Method for improving precision of output angle of magnetic encoder based on Hall effect

Abstract

The invention discloses a method for improving the precision of an output angle of a magnetic encoder based on a Hall effect. The method specifically comprises the following steps: constructing an LM-BP neural network structure; optimizing the initial weight and threshold of the LM-BP neural network through a PSO method: calculating the particle dimension of a PSO particle swarm, calculating the fitness value of particles, updating the positions and speeds of the particles, and obtaining the initial weight and threshold of the LM-BP neural network after PSO optimization; carrying out PSO-LM-BPneural network training: initializing an LM-BP neural network control vector, calculating a square error between output of an output layer and an ideal output signal, updating the control vector, andjudging the size of the square error; and predicting the output angle of the magnetic encoder by the PSO-LM-BP neural network. According to the method, the BP neural network is optimized in a PSO andLM matching manner, and the globally optimal initial weight and threshold are found for the BP neural network method, so that the precision of the original output angle of the magnetic encoder is improved, and the error of the magnetic encoder is reduced, and the precision of the output angle of the magnetic encoder is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of control and detection, and relates to a position sensor detection technology, in particular to a method for improving the output angle accuracy of a magnetic encoder based on Hall effect. Background technique [0002] A magnetic encoder is a position sensor used to detect the position angle of an object, the angular velocity and rotational speed of a motor, etc. It is mainly divided into a magneto-resistive magnetic encoder based on the electromagnetic resistance effect and a Hall-type magnetic encoder based on the Hall effect. . [0003] Magneto-resistive encoders use the change in resistance under different magnetic fields to detect changes in the position of the magnetic field. This technology is relatively mature, and has low power consumption, high integration, and high sensitivity, but the manufacturing process is relatively complicated and the manufacturing cost is high. Hall-type magnetic encode...

AI Technical Summary

Problems solved by technology

[0004] Due to the inevitable errors in the magnetic encoder hardware circuit installation, magnetic grid magnetization and PCB (Printed circuit board, printed circuit board) processing, there is an error in the angle measurement of the magnetic encoder

The steepest descent method adopted by the traditional BP neural network method has been searching for the minimum error solution along the reverse direction of the gradient, and it is easy to fall into a local minimum value, and the BP neural network converges linearly in the final stage of iteration, and the convergence speed is slow

The LM (Levenberg-Mar...

Images