Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for detecting shape of natural crack based on natural crack model

A natural crack, model detection technology, applied in biological neural network models, measurement devices, electromagnetic measurement devices, etc., to achieve the effect of reducing errors

Inactive Publication Date: 2012-03-14
SHANGHAI UNIV OF ENG SCI
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the many overlaps between the stress corrosion crack surfaces, the crack area has a certain degree of conductivity.

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
  • Method for detecting shape of natural crack based on natural crack model
  • Method for detecting shape of natural crack based on natural crack model
  • Method for detecting shape of natural crack based on natural crack model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A method for detecting the shape of a natural crack based on a natural crack model, the method comprising the following steps:

[0039] 11) Establish a natural crack sample shape and detection signal database;

[0040] 12) Utilize the natural crack sample shape and detection signal set up in step 11) to train the neural network;

[0041] 13) Establish the estimation model of the natural crack to be detected, and improve the estimation model of the natural crack to be detected so that it is close to the real crack shape;

[0042] 14) Obtain the shape of the real natural crack from the corresponding point information in the natural crack model obtained in step 13).

[0043] The method of establishing the natural crack sample shape and detection signal database in the above step 11) is as follows:

[0044] 21) Simulate the natural environment to make natural crack samples, the number of which can be 50;

[0045] 22) First conduct eddy current testing and collect signals...

Embodiment 2

[0066] like figure 1 As shown in the flow chart of the method for detecting the shape of natural cracks based on the natural crack model, the present invention relates to a method for detecting the shape of natural cracks based on the natural crack model. The method includes the following steps:

[0067] 11) Establish a natural crack sample shape and detection signal database;

[0068] 12) Utilize the natural crack sample shape and detection signal set up in step 11) to train the neural network;

[0069] 13) Establish the estimation model of the natural crack to be detected, and improve the estimation model of the natural crack to be detected so that it is close to the real crack shape;

[0070] 14) Obtain the shape of the real natural crack from the corresponding point information in the natural crack model obtained in step 13).

[0071] The method of establishing the natural crack sample shape and detection signal database in the above step 11) is as follows:

[0072] 21)...

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 relates to a method for detecting a shape of a natural crack based on a natural crack model, which comprises the following steps that: (1) establishing an estimated model of the shape of a natural crack to be detected; (2) utilizing a trained nerve network to predict an eddy-current detection signal of the natural crack model established in step (1); (3) carrying out the eddy-current detection on the natural crack to be detected and collecting a signal; (4) calculating an error between the actual detection signal collected in step (3) and the predicted signal obtained in step (2): comparing the error with a set threshold value, if the error is greater than the threshold value, returning the step (1) to improve the estimated model of the natural crack to be detected to be re-executed; and if the error is smaller than the threshold value, obtaining the model of the natural crack to be detected; and (5) joining corresponding points in the natural crack model obtained in step (4) to obtain the actual shape of the natural crack. Compared with the prior art, the method has the advantages that the length of the crack is approximate to the actual length, the error is small and the like.

Description

technical field [0001] The invention relates to a method for detecting the shape of a natural crack, in particular to a method for detecting the shape of a natural crack based on a natural crack model. Background technique [0002] Eddy current testing is a widely used non-destructive testing technology, which has excellent performances such as fast detection speed and sensitive response to surface defects. At present, the eddy current testing method has played an important role in the in-service testing of steam generator pipelines, nuclear power plant heat exchange pipelines and many other key equipment. With the further strengthening of the safety requirements for equipment structures, when evaluating the crack growth trend and its severity, it is necessary to obtain the position and shape information of the crack from the eddy current detection signal, which requires an accurate crack model first. [0003] The main types of cracks found in the actual inspection are stre...

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): G01B7/28G01N27/90G06N3/02G01N27/9013
Inventor 张思全陆文华胡盛斌
Owner SHANGHAI UNIV OF ENG SCI