Optimization of maintenance of power system equipment based on a predictive health model

In this paper, a model-predictive control based framework is proposed for modeling and optimization of the health state of power system equipment. In the framework, a predictive health model is proposed that predicts the health state of the equipment based on its usage and maintenance actions. Based on the health state, the failure rate of the equipment can be estimated. We propose to use this predictive health model to predict the effects of different maintenance actions. The effects of maintenance actions over a future time window are evaluated by a cost function. The maintenance actions are optimized using this cost function. The proposed framework is applied in the optimization of the loading of transformers based on the thermal degradation of the paper insulation.