Intelligent reclosing type circuit breaker control system

Abstract

The invention belongs to the technical field of electrical equipment. The intelligent reclosing type circuit breaker control system comprises a scene monitoring unit, a data analysis and decision-making unit, a circuit monitoring unit and a self-adaptive control unit. According to the control system, real-time and planned operation data are combined, dynamic fault critical characteristics are generated and integrated and analyzed, and precise regulation and control of the circuit breaker are achieved. Therefore, timely opening can be realized to avoid faults, timely closing can be realized to restore power supply, misoperation and power supply interruption are reduced, circuit safety and power supply continuity are improved, and the circuit is adaptive to complex load scenes.

Description

Technical Field

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

[0002] In modern power systems, reclosing circuit breakers, as core equipment for energy distribution and circuit protection, have a direct impact on power supply reliability, power safety, and the stable operation of power networks. With the rapid development of industrial automation, smart grids, and various precision electrical equipment, power loads have become more diverse and dynamic. The frequency and complexity of circuit faults such as overloads and short circuits have increased significantly, placing higher demands on the response speed, protection accuracy, and automation level of circuit breakers.

[0003] While traditional reclosing circuit breakers can be operated manually and automatically open and close after a fault, they have significant limitations in pre-identifying and handling overload conditions. On the one hand, most traditional devices rely on fixed current thresholds as the basis for overload detection, making it difficult to adapt to dynamic load changes in different scenarios. For example, the startup of large motors in industrial workshops generates short-term surge currents, and the simultaneous startup of multiple devices in households can also cause transient high loads. These non-fault current fluctuations are often misinterpreted as overloads, leading to unnecessary tripping operations and disrupting normal power supply. On the other hand, traditional systems have a weak ability to predict overload trends, often triggering protection mechanisms only after an overload fault has already occurred. This makes it impossible to take early warning or regulatory measures, which can damage circuit components due to continued overload and even cause more serious electrical accidents.

[0004] Therefore, how to improve the accuracy of reclosing circuit breakers in pre-identifying overload conditions and achieve accurate prediction and adaptive processing of faults is a key issue that needs to be urgently addressed in the current field of power protection equipment. Summary of the Invention

[0005] To this end, the present invention provides an intelligent reclosing circuit breaker control system, electronic equipment, computer storage medium and computer program product to solve at least one of the above technical problems.

[0006] In a first aspect of the present invention, an intelligent reclosing circuit breaker control system is provided, comprising a scenario monitoring unit, a data analysis and decision-making unit, a circuit monitoring unit, and an adaptive control unit; the scenario monitoring unit is configured to obtain load operation data of load devices within the control scenario of the circuit breaker, including real-time operation data and planned operation data.

[0007] The data analysis and decision-making unit is used to determine basic fault critical characteristics based on the real-time operation data, predict critical fluctuation characteristics based on the planned operation data and random fluctuation characteristics, integrate the basic fault critical characteristics with the critical fluctuation characteristics, and obtain fault critical characteristic data for the target time period.

[0008] The circuit monitoring unit is connected to the circuit and is used to collect the current, voltage and power factor of the circuit during the target period, and extract the operating characteristic data after pre-processing the collected data.

[0009] The adaptive control unit is used to perform a similarity analysis on the operating characteristic data and the fault critical characteristic data to determine whether the control conditions are met. If so, a trip control instruction is sent to the circuit breaker; and when a subsequent similarity analysis result does not meet the control conditions, a closing control instruction is sent to the circuit breaker.

[0010] A second aspect of the present invention provides an electronic device for use in an intelligent reclosing circuit breaker control system as described in any of the preceding items, the electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0011] A third aspect of the present invention provides a computer storage medium, which is applied to the intelligent reclosing circuit breaker control system as described in any of the preceding items, and the computer storage medium stores a computer program that can be executed by a processor.

[0012] A fourth aspect of the present invention provides a computer program product, which is applied to the intelligent reclosing circuit breaker control system as described in any of the preceding items, and the computer program product includes a computer program that can be executed by a processor.

[0013] The control system of this invention combines real-time and planned operating data to generate dynamic fault criticality characteristics and integrates them for analysis, enabling precise control of circuit breakers. This allows for both timely opening to prevent faults and timely closing to restore power, minimizing misoperation and power outages, improving circuit safety and power continuity, and adapting to complex load scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1The invention discloses an intelligent reclosing circuit breaker control system.

[0016] Figure 2 This is a flow chart of determining critical features of basic faults based on real-time operating data disclosed in an embodiment of the present invention.

[0017] Figure 3 It is a flow chart of deriving critical fluctuation characteristics based on planned operation data and random fluctuation characteristics prediction disclosed in an embodiment of the present invention.

[0018] Figure 4 It is a schematic diagram of a flow chart of generating a fluctuation probability distribution model disclosed in an embodiment of the present invention.

[0019] Figure 5 It is a flow chart of integrating basic fault criticality characteristics and critical fluctuation characteristics to obtain fault criticality characteristic data for a target period, disclosed in an embodiment of the present invention.

[0020] Figure 6 It is a flowchart of determining whether a control condition is satisfied according to an embodiment of the present invention.

[0021] Figure 7 This is a schematic diagram of a flow chart of sending a closing control instruction to a circuit breaker disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following specific embodiments illustrate the implementation of this application. People familiar with this technology can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0023] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0024] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent reclosing circuit breaker control system 100, including a scene monitoring unit 1001, a data analysis and decision unit 1002, a circuit monitoring unit 1003, and an adaptive control unit 1004; the scene monitoring unit 1001 is used to obtain load operation data of load devices within the control scene range of the circuit breaker, including real-time operation data and planned operation data.

[0025] Among them, the scene monitoring unit is responsible for accurately collecting the operating data of all load devices in the circuit breaker control scene, including: (1) real-time operating data, including the current instantaneous current, real-time power, operating status (such as start, run, stop) and other dynamic parameters of the equipment, such as the current change corresponding to the real-time speed of the motor in the industrial workshop, the real-time power consumption of the air conditioner in the home, etc.; (2) planned operating data, including the preset start and stop time of the equipment, the planned operating time, the load adjustment plan and other pre-set information, such as the production equipment schedule in the factory (such as running equipment A from 8:00 to 12:00, running equipment B from 14:00 to 18:00), the timed start setting of the water heater in the home, etc. After these data are collected through sensors, equipment interfaces, etc., they are summarized and transmitted to the data analysis and decision-making unit in real time.

[0026] The data analysis and decision-making unit 1002 is used to determine the basic fault critical characteristics based on the real-time operation data, predict the critical fluctuation characteristics based on the planned operation data and random fluctuation characteristics, integrate the basic fault critical characteristics with the critical fluctuation characteristics, and obtain the fault critical characteristic data for the target time period.

[0027] The data analysis and decision-making unit is used to generate critical characteristic data for determining circuit faults based on the load operation data provided by the scenario monitoring unit. Specifically, the data is cleaned (removing outliers and noise) and features are extracted (such as extracting the device's average operating current, maximum instantaneous current, load duration, etc.) based on real-time operating data and combined with the rated parameters of the load device (such as rated current and rated power). For example, for a motor with a rated current of 10A, by analyzing the fluctuation range of its current real-time operating current, the overload critical current (such as 12A) under the current operating conditions is calculated. That is, when the real-time current continuously exceeds this value, an overload fault may occur, forming a basic fault critical characteristic that reflects the current static safety boundary.

[0028] Then, the planned operation data is used to extract the equipment's start-up and shutdown periods and load superposition patterns (such as the time window for simultaneous startup of multiple devices). The random fluctuation characteristics (frequency, amplitude, and trend of current fluctuations, such as the pulse current pattern of a welding machine) in the real-time operation data are analyzed. Time series prediction algorithms (such as ARIMA and LSTM) are combined with the planned operation data to predict the load fluctuation curve within the target period. The dynamic load limit (such as the total current limit when multiple devices are running simultaneously) and time-specific risk thresholds (such as the fluctuation tolerance during peak hours) for the coordinated operation of multiple devices within that period are calculated. This generates a critical fluctuation characteristic that reflects the dynamic safety boundary of the target period.

[0029] Next, a weighted distribution model (e.g., weights are assigned based on real-time requirements and device importance) is used to integrate the basic criticality characteristics with the critical fluctuation characteristics. For example, for precision equipment with high real-time requirements, the weight of the basic criticality characteristics is increased; for scenarios with coordinated multi-device operation, the weight of the critical fluctuation characteristics is increased. Ultimately, a set of criticality characteristics data for the target time period is generated, encompassing both the current static safety threshold and the dynamic warning threshold.

[0030] The circuit monitoring unit 1003 is connected to the circuit and is used to collect the current, voltage and power factor of the circuit during the target period, and extract the operating characteristic data after pre-processing the collected data.

[0031] Among them, the circuit monitoring unit collects key electrical parameters such as the total current, line voltage, power factor, etc. of the circuit in real time during the target period through current transformers, voltage sensors and other devices connected in series in the main circuit.

[0032] The collected raw data first undergoes preprocessing, including filtering (to remove high-frequency interference, such as harmonic interference in the power grid), normalization (to unify the data format and magnitude for subsequent analysis), and smoothing (to reduce the impact of transient fluctuations on the analysis results). Subsequently, characteristic quantities reflecting the circuit's operating status during the target period are extracted from the preprocessed data. These include the slope of the real-time current curve (reflecting the current trend; a positive slope indicates rising current), voltage stability indicators (such as whether the voltage fluctuation amplitude is within the allowable range), and the real-time value and rate of change of the power factor. These operational characteristic data are then transmitted to the adaptive control unit.

[0033] The adaptive control unit 1004 is configured to perform a similarity analysis on the operating characteristic data and the fault critical characteristic data to determine whether the control conditions are met. If so, a trip control instruction is sent to the circuit breaker; and when a subsequent similarity analysis result does not meet the control conditions, a closing control instruction is sent to the circuit breaker.

[0034] The adaptive control unit is the execution module of the control system of the present invention, which implements intelligent circuit breaker control. It sends opening or closing commands to the circuit breaker based on the comparison between the circuit operating status and critical standards. The specific process is as follows: the operating characteristic data output by the circuit monitoring unit (such as the slope of the current variation curve, voltage fluctuation amplitude, and power factor change rate within the target time period) is converted into an operating characteristic vector. Simultaneously, the fault critical characteristic data generated by the data analysis and decision-making unit (such as the static safety threshold and dynamic warning threshold within the target time period) is converted into a critical characteristic vector. The similarity between the two characteristic vectors is calculated using algorithms such as cosine similarity and Euclidean distance.

[0035] The similarity analysis results are used to determine whether the control conditions are met. If the similarity between the two feature vectors reaches or exceeds the preset threshold (i.e., the operating feature vector is highly similar to the critical feature vector), the control conditions are determined to be met (there is a risk of failure such as overload). At this time, a trip control command is sent to the circuit breaker, causing it to quickly disconnect the circuit to prevent damage to the load equipment or line due to continuous overload.

[0036] After tripping, the system continuously receives updated operating characteristic data from the circuit monitoring unit during the target period, constructs a new operating characteristic vector in real time, and compares it with the critical fault characteristic vector for similarity. If the similarity analysis shows that the similarity between the two characteristic vectors falls below a preset threshold (i.e., the operating characteristic vector differs significantly from the critical characteristic vector, indicating that the fault has been eliminated), the control conditions are determined to be unmet, and a closing control command is sent to the circuit breaker to restore power to the circuit, ensuring that normal power is restored at the precise time after the fault is eliminated.

[0037] The control system of this invention combines real-time and planned operating data to generate dynamic fault criticality characteristics and integrates them for analysis, enabling precise control of circuit breakers. This allows for both timely opening to prevent faults and timely closing to restore power, minimizing misoperation and power outages, improving circuit safety and power continuity, and adapting to complex load scenarios.

[0038] As an example, Figure 2 As shown, the basic fault critical characteristics are determined based on the real-time operation data, including: 101, extracting the equipment type parameters, real-time current value, real-time power value and continuous operation time from the real-time operation data, and obtaining the rated current threshold, rated power threshold and allowed overload time corresponding to the equipment type parameters based on the preset equipment rated parameter library.

[0039] 102. Calculate a first deviation rate between the real-time current value and the rated current threshold, and a second deviation rate between the real-time power value and the rated power threshold, and calculate an overload risk coefficient based on the first deviation rate, the second deviation rate, and the continuous operation time.

[0040] 103. When the overload risk coefficient reaches a preset risk threshold, the corresponding real-time current value, real-time power value, and continuous operation time are determined as critical characteristics of a basic fault of a single device.

[0041] 104 , calculating a total load critical value based on the device association relationship, and combining the basic fault critical characteristics of each single device and the total load critical value to form the basic fault critical characteristics.

[0042] The following parameters are extracted from the real-time operation data collected by the scene monitoring unit: device type parameters (such as information identifying device attributes such as three-phase asynchronous motors and household air conditioners); real-time current value (the instantaneous current of the device in current operation, unit: A); real-time power value (the current active power of the device, unit: kW); continuous operation time (the continuous operation time of the device from the current startup to the current moment, unit: min).

[0043] At the same time, a device rated parameter library is pre-built to store the factory rated parameters of various types of equipment. Based on the extracted equipment type parameters, the corresponding benchmark thresholds are automatically matched, including: rated current threshold (the maximum current for long-term safe operation of the equipment, such as 10A); rated power threshold (the maximum power limit designed for the equipment, such as 2.2kW); and allowable overload duration (the maximum duration that the equipment can withstand short-term overload, such as 5 minutes).

[0044] Next, calculate the first deviation rate between the real-time current value and the rated current threshold, and the second deviation rate between the real-time power value and the rated power threshold. Specifically, the first deviation rate reflects the degree of current overload and is calculated as follows: First Deviation Rate = (Real-time Current Value - Rated Current Threshold) / Rated Current Threshold × 100%. If the result is negative, it indicates no overload and is set to 0.

[0045] The second deviation rate reflects the degree of power overload and is calculated as: (real-time power value - rated power threshold) / rated power threshold × 100%. Similarly, if the result is negative, it indicates no overload and is set to 0.

[0046] The overload risk factor is calculated based on the first deviation rate, the second deviation rate, and the continuous operating time. This factor quantifies the current overload risk by integrating the effects of current, power overload level, and duration. The formula is: Overload Risk Factor = (First Deviation Rate × First Weight + Second Deviation Rate × Second Weight) × (Continuous Operating Time / Allowable Overload Duration). The first and second weights can be set based on device characteristics. For example, a current-dominant device may have a first weight of 0.6 and a second weight of 0.4 to emphasize the influence of current parameters.

[0047] A preset risk threshold (e.g., 0.8-0.9, adjustable based on the device's importance) is set. When the calculated overload risk coefficient reaches this threshold, it indicates that the device is approaching or has reached a critical failure state. At this point, the corresponding real-time current value, real-time power value, and continuous operating time are recorded as the basic critical failure characteristics. For example, if a motor has a real-time current of 12A, a real-time power of 2.5kW, and operates continuously for 4 minutes, and the overload risk coefficient reaches 0.85, then (12A, 2.5kW, 4 minutes) is determined as the basic critical failure characteristics for the motor.

[0048] Finally, based on device relationships (such as the combined loads of simultaneous operations), the total load threshold is calculated (for example, the total current threshold is 1.1 times the sum of the current thresholds of each device, and the total power threshold is 1.1 times the sum of the power thresholds of each device; these coefficients are used to mitigate coordinated fluctuations). The basic fault criticality signature is composed of the critical parameters of all individual devices (preserving the independent safety boundaries of each device) and the total load threshold (reflecting the coordinated risk of multiple devices).

[0049] As an example, Figure 3 As shown, the critical fluctuation characteristics are obtained based on the planned operation data and the prediction of random fluctuation characteristics, including: 201, extracting the preset start and stop times, single operation time and load type association relationship of each load device from the planned operation data, and constructing the equipment operation time table within the target time period.

[0050] 202 , extract random fluctuation characteristics from the real-time operation data, including current fluctuation frequency, power fluctuation amplitude, and fluctuation duration, and generate a fluctuation probability distribution model through statistical analysis.

[0051] 203. Based on the equipment operation schedule, a load superposition algorithm is used to calculate the theoretical total load reference value at different times within the target period. The theoretical total load reference value is dynamically corrected in combination with the fluctuation probability distribution model to calculate the load fluctuation range under different confidence levels.

[0052] 204. Based on the upper limits of the load fluctuation range at different confidence levels corresponding to the theoretical total load reference value at each moment, critical fluctuation characteristics are obtained, including a periodic total current limit value, a power fluctuation safety threshold, and a load superposition warning line for collaborative operation of multiple devices.

[0053] The following key information is extracted from the planned operation data collected by the scene monitoring unit: preset start and stop times (for example, device A is scheduled to start at 8:00 and stop at 12:00, and device B is scheduled to start at 9:30 and stop at 17:00); single operation duration (calculated from the start and stop times, such as device A running for 4 hours at a time); load type association relationship (reflecting the operation dependency or conflict between devices, such as "device D needs to stop when device C starts" and "device E and device F can run at the same time").

[0054] Based on this information, the operating status of all devices within the target time period (e.g., the next 24 hours) is arranged chronologically to form a visual device operation schedule. For example, from 9:00 AM to 9:30 AM, only device A is operating; from 9:30 AM to 12:00 PM, both device A and device B are operating simultaneously, clearly showing the device operation combinations at each moment.

[0055] Furthermore, key features reflecting random load variations are extracted from real-time operating data: current fluctuation frequency (the number of times the current exceeds the stable range per unit time, e.g., a device fluctuates 5 times per hour); power fluctuation amplitude (the maximum percentage by which the power deviates from the average value, e.g., a device with a power fluctuation amplitude of ±8%); and fluctuation duration (the duration of each fluctuation, e.g., a fluctuation lasting 10 seconds). Statistical analysis (e.g., calculating the mean, variance, and probability density) is performed on these extracted key features to generate a fluctuation probability distribution model. For example, analysis of historical data revealed that the power fluctuation amplitude of device A follows a normal distribution, with 90% of fluctuations falling within ±5% and 95% falling within ±6%.

[0056] Furthermore, based on the equipment operation schedule, a load superposition algorithm is used to calculate the theoretical total load baseline value at different times within the target period. The calculation formula is: Theoretical total load baseline value = Σ(single device rated power × operating state coefficient). The operating state coefficient is 1 when the equipment is operating (included in the total load) and 0 when it is not operating (not included in the total load). For example, if equipment A has a rated power of 2kW and equipment B has a rated power of 3kW, and they are both operating from 9:30 AM to 12:00 PM, the theoretical total load baseline value = 2 × 1 + 3 × 1 = 5kW.

[0057] Furthermore, combining the fluctuation probability distribution model with the theoretical total load baseline value as a reference, we calculated the load fluctuation ranges at different confidence levels. For example, based on the power fluctuation amplitude (±6%) corresponding to a 95% confidence level in the fluctuation probability distribution model, we can deduce that the fluctuation range corresponding to a 5kW baseline value is 5×(1±6%)=4.7kW-5.3kW; at a 90% confidence level, the fluctuation amplitude is ±5%, corresponding to a range of 4.75kW-5.25kW. Different confidence levels correspond to different interval widths; higher confidence levels result in wider intervals, covering more extreme fluctuations.

[0058] Finally, for each moment in the target period, the upper limits of the load fluctuation range of the theoretical total load benchmark at different confidence levels are selected as the critical fluctuation characteristics at that moment. For example, for the 9:30-12:00 period, the theoretical total load benchmark is 5kW, the upper limit of the fluctuation range at a 95% confidence level is 5.3kW, and the upper limit of the fluctuation range at a 90% confidence level is 5.25kW. These upper limits correspond to critical standards for different risk levels.

[0059] The critical fluctuation characteristics specifically include: the time-based total current limit value (converted from the total power, such as 5.3kW corresponds to 24A); the power fluctuation safety threshold (the relative deviation between the upper limit value and the theoretical reference value, such as +6% at 95% confidence level); and the load superposition warning line for the coordinated operation of multiple devices (that is, directly using the power upper limit value as the collaborative control threshold for the total load of multiple devices, such as the warning threshold corresponding to 5.3kW).

[0060] In this embodiment, the critical fluctuation feature is directly centered on the upper limit of the load fluctuation range, which not only retains the reference significance of the theoretical total load benchmark value (clarifies the relative source of the fluctuation), but also focuses on the upper limit threshold related to the overload risk, making the logic of the dynamic critical standard clearer. At the same time, it takes into account the certainty of planned operation and the randomness of actual operation, and can provide an accurate dynamic boundary for predicting overload risks.

[0061] As an example, Figure 4 As shown, random fluctuation characteristics are extracted from the real-time operation data, including current fluctuation frequency, power fluctuation amplitude and fluctuation duration, and a fluctuation probability distribution model is generated through statistical analysis, including: 301, current time series data and power time series data within a preset time window are intercepted from the real-time operation data, and characteristic values ​​of the dynamic fluctuation segment data therein are extracted, including current fluctuation frequency, power fluctuation amplitude, and fluctuation duration.

[0062] 302 , collecting characteristic values ​​of at least a preset number of preset time windows to form a sample set, and using kernel density estimation to perform probability density fitting on the current fluctuation frequency, power fluctuation amplitude, and fluctuation duration in the sample set to generate respective marginal distribution models.

[0063] 303 , constructing a joint probability distribution model of the three eigenvalues ​​through a Copula function, and using it as the fluctuation probability distribution model.

[0064] First, the current time series data (a sequence of current values ​​recorded in chronological order) and power time series data (a sequence of power values ​​recorded in chronological order) within a preset time window (e.g., 5 minutes) are intercepted from the real-time operating data. Steady-state segments are filtered out, such as periods of stable operation with a fluctuation amplitude of less than 2% for 30 consecutive seconds. Only dynamic fluctuation segments, i.e., periods with significant fluctuations in current or power, are retained to ensure that subsequent analysis focuses on the actual fluctuation state. It is understandable that the real-time operating data collected by the aforementioned scene monitoring unit is not operating data at a single moment, but operating data for a period of time.

[0065] The following characteristic values ​​are extracted from the dynamic fluctuation segment data of the current time series data and the power time series data: Current fluctuation frequency: the number of times the current value exceeds the steady-state mean value ±3% within a statistical unit time (such as every minute) (for example, if there are 12 fluctuations in a 5-minute window, the frequency is 2.4 times / minute), reflecting the intensity of the fluctuation.

[0066] Power fluctuation amplitude: Calculate the percentage of the difference between the peak power value and the steady-state mean value in each fluctuation (for example, a power increase from 2 kW to 2.3 kW in a certain fluctuation is 15%). Take the 90th percentile of all fluctuation amplitudes (i.e., 90% of the fluctuation amplitudes are less than this value) as the characteristic value to avoid interference from extreme outliers.

[0067] Fluctuation duration: Record the duration of each fluctuation from exceeding the threshold to returning to the threshold (for example, a fluctuation lasts 15 seconds), and take the average of all durations as the characteristic value to reflect the continuity of the fluctuation.

[0068] Next, feature values ​​for at least a preset number (e.g., 10) of preset time windows are collected. Each window corresponds to a set of current fluctuation frequency, power fluctuation amplitude, and fluctuation duration, forming a sample set containing sufficient statistics. Kernel density estimation is used to perform probability density fitting on each of the three features in the sample set. The sample data for current fluctuation frequency is fitted to generate its marginal distribution model, which, for example, exhibits a distribution pattern where the fluctuation frequency in most windows is concentrated between 1 and 3 times per minute, with a few exceeding 5 times per minute. Similarly, marginal distribution models for power fluctuation amplitude and fluctuation duration are generated separately, each model independently describing the probability distribution characteristics of a specific feature. For example, the power fluctuation amplitude is mostly concentrated within ±5%, with a few exceeding ±8%.

[0069] The marginal distribution models of the three features are connected using a copula function to construct a joint probability distribution model. The copula function captures the correlations between the three features, such as the fact that high current fluctuation frequencies are often accompanied by large power fluctuation amplitudes, and that long-term fluctuations are more likely to occur in high-frequency fluctuation scenarios, rather than simply superimposing individual distributions.

[0070] The construction process is described as follows: 1. For the three features of the periodic total current limit value (X), the power fluctuation safety threshold (Y), and the multi-device collaborative load superposition warning line (Z), edge distribution models are constructed respectively.

[0071] Collect historical data (e.g., feature values ​​at each moment in the past three months), remove outliers, and standardize. Use the KS test (Kolmogorov-Smirnov test) to determine the marginal distribution type of each feature, including: the total current limit value (X) follows a normal distribution. ; Power fluctuation safety threshold (Y) obeys log-normal distribution ; Load superposition warning line (Z) obeys Gamma distribution .

[0072] The maximum likelihood estimation method is used to solve the parameters of each marginal distribution, such as .

[0073] 2. Select an appropriate copula function based on the correlation between the three features (measured by the Pearson or Kendal coefficient): Low correlation scenario (correlation coefficient < 0.3): Use the Gaussian copula, whose joint distribution function is: ;in, is the multivariate normal distribution function, is the correlation coefficient matrix, , is the cumulative distribution function of the marginal distribution.

[0074] High correlation scenario (correlation coefficient ≥ 0.3): Use t-Copula to retain the correlation structure of Gaussian Copula while capturing tail correlation through the degrees of freedom parameter.

[0075] 3. Estimation of Copula function parameters: Based on the maximum likelihood estimation method, the Copula parameters (such as the correlation coefficient matrix of Gaussian Copula) are solved with the goal of maximizing the joint log-likelihood function. ): ;in, is the sample size, Copula parameters.

[0076] The optimal copula model is selected by AIC (Akaike Information Criterion) or BIC (Bayesian Information Criterion). The smaller the value, the better the model fitting effect.

[0077] 4. Construct a joint probability distribution model: Combine the marginal distribution with the Copula function to obtain the joint probability distribution of the three features: ;in, are the marginal cumulative distribution functions of the three features, is the selected Copula function, Parameters of the Copula function.

[0078] The resulting joint probability distribution model is a complete fluctuation probability distribution model that reflects both the distribution patterns of individual features and the interactions between them. For example, the model can directly output the probability of a composite event: "current fluctuation frequency > 3 times / minute, power fluctuation amplitude > 5%, and fluctuation duration > 10 seconds."

[0079] As an example, Figure 5 As shown, the basic fault critical characteristics and critical fluctuation characteristics are integrated to obtain the fault critical characteristic data for the target time period, including: 401, setting the first weight coefficient of the basic fault critical characteristics based on the real-time requirements of the equipment, and setting the second weight coefficient of the critical fluctuation characteristics based on the complexity of the coordinated operation of multiple devices.

[0080] 402 , normalize the basic fault criticality characteristics and the critical fluctuation characteristics, calculate the comprehensive fault criticality index at each moment in the target period using a weighted fusion algorithm, and generate the fault criticality characteristic data based on the comprehensive fault criticality index.

[0081] First, weight coefficients for the fundamental fault criticality signature and critical fluctuation signature are set as follows: The first weight coefficient for the fundamental fault criticality signature is dynamically set based on the device's real-time performance requirements. For devices with high real-time response requirements (such as medical monitors and industrial robot controllers), where transient overloads can directly cause safety incidents or damage precision components, a higher first weight coefficient (such as 0.6-0.7) is used to prioritize the real-time safety margin of individual devices. For devices with lower real-time requirements (such as ventilation fans and general lighting systems), where short-term overloads have less impact, a lower first weight coefficient (such as 0.3-0.4) is used.

[0082] It can be understood that the real-time performance requirement of a device is not the requirement of a single device, but rather the equivalent real-time performance requirements of multiple devices of various types. For example, each device in the control scenario is first classified by real-time performance requirement (e.g., medical equipment and industrial controllers are "high," while lighting and general motors are "low") and assigned a quantitative value (e.g., high = 3, medium = 2, low = 1). A weighted sum is then calculated based on the device's load percentage, using the formula: Equivalent real-time performance requirement = Σ(single device real-time performance quantitative value × device load percentage). The equivalent values ​​are then divided into intervals (e.g., 1-1.5 → 0.3-0.4, 2-2.5 → 0.6-0.7).

[0083] The second weight coefficient for critical fluctuation characteristics is set based on the complexity of multi-device coordinated operation. Specifically, when three or more devices in the system are operating simultaneously (such as a factory production line running at full capacity or a commercial building experiencing peak electricity demand), the fluctuation risk caused by load superposition increases significantly. A higher second weight coefficient (such as 0.6-0.7) is used to strengthen the focus on dynamic load superposition. When only one or two devices are operating independently (such as a refrigerator and TV in a home), the load relationship is simple, so a lower second weight coefficient (such as 0.3-0.4) is used. Furthermore, a weight constraint is required, ensuring that the sum of the first and second weight coefficients is 1 to ensure normalized weight distribution and avoid double counting or weight imbalance.

[0084] Next, because the physical dimensions and numerical ranges of basic fault critical features (such as a single device's critical current of 12A and a critical power of 2.5kW) and critical fluctuation features (such as a total current limit of 24A and a total power threshold of 5.3kW) differ significantly (for example, the critical value of a single device and the total threshold of multiple devices may differ by 1-2 orders of magnitude), direct fusion will cause one type of feature to dominate the calculation results. To address this, this embodiment first uses normalization to uniformly convert both types of features into dimensionless indices (with a value range of 0-1) to eliminate the dimensionality effect. The normalization process is illustrated below: The basic fault criticality characteristic index is calculated by dividing the critical value of a single device by the rated parameters of the device. For example, if a motor has a critical current of 12A and a rated current of 10A, the index is 12 / 10 = 1.2, which is mapped to the 0-1 range through linear scaling. The critical fluctuation characteristic index is calculated by dividing the fluctuation range upper limit by the theoretical total load reference value. For example, if the total power fluctuation upper limit is 5.3kW and the reference value is 5kW, the index is 5.3 / 5 = 1.06, which is similarly mapped to the 0-1 range.

[0085] Furthermore, based on the normalized characteristic index and weight coefficient, the comprehensive fault criticality index at each moment in the target period is calculated using the following formula: Comprehensive Fault Criticality Index = Basic Fault Criticality Characteristic Index × First Weight Coefficient + Critical Fluctuation Characteristic Index × Second Weight Coefficient. For example, in a scenario where a precision device (first weight coefficient is 0.6) operates in conjunction with four devices (second weight coefficient is 0.4), if the basic fault criticality characteristic is 0.8 (close to the critical state of a single device) and the critical fluctuation characteristic is 0.9 (close to the upper limit of total load fluctuation), the comprehensive index = 0.8 × 0.6 + 0.9 × 0.4 = 0.84.

[0086] Finally, with the comprehensive fault critical index as the core and combined with the electrical parameter benchmark of the target time period, a multi-dimensional fault judgment criterion is generated: Time period safety threshold: multiply the comprehensive fault critical index by the theoretical total current / power benchmark value at the corresponding moment (for example, comprehensive fault critical index 0.84 × theoretical total current 25A = 21A) to obtain the actual safety threshold for the time period.

[0087] Dynamic warning curve: The comprehensive fault critical index at each moment is connected in chronological order to form a warning line that is dynamically adjusted with load changes (for example, if the index rises during peak power consumption, the warning line rises synchronously).

[0088] Collaborative criterion matrix: Establishes a multi-dimensional threshold combination of current, power, and duration (such as current exceeding the threshold and power exceeding the threshold and duration > 3 seconds). When the comprehensive fault criticality index exceeds 0.8, a stricter criterion combination is automatically activated.

[0089] As an example, Figure 6As shown, the operation characteristic data and the fault critical characteristic data are subjected to similarity analysis to determine whether the control conditions are met, including: 501, mapping the operation characteristic data into a real-time characteristic vector, mapping the fault critical characteristic data into a critical characteristic vector, and using a similarity algorithm to calculate the similarity between the real-time characteristic vector and the critical characteristic vector.

[0090] 501 , determining an overload risk level by comparing the similarity with a preset similarity interval, and determining that the control condition is satisfied when the overload risk level is higher than a level threshold.

[0091] The operating characteristic data (real-time monitored dynamic parameters such as current, power, fluctuation frequency, and duration) are mapped into real-time feature vectors (for example, [18A, 4.2kW, 3 times / minute, 8 seconds]) according to preset dimensions (such as current value, power value, number of fluctuations within 5 minutes, and duration of a single fluctuation). Each dimension corresponds to the real-time value of a specific operating parameter.

[0092] Map critical fault feature data (such as time-segment safety thresholds, dynamic warning lines, and collaborative judgment thresholds) into critical feature vectors (for example, [21A, 5.3kW, 5 times / minute, 10 seconds]) based on the same dimensions. Each dimension corresponds to the safety threshold of that parameter. Use similarity algorithms such as cosine similarity and Euclidean distance to calculate the degree of match between the two vectors.

[0093] The cosine similarity algorithm is used to calculate the degree of match, or similarity, between the two real-time feature vectors and the critical feature vector. For example, the cosine similarity algorithm is calculated as follows: Similarity = (Real-time vector · Critical vector) / (||Real-time vector|| × ||Critical vector||). The numerator is the dot product of the two vectors (reflecting directional consistency), and the denominator is the product of the two vectors' moduli (eliminating the effect of magnitude). The closer the result is to 1, the more consistent the direction of the real-time operating state and the critical state (higher risk); the closer it is to 0, the greater the difference between the two (lower risk).

[0094] Based on the system security requirements, multiple levels of similarity intervals are preset. Take the three-level interval as an example: high-risk interval: similarity 0.8-1.0 (real-time status approaches or reaches the critical threshold).

[0095] Warning range: Similarity 0.5-0.8 (real-time status fluctuates but does not reach a critical level).

[0096] Safety range: Similarity 0-0.5 (real-time status is far away from the critical threshold).

[0097] When the similarity falls into the high-risk range (e.g., 0.9), the overload risk level is determined to be "high." At this point, it exceeds the preset level threshold (e.g., 0.8), and the control conditions are determined to be met, triggering protection mechanisms (such as issuing an overload warning, automatic load adjustment, or tripping). When the similarity falls into the warning range (e.g., 0.6), the risk level is "medium." It falls below the level threshold and does not meet the control conditions, but load optimization suggestions are generated (e.g., reducing the power of non-critical equipment). When the similarity falls into the safe range (e.g., 0.3), the risk level is "low," and the control conditions are determined to be unmet, maintaining the current operating state.

[0098] As an example, Figure 7 As shown, when the subsequent similarity analysis results do not meet the control conditions, a closing control instruction is sent to the circuit breaker, including: 601, after the opening control instruction is sent and executed, a continuous monitoring cycle is started, and the operating characteristic data of the circuit is re-collected in each monitoring cycle and mapped into a new real-time characteristic vector; wherein, the cycle length of the continuous monitoring cycle is determined comprehensively based on the opening reason, equipment type and load characteristics.

[0099] 602 , calculating the similarity between the new real-time feature vector and the critical fault feature data to determine whether the control condition is no longer satisfied. If so, generating and sending a closing control instruction to the circuit breaker.

[0100] When the trip control command is executed, the system immediately activates a continuous monitoring mechanism, repeatedly collecting real-time circuit operating data at a set period (e.g., 5-30 seconds). The duration of the continuous monitoring cycle is determined by the following factors: Trip Cause: If the trip is caused by a momentary, minor overload (e.g., similarity 0.8-0.9), the fault is likely to subside quickly, so the cycle duration is set to a shorter value (e.g., 5-10 seconds). If the trip is caused by a severe overload (e.g., similarity ≥ 0.95) or sustained fluctuations, the cycle duration is extended (e.g., 20-30 seconds) to prevent premature closing and subsequent faults.

[0101] Equipment type and load characteristics: For equipment with frequent start-stops and rapid load fluctuations (such as stamping machines and high-frequency motors), the cycle duration should be short (3-5 seconds) to adapt to dynamic changes; for equipment with stable loads and slow responses (such as heating furnaces and central air conditioners), the cycle duration should be long (15-20 seconds) to reduce ineffective monitoring.

[0102] The above two factors are combined to determine the cycle duration. For example: (1) The quantization coefficient K1 is set for the tripping reason. The mapping rule is: K1 = 1.0 for instantaneous slight overload (similarity 0.8-0.9); K1 = 1.5 for moderate overload (similarity 0.9-0.95); K1 = 2.0 (basic cycle × 2.0) for severe overload or continuous fluctuation (similarity ≥ 0.95).

[0103] (2) Set the quantization coefficient K2 for the equipment type and load characteristics. The mapping rule is: K2 = 1.0 when the equipment starts and stops frequently and fluctuates rapidly (such as stamping machines and high-frequency motors); K2 = 1.5 when the equipment fluctuates moderately (such as ventilation systems and conveyor belts); K2 = 2.0 when the load is stable and the response is slow (such as heating furnaces and central air conditioners).

[0104] The final cycle duration is calculated by weighted multiplication of the above two factors: Cycle duration = Equipment basic cycle * K1) * K2. The equipment basic cycle can be, for example, 5 seconds, 10 seconds, or 15 seconds.

[0105] Then, during each monitoring cycle, operational characteristic data such as current, power, fluctuation frequency, and duration are recollected and mapped into a new real-time feature vector using the same dimensions as before tripping (e.g., current value, power value, number of fluctuations within 5 minutes, and duration of a single fluctuation). Furthermore, based on the critical fault characteristic data corresponding to the previously determined target period, a critical feature vector (e.g., [21A, 5.3kW, 5 times / minute, 10 seconds]) is generated. The similarity between the new real-time feature vector and the critical feature vector is calculated using the same similarity algorithm used before tripping. By comparing the new similarity with a preset interval, it is determined whether the control conditions are no longer met. If the similarity falls within a safe range (e.g., 0.3) and remains stable within this range for 2-3 consecutive cycles (excluding transient fluctuations), the control conditions are determined to be no longer met, indicating that there is no overload risk. At this point, the adaptive control unit automatically generates a closing control command, including a closing delay (e.g., 2 seconds to reduce transient current surges), and sends it to the circuit breaker to execute the closing operation, restoring power to the circuit breaker. If the similarity is still in the warning or high-risk range (such as 0.6), the switch will continue to be in the open state and enter the next monitoring cycle to repeat the above process.

[0106] An embodiment of the present invention further provides an electronic device, applied to the intelligent reclosing circuit breaker control system as described in any of the preceding items, the electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0107] An embodiment of the present invention further provides a computer storage medium, which is applied to the intelligent reclosing circuit breaker control system as described in any of the preceding items, and the computer storage medium stores a computer program that can be executed by a processor.

[0108] An embodiment of the present invention further provides a computer program product, which is applied to the intelligent reclosing circuit breaker control system as described in any of the preceding items. The computer program product includes a computer program that can be executed by a processor.

[0109] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. 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 to be beyond the scope of the present invention.

[0110] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. An intelligent reclosing circuit breaker control system, characterized in that: The system comprises a scenario monitoring unit, a data analysis and decision-making unit, a circuit monitoring unit, and an adaptive control unit; the scenario monitoring unit is used to obtain load operation data of load devices within the control scenario range of the circuit breaker, including real-time operation data and planned operation data; the data analysis and decision-making unit is used to determine basic fault criticality characteristics based on the real-time operation data, predict critical fluctuation characteristics based on the planned operation data and random fluctuation characteristics, and integrate the basic fault criticality characteristics with the critical fluctuation characteristics to obtain fault criticality characteristic data for the target time period; The circuit monitoring unit is connected to the circuit and is used to collect the current, voltage, and power factor of the circuit during the target period, and extract the operating characteristic data after preprocessing the data; the adaptive control unit is used to perform a similarity analysis on the operating characteristic data and the fault critical characteristic data to determine whether the control conditions are met. If so, a trip control instruction is sent to the circuit breaker; and when the subsequent similarity analysis results do not meet the control conditions, a closing control instruction is sent to the circuit breaker.

2. The intelligent reclosing circuit breaker control system according to claim 1, characterized in that: Determining basic fault critical characteristics based on the real-time operation data includes: extracting equipment type parameters, real-time current value, real-time power value and continuous operation time from the real-time operation data, and obtaining the rated current threshold, rated power threshold and allowable overload time corresponding to the equipment type parameters based on a preset equipment rated parameter library; calculating a first deviation rate between the real-time current value and the rated current threshold, and a second deviation rate between the real-time power value and the rated power threshold, and calculating an overload risk coefficient based on the first deviation rate, the second deviation rate and the continuous operation time; when the overload risk coefficient reaches a preset risk threshold, determining the corresponding real-time current value, real-time power value and continuous operation time as the basic fault critical characteristics of a single device; calculating the total load critical value based on the equipment association relationship, and combining the basic fault critical characteristics of each single device and the total load critical value to constitute the basic fault critical characteristics.

3. The intelligent reclosing circuit breaker control system according to claim 2, characterized in that: Based on the planned operation data and the prediction of random fluctuation characteristics, critical fluctuation characteristics are obtained, including: extracting the preset start and stop time, single operation time and load type association of each load device from the planned operation data, and constructing the equipment operation schedule within the target time period; extracting random fluctuation characteristics from the real-time operation data, including current fluctuation frequency, power fluctuation amplitude and fluctuation duration, and generating a fluctuation probability distribution model through statistical analysis; based on the equipment operation schedule, a load superposition algorithm is used to calculate the theoretical total load reference value at different times within the target time period, and the theoretical total load reference value is dynamically corrected in combination with the fluctuation probability distribution model to calculate the load fluctuation range under different confidence levels; based on the upper limit of the load fluctuation range under different confidence levels corresponding to the theoretical total load reference value at each time, critical fluctuation characteristics are obtained, including the periodic total current limit value, the power fluctuation safety threshold and the load superposition warning line for the coordinated operation of multiple devices.

4. The intelligent reclosing circuit breaker control system according to claim 3, characterized in that: Random fluctuation characteristics are extracted from the real-time operation data, including current fluctuation frequency, power fluctuation amplitude and fluctuation duration, and a fluctuation probability distribution model is generated through statistical analysis, including: intercepting current time series data and power time series data within a preset time window from the real-time operation data, and extracting characteristic values ​​of the dynamic fluctuation segment data therein, including current fluctuation frequency, power fluctuation amplitude, and fluctuation duration; collecting characteristic values ​​of at least a preset number of preset time windows to form a sample set, using the kernel density estimation method to perform probability density fitting on the current fluctuation frequency, power fluctuation amplitude, and fluctuation duration in the sample set, respectively, to generate respective marginal distribution models; and constructing a joint probability distribution model of the above three characteristic values ​​through a Copula function, and using it as the fluctuation probability distribution model.

5. The intelligent reclosing circuit breaker control system according to claim 4, characterized in that: The basic fault critical characteristics and critical fluctuation characteristics are integrated to obtain fault critical characteristic data for the target time period, including: setting a first weight coefficient of the basic fault critical characteristics based on the real-time requirements of the equipment, and setting a second weight coefficient of the critical fluctuation characteristics based on the complexity of the collaborative operation of multiple devices; normalizing the basic fault critical characteristics and the critical fluctuation characteristics, and using a weighted fusion algorithm to calculate the comprehensive fault critical index at each moment in the target time period, and generating the fault critical characteristic data based on the comprehensive fault critical index.

6. The intelligent reclosing circuit breaker control system according to claim 1, characterized in that: The operating characteristic data and the critical fault characteristic data are subjected to similarity analysis to determine whether the control conditions are met, including: mapping the operating characteristic data into a real-time characteristic vector, mapping the critical fault characteristic data into a critical characteristic vector, and using a similarity algorithm to calculate the similarity between the real-time characteristic vector and the critical characteristic vector; by comparing the similarity with a preset similarity interval, the overload risk level is determined, and when the overload risk level is higher than a level threshold, it is determined that the control conditions are met.

7. The intelligent reclosing circuit breaker control system according to claim 6, characterized in that: When the subsequent similarity analysis results do not meet the control conditions, a closing control instruction is sent to the circuit breaker, including: after the opening control instruction is sent and executed, starting a continuous monitoring cycle, re-collecting the circuit's operating characteristic data in each monitoring cycle, and mapping it into a new real-time characteristic vector; wherein the cycle length of the continuous monitoring cycle is determined comprehensively based on the opening reason, equipment type and load characteristics; calculating the similarity between the new real-time characteristic vector and the critical fault characteristic data to determine whether the control conditions are no longer met. If so, generating and sending a closing control instruction to the circuit breaker.

8. An electronic device, applied to the intelligent reclosing circuit breaker control system according to any one of claims 1 to 7, characterized in that: The electronic device includes at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

9. A computer storage medium, applied to the intelligent reclosing circuit breaker control system according to any one of claims 1 to 7, characterized in that: The computer storage medium stores a computer program that can be executed by a processor.

10. A computer program product, applied to the intelligent reclosing circuit breaker control system according to any one of claims 1 to 7, characterized in that: The computer program product comprises a computer program executable by a processor.

Images