An Adaptive Approach Based on Neural Network and Phase-Locked Loop for Correcting Quadrature Sinusoidal Signals of Magnetic Encoders

Abstract

Magnetic encoders have been widely used in many industrial fields due to their appealing features such as working in harsh environment, anti-interference, low cost and so on. Ideally, the output of a magnetic encoder is a pair of quadrature sinusoidal signals. The raw signals of magnetic encoders, however, are often composed of various sources of disturbances and noises, and consequently the measurement accuracy is deteriorated. In this paper, we propose a new method by combining an adaptive neural network and a phase-locked loop (ADNN-PLL). In the proposed method, the non-ideal factors are first estimated and eliminated by ADNN, and then PLL, as a closed-loop system, is used to track signals. The ADNN-PLL method can compensate for a variety of commonly seen disturbances including amplitude mismatch, phase deviation, low and high order harmonics, dc offsets and random noises. In addition, the adaptive learning rate in the neural network accelerates the speed of convergence and ensures better system stability. Simulation results are provided to demonstrate the effectiveness of the proposed ADNN-PLL method.