Data-Driven Fault Prognosis for Pneumatic Valves in Train Electropneumatic Brake System

Abstract

AbstractPneumatic valves are key components of the train electro-pneumatic braking system. In order to obtain health indicators of pneumatic valves and provide faults early-warning, this paper proposes a fault prognosis method using principal component analysis (PCA) and support vector regression (SVR). Two health indicators (\(T^{2}\) and SPE) of pneumatic valves are extracted through PCA method based on the full life cycle data set, which came from the joint simulation model. Second, a pneumatic valve fault prognosis model based on SVR is trained based on the health indicators. Combined with the working model of the train electro-pneumatic braking system, the proposed fault prognosis model can estimate the expected time of pneumatic valve fault time accurately. Results from a semi-physical simulation verification platform of DK-2 braking system indicate that the proposed method can effectively predict the occurrence of faults. This work can provide a scientific basis for the operation of braking system and maintenance strategy of pneumatic valves.KeywordsPneumatic valvePrincipal component analysisSupport vector regressionFault prognosis