Method for controlling brushless direct current motor by fusing sparrow search algorithm and fuzzy neural network

Abstract

The invention discloses a brushless direct current motor control method based on a sparrow search algorithm and a fuzzy control algorithm, the sparrow search algorithm is combined with the fuzzy control algorithm, parameters of a fuzzy neural network controller are updated in real time by using the sparrow search algorithm, and the sparrow search algorithm can avoid falling into local optimum and improve convergence speed. The neural network has good learning ability and is common, the control ability can be greatly improved when the neural network is combined with fuzzy control, the control precision and robustness of the brushless direct current motor can be effectively improved, and the method is suitable for complex and changeable working conditions and has wide application prospects.

Description

Technical Field

[0001] The invention relates to the technical field of brushless DC motor control, and in particular to a brushless DC motor control method and system based on a sparrow search algorithm and a fuzzy neural network. Background Art

[0002] Brushless DC motors (BLDC) are widely used in industrial automation, electric vehicles, household appliances and other fields due to their high efficiency, high power density and good controllability. However, due to their nonlinear characteristics and the influence of external disturbances, traditional control methods (such as PID control) are difficult to achieve high-precision control effects in practical applications. In order to improve the control performance of brushless DC motors, fuzzy neural networks (FNNs) have been introduced into the field of motor control in recent years due to their self-learning and adaptive capabilities. However, the parameter optimization problem of FNNs remains a challenge, especially in complex control scenarios.

[0003] Sparrow Search Algorithm (SSA) is a new type of heuristic optimization algorithm that simulates the foraging behavior of sparrows and has the characteristics of fast convergence and high precision. Combining the Sparrow Search Algorithm with the Fuzzy Neural Network can not only optimize the parameters of the Fuzzy Neural Network, but also improve the control accuracy and robustness of the brushless DC motor. Therefore, the present invention proposes a brushless DC motor control method and system based on the Sparrow Search Algorithm and the Fuzzy Neural Network. Invention patent content

[0004] The purpose of the present invention is to provide a brushless DC motor control method and system based on a sparrow search algorithm and a fuzzy neural network, which realizes efficient and accurate control of a brushless DC motor by combining the global optimization capability of the sparrow search algorithm and the nonlinear modeling capability of the fuzzy neural network. To achieve the above purpose, the technical solution of the present invention is as follows:

[0005] Control system architecture: The control system includes speed controller, current controller, PWM generator and brushless DC motor. The speed controller and current controller adopt fuzzy control algorithm and optimize the parameters through sparrow search algorithm.

[0006] Fuzzy control algorithm: The problem that traditional control cannot self-tune is solved by fuzzy control, but fuzzy inference rules are an approximate behavior and lack the ability to learn by themselves. BP neural network has good learning ability and is relatively common. When combined with fuzzy control, it can greatly improve the control ability. At the same time, adding SSA algorithm can avoid local optimality and speed up the convergence. In this way, the combined control method can give full play to the greatest advantages and make up for their respective shortcomings. Fuzzy neural network is like Figure 2The four-layer structure shown is the input layer, the fuzzification layer, the fuzzy inference layer, and the output layer respectively.

[0007] Sparrow Search Algorithm: The Sparrow Search Algorithm is a new population optimization intelligent algorithm proposed in recent years. In the sparrow population, it is usually divided into discoverers, followers, and vigilant ones. The discoverers are mainly to discover food. The discoverers with relatively good fitness values are the first to find food, and they have the largest search range to ensure that food can be found for the entire population. Followers will move freely when their energy is too low. Vigilant ones will perform anti-predation behaviors when encountering danger. Description of the Drawings

[0008] Figure 1 is the control flow chart described in this invention patent.

[0009] Figure 2 is the fuzzy neural network control structure diagram described in this invention patent.

[0010] Figure 3 is the control structure block diagram of the device described in this invention patent. Detailed Implementation Modes

[0011] The following further elaborates on this invention patent in detail in combination with embodiments and with reference to the drawings:

[0012] System Architecture: As Figure 1 shown, the control system includes a speed controller, a current controller, a PWM generator, and a brushless DC motor. The speed controller and the current controller adopt fuzzy control algorithms, and the Sparrow Search Algorithm is used to optimize the parameters of the fuzzy controller.

[0013] Fuzzy Control Algorithm: The fuzzy control algorithm is used to implement double closed-loop control of speed and current. The inputs of the speed controller are speed error and speed error change rate, and the output is the current reference value; the inputs of the current controller are current error and current error change rate, and the output is the PWM duty cycle.

[0014] Sparrow Search Algorithm: The Sparrow Search Algorithm is used to optimize the parameters of the fuzzy controller. The optimization process includes steps such as initializing the sparrow population, calculating the fitness value, updating the sparrow position, and iterative optimization.

[0015] The control flow is as follows: Collect the real-time speed and current signals of the brushless DC motor. Calculate the speed error and speed error change rate, and generate the current reference value through the speed controller. Calculate the current error and current error change rate, and generate the PWM duty cycle through the current controller. Use the Sparrow Search Algorithm to optimize the parameters of the fuzzy controller to achieve the optimal control effect.

[0016] The description of the above examples is only used to help understand the core idea of this invention patent; at the same time, for those of ordinary skill in the art, based on the idea of this invention patent, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this invention patent.

Claims

1. A brushless DC motor control method based on the fusion of sparrow search algorithm and fuzzy neural network algorithm, characterized in that: The following steps are involved: Design a fuzzy neural network controller to regulate the speed and torque of a brushless DC motor; Optimize the parameters of fuzzy neural network using sparrow search algorithm; The optimized fuzzy neural network controller is applied to the brushless DC motor control system.

2. The method according to claim 1, characterized in that The input of the fuzzy neural network includes the motor speed error, the speed error change rate and the external disturbance signal, and the output is the control voltage of the motor.

3. The method according to claim 1, characterized in that The objective function of the sparrow search algorithm is the integral square sum of the motor speed error, and the fuzzy neural network parameters are optimized by minimizing the objective function.

4. The method according to claim 1, characterized in that The brushless DC motor control system collects the motor's rotation speed, current and other state information in real time through sensors, and inputs the information into the fuzzy neural network controller.

5. The method according to claim 2, characterized in that: The fuzzy neural network adopts a multi-layer feedforward structure, including an input layer, a hidden layer and an output layer.

6. The method according to claim 3, characterized in that The optimization process of the sparrow search algorithm includes two stages: global search and local development.

7. The method according to claim 1, characterized in that The brushless DC motor control system also includes a fault detection module for real-time monitoring of the running state of the motor.

Images