Intelligent low-voltage power distribution cabinet power distribution control system

Abstract

The application discloses a kind of intelligent low-voltage power distribution cabinet power distribution control systems, including data acquisition module, pre-processing module, low-voltage power distribution cabinet fault monitoring model establishment module, parameter optimization module and power distribution control module.The application belongs to the field of power distribution control, specifically refers to a kind of intelligent low-voltage power distribution cabinet power distribution control system, the scheme is handled by introducing lag attenuation coefficient to power distribution cabinet characteristic vector, reduce the interference of noise to subsequent analysis, shorten the lag of system to mutation, it is conducive to timely discovering potential fault;Introduce time memory factor to design power distribution shield loss function, avoid frequent control caused by small amplitude jitter of voltage, current, improve power supply reliability;Restrict continuously abnormal situation, and then improve the control accuracy of low-voltage power distribution cabinet;By optimizing artificial fish swarm algorithm, dynamically adjust parameter, accelerate local convergence;Fish school behavior is combined with reverse learning, and then improve the control efficiency of low-voltage power distribution cabinet.

Description

Technical Field

[0001] The present invention relates to the field of power distribution control, and in particular to an intelligent low-voltage power distribution cabinet power distribution control system. Background Art

[0002] Low-voltage distribution cabinet (LVDC) control systems are a crucial component of power systems, ensuring stable, safe, and efficient low-voltage power supply. They are primarily used to distribute, control, and protect electrical energy, and are widely used in industrial, commercial, and residential applications. However, typical LVDC control systems are sensitive to sensor noise, transient spikes, and subtle jitter caused by switching, leading to false alarms or frequent triggering of protection actions, and an inability to quickly respond to sudden changes. Furthermore, LVDC control systems often suffer from improper parameter settings and a lack of directional parameter adjustment, making them prone to local optimality and, in turn, leading to low LVDC control efficiency. Summary of the Invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent low-voltage distribution cabinet distribution control system. In view of the problem that the general low-voltage distribution cabinet control system is sensitive to sensor noise, transient spikes and slight jitters caused by switch actions, resulting in false alarms or frequent triggering of protection actions, and unable to respond quickly to sudden changes, this solution introduces a hysteresis attenuation coefficient to perform kernel smoothing on the distribution cabinet feature vector, which can erase small noise and reduce the interference of noise on subsequent analysis without excessively passivating normal fluctuations, retaining important information on the operating status of the distribution cabinet, shortening the system's lag in response to sudden changes, and being able to respond to these sudden changes more promptly, which is conducive to timely detection of potential faults; introducing a time memory factor to design the distribution shield loss function to avoid voltage , small jitters in current trigger frequent control, reduce the frequent tripping and closing of circuit breakers and switches in the cabinet, and improve power supply reliability; constrain continuous abnormal situations, increase sensitivity to faults, and thus improve the control accuracy of low-voltage distribution cabinets; for the problem that general low-voltage distribution cabinet control systems have improper parameter settings and lack directionality in parameter adjustment, they are prone to fall into local optimality, which in turn leads to low control efficiency of low-voltage distribution cabinets. This scheme optimizes the artificial fish school algorithm, initializes the fish school position based on the transformation sequence, and improves the ergodicity of the search; dynamically adjusts parameters based on the sinusoidal growth basis and nonlinear amplification, balances global-local exploration, and accelerates local convergence; combines fish school behavior with inverse learning to enhance the ability to escape local optimality; and thus improves the control efficiency of low-voltage distribution cabinets.

[0004] The technical solution adopted by the present invention is as follows: the present invention provides an intelligent low-voltage distribution cabinet power distribution control system, including a data acquisition module, a preprocessing module, a low-voltage distribution cabinet fault monitoring model establishment module, a parameter tuning module and a power distribution control module;

[0005] The data acquisition module collects historical distribution cabinet sensor data and constructs a distribution cabinet feature vector;

[0006] The preprocessing module introduces a hysteresis attenuation coefficient to perform kernel smoothing on the distribution cabinet feature vector to obtain a distribution cabinet data set;

[0007] The low-voltage distribution cabinet fault monitoring model establishment module introduces a time memory factor to design a distribution shield loss function, and designs a low-voltage distribution cabinet fault monitoring model based on the distribution cabinet data set;

[0008] The parameter tuning module performs parameter tuning on the core smoothing process and the low-voltage distribution cabinet fault monitoring model to establish a final low-voltage distribution cabinet fault monitoring model;

[0009] The power distribution control module performs power distribution control on real-time power distribution cabinet sensor data based on a low-voltage power distribution cabinet fault monitoring model.

[0010] Furthermore, the data acquisition module collects historical distribution cabinet sensor data and marks the distribution cabinet status as a data label; normalizes the historical distribution cabinet operation data and constructs a distribution cabinet feature vector.

[0011] Furthermore, the pre-processing module performs kernel smoothing on the distribution cabinet feature vector and gives the remote frame a hysteresis attenuation coefficient. The formula used is: ; ;in, is the kernel smoothing function, u is the function variable; is the Gamma function; is the degree of freedom parameter; is the hysteresis coefficient; is the kernel-smoothed feature of the nth frame; M is the half-width of the sliding window, and k is the frame offset within the sliding window; is the normalized eigenvalue; is the kernel bandwidth; using a sliding window method, the kernel smoothed distribution cabinet feature vectors of the latest T frames are pieced together into a matrix to obtain the distribution cabinet dataset.

[0012] Furthermore, the low-voltage distribution cabinet fault monitoring model establishment module is based on the distribution cabinet data set and uses a one-dimensional convolution + LSTM hybrid network to establish a low-voltage distribution cabinet fault monitoring model, which is expressed as: ; Input from time To the matrix of t total T frame ; It is a one-dimensional convolution operation; It is the feature map after convolution; is a long short-term memory network, is the LSTM network output, It is a fully connected transformation; the final output is the predicted score of the distribution cabinet status ; and embed the power distribution shield loss function and introduce the time memory factor , expressed as: ; Final distribution shield loss function Expressed as: ;in, 、 and are the residuals at time t, time t-1, and time t-2, which are the differences between the true label and the predicted value; and is the memory coefficient; is the indicator function; is the tolerance threshold; is the overall loss scaling factor; a is the steepness parameter; and e is the natural logarithm base.

[0013] Furthermore, the parameter tuning module optimizes the hyperparameters involved in the kernel smoothing process and the low-voltage distribution cabinet fault monitoring model based on the optimized artificial fish swarm algorithm, ensuring that the performance of the final established model meets the standards. Specifically, it includes the following:

[0014] Initialization: Establish a search space based on the hyperparameters to be tuned, set k=0, and randomly generate a sequence , expressed as: , and press Initialize the position of each fish; where, and are the sth and s-1th chaos values ​​respectively; Control the demarcation point of sequence transformation; is the initialization position of the jth dimension of the search space of the i-th fish school individual; and are the minimum and maximum values ​​of the j-th dimension of the search space respectively;

[0015] Pre-setting: Divide the distribution cabinet data set into a test set and a training set, and select the prediction accuracy of the test set when the low-voltage distribution cabinet fault monitoring model converges to the training set loss as the individual fitness value; Initial global optimal ;in, is the fitness value of the initial position of the i-th individual fish school; initialization convergence factor and inertia weight ;

[0016] Iterative search; for k = 0 to Execution: Update parameters based on sinusoidal growth basis and nonlinear amplification ; ; Execute fish school behavior, the formula used is: ; Reverse learning; For each fish, generate a reverse individual and define the range limit and ; Generate reverse points, , ; And select and retain according to the individual fitness value, and update the global optimum; Among them, is the maximum number of iterations; 、 and Control the convergence speed and curve shape; m adjusts the degree of nonlinearity; and are the positions of the i-th individual in the fish school at the k+1-th iteration and the k-th iteration respectively; and are the inertia weight and convergence factor at the kth iteration respectively; Step is the maximum step size; is the optimal individual at the kth iteration; ; N is the population size; yes is the position of the jth dimension of the search space; is the initial reversal point generated; is the kth chaotic value; is the final reversal point;

[0017] Search judgment; set the judgment threshold. During the iterative search process, if there is an individual fitness value higher than the judgment threshold, the search ends and a low-voltage distribution cabinet fault monitoring model is established based on the individual position. If , then go to initialization.

[0018] Furthermore, the power distribution control module collects real-time distribution cabinet sensor data, inputs it into the low-voltage distribution cabinet fault monitoring model after preprocessing, and performs power distribution control based on the distribution cabinet status output by the low-voltage distribution cabinet fault monitoring model.

[0019] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0020] (1) For the general low-voltage power distribution cabinet control system, the sensor noise, transient spikes and switch action bring slight jitter, which leads to false alarm or frequent trigger protection action, and cannot respond quickly to sudden changes. The scheme introduces a hysteresis attenuation coefficient to perform kernel smoothing processing on the power distribution cabinet feature vector, which can not only eliminate small noise and reduce noise interference on subsequent analysis, but also not excessively blunt normal fluctuations, retain important information of the power distribution cabinet running state, shorten the system lag for sudden changes, respond to these sudden changes more timely, and help to discover potential faults in time.

[0021] (2) For the general low-voltage power distribution cabinet control system, the parameter setting is improper, the parameter adjustment lacks directionality, is easy to fall into local optimum, and further leads to low efficiency of low-voltage power distribution cabinet control. The scheme optimizes the artificial fish swarm algorithm, initializes the fish swarm position based on the transformation sequence, improves the search traversal, adjusts the parameters based on the sinusoidal growth base and nonlinear amplification, balances global-local exploration, and speeds up local convergence. The fish swarm behavior is combined with reverse learning to enhance the ability to jump out of local optimum, and further improve the efficiency of low-voltage power distribution cabinet control. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A flowchart of an intelligent low-voltage power distribution cabinet power distribution control system is provided.

[0023] Figure 2 A flowchart of a parameter optimization module.

[0024] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0026] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0027] Example 1, see Figure 1 , the present invention provides an intelligent low-voltage distribution cabinet power distribution control system, including a data acquisition module, a preprocessing module, a low-voltage distribution cabinet fault monitoring model establishment module, a parameter tuning module and a power distribution control module;

[0028] The data acquisition module collects historical distribution cabinet sensor data, constructs a distribution cabinet feature vector, and sends the data to the preprocessing module;

[0029] The preprocessing module introduces a hysteresis attenuation coefficient to perform kernel smoothing on the distribution cabinet feature vector to obtain a distribution cabinet data set; and sends the data to a low-voltage distribution cabinet fault monitoring model establishment module;

[0030] The low-voltage distribution cabinet fault monitoring model establishment module introduces a time memory factor to design a distribution shield loss function, designs a low-voltage distribution cabinet fault monitoring model based on the distribution cabinet data set; and sends the data to the parameter tuning module;

[0031] The parameter tuning module performs parameter tuning on the core smoothing process and the low-voltage distribution cabinet fault monitoring model to establish a final low-voltage distribution cabinet fault monitoring model; and sends the data to the distribution control module;

[0032] The power distribution control module performs power distribution control on real-time power distribution cabinet sensor data based on a low-voltage power distribution cabinet fault monitoring model.

[0033] Example 2, see Figure 1 This embodiment is based on the above embodiment. The data acquisition module collects historical distribution cabinet sensor data and marks the distribution cabinet status as a data label; the distribution cabinet status includes undervoltage, normal and overload; the historical distribution cabinet operation data is normalized to construct a distribution cabinet feature vector; the historical distribution cabinet operation data includes three-phase current, three-phase voltage, temperature, humidity, leakage current and time period code.

[0034] Example 3, see Figure 1 This embodiment is based on the above embodiment. The preprocessing module performs kernel smoothing on the distribution cabinet feature vector to eliminate small noise without excessively passivating normal fluctuations. It also gives the remote frame a hysteresis attenuation coefficient to shorten the system's response to sudden changes from low load at night to early morning startup and arc short circuit. The formula used is: ; ; wherein, is a kernel smoothing function, u is a function variable; is a Gamma function; is a degree of freedom parameter; is a hysteresis coefficient; is the n-th frame of the kernel smoothed feature; M is the half width of the sliding window, and k is the frame offset in the sliding window; is the normalized feature value; is the kernel bandwidth; in a sliding window manner, the kernel smoothing processing of the power distribution cabinet feature vector of the last T frames is spliced into a matrix to obtain a power distribution cabinet data set.

[0035] Embodiment four, see Figure 1 , which is based on the above embodiment, the low-voltage power distribution cabinet fault monitoring model establishment module selects a one-dimensional convolution + LSTM hybrid network based on the power distribution cabinet data set to establish a low-voltage power distribution cabinet fault monitoring model, which takes into account local time sequence features and long short-term dependencies, and is expressed as: ; the input matrix from time t to t+T frames; is a one-dimensional convolution operation; is the feature map after convolution, which is a plurality of one-dimensional activation sequences extracted from the input matrix in the power distribution cabinet data set by one-dimensional convolution in the time axis; is a long short-term memory network, is the long short-term memory network output, is a full connection transformation; the final output is the prediction score of the power distribution cabinet state ; and the power distribution shield loss function is embedded, in a low-voltage power distribution cabinet, voltage and current measurement will be affected by sensor noise, transient spikes and slight fluctuations caused by switching actions; if every slight fluctuation triggers control action, the circuit breaker and switch in the cabinet will frequently trip and close, which not only reduces power supply reliability, but also shortens the service life of the equipment; therefore, the power distribution shield loss function is designed to have zero loss for small fluctuations, avoiding frequent control caused by small amplitude fluctuations of voltage / current; when the residual , the loss tends to the upper limit, resisting abnormal surges, lightning strikes and short-circuit mutations that will not cause the model gradient to explode; and a time memory factor is introduced to punish the continuous violation of the residual, which is expressed as: ; the final power distribution shield loss function is expressed as: ; wherein, , and are the residuals at times t, t-1 and t-2, respectively, and the difference between the true label and the predicted value; and is the memory coefficient; is the indicator function; is the tolerance threshold; is the overall loss scaling factor; a is the steepness parameter; and e is the natural logarithm base.

[0036] By performing the above operations, the control system of a general low-voltage distribution cabinet is sensitive to sensor noise, transient spikes and slight jitters caused by switch actions, which leads to false alarms or frequent triggering of protection actions and an inability to respond quickly to sudden changes. This solution introduces a hysteresis attenuation coefficient to perform kernel smoothing on the characteristic vector of the distribution cabinet. This can not only eliminate small noises and reduce the interference of noise on subsequent analysis, but also does not excessively passivate normal fluctuations, retaining important information about the operating status of the distribution cabinet, shortening the system's lag in responding to sudden changes, and being able to respond to these sudden changes more promptly, which is conducive to the timely detection of potential faults; introducing a time memory factor to design the distribution shield loss function avoids frequent control caused by small jitters in voltage and current, reduces the frequent tripping and closing of circuit breakers and switches in the cabinet, and improves power supply reliability; constrains the occurrence of continuous abnormal conditions, increases sensitivity to faults, and thereby improves the control accuracy of the low-voltage distribution cabinet.

[0037] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. The parameter tuning module optimizes the hyperparameters involved in kernel smoothing and low-voltage distribution cabinet fault monitoring models based on the optimized artificial fish school algorithm, including the sliding window half-width, kernel bandwidth, hysteresis coefficient, number of LSTM hidden units, learning rate, weight decay, and maximum number of training rounds; ensuring that the performance of the final established model meets the standards. Specifically, it includes the following contents:

[0038] Initialization: Establish a search space based on the hyperparameters to be tuned, set k=0, and randomly generate a sequence , expressed as: , and press Initialize the position of each fish; where, and are the sth and s-1th chaos values ​​respectively; Control the demarcation point of sequence transformation; is the initialization position of the jth dimension of the search space of the i-th fish school individual; and are the minimum and maximum values ​​of the j-th dimension of the search space respectively;

[0039] Pre-setting: Divide the distribution cabinet data set into a test set and a training set, and select the prediction accuracy of the test set when the low-voltage distribution cabinet fault monitoring model converges to the training set loss as the individual fitness value; Initial global optimal ;in, is the fitness value of the initial position of the i-th individual fish school; initialization convergence factor and inertia weight ;

[0040] Iterative search; for k = 0 to Execution: Update parameters based on sinusoidal growth basis and nonlinear amplification ; ; Execute fish school behavior, the formula used is: ; Reverse learning; For each fish, generate a reverse individual and define the range limit and ; Generate reverse points, , ; And select and retain according to the individual fitness value, and update the global optimum; Among them, is the maximum number of iterations; 、 and Control the convergence speed and curve shape; m adjusts the degree of nonlinearity; and are the positions of the i-th individual in the fish school at the k+1-th iteration and the k-th iteration respectively; and are the inertia weight and convergence factor at the kth iteration respectively; Step is the maximum step size; is the optimal individual at the kth iteration; ; N is the population size; yes is the position of the jth dimension of the search space; is the initial reversal point generated; is the kth chaotic value; is the final reversal point;

[0041] Search judgment; set the judgment threshold. During the iterative search process, if there is an individual fitness value higher than the judgment threshold, the search ends and a low-voltage distribution cabinet fault monitoring model is established based on the individual position. If , then go to initialization.

[0042] By performing the above operations, we can address the problem that general low-voltage distribution cabinet control systems have improper parameter settings, lack of directionality in parameter adjustment, and are prone to falling into local optimality, which in turn leads to low control efficiency of the low-voltage distribution cabinet. This solution optimizes the artificial fish school algorithm, initializes the fish school position based on the transformation sequence, and improves the ergodicity of the search; dynamically adjusts parameters based on the sinusoidal growth basis and nonlinear amplification to balance global-local exploration and accelerate local convergence; combines fish school behavior with inverse learning to enhance the ability to escape local optimality, thereby improving the control efficiency of the low-voltage distribution cabinet.

[0043] Example 6, see Figure 1 This embodiment is based on the above embodiment. The power distribution control module collects real-time distribution cabinet sensor data, pre-processes it, and inputs it into the low-voltage distribution cabinet fault monitoring model. The power distribution control is performed based on the distribution cabinet status output by the low-voltage distribution cabinet fault monitoring model. If the distribution cabinet status is normal, no equipment is switched and the status quo is maintained. If the distribution cabinet status is undervoltage, the actuators are the voltage tap switch T and the dynamic reactive power compensation device Q. The control law is expressed as follows: ; ;in, is the nominal voltage; is the real-time voltage measurement value; and They are the number of tap switch switching steps and the reactive compensation switching amount; is the voltage regulation gain; press and The tap is shifted up and reactive compensation is switched on and off according to the size of ; if the distribution cabinet is in overload state, the actuators are the controllable circuit breaker B and the segmented load removal device S, and the control law is expressed as: ; ;in, is the maximum current allowed; is the current overload; is the actual bus current value; is the load shedding proportional coefficient; is the load level to be cut off; first perform segmented load shedding S, and if there is still overload after shedding, then perform remote tripping B.

[0044] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0045] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0046] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An intelligent low-voltage distribution cabinet power distribution control system, characterized by: The system includes a data acquisition module, a preprocessing module, a low-voltage distribution cabinet fault monitoring model establishment module, a parameter tuning module and a distribution control module; The data acquisition module collects historical distribution cabinet sensor data and constructs a distribution cabinet feature vector; The preprocessing module introduces a hysteresis attenuation coefficient to perform kernel smoothing on the distribution cabinet feature vector to obtain a distribution cabinet data set; The low-voltage distribution cabinet fault monitoring model establishment module introduces a time memory factor to design a distribution shield loss function, and designs a low-voltage distribution cabinet fault monitoring model based on the distribution cabinet data set; The parameter tuning module performs parameter tuning on the core smoothing process and the low-voltage distribution cabinet fault monitoring model to establish a final low-voltage distribution cabinet fault monitoring model; The power distribution control module performs power distribution control on real-time power distribution cabinet sensor data based on the low-voltage power distribution cabinet fault monitoring model; The preprocessing module performs kernel smoothing on the distribution cabinet feature vector and assigns a hysteresis attenuation coefficient to the remote frame. The formula used is: ; ;in, is the kernel smoothing function, u is the function variable; is the Gamma function; is the degree of freedom parameter; is the hysteresis coefficient; is the kernel-smoothed feature of the nth frame; M is the half-width of the sliding window, and k is the frame offset within the sliding window; is the normalized eigenvalue; is the kernel bandwidth; using a sliding window method, the kernel smoothed distribution cabinet feature vectors of the latest T frames are assembled into a matrix to obtain the distribution cabinet dataset; The low-voltage distribution cabinet fault monitoring model establishment module is based on the distribution cabinet dataset and uses a one-dimensional convolution + LSTM hybrid network to establish a low-voltage distribution cabinet fault monitoring model, which is expressed as: ; Input from time To the matrix of t total T frame ; It is a one-dimensional convolution operation; It is the feature map after convolution; is a long short-term memory network, is the LSTM network output, It is a fully connected transformation; the final output is the predicted score of the distribution cabinet status ; and embed the power distribution shield loss function and introduce the time memory factor , expressed as: ; Final distribution shield loss function Expressed as: ;in, 、 and are the residuals at time t, time t-1, and time t-2, which are the differences between the true label and the predicted value; and is the memory coefficient; is the indicator function; is the tolerance threshold; is the overall loss scaling factor; a is the steepness parameter; and e is the natural logarithm base.

2. The intelligent low-voltage power distribution cabinet power distribution control system according to claim 1, characterized in that: The parameter tuning module optimizes the hyperparameters involved in the kernel smoothing process and the low-voltage distribution cabinet fault monitoring model based on the optimized artificial fish swarm algorithm; Ensure that the performance of the final model meets the standards; Includes the following: Initialization: Establish a search space based on the hyperparameters to be tuned, set k=0, and randomly generate a sequence , expressed as: , and press Initialize the position of each fish; where, and are the sth and s-1th chaos values ​​respectively; Control the demarcation point of sequence transformation; is the initialization position of the jth dimension of the search space of the i-th fish school individual; and are the minimum and maximum values ​​of the j-th dimension of the search space respectively; Pre-setting: Divide the distribution cabinet data set into a test set and a training set, and select the prediction accuracy of the test set when the low-voltage distribution cabinet fault monitoring model converges to the training set loss as the individual fitness value; Initial global optimal ;in, is the fitness value of the initial position of the i-th individual fish school; initialization convergence factor and inertia weight ; Iterative search; Search judgment; set the judgment threshold. During the iterative search process, if there is an individual fitness value higher than the judgment threshold, the search ends and a low-voltage distribution cabinet fault monitoring model is established based on the individual position. If , then go to initialization.

3. The intelligent low-voltage power distribution cabinet power distribution control system according to claim 2, characterized in that: The iterative search is for k=0 to Execution: Update parameters based on sinusoidal growth basis and nonlinear amplification ; ; Execute fish school behavior, the formula used is: ;Reverse learning; For each fish, generate reverse individuals and define range limits and ; Generate reverse points, , ; And select and retain according to the individual fitness value, and update the global optimum; Among them, is the maximum number of iterations; 、 and Control the convergence speed and curve shape; m adjusts the degree of nonlinearity; and are the positions of the i-th individual in the fish school at the k+1-th iteration and the k-th iteration respectively; and are the inertia weight and convergence factor at the kth iteration respectively; Step is the maximum step size; is the optimal individual at the kth iteration; ; N is the population size; yes is the position of the jth dimension of the search space; is the initial reversal point generated; is the kth chaotic value; is the final reversal point.

4. The intelligent low-voltage distribution cabinet power distribution control system according to claim 3, characterized in that: The data acquisition module collects historical distribution cabinet sensor data and marks the distribution cabinet status as a data label; normalizes the historical distribution cabinet operation data and constructs a distribution cabinet feature vector.

5. The intelligent low-voltage power distribution cabinet power distribution control system according to claim 4, characterized in that: The power distribution control module collects real-time distribution cabinet sensor data, inputs it into the low-voltage distribution cabinet fault monitoring model after preprocessing, and performs power distribution control based on the distribution cabinet status output by the low-voltage distribution cabinet fault monitoring model.

Images