Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiency
This work addresses efficiency issues in topology optimization for engineering design, but it is incremental as it builds upon existing neural network methods.
The paper tackles the problem of slow convergence in neural network-based topology optimization by introducing a conditioning field initialization method, resulting in improved convergence speed compared to standalone neural network approaches.
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, (2) demonstrating that by 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. The addition of the strain energy field input improves the convergence speed compared to standalone neural network based topology optimization.