Rapid Classification and Evaluation Method of the Temperature Stress of Continuous Welded Rail Based on the Metal Magnetic Memory Technique

Abstract

How to realize the rapid and real-time monitoring of the temperature stress of continuous welded rail (CWR) is an important problem related to the safety and stability of the railway. Its goal is to give early warning and guide the maintenance of the railway in time, so asto avoid the occurrence of the safety accidents [1]. To solve this problem, this paper proposes a quantitative evaluation method of the temperature stress of CWR based on the metal magnetic memory (MMM) technique.Taking a section of CWR in Baoding, Hebei Province as the research object, the magnetic Barkhausen noise (MBN) technique is used to mark the MMM signal. The MMM signal is analyzed both in the time domain and the frequency domain. The frequency-domain analysis is to perform the wavelet packet decomposition on the MMM signal, and calculate the relative wavelet packet energy of each subband and the wavelet packet energy Shannon entropy as the frequency-domain features. On this basis, the support vector machine (SVM) algorithm is used to establish the quantitative model for the evaluation of the temperature stress. The experiment results show that this method can evaluate the temperature stress of CWR quickly and quantitatively, and provide a principle for the evaluation of the safety and stability of CWR.