Topology Optimization Using Neural Networks With Conditioning Field Initialization for Improved Efficiency

Abstract

We propose conditioning field initialization for neural network-based topology optimization. In this work, we focus on (1) improving upon existing neural network-based topology optimization and (2) demonstrating that using a prior initial field on the unoptimized domain, the efficiency of neural network-based topology optimization can be further improved. Our approach consists of a topology neural network that is trained on a case by case basis to represent the geometry for a single topology optimization problem. It takes in domain coordinates as input to represent the density at each coordinate where the topology is represented by a continuous density field. The displacement is solved through a finite element solver. We employ the strain energy field calculated on the initial design domain as an additional conditioning field input to the neural network throughout the optimization. Running the same number of iterations, our method converges to a lower compliance. To reach the same compliance, our method takes fewer iterations. The addition of the strain energy field input improves the convergence speed compared to standalone neural network-based topology optimization.