Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert-Huang Transform and Deep Learning.

Tong Gao,Wei Sheng,Jiajun Li,Futing Luo,Mingliang Zhou,Bin Fang

doi:10.3390/s20195633

Abstract

In this paper, we propose a novel method for fault diagnosis in micro-electromechanical system (MEMS) inertial sensors using a bidirectional long short-term memory (BLSTM)-based Hilbert–Huang transform (HHT) and a convolutional neural network (CNN). First, the method for fault diagnosis of inertial sensors is formulated into an HHT-based deep learning problem. Second, we present a new BLSTM-based empirical mode decomposition (EMD) method for converting one-dimensional inertial data into two-dimensional Hilbert spectra. Finally, a CNN is used to perform fault classification tasks that use time–frequency HHT spectrums as input. According to our experimental results, significantly improved performance can be achieved, on average, for the proposed BLSTM-based EMD algorithm in terms of EMD computational efficiency compared with state-of-the-art algorithms. In addition, the proposed fault diagnosis method achieves high accuracy in fault classification.

Highlights

The use of unmanned aerial vehicles (UAVs) is growing due to their advantages in mobility and economics
We propose a bidirectional long short-term memory (BLSTM)-based HHT algorithm that performs a direct intrinsic mode functions (IMFs) computation method by introducing BLSTM to empirical mode decomposition (EMD), thereby improving the EMD efficiency by decreasing the number of iterations in obtaining IMFs
We evaluated the performance of the proposed BLSTM-based EMD algorithm, as shown in micro-electromechanical system (MEMS) inertial datasets

Summary

Introduction

The use of unmanned aerial vehicles (UAVs) is growing due to their advantages in mobility and economics. The reliability achieved by sensors as a measurement and control system has a great impact on the performance of UAVs [1,2,3]. Because micro-electromechanical system (MEMS) inertial sensors have obvious advantages in weight, cost, and power consumption, MEMS inertial sensors are widely used in UAVs to perform inertial measuring tasks. The performance of MEMS inertial sensors can be significantly affected by external temperature [4,5,6] so diagnosing this type of fault is crucial in guaranteeing the reliable control of UAVs. Fault diagnosis (FD) performs tasks such as fault detection [7,8,9] and fault tolerance [10,11] There are three main types of FD methods: hardware-redundant, model-based, and data-driven methods

Methods

Results

Conclusion