学术文献库

The capability of multi-input field-to-field regression, i.e. mapping the initial field and applied conditions to the evolved field, is appealing, enabling ultra-fast physics-free simulation of various field evolvements across many disciplines. We hereby propose a y-shaped multi-input deep convolutional network, yNet, which can effectively account for combined effects of multiple mixed inputs on output field. The proposed yNet is applied to the simulation of porosity evolution in selective lasering sintering (SLS). Upon testing, yNet can simulate nearly identical porosity evolution and development to the physics-based model, with a 99.13% morphological similarity for various SLS conditions. We then effortlessly boost the porosity simulation capability to the realistic, full-component level. yNet is generally applicable to simulating various structural/morphological evolutions and other condition-concerned, continuous field evolvements even with spatially and/or temporally non-uniform evolving kinetics. Once trained, the light-weight yNet can be distributed easily and ran with limited computational resource while reducing computation time to a split second. It thus may have a transformative impact by democratizing the capability of ultra-fast and extreme-scale simulation of various field evolvements.