Material crack tip multi-scale strain field measuring and tracking method based on deep learning

Abstract

The invention relates to a material crack tip multi-scale strain field measuring and tracking method based on deep learning. The method comprises the following steps: randomly spraying speckles on the surface of a material, applying an external force to the material to enable the material to deform and generate cracks, and collecting multi-scale information of material deformation by using a combination of cameras with different focal lengths; constructing a multi-scale material deformation image sequence as a data set; combining convolution, transposition convolution and a convolution LSTM neural network, and measuring a neural network model of a material global three-dimensional strain field; training a material three-dimensional strain field measurement neural network model by using the training set data; using the trained material three-dimensional strain field measurement neural network model, inputting a multi-scale image collected by the camera, measuring the three-dimensional strain field of the material in real time, calculating the crack area of the material through the strain field, and then moving the binocular long-focus camera to track the crack tip in real time. The movable long-focus binocular camera is used for tracking a crack area.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to image restoration technology. Background technique [0002] Digital Image Correlation (DIC) is a full-field strain measurement technique that is rapidly popularized in the field of experimental mechanics. It is an optical measurement method that strikes a good balance between versatility, ease of use, and metrology performance. This optical measurement method was proposed in the 1980s. In the past few decades, many scholars have improved the performance, accuracy, and stability of the DIC algorithm, expanding its application range and usability. [0003] 2D-DIC only uses a single camera, which limits it to only measure in-plane deformation and cannot measure complex shapes and deformations. In order to overcome the limitations of 2D-DIC, three-dimensional digital image correlation (3D-DIC) based on the principle of binocular stereo vision has been developed. 3D-DIC can measure ...

AI Technical Summary

Problems solved by technology

[0003] 2D-DIC only uses a single camera, which limits it to only measure in-plane deformation and cannot measure complex shapes and deformations

3D-DIC can measure the shape, strain, and strain of complex objects. The optical axis of the camera does not need to measure the surface of the object vertically before measuring. The early adjustment of the equipment is simple and the environmental sensitivity is low.

However, this technology still belongs to the traditional two-dimensional displacement field and strain field measurement range, and cannot accurately detect three-dimensional displacement.

Images