PATO: Producibility-Aware Topology Optimization using Deep Learning for Metal Additive Manufacturing

TL;DR

This paper introduces PATO, a deep learning-based topology optimization framework that explicitly incorporates manufacturability constraints for metal additive manufacturing, enabling the design of crack-free parts with reduced computational costs.

Contribution

The paper presents a novel integration of deep learning surrogate models with topology optimization to ensure crack-free designs in metal additive manufacturing, using a new crack index and an attention-based U-Net architecture.

Findings

Maximum shear strain index (MSSI) accurately predicts crack susceptibility.

Deep learning surrogate reduces computational cost of build process simulation.

Optimized designs demonstrate improved manufacturability and performance.

Abstract

In this paper, we propose PATO-a producibility-aware topology optimization (TO) framework to help efficiently explore the design space of components fabricated using metal additive manufacturing (AM), while ensuring manufacturability with respect to cracking. Specifically, parts fabricated through Laser Powder Bed Fusion are prone to defects such as warpage or cracking due to high residual stress values generated from the steep thermal gradients produced during the build process. Maturing the design for such parts and planning their fabrication can span months to years, often involving multiple handoffs between design and manufacturing engineers. PATO is based on the a priori discovery of crack-free designs, so that the optimized part can be built defect-free at the outset. To ensure that the design is crack free during optimization, producibility is explicitly encoded within the standard formulation of TO, using a crack index. Multiple crack indices are explored and using experimental validation, maximum shear strain index (MSSI) is shown to be an accurate crack index. Simulating the build process is a coupled, multi-physics computation and incorporating it in the TO loop can be computationally prohibitive. We leverage the current advances in deep convolutional neural networks and present a high-fidelity surrogate model based on an Attention-based U-Net architecture to predict the MSSI values as a spatially varying field over the part's domain. Further, we employ automatic differentiation to directly compute the gradient of maximum MSSI with respect to the input design variables and augment it with the performance-based sensitivity field to optimize the design while considering the trade-off between weight, manufacturability, and functionality. We demonstrate the effectiveness of the proposed method through benchmark studies in 3D as well as experimental validation.