An investigation on acoustic emission detection of rail crack in actual application by chaos theory with improved feature detection method

In order to detect rail cracks by Acoustic Emission (AE) technology, many researches are carried out based on the theoretical and experimental conditions. However, how to detect the crack signals in real noise environment of railway is a key problem for actual application, which has few researches. In this paper, AE detection of rail cracks in real noise environment is investigated and an improved method is proposed to increase the accuracy of crack detection. The AE noise signals are acquired from real operation conditions. They are analyzed and reconstructed by chaos theory. Based on the reconstructed vectors, a reasonable Nonlinear AutoRegressive with eXogenous input (NARX) model of AE noises is built to eliminate noises. For suppressing the abnormal noise interference, a feature detection method is proposed to improve the detection accuracy based on the fused features. Meanwhile, the detection ability of the proposed method is further verified by a longer signal. The results illustrate that the proposed method is effective to detect crack signals in real noise environment. Moreover, the actual application of the proposed method is also discussed and it can provide a useful guidance for AE detection of rail cracks.