Control method for intelligent miniature circuit breaker
By constructing an improved support vector machine and wireless communication technology, remote control and leakage protection of intelligent miniature circuit breakers were realized, solving the problems of insufficient intelligence and safety hazards of traditional circuit breakers, and improving the intelligence and security of circuit monitoring and management.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SHANGHAI HONGTAN INTELLIGENT TECHNOLOGY CO LTD
- Filing Date
- 2025-03-27
- Publication Date
- 2026-05-21
AI Technical Summary
Traditional circuit breakers lack intelligent functions, cannot monitor circuit status in real time, are difficult to control remotely, are difficult to troubleshoot, are inconvenient to manage, and have insufficient leakage protection, posing safety hazards.
By constructing an improved support vector machine, current, voltage, and temperature are monitored in real time. Data is transmitted to a remote server via wireless communication to achieve remote control. The circuit is cut off by a tripping mechanism. In conjunction with a leakage protection module, leakage current is monitored in real time. Communication is achieved using NB-IoT, ZigBee, or LoRa.
It enables remote and precise control of circuit breakers, improving safety and intelligence, reducing the risk of misjudgment and misoperation, and providing detailed power consumption reports and multiple alarm methods to ensure that users receive alarm information in a timely manner.
Smart Images
Figure CN2025085253_21052026_PF_FP_ABST
Abstract
Description
A control method for an intelligent miniature circuit breaker Technical Field
[0001] This application relates to the field of power equipment technology, specifically a control method for an intelligent miniature circuit breaker. Background Technology
[0002] Intelligent miniature circuit breakers are devices that integrate the protection functions of traditional circuit breakers with modern intelligent monitoring and management functions.
[0003] Traditional circuit breakers are primarily used for circuit protection, automatically disconnecting the circuit when the current exceeds the rated value to prevent equipment damage or fire. However, traditional circuit breakers have the following limitations:
[0004] (1) It lacks intelligent functions, cannot monitor the circuit status in real time, and cannot be remotely controlled;
[0005] (2) Troubleshooting is difficult, fault information cannot be recorded, and it is difficult to quickly locate the problem.
[0006] (3) Inconvenient to manage, requiring manual operation, and cannot achieve automated management;
[0007] (4) Insufficient leakage protection: Traditional circuit breakers usually do not have leakage protection function, which poses a safety hazard.
[0008] Therefore, this application proposes a control method for an intelligent miniature circuit breaker, which can effectively overcome the above problems, realize remote and precise control of the circuit breaker, and improve safety, intelligence and practicality. Summary of the Invention
[0009] (a) Technical problems to be solved
[0010] To address the shortcomings of existing technologies, this application provides a control method for an intelligent miniature circuit breaker.
[0011] (II) Technical Solution
[0012] To address the above problems, this application provides the following technical solution:
[0013] A control method for an intelligent miniature circuit breaker includes:
[0014] Obtain the operating parameters of the intelligent miniature circuit breaker and preprocess the operating parameters to obtain a dataset;
[0015] Construct an improved support vector machine;
[0016] The improved support vector machine is used to analyze the dataset, determine the current circuit state, and transmit the data analysis results to a remote server via wireless communication.
[0017] The circuit is cut off by the tripping mechanism.
[0018] Preferably, the step of acquiring the operating parameters of the intelligent miniature circuit breaker and preprocessing the operating parameters to obtain a dataset specifically includes:
[0019] The current in the circuit is monitored by a current transformer, the voltage in the circuit is monitored by a voltage transformer, and the temperature of the intelligent miniature circuit breaker is monitored by a temperature sensor.
[0020] Remove noisy data from the operating parameters, reduce random fluctuations through smoothing filtering, and standardize the operating parameters.
[0021] Preferably, the construction of the improved support vector machine specifically includes:
[0022] Each sample was assigned a category based on historical data; Category 1 was normal condition, Category 2 was overload, Category 3 was short circuit, Category 4 was leakage, and Category 5 was high temperature.
[0023] The radial basis function is determined as the kernel function; the data expression of the radial basis function is: K(x1,x2)=exp(-γ||x1-x2|| 2 (1)
[0024] In formula (1), x1 and x2 are input samples, K(x1,x2) is the kernel function value, which is used to measure the similarity between x1 and x2 in the high-dimensional feature space, γ is the hyperparameter of the kernel function, and γ>0;
[0025] For each category, train a Support Vector Machine (SVM) to form an improved support vector machine;
[0026] Train the improved support vector machine.
[0027] Preferably, for each category, a Support Vector Machine (SVM) is trained to form an improved support vector machine, specifically including:
[0028] Introducing an adaptive adjustment mechanism, the mathematical expression for updating weights based on predicted values is as follows:
[0029] In formula (2), w k1 Let w be the weight vector before the k-th SVM update. k2 Let be the weight vector after the k-th SVM update, and η be the factor controlling the update step size. Let λ be the gradient of the loss function with respect to the predicted values, and λ be the regularization parameter.
[0030] The decision function of the improved support vector machine is:
[0031] In formula (2), b k For the bias term, f k ρ(x) is the decision function value of the k-th SVM, used to determine the category of the input sample. ρ(x) is the feature mapping function, which maps the input sample from the original space to the high-dimensional feature space. x is the input sample.
[0032] Preferably, training the improved support vector machine specifically includes:
[0033] The dataset is divided into a 70% training set, a 15% validation set, and a 15% test set.
[0034] By combining grid search with cross-validation, the width of γ is adaptively adjusted to maximize the classification accuracy on the validation set.
[0035] The improved support vector machine is trained using the training set to obtain classifiers {f1(x),f2(x),f3(x),f4(x),f5(x)}, which correspond to "normal", "overload", "short circuit", "leakage" and "high temperature" respectively.
[0036] Preferably, the step of analyzing the dataset using the improved support vector machine to determine the current circuit state specifically includes:
[0037] The system receives sensor data in real time and inputs it into the improved support vector machine to calculate the score for each category. The mathematical expression for calculating the category by the improved support vector machine is as follows:
[0038] In formula (4), x' represents real-time input data;
[0039] The final prediction result is expressed as: y = argmaxf k (x′)(5)
[0040] In formula (5), y represents the output result;
[0041] When y = 1, the circuit remains operational;
[0042] When y = 2, an alarm signal is issued and the circuit is cut off according to the threshold.
[0043] When y = 3, immediately disconnect the circuit;
[0044] When y = 4, the circuit is immediately cut off and the leakage protection mechanism is triggered;
[0045] When y = 5, an alarm signal is issued and the circuit is cut off according to the threshold.
[0046] Preferably, the step of transmitting the data analysis results to a remote server via wireless communication specifically includes:
[0047] The operating parameters and data analysis results of the intelligent miniature circuit breaker are transmitted to the remote server via NB-IoT, ZigBee, or LoRa.
[0048] The operating parameters of the intelligent miniature circuit breaker are set to be transmitted to the remote server every minute.
[0049] A control method for an intelligent miniature circuit breaker further includes real-time monitoring of leakage current in the circuit via a leakage current protection module, specifically including:
[0050] The leakage current is monitored in real time by a zero-sequence current transformer; the collected leakage current signal is amplified by a differential amplifier and transmitted to the leakage protection chip; when the leakage protection chip reaches the threshold, it outputs a signal to the tripping mechanism.
[0051] A control device for an intelligent miniature circuit breaker includes:
[0052] A data preprocessing device is used to preprocess the acquired operating parameters of the intelligent miniature circuit breaker;
[0053] An improved support vector machine construction apparatus for constructing the improved support vector machine;
[0054] A data analysis device is used to perform data analysis on the dataset using the improved support vector machine and to determine the current circuit state;
[0055] A tripping device is used to cut off the circuit upon receiving a command from a data analysis device.
[0056] A smart miniature circuit breaker, the smart miniature circuit breaker further comprising a controller, wherein the control method of claim 1 is applied to the controller.
[0057] (III) Beneficial Effects
[0058] Compared with the prior art, this application provides a control method for an intelligent miniature circuit breaker, which has the following advantages:
[0059] 1. This intelligent miniature circuit breaker monitors the leakage current in the circuit in real time through a leakage protection chip, and quickly cuts off the power supply when an abnormality is detected, effectively preventing electrical fires and electric shock accidents.
[0060] 2. This intelligent miniature circuit breaker can be remotely monitored and operated through wired and wireless communication technologies;
[0061] 3. This intelligent miniature circuit breaker continuously collects circuit operation data through multiple built-in sensors and accurately identifies different types of fault states through an improved support vector machine model. It then takes appropriate protective measures based on the specific circumstances to reduce the risk of misjudgment and misoperation.
[0062] 4. This intelligent miniature circuit breaker automatically analyzes the collected data and generates detailed electricity consumption reports, which are sent to users on a regular basis. There is no need to manually record and analyze data, saving a lot of time and effort. It also ensures that users can receive alarm information in the first instance through multiple alarm methods and take timely measures.
[0063] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0064] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:
[0065] Figure 1 is a flowchart illustrating a control method for an intelligent miniature circuit breaker according to this application;
[0066] Figure 2 is a schematic diagram of a control method for an intelligent miniature circuit breaker according to this application;
[0067] Figure 3 is a circuit diagram of the leakage protection module in the control method of an intelligent miniature circuit breaker according to this application;
[0068] Figure 4 is a circuit diagram of the tripping module in the control method of an intelligent miniature circuit breaker according to this application;
[0069] Figure 5 is a circuit diagram of the communication module in the control method of an intelligent miniature circuit breaker according to this application. Detailed Implementation
[0070] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0071] The terms "first" and "second" in the specification and claims of this application may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise stated, "multiple" means two or more. Furthermore, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0072] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.
[0073] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0074] Please refer to Figures 1-5. This application provides a new technical solution: a control method for an intelligent miniature circuit breaker, comprising:
[0075] Obtain the operating parameters of the intelligent miniature circuit breaker and preprocess the operating parameters to obtain a dataset;
[0076] Construct an improved support vector machine;
[0077] The improved support vector machine is used to analyze the dataset, determine the current circuit state, and transmit the data analysis results to a remote server via wireless communication.
[0078] The circuit is cut off by the tripping mechanism.
[0079] In a specific embodiment, a control method for an intelligent miniature circuit breaker is based on the following modules:
[0080] The data acquisition module monitors the circuit's operating parameters in real time through sensor units;
[0081] The intelligent control module receives signals from the acquisition module, leakage protection module, and communication module, processes and analyzes the data through a microcontroller, and controls the tripping module.
[0082] The leakage protection module is used to collect leakage signals in the circuit in real time, perform data analysis, generate instructions, and transmit them to the tripping module.
[0083] The button module directly sends a trip command to the trip module;
[0084] The tripping module receives instructions from the intelligent control module, the leakage protection module, and the tripping module, and performs a physical disconnection operation to break the circuit.
[0085] The power module provides power to the intelligent miniature circuit breaker;
[0086] The communication module communicates with a remote server via wired and wireless communication, supporting remote monitoring and control.
[0087] The alarm module receives the alarm signal sent by the intelligent control module and issues an alarm.
[0088] The display module receives data information from the intelligent control module and displays the circuit status information on the display screen.
[0089] The output of the acquisition module is connected to the input of the intelligent control module. The output of the intelligent control module is connected to the input of the alarm module and the display module. The intelligent control module is bidirectionally connected to the communication module and the tripping module. The output of the button module is connected to the input of the tripping module. The output of the leakage current protection module is connected to the input of the tripping module and the output of the leakage current protection module is connected to the input of the intelligent control module.
[0090] In this invention, the step of acquiring the operating parameters of the intelligent miniature circuit breaker and preprocessing the operating parameters to obtain a dataset specifically includes:
[0091] The current in the circuit is monitored by a current transformer, the voltage in the circuit is monitored by a voltage transformer, and the temperature of the intelligent miniature circuit breaker is monitored by a temperature sensor.
[0092] Remove noisy data from the operating parameters, reduce random fluctuations through smoothing filtering, and standardize the operating parameters.
[0093] In this invention, the construction of the improved support vector machine specifically includes:
[0094] Each sample was assigned a category based on historical data; Category 1 was normal condition, Category 2 was overload, Category 3 was short circuit, Category 4 was leakage, and Category 5 was high temperature.
[0095] The radial basis function is determined as the kernel function; the data expression of the radial basis function is: K(x1,x2)=exp(-γ||x1-x2|| 2 (1)
[0096] In formula (1), x1 and x2 are input samples, K(x1,x2) is the kernel function value, which is used to measure the similarity between x1 and x2 in the high-dimensional feature space, γ is the hyperparameter of the kernel function, and γ>0;
[0097] For each category, train a Support Vector Machine (SVM) to form an improved support vector machine;
[0098] Train the improved support vector machine.
[0099] In this invention, training a Support Vector Machine (SVM) for each category to form an improved support vector machine specifically includes:
[0100] Introducing an adaptive adjustment mechanism, the mathematical expression for updating weights based on predicted values is as follows:
[0101] In formula (2), w k1 Let w be the weight vector before the k-th SVM update. k2 Let be the weight vector after the k-th SVM update, and η be the factor controlling the update step size. Let λ be the gradient of the loss function with respect to the predicted values, and λ be the regularization parameter.
[0102] The decision function of the improved support vector machine is:
[0103] In formula (2), b k For the bias term, f k ρ(x) is the decision function value of the k-th SVM, used to determine the category of the input sample. ρ(x) is the feature mapping function, which maps the input sample from the original space to the high-dimensional feature space. x is the input sample.
[0104] In this invention, training the improved support vector machine specifically includes:
[0105] The dataset is divided into a 70% training set, a 15% validation set, and a 15% test set.
[0106] By combining grid search with cross-validation, the width of γ is adaptively adjusted to maximize the classification accuracy on the validation set.
[0107] The improved support vector machine is trained using the training set to obtain classifiers {f1(x),f2(x),f3(x),f4(x),f5(x)}, which correspond to "normal", "overload", "short circuit", "leakage" and "high temperature" respectively.
[0108] In this invention, the step of analyzing the dataset using the improved support vector machine to determine the current circuit state specifically includes:
[0109] The system receives sensor data in real time and inputs it into the improved support vector machine to calculate the score for each category. The mathematical expression for calculating the category by the improved support vector machine is as follows:
[0110] In formula (4), x' represents real-time input data;
[0111] The final prediction result is expressed as: y = argmaxf k (x′)(5)
[0112] In formula (5), y represents the output result;
[0113] When y = 1, the circuit remains operational;
[0114] When y = 2, an alarm signal is issued and the circuit is cut off according to the threshold.
[0115] When y = 3, immediately disconnect the circuit;
[0116] When y = 4, the circuit is immediately cut off and the leakage protection mechanism is triggered;
[0117] When y = 5, an alarm signal is issued and the circuit is cut off according to the threshold.
[0118] In this invention, transmitting the data analysis results to a remote server via wireless communication specifically includes:
[0119] The operating parameters and data analysis results of the intelligent miniature circuit breaker are transmitted to the remote server via NB-IoT, ZigBee, or LoRa.
[0120] The operating parameters of the intelligent miniature circuit breaker are set to be transmitted to the remote server every minute.
[0121] A control method for an intelligent miniature circuit breaker further includes real-time monitoring of leakage current in the circuit via a leakage current protection module, specifically including:
[0122] The leakage current is monitored in real time by a zero-sequence current transformer; the collected leakage current signal is amplified by a differential amplifier and transmitted to the leakage protection chip; when the leakage protection chip reaches the threshold, it outputs a signal to the tripping mechanism.
[0123] A control device for an intelligent miniature circuit breaker includes:
[0124] A data preprocessing device is used to preprocess the acquired operating parameters of the intelligent miniature circuit breaker;
[0125] An improved support vector machine construction apparatus for constructing the improved support vector machine;
[0126] A data analysis device is used to perform data analysis on the dataset using the improved support vector machine and to determine the current circuit state;
[0127] A tripping device is used to cut off the circuit upon receiving a command from a data analysis device.
[0128] A smart miniature circuit breaker, the smart miniature circuit breaker further comprising a controller, wherein the control method of claim 1 is applied to the controller.
[0129] In a specific embodiment, the intelligent control module is connected to the communication module via pins RX and TX; the intelligent control module receives signals from the leakage protection module via pin P1.0; the intelligent control module receives signals from the current transformer via pin P1.1; the intelligent control module receives signals from the voltage transformer via pin P1.2; and the intelligent control module receives signals from the temperature sensor via pin P1.3.
[0130] In a specific embodiment, the intelligent control module receives signals from the acquisition module, the leakage protection module, and the communication module, analyzes and determines whether to cut off the circuit. When an abnormal situation occurs, the OUT pin of the intelligent control module outputs a high level to the input terminal of the tripping module.
[0131] In a specific embodiment, the leakage current protection module includes a zero-sequence current transformer J1, a differential amplifier U6, and a leakage current protection chip. The zero-sequence current transformer J1 is used to monitor leakage current in real time. The differential amplifier is used to amplify the collected leakage current signal and transmit the leakage current signal to the intelligent control module. The leakage current protection chip receives the leakage current signal, and its IN1 and IN2 pins are signal input terminals, while its OS pin is a signal output terminal. When the leakage current protection chip reaches a threshold, the OS pin outputs a high level to the tripping module.
[0132] In a specific embodiment, pin 1 of the zero-sequence current transformer J1 is connected to pin IN1 of the leakage current protection chip U2, and pin 2 of the zero-sequence current transformer J1 is connected to pin IN2 of the leakage current protection chip U2; pin 1 of the differential amplifier U6 is connected to pin 1 of the zero-sequence current transformer J1, and pin 2 of the differential amplifier U6 is connected to pin 2 of the zero-sequence current transformer J1.
[0133] In a specific embodiment, the differential amplifier U6, together with R6, R7, R8, R9, R10, C4, C5, and C6, forms a differential amplifier circuit. The leakage current signal transmitted from the zero-sequence transformer J1 is amplified by the voltage difference and then transmitted to pin P1.0 of the intelligent control module, with a reference voltage of 1.6V.
[0134] In a specific embodiment, the tripping module includes an input unit and an actuator; the input unit receives instructions from the intelligent control module, the leakage protection module, and the tripping module, filters them through a filtering network formed by C9 and R16, and transmits the instructions to the actuator OUT1.
[0135] In a specific embodiment, the pin OUT of the intelligent control module U1 is connected to the actuator OUT1, and the pin OS of the leakage protection chip U2 is connected to the actuator OUT1. Under normal circuit conditions, the button module S1 is connected to the actuator OUT1 through pin 1. When the circuit needs to be cut off, the button module S1 is placed at pin 2.
[0136] In a specific embodiment, the communication module includes a first communication unit and a second communication unit; the first communication unit is for wired communication, transmitting data through an RS-485 chip, with pin RO of the RS-485 chip connected to pin RX of the intelligent control module, and pin DI of the RS-485 chip connected to pin TX of the intelligent control module; the second communication unit is for wireless communication, transmitting data through a ZigBee chip, with pin TX of the ZigBee chip connected to pin RX of the intelligent control module, and pin RX of the ZigBee chip connected to pin TX of the intelligent control module.
[0137] In specific embodiments, the Zigbee communication can be replaced by LoRa, NB-IoT, or 4G / 5G cellular network communication.
[0138] In a specific embodiment, the display module includes a display controller and a display screen; the display controller is an HD44780, and the display screen is an LCD1602.
[0139] In a specific embodiment, the alarm includes a first alarm unit and a second alarm unit; the first alarm unit receives the signal from the intelligent control module and provides an audible and visual alarm through a buzzer and LED indicator; the second alarm unit receives the data report from the intelligent control module and sends alarm information to the user through a communication module.
[0140] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0141] Although embodiments of this application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A control method of an intelligent miniature circuit breaker, characterized by, include: Obtain the operating parameters of the intelligent miniature circuit breaker and preprocess the operating parameters to obtain a dataset; Construct an improved support vector machine; The improved support vector machine is used to analyze the dataset, determine the current circuit state, and transmit the data analysis results to a remote server via wireless communication. The circuit is cut off by the tripping mechanism.
2. The control method of claim 1, wherein, The process of acquiring the operating parameters of the intelligent miniature circuit breaker and preprocessing these parameters to obtain a dataset specifically includes: The current in the circuit is monitored by a current transformer, the voltage in the circuit is monitored by a voltage transformer, and the temperature of the intelligent miniature circuit breaker is monitored by a temperature sensor. Remove noisy data from the operating parameters, reduce random fluctuations through smoothing filtering, and standardize the operating parameters.
3. The control method of claim 1, wherein, The construction of the improved support vector machine specifically includes: Each sample was assigned a category based on historical data; Category 1 was normal condition, Category 2 was overload, Category 3 was short circuit, Category 4 was leakage, and Category 5 was high temperature. The radial basis function is determined as the kernel function; the data expression of the radial basis function is: K(x1,x2) = exp(-γ||x1-x2||2) (1) 2 ) (1) In formula (1), x1 and x2 are input samples, K(x1,x2) is the kernel function value, which is used to measure the similarity between x1 and x2 in the high-dimensional feature space, γ is the hyperparameter of the kernel function, and γ>0; For each category, train a Support Vector Machine (SVM) to form an improved support vector machine; Train the improved support vector machine.
4. The control method of claim 3, wherein, For each category, a Support Vector Machine (SVM) is trained to form an improved support vector machine, specifically including: The adaptive adjustment mechanism is introduced, and the mathematical expression for updating the weight according to the predicted value is: In Equation (2), w k1 is the weight vector of the kth SVM before updating, w k2 is the weight vector of the kth SVM after updating, and η is a control update step factor, Let λ be the gradient of the loss function with respect to the predicted values, and λ be the regularization parameter. The decision function of the improved support vector machine is: In formula (2), b k is a bias term, f k (x) is a decision function value of the kth SVM, used to determine the class to which the input sample belongs, p(x) is a feature mapping function that maps the input sample from the original space to the high-dimensional feature space, and x is the input sample.
5. The control method of claim 3, wherein, The training of the improved support vector machine specifically includes: The dataset is divided into a 70% training set, a 15% validation set, and a 15% test set. By combining grid search with cross-validation, the width of γ is adaptively adjusted to maximize the classification accuracy on the validation set. The improved support vector machine is trained using the training set to obtain classifiers {f1(x),f2(x),f3(x),f4(x),f5(x)}, which correspond to "normal", "overload", "short circuit", "leakage" and "high temperature" respectively.
6. The control method of claim 1, wherein, The step of analyzing the dataset using the improved support vector machine to determine the current circuit state specifically includes: receiving data of the sensors in real time, and inputting the sensor data into the improved support vector machine, calculating the score of each category, and the mathematical expression of the category calculated by the improved support vector machine is: In formula (4), x' represents real-time input data; The expression for the final prediction result is: y = arg maxf k (x') (5) In formula (5), y represents the output result; When y = 1, the circuit remains operational; When y = 2, an alarm signal is issued and the circuit is cut off according to the threshold. When y = 3, immediately disconnect the circuit; When y = 4, the circuit is immediately cut off and the leakage protection mechanism is triggered; When y = 5, an alarm signal is issued and the circuit is cut off according to the threshold.
7. The control method of claim 1, wherein, The step of transmitting the data analysis results to a remote server via wireless communication specifically includes: The operating parameters and data analysis results of the intelligent miniature circuit breaker are transmitted to the remote server via NB-IoT, ZigBee, or LoRa. The operating parameters of the intelligent miniature circuit breaker are set to be transmitted to the remote server every minute.
8. The control method of claim 1, wherein, It also includes real-time monitoring of leakage current in the circuit through a leakage current protection module, specifically including: The leakage current is monitored in real time by a zero-sequence current transformer; the collected leakage current signal is amplified by a differential amplifier and transmitted to the leakage protection chip; when the leakage protection chip reaches the threshold, it outputs a signal to the tripping mechanism.
9. A control device for an intelligent miniature circuit breaker, characterized in that include: A data preprocessing device is used to preprocess the acquired operating parameters of the intelligent miniature circuit breaker; An improved support vector machine construction apparatus for constructing the improved support vector machine; A data analysis device is used to perform data analysis on the dataset using the improved support vector machine and to determine the current circuit state; A tripping device is used to cut off the circuit upon receiving a command from a data analysis device.
10. An intelligent miniature circuit breaker, characterized by The intelligent miniature circuit breaker also includes a controller, and the control method as described in claim 1 is applied to the controller.