June 22, 2017 - June 22, 2017
3:30 pm – 4:30 pm
Erwin van Wingerden
Spare parts planning under uncertain failure rates
In this paper we consider a multi-item inventory problem with a backorder constraint where the distribution of demand is known but not the exact failure rate. We show that when demand follows a Poisson distriubtion, the larger the variance of this failure rate, the larger the costs. First we show that uncertainty of the failure rate is similar to having an uncertain lead time. Next, we show that the expected number of backorders for a given base stock level is always higher, and thus one always requires a higher base stock level (and thus costs) to satisfy the constraint when there is more uncertainty regarding the failure rate. Finally, we show the impact of this uncertainty by presenting numerical results where we consider the failure rate to follow the uniform distribution as well as a Gamma distribution.
System redesign with unknown failure rates
We consider a newly developed advanced system that is sold under a performance-based contract. The system is subject to failures with a random failure rate. The manufacturer is responsible for the availability of the system and makes a redesign decision at each decision period. The trade-off is that low failure rates require high redesign costs while high failure rates result in high repair costs and high penalty costs due to system unavailability. We develop a Markov decision process model to support the manufacturer’s redesign decision. As more information on the failures become available over the time, we use Bayesian model to update the failure rate distribution. We determine the optimal redesign policy and show that the optimal policy has a nondecreasing control limit structure. In numerical analysis, we benchmark the optimal policy against the policy optimizing the initial design but has no redesign options during the contract period.
Location: TU/e, Building 62, Paviljoen F9. Feel free to join, if you are interested!
Eindhoven University of Technology