A Digital Twin Framework For Enhancing Predictive Maintenance Of Pumps In Wastewater Treatment Plants

Abstract

Wastewater Treatment Plants (WWTPs) Are A Type Of Critical Civil Infrastructure That Play An Integral Role In Maintaining The Standard Of Living And Protecting The Environment. The Sustainable Operation Of WWTPs Requires Maintaining The Optimal Performance Of Their Critical Assets (E.G., Pumps) At Minimum Cost. Effective Maintenance Of Critical Assets In WWTPs Is Essential To Ensure Efficient And Uninterrupted Treatment Services, While Ineffective Maintenance Strategies Can Incur High Costs And Catastrophic Incidents. Predictive Maintenance (PdM) Is An Emerging Facility Maintenance Technique That Predicts The Performance Of Critical Equipment Based On Condition Monitoring Data And Thus Estimates When Maintenance Should Be Performed. PdM Has Been Proven Effective In Optimising The Maintenance Of Individual Equipment, But Its Potential In Predicting System-Level Maintenance Demands Is Yet To Be Explored. This Study Proposes A Digital Twin Framework To Extend The Scope Of PdM By Leveraging Building Information Modelling And Deep Learning.