Fault Detection and Identification using Bayesian Recurrent Neural Networks

TL;DR

This paper introduces a novel Bayesian recurrent neural network approach for fault detection and identification in industrial processes, providing uncertainty estimates for improved fault diagnosis and process monitoring.

Contribution

It develops a new probabilistic deep learning method using BRNNs with variational dropout for enhanced fault detection and identification in complex nonlinear systems.

Findings

Outperforms traditional PCA-based methods in fault detection accuracy.

Provides uncertainty estimates for better fault diagnosis.

Demonstrates effectiveness on benchmark and real datasets.

Abstract

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal operations. While the control system can compensate for many types of disturbances, there are changes to the process which it still cannot handle adequately. It is therefore important to further develop monitoring systems to effectively detect and identify those faults such that they can be quickly resolved by operators. In this paper, a novel probabilistic fault detection and identification method is proposed which adopts a newly developed deep learning approach using Bayesian recurrent neural networks~(BRNNs) with variational dropout. The BRNN model is general and can model complex nonlinear dynamics. Moreover, compared to traditional statistic-based data-driven fault detection and identification methods, the proposed BRNN-based method yields uncertainty estimates which allow for simultaneous fault detection of chemical processes, direct fault identification, and fault propagation analysis. The outstanding performance of this method is demonstrated and contrasted to (dynamic) principal component analysis, which are widely applied in the industry, in the benchmark Tennessee Eastman process~(TEP) and a real chemical manufacturing dataset.