Fuzzy logic boosts explainable maintenance for naval propulsion systems
Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic
Machine Learning
Summary
Ships need to be maintained so they don't break down and stay safe, but it's hard for people to understand why maintenance predictions happen. The authors created a new approach combining fuzzy logic and neural networks to predict when ship machines might fail and explain why in simple terms. This makes it easier for users to trust the maintenance advice. Their method was tested on real data and achieved very high accuracy in predicting failures.
What this means in practice
- •For marine maintenance teams: Help maintenance staff understand and act on naval engine failure predictions with clear cause-effect explanations from the fuzzy decision framework.
- •For industrial machine operators: Use explainable predictive maintenance methods to improve safety and uptime of heavy machinery beyond naval applications.
Authors
Dionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis
Abstract
The shipping industry has a significant impact on the global economy, emphasizing the need for operational availability and safety through the use of effective maintenance techniques. During the last decades, predictive maintenance (PdM) has emerged as a promising solution compared to the existing conventional maintenance systems. This is because it offers several advantageous functions, such as damage predictions for vessel components, reduced downtime, improved and extended life of machinery, as well as higher safety during voyages. However, existing methodologies developed for performing PdM do not provide explanations of their results to users, so that they can understand the failures that may occur. To address this limitation, this paper proposes a novel framework based on a fuzzy decision tree and a deep residual neural network, aiming to perform explainable PdM on naval vessels. The proposed framework is able to generate fuzzy local rules based on the dataset used, and can provide explanations of its outcomes, using cause-and-effect relationships, in a way that are understandable to users, thereby gaining their trust. Experiments using a publicly available dataset demonstrate the effectiveness of the proposed framework, as it achieves an accuracy of 99.24%.