Search

International audience; In this work, a multi-component series system is considered. The failure is not self-announced and the systemis periodically inspected. At inspection times, the failed components are repaired and the type of repairdepends on the failure time. The general maintenance actions are perfect corrective maintenance, imperfectcorrective maintenance and minimal corrective maintenance actions for the failed component, which can beconsidered as imperfect corrective maintenance for the whole system. The inspection interval is consideredas a decision parameter, and the maintenance policy is optimized using the long-run cost rate function basedon the renewal reward theorem.It is assumed that there is historical data storage for the system that includes information related to pastrepairs. It is considered that there is no information related to components’ lifetime distributions and theirparameters. The optimal decision parameter is derived considering historical data using density estimationand statistical learning algorithms like the random forest, KNN and Naïve Bayes. Eventually, the efficiencyof the proposed optimal decision parameter according to available data is compared to the one derived whereall information on the system is available.

The objective of this paper is to discuss the problem of maintenance modelling and optimisation for a deteriorating Photo- voltaic panel system. In this paper, we model the dust accumulation process as PV panels’ as the main degradation cause considering the wind conditions as covariates. The dust accumulation process is mod- eled by a non-homogeneous compound Poisson process (NHCPP). The covariates process is assumed to be a time-homogenous Markov chain with finite state space. A model similar to the proportional hazards model is used to show the influence of covariates on the degradation process. In the framework of the system under consideration, an appropriate maintenance policy which minimises the long run average maintenance cost and maximises the long run average profits is derived. Numerical implementations are presented to illustrate the performance of the proposed model.

International audience; In this paper, a multi-component series system is considered. The failure is not self-announced and the system is periodically inspected. At inspection times, the failed components are replaced by a new one. Therefore, the maintenance action is a perfect corrective maintenance for the failed component, and it can be considered as imperfect corrective maintenance for the whole system. The inspection interval is considered as a decision parameter, and the maintenance policy is optimized using the long-run cost rate function based on the renewal reward theorem. It is assumed that there is a historical data storage for the system that includes information related to past repairs. It is considered that there is no information related to components' lifetime distributions and their parameters. The optimal decision parameter is derived considering historical data using density estimation and machine learning algorithms like the random forest, KNN and Naïve Bayes. Eventually, the efficiency of the proposed optimal decision parameter according to available data is compared to the one derived where all information on the system is available.

International audience; In this paper, a multi-component series system is considered which is periodically inspected and at inspection times the failed components are replaced by a new one. Therefore, this maintenance action is perfect corrective maintenance for the failed component, and it can be considered as imperfect corrective maintenance for the system. The inspection interval is considered as a decision parameter and the maintenance policy is optimized using long-run cost rate function. It is assumed that there is no information related to components' lifetime distributions and their parameters. Therefore, an optimal decision parameter is derived considering historical data (a data storage for the system that includes information related to past repairs) using density estimation and random forest algorithms. Eventually, the efficiency of the proposed optimal decision parameter according to available data is compared to the one derived when all information on the system is available.

International audience; The same maintenance actions could induce different costs during time. In this paper, a single-unit system is considered under the lifetime test. The system is inspected periodically, and the inspection interval is considered as a decision parameter which should be optimized. A maintenance policy is proposed such that a set of corrective maintenance actions with different costs is considered and in the case of failure detection at inspection times the system is replaced by a new one. In this setup, it makes sense that choose of maintenance action depends on time or other covariates, through a statistical model. Eventually, the proposed maintenance policy is applied by a numerical simulation.