Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems

TL;DR

This paper demonstrates how Explainable AI techniques, specifically SHAP values, can enhance the reliability and predictive performance of machine learning models in industrial cyber-physical systems by analyzing data decomposition effects.

Contribution

It introduces a method to use XAI for analyzing and improving ML model performance in industrial CPS through data window adjustments based on model explanations.

Findings

Increasing data window size improves model performance.

SHAP values reveal lack of contextual information during training.

Data decomposition analysis aids in model reliability enhancement.

Abstract

Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability critically important. Machine Learning (ML), specifically deep learning, is increasingly integrated in industrial CPS, but the inherent complexity of ML models results in non-transparent operation. Rigorous evaluation is needed to prevent models from exhibiting unexpected behaviour on future, unseen data. Explainable AI (XAI) can be used to uncover model reasoning, allowing a more extensive analysis of behaviour. We apply XAI to improve predictive performance of ML models intended for an industrial CPS use-case. We analyse the effects of components from time-series data decomposition on model predictions using SHAP values. Through this method, we observe evidence on the lack of sufficient contextual information during model training. By increasing the window size of data instances, informed by the XAI findings for this use-case, we are able to improve model performance.