Explainable AI predicts maritime system faults with high accuracy
Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime
Machine Learning
Summary
Maritime systems like ships need regular maintenance to avoid costly and dangerous failures. This paper presents a new technique that not only predicts when these systems might fail but also explains why the prediction was made. The method combines neural networks with fuzzy logic to offer clear, simple rules and highlight important features, making the AI's decisions easier to trust. The authors tested their approach on public datasets and on real ship propulsion system data, showing it can predict failures with around 99% accuracy while providing understandable explanations.
What this means in practice
- •For marine maintenance teams: Identify impending faults in naval propulsion systems with both accurate predictions and clear explanations to support maintenance decisions.
- •For industrial ai developers: Integrate a combined neuro-fuzzy explainability framework into deep learning models to improve trustworthiness in safety-critical system predictions.
Authors
Dionisis Kalogeropoulos, Georgia Sovatzidi, Dimitris K. Iakovidis
Abstract
Predicting when maritime systems require maintenance can be critical, avoiding hazards and costly consequences. To address this problem, this paper proposes an explainable decision-making framework that integrates a neuro-fuzzy prediction model with a two-stage explainable component. The first stage of this component produces feature-attribution explanations, using gradient-based saliency maps, and the second stage extracts local rules using a fuzzy decision tree. The proposed framework is generic and can be integrated into any deep learning-based approach, rendering it explainable. To the best of our knowledge, this is the first fuzzy logic-based framework enabling both feature-level and local rule-based explanations of black box models. This approach aims to foster trustworthiness in decision making through user-understandable machine inferences. The performance of the proposed framework using a deep residual-based neural backbone is evaluated on various general-purpose public benchmark datasets, and its utility in maritime is demonstrated in the context of early fault detection in a naval propulsion system dataset. The results indicate that it can provide predictions outperforming relevant state-of-the-art approaches, with an average AUC-ROC (Area Under the Receiver Operating Characteristic Curve) value, reaching up to 99%, while offering the advantage of explainability.