AN APPLICATION OF RBFNN FOR AUTOMOTIVE AIR CONDITIONING FAULT DETECTION AND DIAGNOSIS STRATEGY

Abstract

An accurate reference model plays an essential role in enhancing the accuracy rate of the automotive air conditioning fault detection and diagnosis strategy. Thus, RBFNN model is adopted in this study to capture operating characteristics of the automotive air conditioning system. Therein, a strategy includes the RBFNN model, EWMA method and a diagnosis rule is combined in this study. The automotive air conditioning FDD strategy is tested and validated using the simulated experimental data. Results of this study show that the approximation ability of RBFNN model achieves high accuracy and this proposed method is robust for fault detection and diagnosis in the automotive air conditioning systems.