Intelligent circuit breaker system based on fuzzy control theory

Abstract

The invention discloses an intelligent circuit breaker system based on a fuzzy control theory. In the intelligent circuit breaker, current changes are monitored in real time through a fuzzy controller, an input variable is converted into an input fuzzy quantity for expression according to a membership function, fuzzy reasoning is carried out on the converted input fuzzy quantity according to a preset fuzzy rule base to obtain an output fuzzy quantity, and finally the output fuzzy quantity is defuzzified. And a final circuit breaker action instruction is obtained. The method has the beneficial effects that the safety stability and the response flexibility of the system are improved, and the protection strategy is dynamically adjusted, so that various complex power failure scenes can be more flexibly and efficiently handled.

Description

Technical Field

[0001] The present invention relates to the technical field related to miniature circuit breakers, and in particular to an intelligent circuit breaker system based on fuzzy control theory. Background Art

[0002] In power and communication infrastructure, circuit breakers serve as key protective barriers for computer rooms, communication cabinets, and user lines, and they bear the important responsibilities of isolation, short circuit, and overload protection. However, the operating characteristics of traditional communication or power DC power systems are complex and changeable, and their power consumption levels often fluctuate with business configuration adjustments, resulting in significant differences between actual power consumption and initial planning. When faced with this uncertainty, operation and maintenance personnel lack effective real-time monitoring and evaluation methods, making it difficult to accurately grasp the actual power supply needs of the power system, which in turn increases the risk of power overload, equipment failure, and even communication network interruption.

[0003] In response to the above challenges, intelligent miniature circuit breakers have emerged in recent years. This type of circuit breaker can automatically adjust the operating status and power output according to the load size set by the user, realizing the refinement and intelligence of energy management. By integrating real-time monitoring and fault diagnosis functions of voltage and current, intelligent circuit breakers can quickly identify and handle equipment failures or abnormal conditions, significantly improving system reliability. However, due to the high uncertainty of the previous load characteristics, the actual overload or short-circuit current varies significantly, and the traditional time-limited or inverse-time-limited tripping mechanism based on the rated current can no longer meet the needs of fast and accurate fault protection. Summary of the invention

[0004] The present invention aims to overcome the above-mentioned deficiencies in the prior art and provides an intelligent circuit breaker system based on fuzzy control theory that can improve safety stability and response flexibility.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An intelligent circuit breaker system based on fuzzy control theory. In the intelligent circuit breaker, the fuzzy controller monitors the current change in real time, converts the input variable into an input fuzzy quantity according to the membership function, performs fuzzy reasoning on the converted input fuzzy quantity according to the preset fuzzy rule library to obtain the output fuzzy quantity, and finally defuzzifies the output fuzzy quantity to obtain the final circuit breaker action instruction. The specific implementation is as follows:

[0007] (1) The input current change value is first fuzzified by the fuzzy controller, and the precise input variable is converted into an input fuzzy quantity represented by a fuzzy set according to the membership function;

[0008] (2) According to the preset fuzzy rule base, the fuzzy control rules are stored, and fuzzy reasoning is performed on the converted input fuzzy quantity to obtain the total fuzzy relationship of the system; the final output fuzzy quantity can be obtained by performing matrix merging operation on the input at different times and the total fuzzy relationship, and the fuzzy judgment result of whether there is overload or short circuit can be obtained;

[0009] (3) Defuzzify the output fuzzy quantity and convert the fuzzy judgment result into an accurate switch control signal to trigger or inhibit the protection action of the circuit breaker.

[0010] This method proposes to introduce fuzzy control theory into the design of intelligent circuit breakers, aiming to analyze real-time current data through intelligent algorithms, monitor the load current change rate in real time, intelligently identify fault current characteristics, and quickly perform fault isolation operations, in order to improve the safety stability and response flexibility of the system, dynamically adjust the protection strategy, and respond to various complex power fault scenarios more flexibly and efficiently.

[0011] Preferably, the fuzzy controller is composed of the following parts: a fuzzification interface, which converts precise input variables into fuzzy quantities represented by fuzzy sets; a fuzzy rule base, which stores fuzzy control rules and is used to perform fuzzy reasoning based on the input fuzzy quantities; a fuzzy inference engine, which performs fuzzy reasoning based on the rules in the fuzzy rule base and the input fuzzy quantities to obtain output fuzzy quantities; and a defuzzification interface, which converts the output fuzzy quantities into precise output variables to drive the controlled object.

[0012] Preferably, in step (1), in the intelligent circuit breaker system, assuming that the current at the previous moment is I(t0) and the real-time current is I(t1), the calculation formula of the real-time current change rate Ki is as follows:

[0013] (1) If I(t1)>=In:

[0014] Ki=I(t1) / In

[0015] Among them, In represents the rated current value; at this time, the basic domain of Ki can be divided into six parts according to relevant standards: (-∞,-1.3], (-1.3,-1.1], (-1.1,0), [0,1.1), [1.1,1.3), [1.3,+∞);

[0016] (2) When I(t1)∈(-∞,+∞) and I(t0) is not 0:

[0017] Ki=△I / I(t0)=(I(t1)-I(t0)) / I(t0)

[0018] At this point, after repeated experiments and past experience, the basic domain of Ki can be divided into six parts: (-∞,-10], (-10,-5], (-5,0), [0,5), [5,10), [10,+∞);

[0019] The fuzzy subset of the input current change rate Ki is taken as: {NL, NN, NS, PS, PN, PL}; the fuzzy subset of the output circuit breaker action instruction is: {ON, WT, IT}; the elements in the fuzzy subset are all fuzzy linguistic variables, and the fuzzy subsets of the input current change rate Ki represent large negative, medium negative, small negative, small positive, medium positive, and large positive respectively; the fuzzy subsets of the output circuit breaker action instruction represent closing, tripping after waiting, and immediate tripping respectively.

[0020] Preferably, in step (2), in order to describe the fuzziness of the real-time current change rate Ki, it is necessary to create membership functions for the input current change rate Ki and the output circuit breaker action instruction respectively. Here, a triangular membership function is selected; the fuzzy rule defines the fuzzy relationship between the input current change rate Ki and the output circuit breaker action instruction. In the intelligent circuit breaker system, according to experimental data and past experience, the corresponding fuzzy control rule base can be obtained:

[0021]

[0022] Through the "AND" operation of the above 36 fuzzy relations, the total fuzzy relationship of the system can be obtained; the final fuzzy output can be obtained by matrix merging the input at different times with the total fuzzy relationship, and the fuzzy judgment result of whether there is an overload or short circuit can be obtained.

[0023] Preferably, in step (3), defuzzification is the process of converting the fuzzy output into a precise control quantity. In the intelligent circuit breaker system, the area centroid method is selected as the defuzzification method, and the fuzzy judgment result is converted into a precise switch control signal to trigger or inhibit the protection action of the circuit breaker.

[0024] The beneficial effects of the present invention are: improving the safety stability and response flexibility of the system, dynamically adjusting the protection strategy, so as to respond to various complex power failure scenarios more flexibly and efficiently; by reducing the dependence on external manual intervention and complex parameter configuration, the circuit breaker not only simplifies the operation and maintenance process, but also significantly reduces labor costs and the risk of human errors, providing strong support for the intelligent management of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is the triangular membership function graph of the input variable Ki-In;

[0026] Figure 2 It is the triangular membership function graph of input variable Ki-It;

[0027] Figure 3 is the triangular membership function diagram of the output variable circuit breaker action;

[0028] Figure 4 This is the editing interface diagram of fuzzy inference rules in the rule editor of MATLAB;

[0029] Figure 5 It is a visualization diagram of fuzzy inference rules;

[0030] Figure 6 It is a three-dimensional diagram of the fuzzy reasoning result of the circuit breaker action instruction;

[0031] Figure 7 It is the tripping curve diagram of the circuit breaker automatically breaking;

[0032] Figure 8 It is the tripping curve (fitting) diagram after the circuit breaker is automatically disconnected and optimized;

[0033] Fig. 9 This is the hardware structure diagram of the intelligent circuit breaker. DETAILED DESCRIPTION

[0034] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0035] Intelligent circuit breakers are generally composed of control panels, sampling components, contact systems, arc extinguishing systems, operating mechanisms, trip devices, housings, etc. Fig. 9 It is the hardware structure of the intelligent circuit breaker.

[0036] The current intelligent circuit breakers mainly have functions such as thermal magnetic protection, automatic disconnection (motor control), manual disconnection, disconnection status detection, voltage detection, current detection, power, electricity metering, internal temperature detection, and RS485 communication.

[0037] As a hardware protection method, thermal magnetic protection combines thermal protection and magnetic protection mechanisms, and can simultaneously deal with overload and short-circuit circuit faults. The thermal protection mechanism provides overload protection. When overloaded, the current passes through the bimetallic strip in the thermal protector. The bimetallic strip is composed of two or more metals or alloys with different expansion coefficients. The greater the current and the higher the temperature, the faster the deformation and the greater the degree of deformation. When the bimetallic strip deforms to a certain extent, it will drive the mechanism to trip the circuit breaker and cut off the circuit. The magnetic protector is used to detect the short circuit of the circuit. When a large instantaneous current appears in the circuit, the large current will generate a magnetic field. This magnetic field will overcome the reaction spring in the magnetic protector, and the release will pull the operating mechanism to cause the circuit breaker to trip quickly, cut off the circuit, and protect the equipment and cables from damage by the short-circuit current. However, thermal magnetic protection is limited by the rated current value of the hardware design. The minimum tripping current of magnetic protection is generally more than 3 to 5 times the rated current, and thermal protection generally needs to last for a period of time before it can trip. Therefore, this method can only play a good protection effect when the current is large.

[0038] Automatic disconnection is a software protection method. It controls the on and off of the electronic circuit according to the collected fault current value and the preset time limit or inverse time limit curve. The specific curve is as follows: Figure 7 As shown. Figure 7 It can be seen that when the current value is greater than 2.55 times the rated current value In (hereinafter referred to as In to represent the rated current value) (normal impact current size), the response time of the circuit breaker is still 1 to 60 seconds (In≤32A) or 1 to 120 seconds (In>32A). The closer the current value is to the upper limit of the current circuit breaker judgment range, the faster the response time is (for example, the response time of a type B circuit breaker is 0.01 seconds when the current value is 5In and above).

[0039] The response speed, accuracy and flexibility of the above two methods cannot meet the needs of rapid disconnection when the current is small. In view of this, the introduction of fuzzy control theory can intelligently analyze the change value of the current within a certain period of time to determine whether there is a short circuit, which can achieve faster and more accurate fault identification and protection response; and can adapt to various types of loads to enhance the flexibility and reliability of the system.

[0040] Users have the ability to activate or disable this protection strategy through advanced configuration options.

[0041] In the disabled state, the system defaults to the above-mentioned traditional protection mechanism, which relies on thermal-magnetic protection and automatic disconnection. Based on the proportional relationship between the real-time current and the preset rated current, it intelligently evaluates whether to trigger the circuit breaker disconnection operation to achieve effective protection of the circuit.

[0042] When the user chooses to enable the optimization solution, the system switches to a more sensitive protection logic, which monitors and analyzes the real-time current change rate based on the stabilized load current value, accurately determines whether the switch needs to be disconnected quickly, and achieves efficient protection of the load equipment. When the system needs to integrate a new load, the user only needs to follow the standardized operating process, that is, first safely disconnect the corresponding switch, then connect the new load to the system, and reserve enough time to ensure that the load status is stable. After this process is completed, the system can automatically detect and identify the newly connected load, and then automatically load and adapt the corresponding new load parameter values. The user does not need to perform tedious manual configuration adjustments throughout the process, which greatly improves the convenience and efficiency of system integration.

[0043] Specifically, the real-time current change rate is monitored and analyzed in the following manner to infer the final circuit breaker action instruction, wherein the tripping curve (fitting) after the circuit breaker is automatically disconnected and optimized is shown in the figure: Figure 8 shown.

[0044] An intelligent circuit breaker system based on fuzzy control theory. In the intelligent circuit breaker, a fuzzy controller is used to monitor the change of current in real time. The input variable is converted into an input fuzzy quantity representation according to a membership function. The converted input fuzzy quantity is fuzzy inferred according to a preset fuzzy rule library to obtain an output fuzzy quantity. Finally, the output fuzzy quantity is defuzzified to obtain the final circuit breaker action instruction.

[0045] Among them, fuzzy control theory allows the system to be effectively controlled based on the experience and intuition of human experts in an environment with high uncertainty and ambiguity. The design of the fuzzy controller is the key to achieve fuzzy control. The fuzzy controller consists of the following parts:

[0046] Fuzzification interface, which converts precise input variables into fuzzy quantities represented by fuzzy sets;

[0047] A fuzzy rule base stores fuzzy control rules and is used to perform fuzzy reasoning based on input fuzzy quantities;

[0048] The fuzzy inference engine performs fuzzy inference according to the rules in the fuzzy rule base and the input fuzzy quantity to obtain the output fuzzy quantity;

[0049] The defuzzification interface converts the output fuzzy quantity into an accurate output variable to drive the controlled object.

[0050] The specific implementation is as follows:

[0051] (1) Since the analog quantity actually sampled at a certain moment cannot be directly used for fuzzy decision-making, the input current change value is first fuzzified through the fuzzy controller, and the precise input variable is converted into an input fuzzy quantity represented by a fuzzy set according to the membership function.

[0052] In the intelligent circuit breaker system, after the load is stable, the current at the previous moment is I(t0) and the real-time current is I(t1), then the calculation formula of the real-time current change rate Ki is as follows:

[0053] (1) If I(t1)>=In:

[0054] Ki=I(t1) / In

[0055] Among them, In represents the rated current value; at this time, the basic domain of Ki can be divided into six parts according to relevant standards: (-∞,-1.3], (-1.3,-1.1], (-1.1,0), [0,1.1), [1.1,1.3), [1.3,+∞);

[0056] (2) When I(t1)∈(-∞,+∞) and I(t0) is not 0:

[0057] Ki=△I / I(t0)=(I(t1)-I(t0)) / I(t0)

[0058] At this time, after repeated experiments and past experience, the basic domain of Ki can be divided into six parts: (-∞,-10], (-10,-5], (-5,0), [0,5), [5,10), [10,+∞) (the value range of the domain varies depending on the system).

[0059] The explanation of the domain division is as follows: According to the relationship between the real-time current and the rated current, it can be divided into the following two cases for discussion:

[0060] (a) When the real-time current is greater than the rated current, the current is relatively large. Considering the device performance and relevant standards, the rated current should be used as the standard to divide the domain. When the short-circuit protection device is a circuit breaker that complies with the GB / T10963.1 standard, the short-circuit current at the end of the protected line should not be less than 1.1 times the upper limit of the instantaneous protection action current of the circuit breaker. According to the provisions of GB / T14048.2, when the current rises to 1.3 times the current setting value, that is, it reaches the agreed tripping current, the circuit breaker should trip within a time less than the agreed time specified by the latter. Therefore, the domain of (1) is divided into the above intervals.

[0061] (b) When the real-time current is less than the rated current, the current is small and does not exceed the device performance range. Therefore, based on past experience, the domain can be divided according to the current change rate as the standard. Among them, the general overload current growth rate is 5 to 10 times, and the short-circuit current growth rate is more than 10 times. Therefore, the domain of (2) is divided into the above intervals.

[0062] The fuzzy subset of the input current change rate Ki is taken as: {NL, NN, NS, PS, PN, PL}; the fuzzy subset of the output circuit breaker action instruction is: {ON, WT, IT}; the elements in the fuzzy subset are all fuzzy linguistic variables, and the fuzzy subsets of the input current change rate Ki represent large negative, medium negative, small negative, small positive, medium positive, and large positive respectively; the fuzzy subsets of the output circuit breaker action instruction represent closing, tripping after waiting, and immediate tripping respectively.

[0063] Explanation of the fuzzy subset of the input current change rate Ki: When making logical judgments, the domains of the above two judgment methods can be normalized into negative large change rate (Negative large, NL. Corresponding to (-∞, -1.3] and (-∞, -10]), negative normal change rate (Negative normal, NN. Corresponding to (-1.3, -1.1] and (-10, -5]), negative small change rate (Negative small, NS. Corresponding to (-1.1, 0) and (-5, 0)), positive small change rate (Positive small, PS. Corresponding to [0, 1.1) and [0, 5)), positive normal (PN. Corresponding to [1.1, 1.3) and [5, 10)), and positive large (PL. Corresponding to [1.3, +∞) and [10, +∞)).

[0064] In order to describe the fuzziness of the real-time current change rate Ki, it is necessary to create membership functions for the input current change rate Ki and the output circuit breaker action command respectively. Here, the triangular membership function is selected;

[0065] Since circuit breaker control involves the safety of equipment and personnel, it is necessary to accurately identify fault currents and respond quickly. Therefore, the triangular membership function with high sensitivity, fast calculation speed and strong adaptability in the fuzzy logic control system is selected. In MATLAB, after creating a fuzzy inference system, when adding the domain of fuzzy input variables according to the above fuzzy subset, select its type as "trimf" to draw the corresponding triangular membership function diagram.

[0066] The triangular membership function of the input current change rate Ki is as follows: Figure 1 , Figure 2 As shown;

[0067] The triangular membership function of the output circuit breaker action command is as follows: Figure 3 shown.

[0068] (2) According to the preset fuzzy rule base, the fuzzy control rules are stored, and fuzzy reasoning is performed on the converted input fuzzy quantity to obtain the total fuzzy relationship of the system; the final output fuzzy quantity can be obtained by performing matrix merging operation on the input at different times and the total fuzzy relationship, and the fuzzy judgment result of whether there is overload or short circuit can be obtained;

[0069] The fuzzy rule base is the core of the fuzzy controller. The fuzzy rules define the fuzzy relationship between the input current change rate Ki and the output circuit breaker action command. In the intelligent circuit breaker system, based on experimental data and past experience, the corresponding fuzzy control rule base can be obtained:

[0070]

[0071] According to the above fuzzy control rules, corresponding conditional statements can be added in the MATLAB rule editor, such as Figure 4 shown.

[0072] There are 36 fuzzy conditional statements in total. After adding them, the fuzzy conditions can be visualized as Figure 5 As shown in the figure. Each fuzzy conditional statement determines a fuzzy relationship. Through the "and" operation of 36 fuzzy relationships, the total fuzzy relationship of the system can be obtained. The final output fuzzy quantity can be obtained by performing matrix merging operation on the input at different times and the total fuzzy relationship, and the fuzzy judgment result of whether there is overload or short circuit can be obtained.

[0073] Among them, the "and" operation is to combine the membership of two fuzzy relations by taking the greater operation, thereby obtaining a new fuzzy relation. This method embodies the concept of "fuzzy OR" in fuzzy set theory, that is, as long as one of the two fuzzy conditions is met, the result can be considered to be established, but the degree of establishment (i.e., membership) is the larger of the two. In practical applications, if all relevant parameters have been input and given, MATLAB's fuzzy reasoning system can automatically calculate without the need for users to make inferences themselves.

[0074] (3) Defuzzify the output fuzzy quantity and convert the fuzzy judgment result into an accurate switch control signal to trigger or inhibit the protection action of the circuit breaker.

[0075] Defuzzification is the process of converting fuzzy output into precise control quantity. In the intelligent circuit breaker system, the area centroid method is selected as the defuzzification method, which takes into account the information of all fuzzy subsets and does not require the precise value to be determined in advance. After the fuzzy judgment result is converted into a precise switch control signal, the protection action of the circuit breaker is triggered or inhibited. Figure 6 This is the fuzzy reasoning output diagram of the circuit breaker action instruction.

[0076] Among them, the area centroid method (also called the centroid method) is a commonly used defuzzification (or clarification) method in fuzzy control. It is used to convert the result of fuzzy reasoning into a clear control quantity. Specifically, the area centroid method takes the centroid of the area enclosed by the membership function curve of the output fuzzy set and its corresponding horizontal coordinate (i.e., the possible value of the control quantity) as the final output control quantity. This method calculates the area under the membership function curve and finds the centroid position of this area to obtain an accurate value as the control quantity. It has the advantages of more comprehensive information, stronger adaptability, and better control performance. Therefore, in situations where precise control is required and the system characteristics are complex and changeable, the area centroid method is generally used as the defuzzification method.

[0077] In order to systematically evaluate the performance of intelligent circuit breakers with integrated fuzzy control technology, a circuit breaker with a rated current specification of 64A was selected as the test object. Its rated current setting value was precisely matched to 64A, and the preset delay disconnection time was 120 seconds, so that it can perform load protection according to the real-time current change rate. During the experiment, a constant load current of 5A was first connected to the circuit breaker for 30 seconds to ensure that the system reached a stable state. Subsequently, in order to fully simulate the overload and short-circuit scenarios in actual operation, each fault condition was independently simulated 10 times, and the experimental data was displayed in the form of a chart by accurately recording and calculating the average value of the disconnection time, as shown in the attached table.

[0078]

[0079] The experimental results significantly reveal the superior performance of the adaptive circuit breaker based on the fuzzy control principle. The circuit breaker exhibits strong adaptive capabilities, and can automatically optimize the protection strategy and parameter settings according to the dynamic changes of load characteristics, realizing the intelligent upgrade of the protection mechanism. More importantly, its built-in fuzzy control logic, as the core of software integration, gives the circuit breaker the ability to respond extremely quickly to emergency conditions such as short circuits and overloads, effectively ensuring the safety boundaries and stable operation of the power network. In addition, by reducing dependence on external manual intervention and complex parameter configuration, the circuit breaker not only simplifies the operation and maintenance process, but also significantly reduces labor costs and the risk of human errors, providing strong support for the intelligent management of power systems.

Claims

1. An intelligent circuit breaker system based on fuzzy control theory, characterized in that: In the intelligent circuit breaker, the fuzzy controller monitors the current change in real time, converts the input variable into input fuzzy quantity representation according to the membership function, performs fuzzy reasoning on the converted input fuzzy quantity according to the preset fuzzy rule library to obtain the output fuzzy quantity, and finally defuzzifies the output fuzzy quantity to obtain the final circuit breaker action instruction; the specific implementation is as follows: (1) The input current change value is first fuzzified by the fuzzy controller, and the precise input variable is converted into an input fuzzy quantity represented by a fuzzy set according to the membership function; (2) According to the preset fuzzy rule base, the fuzzy control rules are stored, and fuzzy reasoning is performed on the converted input fuzzy quantity to obtain the total fuzzy relationship of the system; the final output fuzzy quantity can be obtained by performing matrix merging operation on the input at different times and the total fuzzy relationship, and the fuzzy judgment result of whether there is overload or short circuit can be obtained; (3) Defuzzify the output fuzzy quantity and convert the fuzzy judgment result into an accurate switch control signal to trigger or inhibit the protection action of the circuit breaker.

2. According to claim 1, the intelligent circuit breaker system based on fuzzy control theory is characterized in that: The fuzzy controller is composed of the following parts: a fuzzification interface, which converts precise input variables into fuzzy quantities represented by fuzzy sets; a fuzzy rule base, which stores fuzzy control rules and is used to perform fuzzy reasoning based on the input fuzzy quantities; a fuzzy inference engine, which performs fuzzy reasoning based on the rules in the fuzzy rule base and the input fuzzy quantities to obtain output fuzzy quantities; and a defuzzification interface, which converts the output fuzzy quantities into precise output variables to drive the controlled object.

3. An intelligent circuit breaker system based on fuzzy control theory according to claim 1 or 2, characterized in that: In step (1), in the intelligent circuit breaker system, assuming that the current at the previous moment is I(t0) and the real-time current is I(t1), the calculation formula of the real-time current change rate Ki is as follows: (1) If I(t1)>=In: Ki=I(t1) / In Among them, In represents the rated current value; at this time, the basic domain of Ki can be divided into six parts according to relevant standards: (-∞,-1.3], (-1.3,-1.1], (-1.1,0), [0,1.1), [1.1,1.3), [1.3,+∞); (2) When I(t1)∈(-∞,+∞) and I(t0) is not 0: Ki=△I / I(t0)=(I(t1)-I(t0)) / I(t0) At this time, after repeated experiments and past experience, the basic domain of Ki can be divided into six parts: (-∞,-10], (-10,-5]、(-5,0)、[0,5)、[5,10)、[10,+∞)； The fuzzy subset of the input current change rate Ki is taken as: {NL, NN, NS, PS, PN, PL}; the fuzzy subset of the output circuit breaker action instruction is: {ON, WT, IT}; the elements in the fuzzy subset are all fuzzy linguistic variables, and the fuzzy subsets of the input current change rate Ki represent large negative, medium negative, small negative, small positive, medium positive, and large positive respectively; the fuzzy subsets of the output circuit breaker action instruction represent closing, tripping after waiting, and immediate tripping respectively.

4. The intelligent circuit breaker system based on fuzzy control theory according to claim 3 is characterized in that: In step (2), in order to describe the fuzziness of the real-time current change rate Ki, it is necessary to create membership functions for the input current change rate Ki and the output circuit breaker action command respectively. Here, the triangular membership function is selected; the fuzzy rule defines the fuzzy relationship between the input current change rate Ki and the output circuit breaker action command. In the intelligent circuit breaker system, based on experimental data and past experience, the corresponding fuzzy control rule base can be obtained: Through the "AND" operation of the above 36 fuzzy relations, the total fuzzy relation of the system can be obtained; the final fuzzy output can be obtained by matrix merging the input at different times with the total fuzzy relation, and the fuzzy judgment result of whether there is an overload or short circuit can be obtained.

5. The intelligent circuit breaker system based on fuzzy control theory according to claim 4 is characterized in that In step (3), defuzzification is the process of converting fuzzy output into precise control quantity. In the intelligent circuit breaker system, the area centroid method is selected as the defuzzification method. After the fuzzy judgment result is converted into a precise switch control signal, the protection action of the circuit breaker is triggered or inhibited.

Images