Condition and health monitoring can bring out useful information for the maintenance decision-making but few models allow their integration in the decision process. This thesis aims to construct new probabilistic quantitative models to evaluate the value of this kind of information depending on its quality and on the nature of the observed variables. The proposed stochastic failure and measurement models take into account the degradation/failure sensor data, the impact of operational environment on the degradation, as well as the nature of control techniques. Based on these models, we propose different maintenance policies and we develop the associated cost model to study the best methods for the exploitation of monitoring information. The studies in this thesis show the advantage of developing quantitative maintenance decision framework which allows integrating and evaluating the impact of condition monitoring information on the performance of maintenance operations.
