A Combined Method for MEMS Gyroscope Error Compensation Using a Long Short-Term Memory Network and Kalman Filter in Random Vibration Environments.

Wei Xu,Chenhao Zhu,Yifan Yang,Honghai Shen,Hairong Chu,Sheng Cai

doi:10.3390/s21041181

Abstract

In applications such as carrier attitude control and mobile device navigation, a micro-electro-mechanical-system (MEMS) gyroscope will inevitably be affected by random vibration, which significantly affects the performance of the MEMS gyroscope. In order to solve the degradation of MEMS gyroscope performance in random vibration environments, in this paper, a combined method of a long short-term memory (LSTM) network and Kalman filter (KF) is proposed for error compensation, where Kalman filter parameters are iteratively optimized using the Kalman smoother and expectation-maximization (EM) algorithm. In order to verify the effectiveness of the proposed method, we performed a linear random vibration test to acquire MEMS gyroscope data. Subsequently, an analysis of the effects of input data step size and network topology on gyroscope error compensation performance is presented. Furthermore, the autoregressive moving average-Kalman filter (ARMA-KF) model, which is commonly used in gyroscope error compensation, was also combined with the LSTM network as a comparison method. The results show that, for the x-axis data, the proposed combined method reduces the standard deviation (STD) by 51.58% and 31.92% compared to the bidirectional LSTM (BiLSTM) network, and EM-KF method, respectively. For the z-axis data, the proposed combined method reduces the standard deviation by 29.19% and 12.75% compared to the BiLSTM network and EM-KF method, respectively. Furthermore, for x-axis data and z-axis data, the proposed combined method reduces the standard deviation by 46.54% and 22.30% compared to the BiLSTM-ARMA-KF method, respectively, and the output is smoother, proving the effectiveness of the proposed method.

Highlights

Fiber optic gyroscopes and laser gyroscopes have excellent performance, but they are too large and expensive for portable devices [1,2]
The remainder of this paper is organized as follows: (1) Section 2 introduces the methods, including bidirectional LSTM (BiLSTM) network, Kalman filter, autoregressive moving averageKalman filter (ARMA-KF) model, and EM-KF model, and gives the illustration of this paper proposed method; (2) Section 3 presents the experiment, results, and comparisons; and (3) the remaining sections are the conclusion, appendix, and references
For the z-axis data, the standard deviation of the BiLSTM-EM-KF results was reduced by 29.19% and 12.75% compared to the BiLSTM

Summary

Introduction

Fiber optic gyroscopes and laser gyroscopes have excellent performance, but they are too large and expensive for portable devices [1,2]. Micro-electro-mechanical-system (MEMS) gyroscopes have, in recent years, been used in low-cost inertial navigation systems (INS) due to their small size and low cost. The MEMS gyroscope has a significant error due to the manufacturing technology and structural composition [3,4]. The error of the MEMS gyroscope can be divided into deterministic error and random error. The deterministic error mainly refers to perturbation errors such as zero offsets and the scale factor, which can be corrected by a calibration test [5,6]. Random error refers to the random drift caused by uncertain factors, usually determined by the device’s accuracy level [7], with no precise repeatability. It is difficult to accurately compensate for random error, which hinders the further improvement of MEMS gyroscope performance

Methods

Results

Conclusion