Search

The hunting motion of the vehicle increases the wear of the wheel tracks and affects the lateral stability of the vehicle system and safety, so the hunting motion of the vehicle needs to be recognized. However, the existing recognition methods ignore the small-amplitude hunting motion that precedes the onset of the running motion. In addition, due to the scarcity of real hunting data of high-speed trains, there is a problem of underfitting when training with traditional deep learning methods. In this paper, first, the dynamics model of a high-speed train is established, and the normal, small-amplitude hunting and hunting motions of high-speed trains in the process are simulated. Second, this paper proposes a transfer learning-based method for high-speed train hunting motion recognition. The method uses easily collected normal data samples in the training process, does not use real data samples of small-amplitude hunting and hunting motions, and completes the high-speed train running motions recognition task by transferring from simulation data (source domain) to real data (target domain). Finally, the validation is carried out using the real data, which proves that the method-related approach has some engineering application value in the intelligent monitoring of high-speed trains. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Joint Approximate Diagonalization of Eigen-matrices (JADE) cannot deal with non-stationary data. Therefore, in this paper, a method called Non-stationary Kernel JADE (NKJADE) is proposed, which can extract non-stationary features and fuse multi-sensor features precisely and rapidly. In this method, the non-stationarity of the data is considered and the data from multi-sensor are used to fuse the features efficiently. The method is compared with EEMD-SVD-LTSA and EEMD-JADE using the bearing fault data of CWRU, and the validity of the method is verified. Considering that the vibration signals of high-speed trains are typically non-stationary, it is necessary to utilize a rapid feature fusion method to identify the evolutionary trends of hunting motions quickly before the phenomenon is fully manifested. In this paper, the proposed method is applied to identify the evolutionary trend of hunting motions quickly and accurately. Results verify that the accuracy of this method is much higher than that of the EEMD-JADE and EEMD-SVD-LTSA methods. This method can also be used to fuse multi-sensor features of non-stationary data rapidly. [ABSTRACT FROM AUTHOR]