Optimal Compensation of MEMS Gyroscope Noise Kalman Filter Based on Conv-DAE and MultiTCN-Attention Model in Static Base Environment

Abstract

Errors in microelectromechanical systems (MEMS) inertial measurement units (IMUs) are large, complex, nonlinear, and time varying. The traditional noise reduction and compensation methods based on traditional models are not applicable. This paper proposes a noise reduction method based on multi-layer combined deep learning for the MEMS gyroscope in the static base state. In this method, the combined model of MEMS gyroscope is constructed by Convolutional Denoising Auto-Encoder (Conv-DAE) and Multi-layer Temporal Convolutional Neural with the Attention Mechanism (MultiTCN-Attention) model. Based on the robust data processing capability of deep learning, the noise features are obtained from the past gyroscope data, and the parameter optimization of the Kalman filter (KF) by the Particle Swarm Optimization algorithm (PSO) significantly improves the filtering and noise reduction accuracy. The experimental results show that, compared with the original data, the noise standard deviation of the filtering effect of the combined model proposed in this paper decreases by 77.81% and 76.44% on the x and y axes, respectively; compared with the existing MEMS gyroscope noise compensation method based on the Autoregressive Moving Average with Kalman filter (ARMA-KF) model, the noise standard deviation of the filtering effect of the combined model proposed in this paper decreases by 44.00% and 46.66% on the x and y axes, respectively, reducing the noise impact by nearly three times.

Deep Learning-Based Approach for Autonomous Vehicle Localization: Application and Experimental Analysis

“…To properly tune these kinds of systems, a substantial investment of time and effort is needed. For example, to tune various Kalman filter model parameters, e.g., process noise covariance, pre-whitening filter models for non-white noise, and frequently even optimization methods are applied [5][6][7][8]. In contrast, neural network-based algorithms offer a promising alternative that circumvents these stringent requirements.…”

Weigh-in-Motion System Based on an Improved Kalman and LSTM-Attention Algorithm

“…The filtered signal is partially decided by estimating the system identification equation and codetermined via the probability distributions of environmental noise. A Kalman filter (KF), as the typical system identification filter, is widely used in the WIM area [ 20 , 21 , 22 ]. The filtered signal is codetermined using a system-state matrix and sensor-sampling value at each time.…”