Error compensation method for photoelectric encoder

Abstract

The invention discloses an error compensation method for a photoelectric encoder. Based on improved particle swarm optimization and a Fourier neural network principle, the method is used for improving the measurement accuracy of the photoelectric encoder, and is particularly suitable for an angle measuring system requiring low cost and high accuracy. According to the method, a compass error is modeled by a Fourier neural network, and the weight of the neural network is optimized by the improved particle swarm optimization, so that an accurate error model is obtained to compensate a measured value of the photoelectric encoder. The error model established by the method can realize accurate mapping of a sample space and has high nonlinear approximation capability; and by the method, local minimum is avoided, a defect that the neural network has ultralow convergence rate, oscillates and the like is overcome, measurement errors of the photoelectric encoder are effectively reduced, and the measurement accuracy of the photoelectric encoder is greatly improved.

Description

technical field [0001] The invention belongs to the field of angle measurement and relates to an error compensation method of a photoelectric encoder based on a Fourier neural network and an improved particle swarm algorithm. Background technique [0002] A photoelectric encoder is a device or device that converts an angle signal into a signal (generally an electrical signal) that is easy to collect, transmit and process according to a certain rule to determine the angular displacement or azimuth angle. It is an important sensor that is widely used It is used in instrument measurement, industrial automation, signal detection, robotics, aviation and navigation and other fields. At present, according to the nature of the output signal, photoelectric encoders are divided into two categories: analog type and digital type. Analog type is divided into synchronous machine, resolver, potentiometer, inductive sensor, etc.; type, photoelectric coding type, electromagnetic coding type...

AI Technical Summary

Problems solved by technology

[0003] At present, the main methods of compensating the photoelectric encoder include the improvement of the hardware circuit, the use of software RBF (Radical Basis Function, Radial Basis Function) neural network, and the method of correction with the help of other high-precision instruments, etc. The improvement of the hardware circuit requires It is more complicated to dismantle or refit the photoelectric encoder; the compensation accuracy achieved by using the software RBF neural network compensation method is not enough; and the method of using high-precision instrument calibration has higher requirements for the calibration instrument, which increases the economic requirements for compensation

Images