Machine Learning–Driven Predictive Maintenance for Sustainable Industrial Water-Treatment Operations

Shevantikar, Pradnesh Amar, Stynes, Paul and Muntean, Cristina Hava (2026) Machine Learning–Driven Predictive Maintenance for Sustainable Industrial Water-Treatment Operations. In: 2026 International Conference on Artificial Intelligence for Sustainable Engineering and Innovation, AISEI 2026. IEEE, Irbid, Jordan, pp. 609-615. ISBN 979-833157976-0

Full text not available from this repository.

Abstract

Water-treatment plants are intended for continuous operation, yet maintenance is often reactive, resulting in costly downtime and reduced reliability. This paper proposes a machine-learning-based predictive maintenance framework for industrial water-treatment systems using a a dataset reflecting real operating conditions. The dataset included over 40,000 records and 52 variables covering sensor data, environmental conditions, and treatment parameters; 22 key features were retained after preprocessing. A watertreatment plant failure prediction solution was investigated using Logistic Regression, Random Forest, and XGBoost, while Isolation Forest was used for detecting anomalies. SHAP analysis identified vibration, RO pressure, and UV intensity as the most influential predictors. The optimized XGBoost model achieved the best performance, indicating strong detection capability with some false alarms. The proposed framework generates risk scores and explainable insights for dashboard integration, supporting data-driven decision-making. By improving resource efficiency and reducing pollutant discharge, this research contributes to sustainable and resilient watertreatment operations.

Item Type:	Book Section
Uncontrolled Keywords:	Machine Learning; predictive maintenance; Smart sensors; Sustainable water treatment
Subjects:	T Technology > TC Hydraulic engineering. Ocean engineering T Technology > TD Environmental technology. Sanitary engineering Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Staff Research and Publications
Depositing User:	Tamara Malone
Date Deposited:	24 Jul 2026 13:14
Last Modified:	24 Jul 2026 14:19
URI:	https://norma.ncirl.ie/id/eprint/9481

Actions (login required)

View Item