Location
Innovation Lab Atrium
Start Date
3-3-2025 2:00 PM
End Date
4-3-2025 3:30 PM
Presentation Date
3 April 2025, 2:00pm - 3:30pm
Meeting Name
2025 - Miners Solving for Tomorrow Research Conference
Department(s)
Engineering Management and Systems Engineering
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2025 The Authors, All rights reserved
Mar 3rd, 2:00 PM
Apr 3rd, 3:30 PM
Neural Network-Based Renewal Reward Theory (RRT) for Optimal Maintenance Scheduling
Innovation Lab Atrium
Comments
Advisor: Abhijit Gosavi
Co-advisor: Susan L. Murray
Abstract:
In manufacturing, equipment failure disrupts production processes, leading to increased costs and inefficiencies. - Maintenance strategies have historically evolved from reactive Corrective Maintenance (CM) to more proactive approaches, such as Preventive Maintenance (PM), which includes Condition-Based Maintenance (CBM) and Time-Based Maintenance (TBM). This research presents a novel PM scheduling model that integrates Neural Networks (NN) with Renewal Reward Theory (RRT), enhanced by real-time Digital Twin technology. The model effectively addresses the limitations of previous methods. It dynamically predicts the empirical distribution of Time-to-Failure (TTF) using historical failure data, eliminating the need for traditional statistical distributions. By employing RRT, the model optimizes maintenance schedules to balance operational efficiency, cost-effectiveness, and equipment reliability. Preliminary evaluations show significant reductions in maintenance costs and downtime, highlighting the practical potential and economic benefits of the proposed approach within advanced Industry 4.0 manufacturing environments.