Case-study Led Investigation of Explainable AI (XAI) to Support Deployment of Prognostics in the industry

Abstract

Civil nuclear generation plant must maximise it’s operational uptime in order to maintain it’s viability. With aging plant and heavily regulated operating constraints, monitoring is commonplace, but identifying health indicators to pre-empt disruptive faults is challenging owing to the volumes of data involved. Machine learning (ML) models are increasingly deployed in prognostics and health management (PHM) systems in various industrial applications, however, many of these are black box models that provide good performance but little or no insight into how predictions are reached. In nuclear generation, there is significant regulatory oversight and therefore a necessity to explain decisions based on outputs from predictive models. These explanations can then enable stakeholders to trust these outputs, satisfy regulatory bodies and subsequently make more effective operational decisions. How ML model outputs convey explanations to stakeholders is important, so these explanations must be in human (and technical domain related) understandable terms. Consequently, stakeholders can rapidly interpret, then trust predictions better, and will be able to act on them more effectively. The main contributions of this paper are: 1. introduce XAI into the PHM of industrial assets and provide a novel set of algorithms that translate the explanations produced by SHAP to text-based human-interpretable explanations; and 2. consider the context of these explanations as intended for application to prognostics of critical assets in industrial applications. The use of XAI will not only help in understanding how these ML models work, but also describe the most important features contributing to predicted degradation of the nuclear generation asset.

AI for Automating Data Center Operations: Model Explainability in the Data Centre Context Using Shapley Additive Explanations (SHAP)

“…However, unlike traditional heuristics and statistical models, interpreting these black-box AI and ML models is challenging and represents a significant concern. Hence, incorporating XAI approaches has become paramount as a way to ensure that advances in ML models remain explainable and transparent [14][15][16]. XAI strives to encompass particular motivations, such as accountability, fairness, privacy, reliability, transparency, and trust-building [17], in order to ensure the overarching goal of applying AI and ML technologies [18].…”

Explainable multimodal learning for predictive maintenance of steam generators

“…The use of XAI in prognostics has emerged as a noteworthy subject in recent years. For instance, in (Amin, Brown, Stephen, & McArthur, 2022), the authors used SHapley Additive exPlanations (SHAP) to explain prognostic models built from nuclear power station data. Besides, (Nor, Pedapati, Muhammad, & Leiva, 2022), authors built Bayesian deep learning models and apply SHAP to determine the contribution of data from sensors.…”