1081. Risk Assessment of Condition-Based Maintenance Contracts
Invited abstract in session TC-34: Advancements of OR-analytics in statistics, machine learning and data science 4, stream Advancements of OR-analytics in statistics, machine learning and data science.
Tuesday, 12:30-14:00Room: Michael Sadler LG10
Authors (first author is the speaker)
| 1. | Stijn Loeys
|
| Faculty of economics and business, KU Leuven | |
| 2. | Melvin Drent
|
| School of Economics and Management, Tilburg University | |
| 3. | Robert Boute
|
| Vlerick Business School and KU Leuven | |
| 4. | Collin Drent
|
| School of Industrial Engineering, Eindhoven University of Technology | |
| 5. | Katrien Antonio
|
| KU Leuven |
Abstract
We assess the financial risk incurred by maintenance service providers responsible for delivering preventive and corrective maintenance under a fixed upfront fee agreement. Preventive maintenance is optimized based on operational condition data to minimise maintenance costs. Operational data allows the explanation of machine heterogeneity in the failure behaviour, however, this data is only accrued during the contract. We propose a method to jointly estimate the failure distribution and optimize the preventive maintenance policy using operational data revealed during the contract. We incorporate machine heterogeneity via Bayesian updating of the failure distribution's parameters. Bayesian updating is used to sequentially estimate the contract's maintenance costs and hence estimate its risk.
The posterior distributions of the failure parameters allow us to quantify the parameter uncertainty at each moment in the contract by building a maintenance cost distribution. By performing an extensive simulation study, we show that including operational data revealed during the joint estimation of the failure distribution and optimization of the preventive maintenance policy, the contract's expected maintenance costs are more accurate, and more competitive compared to a one-size-fits-all approach.
Keywords
- Reliability
- Risk Analysis and Management
Status: accepted
Back to the list of papers