Fault Diagnosis for Power Electronic System Based on Diagnostic Reasoning Model Ensembles

Abstract

In this paper, we propose a general framework for designing diagnostic reasoning model ensembles(DRME) by means of cooperative coevolution. The proposed model has two main objectives: first, the improvement of the combination of the trained individual diagnostic reasoning model; second, the cooperative evolution of such DRME by encouraging collaboration among them instead of a separate training of each DRM. In order to favor the cooperation of the DRME, each DRME is evaluated throughout the evolutionary process using a multi-objective method. For each DRME, different objectives are defined, considering not only its performance in the given problem, but also its cooperation with the rest of the DRME. The experiment proved the precision and the effectiveness of the proposed approach, which is consequently a powerful tool in fault diagnosis of complex system.