A multi-sensor fusion framework for detecting small amplitude hunting of high-speed trains

Abstract

Hunting monitoring is very important for high-speed trains to achieve safe operation. But all the monitoring systems are designed to detect hunting only after hunting has developed sufficiently. Under these circumstances, some damage may be caused to the railway track and train wheels. The work reported in this paper aims to solve the detection problem of small amplitude hunting before the lateral instability of high-speed trains occurs. But the information from a single sensor can only reflect the local operation state of a train. So, to improve the accuracy and robustness of the monitoring system, a multi-sensor fusion framework for detecting small amplitude hunting of high-speed trains based on an improved Dempster–Shafer (DS) theory is proposed. The framework consists of a series of steps. Firstly, the method of combining empirical mode decomposition and sample entropy is used to extract features of each operation condition. Secondly, the posterior probability support vector machine is used to get the basic probability assignment. Finally, the DS theory improved by the authors is proposed to get a more accurate detection result. This framework developed by the authors is used on high-speed trains with success and experimental findings are provided. This multi-sensor fusion framework can also be used in other condition monitoring systems on high-speed trains, such as the gearbox monitoring system, from which nonstationary signals are acquired too.

Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review

“…Ning et al [ 336 ] took into consideration the problem of small-amplitude hunting detection before the occurrence of lateral instability observed in the case of high-speed trains. Data obtained with only one sensor were considered by authors to be insufficient; therefore, in order to improve the accuracy and robustness of the monitoring system for the detection of small-amplitude hunting, the authors developed a multi sensor fusion framework using the Dempster–Shafer theory.…”

iVRIDA: intelligent Vehicle Running Instability Detection Algorithm for High-speed Rail Vehicles using Temporal Convolution Network – A Pilot Study

“…These signal-based features are fed into k Nearest Neighbor (kNN) and Artificial Neural Network (ANN) fault classifiers to diagnose the reason behind the observed vehicle running instability, mainly vehicle-based faults. Ning et al, (2018), propose data-driven fault classifiers combined with data fusion of multiple bogie frame accelerations for diagnostics of vehicle hunting. The authors employ Empirical Mode Decomposition (EMD) and Sample Entropy (SE) methods to extract features associated with small amplitude hunting and incorporate them into Support Vector Machine (SVM) classifier as fault identifiers.…”

Vehicle running instability detection algorithm (VRIDA): A signal based onboard diagnostic method for detecting hunting instability of rail vehicles

“…Bosso et al 11 proposed a stability index (P18) which is calculated by comparing lateral axlebox acceleration against EN14363 12 instability criterion after considering harmonization among lateral and longitudinal axlebox acceleration signals, however the authors only investigated amplitude harmonization. Ning et al 13 proposed datadriven fault classifiers combined with data fusion of multiple bogie frame accelerations for diagnostics of vehicle hunting. Zeng et al 14 proposed an data-driven algorithm to estimate state variable's periodicity in the non-linear dynamic system to detect hunting based on axlebox accelerations and described a corresponding hunting alarm strategy.…”