An Artificial Neural Network Approach for Generating High-Resolution Designs From Low-Resolution Input in Topology Optimization

Abstract

Abstract We address a central issue that arises within element-based topology optimization. To achieve a sufficiently well-defined material interface, one requires a highly refined finite element mesh; however, this leads to an increased computational cost due to the solution of the finite element analysis problem. By generating an optimal structure on a coarse mesh and using an artificial neural network to map this coarse solution to a refined mesh, we can greatly reduce computational time. This approach resulted in time savings of up to 85% for test cases considered. This significant advantage in computational time also preserves the structural integrity when compared with a fine-mesh optimization with limited error. Along with the savings in computational time, the boundary edges become more refined during the process, allowing for a sharp transition from solid to void. This improved boundary edge can be leveraged to improve the manufacturability of the optimized designs.