Intelligent detection method of high-speed turnout crack damage based on vibration signal fusion

Abstract

The invention discloses an intelligent detection method of high-speed turnout crack damage based on vibration signal fusion. The intelligent detection method comprises the following steps: firstly, respectively mounting vibration acceleration sensors at a turnout tip, a turnout center and a turnout tail of a high-speed turnout, so as to collect vibration signals, and respectively carrying out CEEMD adaptive decomposition on the vibration signals of the three detection points, so as to obtain a limit number of IMF components; then, screening out a main IMF component by using correlation analysis, and calculating singularity entropy eigenvalue of the main IMF component; fusing singularity entropy eigenvalue of the vibration signals of a plurality of the detection points into an eigenvector, and inputting the eigenvector into LSSVM for training and testing, so as to achieve judgement of the working condition and damage type of the turnout. According to the intelligent detection method, different crack damage of the turnout can be effectively distinguished, and the method has good realtime performance and noise resistance, and provides a novel technological means for intelligent diagnosis of turnout fault.

Description

technical field [0001] The invention relates to an intelligent detection method for crack damage of high-speed turnouts based on vibration signals, and belongs to the technical field of railway turnout detection and maintenance. Background technique [0002] As an important part of the railway track, the turnout is an indispensable line equipment for high-speed railways, and it is also a weak link on the line, which is closely related to the train speed and safety performance. When the train passes through the turnout line, due to the strong impact force of the wheels on the track, it may cause damage types such as contact fatigue, wear, cracks and even track deformation. If the damage of the turnout is not detected and treated in time, as time goes by, the damage of the turnout will further deteriorate, which may cause major accidents such as train derailment, which poses a serious threat to the safe operation of the train. Therefore, it is of great significance to study t...

AI Technical Summary

Problems solved by technology

From a technical point of view, the patent application only collects signals from one vibration pickup point for damage detection, and cannot detect the location of the damage (along the direction of the rail line), nor does it know how far the damage is from the vibration pickup point able to detect

Because the track line is too long, to detect the damage position, it is necessary to lay a huge number of sensors along the line and build a sensor network (see paragraph 26 of the patent application specification). The consequences of doing this are: first, the amount of data is too large to handle; After the vibration signal propagates through the rigidity of the rail, it will affect multiple sensors, that is, the damage information will be reflected in the power spectrum characteristics of the vibration signals of multiple sensors, making it difficult to identify damage by the power spectrum feature distinction method

Figure 8 The actual measurement results also verified that the power spectrum feature cannot judge the working status and damage type of the turnout.

Images