Predicting elastic strain fields in defective microstructures using image colorization algorithms

Deep learning prediction of stress fields in additively manufactured metals with intricate defect networks

“…This architecture has recently been extended to predict the mechanical response of fiber-reinforced composites at the microscale [29] and mesoscale [30], and also to predict stress concentrations around microscale pores in a multiscale FE model [31]. Alternative CNN architectures such as generative adversarial network [32] or image colorization networks [33] used to predict stress from microstructural images with varying levels of success. While promising, these studies have exposed several limitations.…”

“… Finally, we introduce a U-Net style architecture [37] that includes shortcut connections between the encoder and decoder portions of the model. Compared to the StressNet [28] and simple image colorization CNN [33] architectures, this design allows the model to readily incorporate information from multiple length scales into the stress prediction, which enhances the model's performance.…”

Effect of Prior Surface Textures on the Resulting Roughness and Residual Stress during Bead-Blasting of Electron Beam Melted Ti-6Al-4V

“…In 382 previous studies that focused on indentation of Inconel 718 [18,62], the authors explored 383 the combined effect of surface roughness and void inhomogeneities on the mechanics of 384 indentation. Using numerical simulations the authors have also realized that the nature 385 of the inhomogeneities characterized by their shape, size, aspect ratio [63] and location 386 We note that there are different sources of inhomogeneity in AM components. In previous studies that focused on indentation of Inconel 718 [18,62], the authors explored the combined effect of surface roughness and void inhomogeneities on the mechanics of indentation.…”

“…In previous studies that focused on indentation of Inconel 718 [18,62], the authors explored the combined effect of surface roughness and void inhomogeneities on the mechanics of indentation. Using numerical simulations, the authors have also realized that the nature of the inhomogeneities characterized by their shape, size, aspect ratio [63], and location within the part geometry [64] complicate the mechanical response of components. However, these variables are not tested in the context of bead-blasting in this study.…”

A Pilot Study on the Prevalence of Artificial Intelligence in Canadian Engineering Design Curricula

“…Engineering design researchers utilize AI-based algorithms methods, especially machine learning, for rapid design data learning and processing [17]- [19] and have achieved successful results in their research contributions. Such contributions include evaluating design concepts [20], decision making for design support systems [21], design for additive manufacturing [22], predicting strain fields in microstructure designs [23], predicting performance of design based on its shape and vice-versa [24], material selection for sustainable product design [25] etc. Certain applications of AI that have proven efficient in analyzing computer-aided design (CAD) data include predicting the function of CAD model from its form [26], suitable feature-removal in CAD models for simulations [27], and CAD design shape matching [28].…”