An Intelligence Method for Recognizing Multiple Defects in Rail.

Fei Deng,Cheng Zhou,Lin Zhao,Shu-Qing Li,Xi-Ran Zhang,Ji-Bing Huang

doi:10.3390/s21238108

Fei Deng, Cheng Zhou + Show 4 more

Open Access

https://doi.org/10.3390/s21238108

Copy DOI

Abstract

Ultrasonic guided waves are sensitive to many different types of defects and have been studied for defect recognition in rail. However, most fault recognition algorithms need to extract features from the time domain, frequency domain, or time-frequency domain based on experience or professional knowledge. This paper proposes a new method for identifying many different types of rail defects. The segment principal components analysis (S-PCA) is developed to extract characteristics from signals collected by sensors located at different positions. Then, the Support Vector Machine (SVM) model is used to identify different defects depending on the features extracted. Combining simulations and experiments of the rails with different kinds of defects are established to verify the effectiveness of the proposed defect identification techniques, such as crack, corrosion, and transverse crack under the shelling. There are nine channels of the excitation-reception to acquire guided wave detection signals. The results show that the defect classification accuracy rates are 96.29% and 96.15% for combining multiple signals, such as the method of single-point excitation and multi-point reception, or the method of multi-point excitation and reception at a single point.

Highlights

As an infrastructure, the structural health of the rails has attracted much attention in the fields of engineering and NDT
The guided wave detection signals are divided into P sub-signal segments with a time interval Tc
Aiming to identify multiple defects in rail, experiments and numerical simulations are used to focus on the ultrasonic guided wave detection signals of crack defect, transverse crack under shelling, and corrosion defect

Summary

Introduction

The structural health of the rails has attracted much attention in the fields of engineering and NDT. Because of the influence of the manufacturing process, the operating situation, and the geographic conditions, rails are prone to various defects. Based on the analysis of the operating situation, rolling contact is the main reason for the rail surface crack. The inclusion in the railhead can lead to an area-shaped section within the rail, which will lead to the formation of transverse cracks under the shelling. Attracted by multi-mode and low attenuation, ultrasonic guided waves can perform nondestructive testing of multiple types of defects in long-range rails [4,5,6,7,8]. Lee et al [12] presented a hybrid analytical-FEM technique based on the dispersion characteristics of the guided wave to design the sensor which can excite specific modes and frequencies for identifying transverse cracking under the shelling. Based on the Lamb wave, Deng et al [15] proposed the method of automatically searching defects to achieve defect location in the plate structure

Methods

Results

Conclusion