Title: Zero-bias error compensation method of laser gyro based on neural network

Authors: Juan Cui; Cong Zhong

Addresses: Department of Basic Courses, Xi'an Traffic Engineering Institute, Xi'an, Shaanxi Province, China ' Technical Department, Xi'an North Jierui Opto-electronic Technology Co., Ltd., Xi'an, Shaanxi Province, China

Abstract: Aiming at the problem that the accuracy of the current compensation model for laser gyro bias error is low, an improved RBFNN bias error compensation model of laser gyro is proposed. The standardisation constant and data centre of the original data are obtained through the self-organising feature mapping network. The sample centre of the new sample data is obtained by the fastest decline of the expected variance of OLS algorithm. The results show, the improved RBF neural network algorithm has the best performance. under normal temperature, temperature change rate of 1°C/min and temperature change rate of 3°C/min, the zero-bias range of laser gyro is 3.491-3.508°C/h, 3.992-4.021°C/h and 4.092-4.123°C/h, respectively. The research results provide new reference suggestions for the zero bias temperature compensation scheme of laser gyro at different temperatures.

Keywords: laser gyroscope; radial basis function neural network; self-organising feature mapping network; least square method; temperature compensation.

DOI: 10.1504/IJWMC.2023.129092

International Journal of Wireless and Mobile Computing, 2023 Vol.24 No.1, pp.91 - 100

Received: 18 Apr 2022
Received in revised form: 11 Aug 2022
Accepted: 28 Sep 2022
Published online: 17 Feb 2023 *