Fault Detection and Diagnosis Using Combined Autoencoder and Long Short-Term Memory Network.

Pangun Park,Junseong Bang,Hyejeon Shin,Piergiuseppe Di Marco

doi:10.3390/s19214612

Abstract

Fault detection and diagnosis is one of the most critical components of preventing accidents and ensuring the system safety of industrial processes. In this paper, we propose an integrated learning approach for jointly achieving fault detection and fault diagnosis of rare events in multivariate time series data. The proposed approach combines an autoencoder to detect a rare fault event and a long short-term memory (LSTM) network to classify different types of faults. The autoencoder is trained with offline normal data, which is then used as the anomaly detection. The predicted faulty data, captured by autoencoder, are put into the LSTM network to identify the types of faults. It basically combines the strong low-dimensional nonlinear representations of the autoencoder for the rare event detection and the strong time series learning ability of LSTM for the fault diagnosis. The proposed approach is compared with a deep convolutional neural network approach for fault detection and identification on the Tennessee Eastman process. Experimental results show that the combined approach accurately detects deviations from normal behaviour and identifies the types of faults within the useful time.

Highlights

Modern industrial control systems deal with multivariate time series data of multiple correlated signals between sensors and actuators [1,2,3,4]
We evaluate the performance of the proposed method for Fault detection and diagnosis (FDD) on Tennessee Eastman Process (TEP) [45]
This paper proposes a learning approach consisting of autoencoder and long short-term memory (LSTM) network for fault detection and diagnosis of rare events in a multivariate industrial process

Summary

Introduction

Modern industrial control systems deal with multivariate time series data of multiple correlated signals between sensors and actuators [1,2,3,4]. Fault detection and diagnosis (FDD) has tremendous potential to improve the operational reliability and stability of industrial processes since the objective of FDD is to minimize the production losses, while ensuring the safety of human and equipment [5]. FDD identifies anomalies of critical equipment by analyzing and mining recorded data to deliver notifications to operators [6,7]. Since industrial monitoring data have become much larger as both the number of samples and the dimensionality increased, traditional model- or knowledge-based approaches, involving extensive human intervention, are becoming too difficult to implement [6]. Industrial faults rarely occur during the stable operation of the control processes such as machine

Objectives

Results

Conclusion