Explainability: Relevance based dynamic deep learning algorithm for fault detection and diagnosis in chemical processes

Abstract

The focus of this work is on Statistical Process Control (SPC) of a manufacturing process based on available measurements. Two important applications of SPC in industrial settings are fault detection and diagnosis (FDD). In this work, a deep learning (DL) based methodology is proposed for FDD. We investigate the application of an explainability concept (explainable artificial intelligence (XAI)) to enhance the FDD accuracy of a deep neural network model trained with a dataset of relatively small number of samples. The explainability is quantified by a novel relevance measure of input variables that is calculated from a Layerwise Relevance Propagation (LRP) algorithm. It is shown that the relevances can be used to discard redundant input feature vectors/ variables iteratively thus resulting in reduced over-fitting of noisy data, increasing distinguishability between output classes and superior FDD test accuracy. The efficacy of the proposed method is demonstrated on the benchmark Tennessee Eastman Process.