Predictive Maintenance for Ultrafiltration Membranes Using Explainable Similarity-Based Prognostics

2026-01-31

AI Summary

This study addresses the challenge of performance degradation in ultrafiltration membranes due to fouling and the limited trust in existing predictive maintenance models stemming from their lack of interpretability. To overcome this, the authors propose an interpretable remaining useful life (RUL) prediction framework based on fuzzy similarity reasoning. The approach integrates physically informed health indicators—transmembrane pressure, flux, and resistance—with Takagi-Sugeno fuzzy rules, employing Gaussian membership functions for fuzzification and matching against historical degradation trajectories to yield transparent, expert-comprehensible RUL estimates. Validated on 12,528 industrial operational cycles, the method achieves a mean absolute error of 4.50 cycles, and the generated rule base demonstrates strong alignment with domain expert knowledge.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Life-Long and Continual Learning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In reverse osmosis desalination, ultrafiltration (UF) membranes degrade due to fouling, leading to performance loss and costly downtime. Most plants rely on scheduled preventive maintenance, since existing predictive maintenance models, often based on opaque machine learning methods, lack interpretability and operator trust. This study proposes an explainable prognostic framework for UF membrane remaining useful life (RUL) estimation using fuzzy similarity reasoning. A physics-informed Health Index, derived from transmembrane pressure, flux, and resistance, captures degradation dynamics, which are then fuzzified via Gaussian membership functions. Using a similarity measure, the model identifies historical degradation trajectories resembling the current state and formulates RUL predictions as Takagi-Sugeno fuzzy rules. Each rule corresponds to a historical exemplar and contributes to a transparent, similarity-weighted RUL estimate. Tested on 12,528 operational cycles from an industrial-scale UF system, the framework achieved a mean absolute error of 4.50 cycles, while generating interpretable rule bases consistent with expert understanding.

Problem

• Predictive Maintenance
• Ultrafiltration Membranes
• Fouling
• Remaining Useful Life
• Interpretability

Innovation

• explainable AI
• fuzzy similarity reasoning
• remaining useful life
• health index
• predictive maintenance