Remote real-time monitoring system for operation state of intelligent circuit breaker

Abstract

The invention discloses a remote real-time monitoring system for the running state of an intelligent circuit breaker, and relates to the technical field of circuit breaker monitoring. The system comprises an operation data acquisition and processing module, a circuit breaker health database, a fault risk prediction module, a real-time monitoring module and an operation and maintenance terminal. The operation data acquisition and processing module acquires numerical data and state data and extracts operation state characteristics of the circuit breaker; the circuit breaker health database stores a normal value range of circuit breaker operation state characteristics and a normal operation range of numerical data; the fault risk prediction module constructs a composite fault risk prediction index based on the operating state characteristics of the circuit breaker, and obtains a fault risk index through an LSTM model; the real-time monitoring module judges the real-time operation state of the circuit breaker; and the operation and maintenance terminal visualizes data and carries out graded early warning according to a three-level standard, and supports remote operation and maintenance at the same time. Real-time monitoring and accurate early warning of the operation state of the circuit breaker are achieved, and efficient closed loop of operation and maintenance of the circuit breaker is guaranteed.

Description

A remote real-time monitoring system for the operating status of intelligent circuit breakers Technical Field

[0001] This invention relates to the field of circuit breaker monitoring technology, and more specifically to a remote real-time monitoring system for the operating status of an intelligent circuit breaker. Background Technology

[0002] As a core device in power systems for connecting and disconnecting circuits and ensuring fault isolation, the stability of circuit breaker operation directly determines the safety and continuity of power supply. Circuit breakers are widely used in critical scenarios such as industrial power distribution, urban power grids, and new energy power plants. With the development of power systems towards intelligence and large-scale operation, higher requirements are placed on the monitoring accuracy, predictive capabilities, and maintenance efficiency of circuit breaker operation status.

[0003] However, existing circuit breaker monitoring technologies still have many shortcomings: First, data acquisition dimensions are limited; traditional monitoring focuses mainly on basic numerical data such as current and voltage, making it difficult to comprehensively depict the health status of the equipment. Second, there is a lack of standardized health database support; deviation analysis relies solely on empirical thresholds or factory parameters, without combining actual measured data from the healthy operation of the same model of equipment, resulting in insufficient quantitative assessment accuracy. Third, fault risk prediction methods are simplistic, often employing simple threshold judgments or linear models, failing to integrate feature correlations and time-series change trends, thus failing to achieve early fault prediction and relying primarily on post-fault maintenance. Fourth, the operation and maintenance model is inefficient, lacking a tiered early warning mechanism and relying on on-site inspections, with weak remote operation and maintenance capabilities, leading to delayed fault response. To address these issues and achieve comprehensive monitoring, accurate prediction, and intelligent operation and maintenance of circuit breaker operating status, this invention proposes a remote real-time monitoring system for the operating status of intelligent circuit breakers. Summary of the Invention

[0004] The purpose of this invention is to provide a remote real-time monitoring system for the operating status of intelligent circuit breakers, so as to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a remote real-time monitoring system for the operating status of an intelligent circuit breaker, comprising an operating data acquisition and processing module, a circuit breaker health database, a fault risk prediction module, a real-time monitoring module, and an operation and maintenance terminal; the operating data acquisition and processing module is used to collect operating data during the circuit breaker's operation, the operating data including numerical data and status data, and to extract features from the numerical data to obtain the circuit breaker's operating status characteristics; the circuit breaker health database is used to store the normal value range of the circuit breaker's operating status characteristics under the circuit breaker's health status and the normal operation of the numerical data. The scope includes: the fault risk prediction module, which performs deviation analysis on the circuit breaker's operating status characteristics to obtain characteristic deviation data, and constructs a composite fault risk prediction index by weighting, correlation, and trend analysis of the characteristic deviation data; and obtains the circuit breaker's fault risk index based on the composite fault prediction index; the real-time monitoring module, which performs real-time comparison and judgment on numerical data according to the normal operating range of numerical data to obtain the circuit breaker's real-time operating status; and the operation and maintenance terminal, which visualizes the operating data during the circuit breaker's operation and performs graded early warning and remote operation and maintenance based on the circuit breaker's fault risk index and real-time operating status.

[0006] Preferably, the numerical data includes current, power factor, vibration signal of the operating mechanism, contact temperature, and ambient temperature, which are collected by a Hall current sensor deployed at the circuit breaker's incoming end, a multi-functional power meter integrated in the circuit breaker control cabinet, a piezoelectric vibration acceleration sensor deployed at the circuit breaker's opening and closing operating mechanism, a PT100 platinum resistance thermometer deployed at key positions of the circuit breaker contacts, and a digital temperature and humidity sensor deployed in the circuit breaker cabinet, respectively; the status data includes the circuit breaker's opening and closing status, protection action trigger status, and operation stop status, which are collected by connecting to the status feedback dry contacts and auxiliary contacts of the circuit breaker body.

[0007] Preferably, the circuit breaker operating status characteristics include the effective value of the current, harmonic distortion rate, power factor fluctuation, peak value of the vibration signal spectrum, maximum temperature rise, and temperature change rate. The feature extraction process is as follows: the current is calculated using effective value calculation and harmonic analysis to obtain the effective value of the current and the harmonic distortion rate. The harmonic analysis is performed by Fourier decomposition of the current to obtain the effective value of the fundamental current and the effective values ​​of each harmonic current. The harmonic distortion rate is calculated based on the effective value of the fundamental current and the effective values ​​of each harmonic current. The formula for calculating the effective value is: Among them, I rms Let be the effective value of the current, T be the period of the current, and i(t) be the current; the formula for calculating the harmonic distortion rate is: Where THD is the harmonic distortion rate, I1 is the effective value of the fundamental current, and I2~I nThe effective values ​​of the 2nd to nth harmonic currents are respectively; the power factor fluctuation is calculated using the standard deviation algorithm, and the calculation formula of the standard deviation algorithm is as follows: In the formula, σ represents the power factor fluctuation, and N represents the number of consecutive sampling periods for the power factor. The power factor for the k-th sampling period. This represents the average power factor over N sampling periods; the vibration signal of the operating mechanism is converted into a frequency domain signal using a Fast Fourier Transform, and the maximum amplitude peak of the frequency domain signal is extracted as the peak value of the vibration signal spectrum, i.e., A. peak =max(|X(f)|), where A peak Let X(f) be the peak value of the vibration signal spectrum, X(f) be the frequency domain amplitude of the signal, and f be the frequency domain frequency. After subtracting the ambient temperature from the contact temperature, the maximum temperature rise is extracted by a point-by-point comparison method. The formula for calculating the maximum temperature rise is: ΔT max =max(T c -T e ), where ΔT max The maximum temperature rise, T c For contact temperature, T e The ambient temperature is used; simultaneously, the rate of temperature change is calculated using the first-order difference method, which is... In the formula, v T Let ΔT be the rate of temperature change. k Let ΔT be the temperature rise at the k-th sampling time. k-1 Let Δt be the temperature rise at the (k-1)th sampling time, and Δt be the time interval between adjacent sampling times.

[0008] Preferably, the normal value range of circuit breaker operating status characteristics and the normal operating range of numerical data in the circuit breaker health database are both obtained through statistical analysis and calculation based on the factory rated parameters of the circuit breaker and the measured operating data of more than 30 groups of circuit breakers of the same model under healthy operating conditions. The deviation analysis is performed by retrieving the normal value range of circuit breaker operating status characteristics from the circuit breaker health database and using the relative deviation method to calculate the characteristic deviation value between each operating characteristic of the circuit breaker operating status characteristics and its corresponding normal value range, thereby forming characteristic deviation data. The relative deviation method is as follows: In the formula D i F is the characteristic deviation value of the i-th state operation characteristic. i For the i-th state operation characteristic, F i0 The value of is the median of the normal range of the i-th state operation characteristic, i=1,2,…,6, which respectively represent the effective value of current, harmonic distortion rate, power factor fluctuation, peak value of vibration signal spectrum, maximum temperature rise and temperature change rate.

[0009] Preferably, the method for constructing the composite fault risk prediction index is as follows: S1. Weight assignment: Based on the analytic hierarchy process and combined with the experience of power industry experts, a fault impact degree judgment matrix for each feature deviation value is constructed. After the matrix is ​​verified to be effective through consistency testing, the fault impact weight W for each feature deviation value is calculated. i (i=1,2,…,6), i.e., the fault impact weight W of the state operation characteristics. i And all W i The sum is 1, and it supports adjustment as needed according to the actual application scenario of the circuit breaker; S2. Deviation correlation and trend analysis: The correlation r of any two characteristic deviation values ​​is calculated using the Pearson correlation coefficient. ij When r ij When the deviation of the two features is ≥0.7, the combination of strongly correlated deviations is determined. Based on this, all strongly correlated deviation combinations are identified, and the number M of strongly correlated deviation combinations belonging to each feature deviation value is counted. i Based on the number of combinations M i Through formula α i =1.0+0.1×min(M i 3) Calculate the deviation correlation correction coefficient α for this characteristic deviation value. i Simultaneously, linear regression combined with exponential smoothing is used to fit the time-series variation trend of each characteristic deviation value to obtain the trend slope k. When k > 0.05, the trend type of the time-series variation trend is determined to be continuous expansion of deviation, and the trend correction coefficient K of the characteristic deviation value is then determined. i Set within the range of [1.2, 1.5], when k ≤ 0.05, the trend type of the time series change trend is determined to be stationary. The trend correction coefficient K for the eigenvalue is then set accordingly. i The value is set to 1.0. When k < -0.05, the trend type of the time series change trend is determined to be shrinking and then expanding. The trend correction coefficient K of the characteristic deviation value is then set. i Set within the range of [0.8, 0.9]; S3. Based on the weighted summation method, fuse the deviation values ​​of each feature and the corresponding fault impact weight, deviation correlation correction coefficient, and trend correction coefficient to obtain the composite fault risk prediction index F; the weighted summation method is: ; where, |D i | represents the absolute value of the i-th characteristic deviation value, W i As the weight of the impact of faults, α i K is the deviation correlation correction coefficient. i This is the trend correction coefficient.

[0010] Preferably, the fault risk index is obtained by predicting the fault risk index by inputting time-series features into a pre-trained machine learning model. The fault risk index is positively correlated with the probability of circuit breaker fault occurrence. The pre-trained machine learning model uses LSTM (Long Short-Term Memory) as the basic prediction model and is trained and optimized using a historical time-series composite index sequence of real fault risk indices within a preset future time period, which is manually labeled. The time-series features are obtained by recording the composite fault risk prediction indicators in a time series to form a time-series composite index sequence and extracting time-series features from the time-series composite index sequence. The time-series features include the rate of change of the indicators and the periodic fluctuation pattern, wherein the rate of change of the indicators is calculated according to the formula... The calculation yields the result, where v is the rate of change of the index, and F... k This is a composite failure risk prediction indicator for the current point in time. S is the average of the composite fault risk prediction index over the first N preset periods. k-N The standard deviation of the composite fault risk prediction index within the first N preset periods is given. The periodic fluctuation pattern is obtained by analyzing the time-series composite index sequence through a sliding window.

[0011] Preferably, the real-time operating status is either an abnormal state or a healthy state. The determination of the real-time operating status is based on the following criteria: if all data items in the numerical data are within their corresponding normal operating range in the circuit breaker health database, then the real-time operating status of the circuit breaker is determined to be a healthy state; otherwise, the real-time operating status of the circuit breaker is determined to be an abnormal state. The data items refer to current, power factor, vibration signal of the operating mechanism, contact temperature, and ambient temperature.

[0012] Preferably, the maintenance terminal is used to visually display numerical and status data of the circuit breaker's operation process. The numerical data is presented in the form of a time-series curve, and data items exceeding the normal operating range are highlighted. Status data is displayed through status indicator lights. Simultaneously, it combines the circuit breaker's fault risk index and real-time operating status to execute tiered early warnings: Level 1 warning corresponds to a fault risk index in the range [30, 50) and a healthy real-time operating status, maintaining routine monitoring of the circuit breaker; Level 2 warning corresponds to a fault risk index in the range [50, 80) or an abnormal real-time operating status with a fault risk index ≥ 30, prompting maintenance personnel to strengthen monitoring and investigate the source of the anomaly; Level 3 warning corresponds to a fault risk index ≥ 80 or an abnormal real-time operating status with a fault risk index ≥ 60, prompting maintenance personnel to immediately initiate intervention measures. The maintenance terminal can also issue compliant maintenance instructions to the circuit breaker's control unit to achieve remote closed-loop maintenance management.

[0013] Due to the adoption of the above technical solutions, the technical progress achieved by this invention compared with the prior art is as follows: 1. This invention breaks through the limitation of the one-sided dimension of traditional circuit breaker monitoring data collection, comprehensively collects the circuit breaker's operating data through multiple types of sensors, and extracts its key operating status characteristics to achieve a comprehensive characterization of the circuit breaker's health status.

[0014] 2. This invention solves the problems of the lack of a standardized health database and the single prediction method in existing circuit breaker monitoring. It constructs a standardized health database based on the circuit breaker's factory parameters and measured data of the circuit breaker under healthy conditions, and constructs a composite fault index by combining the analytic hierarchy process, correlation analysis, and trend analysis. Combined with the LSTM model, it achieves accurate prediction of fault risk and gets rid of the reactive maintenance mode.

[0015] 3. This invention improves upon the inefficiency and slow response of traditional circuit breaker operation and maintenance. It enables data visualization and highlighting through the operation and maintenance terminal, performs three-level early warning based on the fault risk index and operating status, supports remote issuance of operation and maintenance instructions, forms closed-loop management, and improves fault response efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0017] Figure 1 is a schematic diagram of the system functional modules of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] As shown in Figure 1, an embodiment of a remote real-time monitoring system for the operating status of an intelligent circuit breaker includes an operating data acquisition and processing module, a circuit breaker health database, a fault risk prediction module, a real-time monitoring module, and an operation and maintenance terminal, which work together to complete the model training task.

[0020] The operational data acquisition and processing module is used to collect operational data during the circuit breaker's operation. This operational data includes numerical data and status data, and features are extracted from the numerical data to obtain the circuit breaker's operational status characteristics. The circuit breaker health database stores the normal value ranges of the circuit breaker's operational status characteristics and the normal operating ranges of the numerical data under healthy conditions. The fault risk prediction module performs deviation analysis on the circuit breaker's operational status characteristics to obtain feature deviation data. It then constructs a composite fault risk prediction index based on the feature deviation data through weighting, deviation correlation, and trend analysis. The fault risk index of the circuit breaker is obtained based on this composite fault prediction index. The real-time monitoring module compares and judges the numerical data in real time according to its normal operating range to obtain the circuit breaker's real-time operational status. The maintenance terminal visualizes the operational data during the circuit breaker's operation and performs tiered early warnings and remote maintenance based on the circuit breaker's fault risk index and real-time operational status.

[0021] Furthermore, the working principle of this invention is illustrated below using a 10kV ZN63A-12 intelligent circuit breaker in an industrial power distribution system as an example: A Hall current sensor is deployed in the data acquisition and processing module to collect current; a multi-functional power meter collects the power factor; a piezoelectric vibration acceleration sensor is deployed at the circuit breaker's opening and closing operating mechanism to collect vibration signals; a PT100 platinum resistance thermometer is deployed at key contact locations to collect contact temperature; and a digital temperature and humidity sensor is deployed in the circuit breaker cabinet to collect ambient temperature. Simultaneously, status data, including opening and closing status, protection action trigger status, and operation stop status, is collected through the status feedback dry contacts and auxiliary contacts of the circuit breaker body. The controller for the data acquisition and processing module is an STM32H743VIT. 6. Supports real-time preprocessing and feature extraction of operational data; the circuit breaker health database is built on MySQL 8.0 and deployed on an industrial-grade server, communicating with other modules via Ethernet to store normal value ranges and historical operational data; the fault risk prediction module adopts an edge computing gateway, with a built-in Python 3.9 runtime environment, integrating Scikit-learn and TensorFlow 2.8 frameworks for deviation analysis, construction of composite fault risk prediction indicators, and LSTM model inference; the real-time monitoring module communicates with the operational data acquisition and processing module via a CAN bus to compare numerical data with normal operating ranges in real time; the maintenance terminal uses an industrial tablet PC with customized monitoring software installed, supporting 4G / 5G remote communication, and enabling data visualization, hierarchical early warning, and command issuance.

[0022] Operating data of the circuit breaker is collected at a preset frequency. Status-based data is uploaded to the real-time monitoring module in real time. Feature extraction is performed on the numerical data to obtain the circuit breaker's operating status characteristics. Specifically, the current period T = 0.02s is taken, and the effective value formula is used... Integrating the collected current yields an effective current value of 102 A. Fourier decomposition of the current yields the fundamental current effective value I1 = 101.5 A, and the effective values ​​of the 2nd to 5th harmonic currents are I2 = 3.2 A, I3 = 2.8 A, and I5 = 1.5 A, respectively. Substituting these values ​​into the harmonic distortion rate formula... The calculated THD is 4.2%; the power factor is taken over 50 consecutive sampling periods, and the power factor in the kth sampling period is... The values ​​are 0.92, 0.93, ..., 0.91 respectively. Calculate the average value. Substitute into the standard deviation formula The power factor fluctuation σ is found to be 0.018; a fast Fourier transform is performed on the vibration signal of the operating mechanism to obtain the frequency domain amplitude X(f), and the maximum amplitude A is extracted. peak =max(|X(f)|)=2.3g as the peak value of the vibration signal spectrum; contact temperature T c =75℃, ambient temperature T e =25℃, substitute into the formula for maximum temperature rise ΔT max =max(T c -T e The maximum temperature rise ΔT is obtained. max =50℃, the time interval between adjacent sampling times is Δt=1s, the temperature rise ΔT at the kth sampling time is... k =50℃, temperature rise ΔT at the (k-1)th sampling time k-1 =48℃, according to the temperature change rate formula The calculated rate of temperature change v T =2℃ / s.

[0023] Based on the factory rated parameters of the ZN63A-12 circuit breaker, and combined with the measured operating data of 30 groups of the same model circuit breakers under healthy operating conditions, the normal value range of each operating condition characteristic was determined and stored by statistical analysis and taking the mean ± 3 times the standard deviation. The normal value range of the circuit breaker operating condition characteristics is as follows: current effective value [95A, 105A], harmonic distortion rate [0%, 5%], power factor fluctuation [0, 0.03], vibration signal spectrum peak value [0.5g, 2.0g], maximum temperature rise [0℃, 45℃], and temperature change rate [0℃ / s, 1.5℃ / s]. The normal operating range of numerical data is as follows: current [0A, 630A], power factor [0.85, 1.0], operating mechanism vibration signal amplitude [0g, 3g], contact temperature [0℃, 120℃], and ambient temperature [-10℃, 60℃].

[0024] During the deviation analysis phase, the normal value range of the circuit breaker operating status characteristics is retrieved from the health database, and the median value F of the range is taken. i0 (Median effective current 100A, median harmonic distortion rate 2.5%, median power factor fluctuation 0.015, median peak value of vibration signal spectrum 1.25g, median maximum temperature rise 22.5℃, median temperature change rate 0.75℃ / s), according to the relative deviation formula The calculated deviations were: current RMS value deviation D1 = 2.0%, harmonic distortion rate deviation D2 = 68.0%, power factor fluctuation deviation D3 = 20.0%, vibration signal spectrum peak value deviation D4 = 84.0%, maximum temperature rise deviation D5 = 122.2%, and temperature change rate deviation D6 = 166.7%. These deviations were integrated to form characteristic deviation data. When constructing the composite fault risk prediction index, a fault impact degree judgment matrix was first built based on the analytic hierarchy process combined with the experience of power industry experts. This matrix was then used for consensus analysis. After verification, the fault impact weights of each characteristic deviation value were obtained as W1=0.25, W2=0.20, W3=0.10, W4=0.15, W5=0.18, and W6=0.12. Then, the Pearson correlation coefficient was used to calculate the correlation between any two characteristic deviation values. D5 and D6, and D4 and D5 were determined to be strongly correlated deviation combinations. The number of combinations belonging to each characteristic deviation value was counted as M1=0, M2=0, M3=0, M4=1, M5=2, and M6=1. According to formula α... i =1.0+0.1×min(M i 3) Calculate the correlation correction coefficients α1=1.0, α2=1.0, α3=1.0, α4=1.1, α5=1.2, and α6=1.1. Simultaneously, use linear regression combined with exponential smoothing to fit the time-series trend, obtaining trend slopes k1=0.02, k2=0.03, k3=0.01, k4=0.07, k5=0.09, and k6=0.08. Set the trend correction coefficients K1=1.0, K2=1.0, K3=1.0, K4=1.3, K5=1.4, and K6=1.3. Finally, substitute these values ​​into the weighted summation formula. The composite failure risk prediction index F≈89.6 was obtained. When predicting the failure risk index, the composite failure risk prediction index was recorded in time series to form a time-series composite index sequence, with N=20. The current index F... k =89.6, the average of the indicators over the previous 20 periods Standard deviation S k-N =15.8, according to the formula The rate of change of the index was calculated to be v≈1.1. Fourier transform was performed on the time-series composite index sequence, and the dominant period of 15 min corresponding to the frequency of the maximum amplitude was extracted as the characterization of the periodic fluctuation law. An LSTM model with two hidden layers was selected. The training set was 1000 sets of historical time-series composite index sequences with manual annotation of real fault risk indices. After Z-score standardization preprocessing, the model was trained and optimized with mean square error as the loss function. The number of training iterations was 500 rounds and the learning rate was 0.001. The extracted time-series features were input into the pre-trained model, and the output fault risk index was 78.

[0025] The real-time monitoring module retrieves the normal operating range of numerical data from the health database and compares the collected numerical data. The current of 102A, power factor of 0.92, vibration signal amplitude of 2.3g, contact temperature of 75℃, and ambient temperature of 25℃ are all within the corresponding normal operating range. However, the maximum temperature rise of 50℃ exceeds the normal range. Based on this, the real-time operating status of the circuit breaker is determined to be abnormal.

[0026] The maintenance terminal displays numerical data such as current and power factor in the form of time-series curves. Temperature rise data that exceeds the normal range is highlighted in red and indicated by green indicator lights for "closing / opening status - closed", blue indicator lights for "protection action triggered status - not triggered", and yellow indicator lights for "operation stopped status - running", providing intuitive feedback on status data. Combined with the fault risk index of 78 and the abnormal status, a level-two warning is triggered. The terminal pops up a warning window and issues an audible and visual prompt, stating "The circuit breaker's real-time operating status is abnormal, the fault risk index is 78, and the temperature rise is suspected to be caused by overheating of the contacts. Please strengthen monitoring and investigate the source of the abnormality." Maintenance personnel can view historical warning records through the maintenance terminal. After confirming the abnormality, they issue compliant maintenance instructions to the circuit breaker control unit, such as "reduce the load to 80% of the rated capacity and conduct on-site inspection of the contact conditions within 24 hours". This instruction is transmitted to the circuit breaker controller in encrypted form, realizing remote maintenance closed-loop management.

[0027] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A remote real-time monitoring system for the operating status of an intelligent circuit breaker, characterized in that, include: The system operates a data acquisition and processing module, which is used to collect operating data during the operation of the circuit breaker. The operating data includes numerical data and status data, and the system extracts features from the numerical data to obtain the operating status features of the circuit breaker. The circuit breaker health database stores the normal value range of the circuit breaker's operating status characteristics and the normal operating range of numerical data under the circuit breaker's health status. The fault risk prediction module performs deviation analysis on the circuit breaker's operating status characteristics to obtain characteristic deviation data, and constructs a composite fault risk prediction index by weighting, deviation correlation, and trend analysis of the characteristic deviation data. Based on the composite fault prediction index, the fault risk index of the circuit breaker is obtained. The real-time monitoring module is used to compare and judge numerical data in real time according to the normal operating range of numerical data to obtain the real-time operating status of the circuit breaker; the operation and maintenance terminal is used to visualize the operation data of the circuit breaker during operation, and at the same time to perform graded early warning and remote operation and maintenance based on the fault risk index and real-time operating status of the circuit breaker.

2. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 1, characterized in that, The numerical data includes current, power factor, vibration signal of operating mechanism, contact temperature and ambient temperature, and the status data includes circuit breaker opening and closing status, protection action triggering status and operation stop status.

3. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 2, characterized in that, The circuit breaker operating status characteristics include the effective value of current, harmonic distortion rate, power factor fluctuation, peak value of vibration signal spectrum, maximum temperature rise, and temperature change rate. The feature extraction process is as follows: the current is calculated and processed by harmonic analysis to obtain the effective value of current and harmonic distortion rate; the power factor fluctuation is calculated by the standard deviation algorithm; the vibration signal of the operating mechanism is converted into a frequency domain signal by fast Fourier transform, and the maximum amplitude peak value of the frequency domain signal is extracted as the peak value of the vibration signal spectrum; the maximum temperature rise is extracted by point-by-point comparison after subtracting the ambient temperature from the contact temperature, and the temperature change rate is calculated by the first-order difference method.

4. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 3, characterized in that, The deviation analysis involves retrieving the normal value range of the circuit breaker operating status characteristics from the circuit breaker health database, and using the relative deviation method to calculate the characteristic deviation value between each operating status characteristic and its corresponding normal value range, thereby forming characteristic deviation data.

5. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 4, characterized in that, The construction method of the composite fault risk prediction index is as follows: S1. Based on the analytic hierarchy process and combined with the experience of power industry experts, weights are assigned to each characteristic deviation value in the characteristic deviation data to obtain the fault impact weight of each characteristic deviation value, and the sum of the fault impact weights of each characteristic deviation value is 1; S2. The correlation between any two characteristic deviation values ​​is calculated using the Pearson correlation coefficient, and strong correlation deviation combinations are identified accordingly. The number of combinations to which each characteristic deviation value belongs is counted, and the deviation correlation correction coefficient of the characteristic deviation value is obtained based on the number of combinations; at the same time, the time-series change trend of each characteristic deviation value is fitted using linear regression combined with exponential smoothing, and the trend correction coefficient of the characteristic deviation value is set based on the trend type to which the time-series change trend belongs; S3. The composite fault risk prediction index is obtained by merging each characteristic deviation value and the corresponding fault impact weight, deviation correlation correction coefficient and trend correction coefficient based on the weighted summation method.

6. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 5, characterized in that, The fault risk index is obtained by inputting time-series features into a pre-trained machine learning model for prediction; the time-series features are obtained by recording composite fault risk prediction indicators in a time series to form a time-series composite indicator sequence, and extracting time-series features from the time-series composite indicator sequence, the time-series features including the rate of change of indicators and periodic fluctuation patterns.

7. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 6, characterized in that, The real-time operating status can be either an abnormal state or a healthy state. The determination of the real-time operating status is based on the following criteria: if all data items in the numerical data are within their corresponding normal operating range, the real-time operating status is determined to be a healthy state; otherwise, the real-time operating status is determined to be an abnormal state.

8. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 7, characterized in that, The operation and maintenance terminal visualizes numerical data in the form of time-series curves, highlights data items that exceed the normal operating range, and visualizes status data using status indicator lights.

9. The remote real-time monitoring system for the operating status of an intelligent circuit breaker according to claim 8, characterized in that, The criteria for the graded early warning are as follows: Level 1 early warning is when the fault risk index is within [30, 50) and the real-time operating status is healthy; Level 2 early warning is when the fault risk index is within [50, 80) or the real-time operating status is abnormal and the fault risk index is ≥30; Level 3 early warning is when the fault risk index is ≥80 or the real-time operating status is abnormal and the fault risk index is ≥60.

Images