An Acoustic Emission Signal Detection Method for Rail Cracks Based on Improved Long-Short-Term Memory Network

Abstract

A rail crack acoustic emission signal detection method based on an improved long-short-term memory network. The invention solves the problem of automatically filtering out complex noise by training a noise model through an LSTM cycle network in the complex noise environment of a railway site. The main steps of the present invention are to establish the timing model of the background noise and the timing model of the crack signal twice in a row based on the LSTM network of the same structure, and take the upper envelope of the error signal predicted by the two to make a difference, so as to remove the abnormal noise therein, Finally, the crack signal component contained in the noise signal is detected. Compared with the prior art, the present invention has the following advantages: 1) the cascaded timing model can be used to filter out abnormal noise with unknown generation mechanism; 2) automatically learns the noise model without any prior knowledge; When the signal is completely submerged by the noise under the background of strong noise, the method can still effectively detect the acoustic emission signal of the crack.

Description

technical field [0001] The invention relates to a method in the field of denoising and detection of high-speed railway rail crack signals, in particular to a rail crack acoustic emission signal detection method based on an improved long-short-term memory network. Background technique [0002] In today's world, the development of high-speed railways benefits people's livelihood. At present, my country is vigorously promoting the construction of high-speed railway network, which not only brings convenience to people's daily travel, but also promotes national economic development. However, the current situation of high-speed rail lines with complex interlacing and large mileage also brings more severe challenges to the task of rail safety monitoring. With the rapid development of high-speed railway, the safety of high-speed railway has been paid more and more attention by people. In the high-speed railway system, the effects of long-term collision and extrusion caused by high...

AI Technical Summary

Problems solved by technology

However, due to the sensitivity and passive characteristics of acoustic emission detection technology, acoustic emission acquisition signals are more easily affected by noise.

There are usually more complex noise components in the signals collected on the railway site. The background noise is mainly caused by friction and wear accompanied by the mechanical interaction between the wheels and rails, and has obvious stability and timing; sex noise

Images