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

Analysis of the Stress Field in Photoelasticity Used to Evaluate the Residual Stresses of a Plastic Injection-Molded Part

The degree of quality of thermoplastic injection-molded parts can be established based on their weight, appearance, and defects. However, the conditions of the injection process may induce effects on the mechanical performance of the injected parts, and the residual stresses can cause cracks or early failures when an external load or force is applied. To evaluate these mechanical behaviors, different experimental techniques have been reported in the literature, where digital photoelasticity has stood out both for being a non-contact technique and for achieving quantitative results through sophisticated computational algorithms. Against this background, our proposal consists of analyzing the overall residual stress distribution of parts injected under different molding conditions by using digital photoelasticity. In this case, the specimens are subjected to bending strength tests to identify possible effects of the injection process conditions. The findings show that, at mold temperatures of 80 °C, flow-induced residual stresses increase with packing pressure. However, these internal stress levels do not affect the external load applied by the mechanical bending test, while the mass injected at higher levels of packing pressure helps to increase the bending strength of the injected part. At lower mold temperatures (50 °C), the mechanical strength of the injected part is slightly reduced, possibly due to a lower effect of the packing pressure.

Fringe pattern analysis to evaluate light sources and sensors in digital photoelasticity

When experimental photoelasticity images are acquired, the spectral interaction between the light source and the sensor used affect the visual information of the fringe patterns in the produced images. Such interaction can lead to fringe patterns with an overall high quality, but also can lead to images with indistinguishable fringes, and bad stress field reconstruction. We introduce a strategy to evaluate such interaction that relies on measuring the value of four handcrafted descriptors: contrast, an image descriptor that accounts simultaneously for blur and noise, a Fourier-based descriptor to measure image quality, and image entropy. The utility of the proposed strategy was validated by measuring the selected descriptors on computational photoelasticity images, and the fringe orders achieved when evaluating the stress field, from 240 spectral configurations: 24 light sources and 10 sensors. We found that high values of the selected descriptors can be related to spectral configurations that lead to better stress field reconstruction. Overall, the results show that the selected descriptors can be useful to identify bad and good spectral interactions, which could help to design better protocols for acquiring photoelasticity images.

Isochromatic-Art: A Computational Dataset for Digital Photoelasticity Studies

The importance of evaluating the stress field of loaded structures lies in the need for identifying the forces which make them fail, redesigning their geometry to increase the mechanical resistance, or characterizing unstressed regions to remove material. In such work line, digital photoelasticity highlights with the possibility of revealing the stress information through isochromatic color fringes, and quantifying it through inverse problem strategies. However, the absence of public data with a high variety of spatial fringe distribution has limited developing new proposals which generalize the stress evaluation in a wider variety of industrial applications. This dataset shares a variated collection of stress maps and their respective representation in color fringe patterns. In this case, the data were generated following a computational strategy that emulates the circular polariscope in dark field, but assuming stress surfaces and patches derived from analytical stress models, 3D reconstructions, saliency maps, and superpositions of Gaussian surfaces. In total, two sets of ‘101430’ raw images were separately generated for stress maps and isochromatic color fringes, respectively. This dataset can be valuable for researchers interested in characterizing the mechanical response in loaded models, engineers in computer science interested in modeling inverse problems, and scientists who work in physical phenomena such as 3D reconstruction in visible light, bubble analysis, oil surfaces, and film thickness.

Accuracy improvement of demodulating the stress field with StressUnet in photoelasticity

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.

Photoelastic Stress Field Recovery Using Deep Convolutional Neural Network

Recent work has shown that deep convolutional neural network is capable of solving inverse problems in computational imaging, and recovering the stress field of the loaded object from the photoelastic fringe pattern can also be regarded as an inverse problem solving process. However, the formation of the fringe pattern is affected by the geometry of the specimen and experimental configuration. When the loaded object produces complex fringe distribution, the traditional stress analysis methods still face difficulty in unwrapping. In this study, a deep convolutional neural network based on the encoder-decoder structure is proposed, which can accurately decode stress distribution information from complex photoelastic fringe images generated under different experimental configurations. The proposed method is validated on a synthetic dataset, and the quality of stress distribution images generated by the network model is evaluated using mean squared error (MSE), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and other evaluation indexes. The results show that the proposed stress recovery network can achieve an average performance of more than 0.99 on the SSIM.