Damage crack acoustic emission signal detection method based on unequal distance optimization clustering algorithm

A technology of acoustic emission signal and clustering algorithm, which is applied in the processing of detection response signals, material analysis and calculation using acoustic emission technology, and can solve noise misjudgment, detection accuracy lower than other methods, and detection speed change. Slow and other problems, to achieve the effect of increasing the signal detection rate, reducing the amount of data calculation, and saving time and cost

Active Publication Date: 2021-04-30
HARBIN INST OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The principles and characteristics of the above detection methods are different, and are widely used in the field of damage crack detection, but there are also many shortcomings
The ultrasonic testing method needs to add a coupling agent between the testing probe and the object to be tested, which slows down the testing speed and seriously affects the testing efficiency.
The magnetic flux leakage detection technology has a fast detection speed for damage cracks, but it is often limited by the physical mechanism. It can only detect surface or shallow surface cracks, but cannot detect internal damage cracks, and the detection accuracy is low; eddy current detection technology can detect internal cracks. Damage cracks, and the detection efficiency is high, and the detection process is simple. However, the application of eddy current detection method is limited, and it is only suitable for damage detection of objects with large cracks in the cross section; visual detection is widely used, but the detection accuracy is far lower than other methods. several methods
In recent years, the acoustic emission detection method has attracted more and more attention. This method is a passive monitoring method that can monitor the damage state of the rail in real time. However, due to the huge noise interference in the train running process, the detection method The accuracy is low, and it is easy to misjudge the noise. Therefore, it is of great significance to propose a damage detection method that can overcome noise interference and have high detection accuracy.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Damage crack acoustic emission signal detection method based on unequal distance optimization clustering algorithm
  • Damage crack acoustic emission signal detection method based on unequal distance optimization clustering algorithm
  • Damage crack acoustic emission signal detection method based on unequal distance optimization clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0055] Execute step 1: load the acoustic emission signal containing the damaged crack Signal sampling rate 5MHz at this time N 0 =2867200. Obtain multi-segment noise signals and concatenate them into longer acoustic emission signals in the time dimension At this time N 1 =503937, signal such as figure 2 shown.

[0056] Execute Step 2: Under the moving time window processing, the acoustic emission signal Extract the γ cepstral coefficient feature, denoted as M 11855×39 , that is, after obtaining 39-dimensional features, the GTCC coefficients, first-order difference GTCC coefficients, and second-order difference GTCC coefficients each have 13 dimensions. The robust coefficients of the 39-dimensional γ-cepstral coefficient features are calculated, and the results are shown in Table 1.

[0057] Table 1 Clustering γ cepstral coefficient robustness coefficients in each dimension

[0058] dimension 1 2 3 4 5 6 7 8 Robust coefficient 0.9861 0.9820 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a damage crack acoustic emission signal detection method based on an unequal distance optimization clustering algorithm, relates to a method in the field of damage crack signal processing and detection, and solves the problems of low speed and low efficiency of a traditional crack signal detection method. The method comprises the following steps: 1, an original acoustic emission signal is loaded to obtain a noise acoustic emission signal; 2, gamma cepstrum coefficient characteristics are extracted from the noise acoustic emission signals, and the noise acoustic emission signals are screened according to adaptive robust coefficients; 3, the noise signal features are clustered, the distance from each feature to the centroid of each cluster is calculated, and the unequal optimized distance value of each cluster is calculated; and S3, gamma cepstrum coefficient characteristics of a to-be-detected acoustic emission signal are extracted, the characteristics of the to-be-detected signal are selected according to the step S2, the distance from each characteristic to each cluster centroid is calculated, and the to-be-detected signal is judged according to the unequal distance optimization judgment algorithm. The method is high in operation rate and high in detection precision. The method has very high social significance and economic value in the field of high-speed rail steel rail and wheel damage crack detection.

Description

technical field [0001] The invention relates to a method in the field of rail crack signal processing and detection, in particular to a damage crack acoustic emission signal detection method based on an unequal distance optimization clustering algorithm. Background technique [0002] Since the opening of China's first high-speed railway Qinshen Passenger Dedicated Line in 2003, China's high-speed rail industry has begun to leap forward rapidly. In 17 years, the high-speed rail version Figure 1 Further expansion will spread all over the great rivers and mountains of the motherland, connecting the north and the south, and stretching across the east and west. In recent years, high-speed rail has gone abroad and become a beautiful business card of Chinese manufacturing. Faced with the current situation of high-speed railways with staggered and complex lines and large mileage, ensuring the safe, stable and reliable operation of high-speed railways will be the top priority of rai...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N29/14G01N29/46G06K9/62
CPCG01N29/14G01N29/46G01N2291/2623G01N2291/0289G06F18/23
Inventor 章欣常永祺郝秋实宋树帜沈毅王艳
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products