Exploring diagnosis of bogie faults using bearing simulation.

Original data of bogie faults is hardly obtained by a real experimental because a failure bogie system will make the train suffer from serious danger. Therefore a simulation train dynamics often used to simulate a bogie to obtain failure data. A high speed train is a multi body system which includes train body, bogie frameworks and wheels. This paper focused on bearing vibration analysis using data obtained from bearing simulation. A fault simulation platform was adopted as the experimental device. Data collection was conducted to normal state, inner fault, outer fault and rolling fault. Each fault was collected under the rotation of 300 rpm, 10 groups of data were collected of 10 second for.1 second of measurements. It is the objective of bogie fault characterization to develop an accurate diagnosis method. Deep neural network was proposed for fault diagnosis of bogie bearing. Features, time domain and frquency domain, should be extrcted prior to fault diagnosis. Sixteen time and frequency feature domains are used in fault characterization. This paper proposes bearing simulation methodology to explore diagnosis of bearing bogie faults. The simulation is based on mechanical modeling, lifetime of bearing can be determined. Lifetime data with operating conditions are modeled using Weibull regression, and then remaining life of bearing can be predicted. Multivariate analysis is propsed to characterized the bogie bearing faults. Neural networks is proposed to explore the characterization of bogie fault diagnosis and compared to multivariate analysis. [ABSTRACT FROM AUTHOR]