Session: CIE-10-01 - CAPPD: Product and Process Design Automation and Computational Fabrication

Paper Number: 89538

89538 - Multi-Scale Topology Optimization With Neural Network-Assisted Optimizer 

The advent of additive manufacturing and its call for high-resolution structural designs attracts many researchers to multi-scale topology optimizations (TO) frameworks. With the advances of machine learning (ML) methods, the integration of ML with TO has been attempted in many works. However, most works employ ML in a data-driven paradigm, which requires abundant training data. The generalization ability of such a data-driven paradigm is also ambiguous.
This research aims to utilize the machine learning techniques as an optimizer for multi-scale structural design problems instead of just using them to accelerate the optimization. First, parameterized cellular materials (PCM) are utilized to develop a multi-scale parameterized TO problem. Then the problem is reformulated into a single unconstrained objective function using the penalty method and parameterized into a neural network (NN) that optimizes its weights and biases. The optimized network acts as a continuous model all over the design domain with the cellular material parameter as its response. 
This approach does not need to eliminate the elements with the intermediate densities, unlike density-based TO frameworks (e.g.,  SIMP).
It can also solve the high-resolution TO problems twenty thousand times faster than the Two-Scale method because of the NN-assisted optimizer. Also, to handle the connectivity issue (an issue related to multi-scale TO frameworks) between adjacent structures, the optimized NN can be discretized to a higher resolution, eliminating the need to use an interpolation filter. The performance of the proposed framework is significantly enhanced compared to the previously published method.

Presenting Author: Sina Rastegarzadeh University of Illinois at Chicago

Presenting Author Biography: Sina is a PhD student at UIC.

Authors:

Sina Rastegarzadeh University of Illinois at Chicago
Jun Wang University of Maryland
Jida Huang University of Illinois At Chicago