Brushless direct current motor PID speed regulation method based on genetic neural network

Abstract

The invention discloses a brushless direct current motor PID speed regulation method based on a genetic neural network. The method comprises a BP neural network, a PID controller and a brushless direct current motor. The input end of the PID controller is connected with the output end of the BP neural network, and the output end of the PID controller is connected with the brushless direct currentmotor. The method is characterized by comprising the step of optimizing the weight and threshold of the BP neural network by using a genetic algorithm, wherein the BP neural network has three layers including an input layer, a hidden layer and an output layer; the number of nodes of the input layer is 2, the number of nodes of the hidden layer is 6, and the number of nodes of the output layer is 3; the threshold value of the hidden layer is shown in the specification, the threshold value of the output layer is shown in the specification, the weight from the input layer to the hidden layer is shown in the specification, and the weight from the hidden layer to the output layer is shown in the specification; and {0 < = < = 2, 0 < = < = 6, 0 < = < = 3; , epsilon}. According to the method, thecontrol state of the PID controller can be more stable, and the method can effectively adapt to the nonlinear condition of a controlled object.

Description

technical field [0001] The invention relates to the technical field of motor control technology, in particular to a PID speed regulation method of a brushless DC motor based on a genetic neural network. Background technique [0002] Brushless DC motor is a kind of DC motor that has been rapidly developed with the development of modern semiconductor technology, especially the development of microprocessors, the adoption of high-frequency and low-power switching devices, and the continuous improvement of drive control methods. Compared with traditional asynchronous motors, synchronous motors, and brushed DC motors, brushless DC motors get rid of the poor speed regulation performance of asynchronous motors, low operating efficiency and poor speed regulation performance of synchronous motors, and brushed DC motors are prone to sparks , the disadvantage of complex structure and difficult maintenance, but also has the advantages of high operating efficiency, good stability, simple...

AI Technical Summary

Problems solved by technology

In the traditional BP neural network, the initial values ​​of weights and thresholds are initialized with any value in the fixed interval [-1, 1], and then preliminarily adjusted in subsequent sample training to obtain suitable weights and thresholds. Threshold, but due to the problem that the search space is too large, the training of the neural network will fall into a local minimum, and it is impossible to obtain a better distribution of weights and thresholds

At the same time, there are still a series of shortcomings in the BP neural network: 1. The convergence speed of the neural network algorithm is slow; 2. The selection of the neural structure is different; 3. The contradiction between the application example and the network scale; 4. The contradiction between the prediction ability and the training ability of the neural network; 5. The network depends on the samples given; 6. Poor robustness

These shortcomings make this good control method that can satisfy the nonlinear system cannot be well applied to the speed control system of the brushless DC motor, which will reduce the reliability of the controller and greatly affect the use of the brushless DC motor.

Images