Predictive Maintenance Strategy Optimization for System Cost Minimization
Open Access DepositedThe emerging field of predictive maintenance offers significant potential to simultaneously improve both cost and readiness. Provided with the ability to accurately predict a future system condition allows for effective spares prepositioning and maintenance scheduling optimization. Even small reductions in unscheduled maintenance events can result in substantial cost savings, possibly billions of dollars for large or complex systems. This research proposes a methodology utilizing contemporary knowledge in prognostics theory to achieve reductions in system maintenance costs exceeding 10%. It also presents a technique to prioritize parts which offer the greatest potential for cost avoidance using predictive maintenance.Although previous research has explored optimization methods for maintenance scheduling and prognostics algorithm development, no previous studies offer techniques to assess predictive maintenance effects at the system-level. As such, this research presents an approach for assessing the value that predictive maintenance can provide to a given system during its operational life. This bridges the gap between failure-mode algorithm development and system-level cost, with minimal disruption to existing maintenance strategies currently in use. The data for this analysis is sourced from ten years’ worth of maintenance and procurement records for a United States Air Force weapon system. The data generates part-level metrics, which are then evaluated within a singular, optimization framework, utilizing part-level prognostic failure mode and confidence evaluation. The methodology balances corrective, preventative, and predictive maintenance to minimize maintenance costs while also conserving system-level availability. The results from this research indicate that parts designated for scheduled replacement are the most influential indicator of potential cost avoidance for predictive maintenance. For the system analyzed, the implementation of predictive maintenance is found to reduce maintenance costs by approximately 13% while simultaneously increasing system availability by 1-2%. This technique serves as a tool for evaluating the value that predictive maintenance may provide to a system. Future applications may employ this framework to compare with costs associated for prognostics development and implementation to assess return on investment for total lifecycle management.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.