Abstract

Evaluating the stress field based on photoelasticity is of vital significance in engineering fields. To achieve the goal of efficiently demodulating stress distribution and to overcome the limitations of conventional methods, it is essential to develop a deep learning method to simplify and accelerate the process of image acquisition and processing. A framework is proposed to enhance prediction accuracy. By adopting Resnet as the backbone, applying U-Net architecture, and adding a physical constraint module, our model recovers the stress field with higher structural similarity. Under different conditions, our model performs robustly despite complicated geometry and a large stress range. The results prove the universality and effectiveness of our model and offer an opportunity for instant stress detection.

© 2022 Optica Publishing Group

PhotoelastNet: a deep convolutional neural network for evaluating the stress field by using a single color photoelasticity image

Juan C. Briñez-de León, Mateo Rico-García, and Alejandro Restrepo-Martínez
Appl. Opt. 61(7) D50-D62 (2022)

Practical method for improving the accuracy of weakly stressed birefringence detection by circularly polarized instantaneous photoelasticity

Yang Gao, Xinjun Wan, Zhenlei Wang, and Xiaoxiao Wei
Appl. Opt. 62(5) 1237-1242 (2023)

Algorithm and its application for automatic measurement of the full-field isoclinic parameter by digital phase-shifting photoelasticity

Wei Shang, Hulin Li, Jinghong Liu, and Jinzhao Liu
Appl. Opt. 61(35) 10433-10438 (2022)

Improvement of digital photoelasticity based on camera response function

Shih-Hsin Chang and Hsien-Huang P. Wu
Appl. Opt. 50(27) 5263-5270 (2011)

Experimental analysis of stress fields of rotating structural elements by means of reflection photoelasticity

Peter Frankovský, Oskar Ostertag, Eva Ostertagová, František Trebuňa, Ján Kostka, and Marek Výrostek
Appl. Opt. 56(11) 3064-3070 (2017)