Predicting mechanical properties in metal additive manufacturing (MAM) is
vital to ensure the printed parts' performance, reliability, and whether they
can fulfill requirements for a specific application. Conducting experiments to
estimate mechanical properties in MAM processes, however, is a laborious and
expensive task. Also, they can solely be designed for a particular material in
a certain MAM process. Nonetheless, Machine learning (ML) methods, which are
more flexible and cost-effective solutions, can be utilized to predict
mechanical properties based on the processing parameters and material
properties. To this end, in this work, a comprehensive framework for
benchmarking ML for mechanical properties is introduced. An extensive
experimental dataset is collected from more than 90 MAM articles and 140 MAM
companies' data sheets containing MAM processing conditions, machines,
materials, and resultant mechanical properties, including yield strength,
ultimate tensile strength, elastic modulus, elongation, hardness as well as
surface roughness. Physics-aware MAM featurization, adjustable ML models, and
evaluation metrics are proposed to construct a comprehensive learning framework
for mechanical properties prediction. Additionally, the Explainable AI method,
i.e., SHAP analysis was studied to explain and interpret the ML models'
predicted values for mechanical properties. Moreover, data-driven explicit
models have been identified to estimate mechanical properties based on the
processing parameters and material properties with more interpretability as
compared to the employed ML models.

本文介绍了一种基于机器学习的综合框架，用于金属增材制造过程中机械性能的预测，并提出了利用 SHAP 分析对机器学习模型预测结果进行解释和解读的方法，同时比较了数据驱动的显式模型相对于机器学习模型更具可解释性。