring system, characterized in that: include: The surface feature data monitoring module monitors the temperature and humidity data at different monitoring points through distributed temperature and humidity sensors evenly covering the surface of the high-voltage circuit breaker insulation bushing, and simultaneously collects the partial discharge pulse signal on the insulation bushing surface; The surface feature data processing module generates the surface dew point temperature distribution characteristics of the insulating sleeve based on the temperature and humidity data. Based on the temperature distribution characteristics, it screens the areas prone to micro-water accumulation. It also performs phase analysis on the partial discharge pulse signal to obtain the partial discharge pulse phase distribution characteristics and identify the active partial discharge areas. The condensation high-risk area positioning module conducts spatiotemporal coupling analysis between areas prone to micro-water accumulation and areas with active partial discharge to locate high-risk areas of condensation; The circuit breaker failure probability analysis module generates an insulation dielectric performance attenuation index based on the energy entropy change curve of the partial discharge pulse signal corresponding to the high-risk condensation area. It then compares the high-risk condensation area with the historical monitoring database to output the high-voltage circuit breaker failure probability. The circuit breaker control deduction module performs operational control according to the failure probability of the high-voltage circuit breaker, collects the arcing spectrum and arc extinguishing chamber pressure transient waveform of the high-voltage circuit breaker during the control process, and deduces the circuit breaker contact status.

2. A high-voltage circuit breaker real-time monitoring system according to claim 1, characterized in that: The specific contents of the surface feature data processing module include: The continuous temperature and humidity distribution field on the surface of the insulating bushing of the high-voltage circuit breaker is constructed by using the inverse distance weighted interpolation method for the temperature and humidity data of each monitoring point in real time. The continuous temperature and humidity distribution field is divided into grid areas, and the surface dew point temperature is calculated based on the average temperature and humidity of each grid area. The temperature difference between the surface average temperature of each grid area and the corresponding surface dew point temperature is obtained. The temperature difference is compared with the set temperature threshold of micro-water accumulation tendency, and the grid areas with temperature difference less than the set temperature threshold of micro-water accumulation tendency are screened as micro-water accumulation tendency areas.

3. A high-voltage circuit breaker real-time monitoring system according to claim 2, characterized in that: The specific contents of the surface feature data processing module also include: The waveform phase analysis of the partial discharge pulse signal on the surface of the insulating bushing of the high-voltage circuit breaker is performed to calculate the peak discharge amount of the partial discharge pulse signal in each phase window, the number of discharges per unit cycle, and the amplitude difference between the positive and negative half-wave discharge pulses; The discharge peak value of the partial discharge pulse signal in each phase window, the number of discharges in a unit cycle, and the amplitude difference between the positive and negative half-wave discharge pulses are used to judge the characteristics of the discharge active area and identify the partial discharge active area.

4. A high-voltage circuit breaker real-time monitoring system according to claim 3, characterized in that: The rule for judging the characteristics of the discharge active area is: The phase window with the largest difference in discharge peak value, number of discharges per unit cycle, and amplitude of positive and negative half-wave discharge pulses is screened. If the phase windows are the same, the area corresponding to the phase window is regarded as the discharge active area. If the phase windows are different, the areas corresponding to different phase windows are integrated to obtain the discharge active area.

5. A high-voltage circuit breaker real-time monitoring system according to claim 1, characterized in that: The method for locating the high-risk area for condensation is: The micro-water accumulation tendency area is spatially overlapped with the local discharge active area to obtain the spatial overlap area; The surface temperature and ambient temperature of the spatially overlapping area at each historical time point in the historical time period are retrieved from the historical monitoring database, and the temperature change rate is analyzed based on the surface temperature and ambient temperature at each historical time point to obtain the surface temperature change rate and ambient temperature change rate; If the surface temperature change rate of the spatial overlap area exceeds the ambient temperature change rate during the historical time period, the spatial overlap area will be regarded as a high-risk area for condensation.

6. A high-voltage circuit breaker real-time monitoring system according to claim 1, characterized in that: The insulating medium performance attenuation index is generated as follows: Extract the partial discharge pulse signal corresponding to the high-risk condensation area from the partial discharge pulse signal on the surface of the insulating sleeve, and screen out the continuous pulse signal sequence in the high-risk condensation area within the set time domain; Calculating the energy value according to the pulse voltage and pulse current of each partial discharge pulse in the continuous pulse signal sequence to form a continuous pulse signal energy value sequence; The probability distribution of each partial discharge pulse is constructed using the continuous pulse signal energy value sequence as a sample. The probability distribution is substituted into the information entropy formula to calculate the entropy value of the partial discharge energy in the high-risk area of ​​condensation within the set time domain. With time as the horizontal axis and the energy entropy values ​​in different time domains as the vertical axis, an energy entropy change curve that changes with time is formed. The mean entropy value, entropy change slope and entropy value fluctuation variance in the energy entropy change curve are extracted, and the fusion feature analysis is performed to obtain the insulation medium performance attenuation index.

7. A high-voltage circuit breaker real-time monitoring system according to claim 6, characterized in that: The insulation medium performance attenuation index is analyzed by fusion characteristics as follows: The entropy mean, entropy change slope and entropy fluctuation variance in the energy entropy change curve are normalized to obtain the normalized entropy mean, entropy change slope and entropy fluctuation variance; A historical data set is constructed based on multiple sets of historical monitoring data corresponding to high-voltage circuit breakers obtained from the historical monitoring database. The weight coefficients of the entropy mean, entropy change slope, and entropy fluctuation variance are obtained through training based on the historical data set. The normalized entropy mean, entropy change slope, and entropy fluctuation variance are multiplied and accumulated with the corresponding weight coefficient to obtain the insulation medium performance attenuation index.

8. A high-voltage circuit breaker real-time monitoring system according to claim 1, characterized in that: The fault probability output mode of the high voltage circuit breaker is: Obtain the area and location coordinates of high-risk condensation areas and combine them with the insulation medium performance attenuation index to form a real-time feature vector; Abstract: In order to solve the problem of high-voltage circuit breaker failure, a novel fault characterization method based on the real-time feature vector and the historical feature vector is proposed. The historical feature vectors corresponding to multiple groups of historical monitoring data of high-voltage circuit breakers in the historical monitoring database are constructed. The Euclidean distance between the real-time feature vector and the historical feature vector is analyzed. The fault characterization value corresponding to each historical feature vector whose Euclidean distance is less than the set Euclidean distance is retrieved. The failure probability of the high-voltage circuit breaker is determined based on the fault characterization value. The experimental results show that the proposed method can be applied to the fault characterization of high-voltage circuit breakers in the historical monitoring database. The proposed method can be applied to the fault characterization of high-voltage circuit breakers in the historical monitoring database.

9. A high-voltage circuit breaker real-time monitoring system according to claim 8, characterized in that: The specific method of determining the fault probability of the high-voltage circuit breaker based on the fault characterization value is as follows: The number of historical feature vectors whose fault characterization values ​​represent faults is screened from each historical feature vector whose Euclidean distance is less than the set Euclidean distance, and the ratio of the historical feature vectors to the total number of historical feature vectors whose Euclidean distance is less than the set Euclidean distance is used as the failure probability of the high-voltage circuit breaker.

10. A high-voltage circuit breaker real-time monitoring system according to claim 1, characterized in that: The specific analysis process of the circuit breaker control deduction module is as follows: When the failure probability of the high-voltage circuit breaker is greater than the set failure probability threshold, the high-voltage circuit breaker is controlled to perform circuit breaking control; An ultraviolet fiber optic sensor is used to collect the arcing spectrum of a high-voltage circuit breaker during the circuit breaking control process. The peak wavelength offset is analyzed based on the arcing spectrum. The pressure transient waveform of the arc extinguishing chamber is monitored through a pressure transmitter, and the pressure recovery rate is obtained based on the pressure transient waveform of the arc extinguishing chamber. When the peak wavelength offset exceeds the set threshold of the circuit breaker material and the pressure recovery rate is lower than the standard pressure recovery rate, the circuit breaker contact is in a burnt state and a contact replacement warning is triggered.

Images