Scalable deep-learning-accelerated topology optimization for additively manufactured materials

This is an illustration of the key idea. The sequence of local DNNs are trained using local samples (red dots) covering only the search path (black line).


We developed a scalable deep-learning-based optimal design method that exploits SUMMIT to significantly accelerate composite material design process with up to 85% cost reduction. The new method addresses three grand challenges in optimal design: (i) high-dimensional design space, (ii) computationally expensive multi-physics models, (iii) non-parallelizable optimization algorithms. Those challenges are addressed based on our observation that an optimizer only walks along a 1-D search path to find the optimum, regardless of the dimension of the design space. Thus, our goal is to construct a low-dimensional ML-model that can cover the 1-D search path. To this end, we developed a sequence of local deep neural networks (DNNs), each of which only covers a segment of the search path. To further reduce the dimensionality, we designed a new sampling strategy that can concentrate the training samples along the gradient descent direction. Our algorithm was implemented on SUMMIT, where hundreds of CPUs are used to produce training data, and hundreds of GPUs are used to train DNN models. 

Significance and Impact

Our method can exploit the powerfulness of SUMMIT to accelerate a high-resolution material design process with up to 85% time cost reduction.

Research Details


Jiaxin Zhang, Sirui Bi, and Guannan Zhang, Scalable deep-learning-accelerated topology optimization for additively manufactured materials, NeurIPS Workshop on Machine Learning for Engineering Modeling, Simulation and Design, 2020. [Download our poster] [A short video presentation]


Last Updated: January 14, 2021 - 11:04 am