Joint Optimization of Equipment Predictive Maintenance and Spare Part Ordering Policy Considering Spare Part Types  
Author Yi Chen

 
Co-Author(s) Lan Chen; Xiaobing Ma; Fanping Wei; Li Yang

 
Abstract Predictive maintenance and spare part planning are essential for ensuring equipment performance, minimizing operational risks, and enhancing operational safety. While existing research primarily focuses on spare part ordering time, this paper further incorporates the impact of spare part types into the maintenance policy, such that to promote the accuracy of safety-centered predictive maintenance. A stochastic process-based degradation model is utilized to establish the relationship between equipment degradation and remaining useful lifetime, with key parameters dynamically updated online through maximum likelihood estimation. A condition-based maintenance-spare ordering policy is developed by modeling potential failure thresholds and calculating the probabilities of preventive and corrective maintenance, thereby reducing the risk of unexpected failures. A genetic algorithm is applied to optimize maintenance costs and system availability, achieving joint optimization of maintenance and spare part ordering to ensure safety and operational reliability. A case study on bearings demonstrates that the proposed policy significantly reduces maintenance costs, lowers failure risks, and improves availability compared to traditional policy.

 
Keywords Predictive maintenance, Spare part order, Lifetime prediction, Failure risk control, Genetic algorithm
   
    Article #:  DSBFI25-103
 
Proceedings of 3rd ISSAT International Conference on Data Science in Business, Finance and Industry
January 6-8, 2025 - Da Nang, Vietnam