Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism
This work addresses the need for safer and more efficient material testing for researchers, though it appears incremental as it builds on existing generative and attention-based methods.
The authors tackled the problem of dangerous and complex material irradiation experiments by proposing a generative adversarial model that generates irradiated material images from experimental parameters and predicts industrial performance from images, achieving high-quality results compared to baseline models.
Material irradiation experiment is dangerous and complex, thus it requires those with a vast advanced expertise to process the images and data manually. In this paper, we propose a generative adversarial model based on prior knowledge and attention mechanism to achieve the generation of irradiated material images (data-to-image model), and a prediction model for corresponding industrial performance (image-to-data model). With the proposed models, researchers can skip the dangerous and complex irradiation experiments and obtain the irradiation images and industrial performance parameters directly by inputing some experimental parameters only. We also introduce a new dataset ISMD which contains 22000 irradiated images with 22,143 sets of corresponding parameters. Our model achieved high quality results by compared with several baseline models. The evaluation and detailed analysis are also performed.