Publication Date

Fall 2023

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Melody Moh

Second Advisor

Mahboubeh Madadi

Third Advisor

Fabio di Troia

Keywords

XAI, uncertainty quantification, multiclass classification, nuclear power plants

Abstract

Nuclear Power Plants (NPPs) can face challenges in maintaining standard operations due to a range of issues, including human mistakes, mechanical breakdowns, electrical problems, measurement errors, and external influences. Swift and precise detection of these issues is crucial for stabilizing the NPPs. Identifying such operational anomalies is complex due to the numerous potential scenarios. Additionally, operators need to promptly discern the nature of an incident by tracking various indicators, a process that can be mentally taxing and increase the likelihood of human errors. Inaccurate identification of problems leads to inappropriate corrective actions, adversely affecting the safety and efficiency of NPPs. In this study, we leverage ensemble and uncertainty-aware models to identify such errors, and thereby increase the chances of mitigating them, using the data collected from a physical testbed. Furthermore, the goal is to identify both certain and reliable models. For this, the two main aspects of focus are, EXplainable Artificial intelligence (XAI) and Uncertainty Quantification (UQ). While XAI elucidates the decision pathway, UQ evaluates decision reliability. Their integration paints a comprehensive picture, signifying that understanding decisions and their confidence should be interlinked. Thus, in this study, we leverage measures like entropy and mutual information along with SHAP (SHapley Additive explanations) and LIME (Local Interpretable Model-Agnostic Explanations) to gain insights into the features contributing to the identification. Our results show that uncertainty-aware models combined with XAI tools can explain the AI-prescribed decisions, with the potential of better explaining errors for the operators.

Download

Share

COinS