Predictive Maintenance for Ultrafiltration Membranes Using Explainable Similarity-Based Prognostics

TL;DR

This paper introduces an explainable, similarity-based prognostic framework for estimating the remaining useful life of ultrafiltration membranes in desalination plants, improving interpretability and accuracy over traditional opaque models.

Contribution

The study presents a novel fuzzy similarity reasoning approach that incorporates physics-informed health indices for transparent RUL prediction in UF membranes.

Findings

Achieved a mean absolute error of 4.50 cycles on industrial data

Generated interpretable rule bases aligned with expert knowledge

Demonstrated effectiveness on 12,528 operational cycles

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.