Artificial intelligence (AI) based deep learning of defects, surface roughness and their linkage to mechanical performance of additively manufactured (AM) aluminum alloys

该联盟项目专注于将基于人工智能(AI)的机器学习(ML)方法应用于添加剂制造(AM)领域，以开发一个框架，用于连接长度尺度，并在工艺参数、微结构特征和由此产生的添加剂制造部件的机械性能特征之间建立联系。AM成型零件的主要问题之一是显微组织随工艺引起的缺陷(如气孔和表面粗糙度)的变化。这些材料的机械性能，如疲劳寿命，在很大程度上取决于制造过程中所采用的工艺参数的选择。激光加工工艺参数、表面粗糙度、残余应力和气孔率等多种因素的协同作用对AM零件的疲劳行为有显著影响。缺乏对这些因素之间联系的了解是AM过程优化及其广泛适用性的最关键的决策差距。在这些方面，基于人工智能(AI)的机器学习工具是识别和量化这些基本材料和工艺参数或显著特征的关键因素，以提高AM部件的机械性能。该项目结合了人工智能和添加剂制造领域的最新进展，从理论和实验两个方面研究了利用激光粉床熔化技术(LPBF)制备3D打印铝合金的组织、性能和性能之间的关系。

This Alliance project focuses on application of artificial intelligence (AI) based machine learning (ML) approaches to the field of additive manufacturing (AM) to develop a framework for bridging length scales and establishing linkages between process parameters, microstructural features and the resulting mechanical performance characteristics of additively manufactured parts. One of the major concerns in AM build parts is the variation in the microstructure along with the process induced defects such as porosity and surface roughness. The mechanical properties such as fatigue life of these materials are strongly governed by the choice of process parameters employed during the fabrication process. A wide variety of synergistic factors such as laser process parameters, surface roughness, residual stresses and porosity can significantly influence the fatigue behavior of AM parts. A lack of understanding of the linkages between such factors is the most critical decision-making gap for AM process optimization and its wide scale applicability. In these regards, artificial intelligence (AI) based machine learning tools are key enablers for identification and quantification of such essential material and process parameters or salient features for improved mechanical performance of AM parts. This project combines the latest advancements in the field of artificial intelligence and additive manufacturing, both theoretically and experimentally with an aim to investigate microstructure, property and performance relationships for 3D printed aluminum alloys by means of laser powder bed fusion (LPBF) technology.