Additive manufacturing (AM) of high-strength metals is currently based on the laser powder bed fusion (LPBF) process, which can introduce internal material flaws, such as pores and anisotropy. Quality control (QC) requires nondestructive evaluation of actual AM structures. Flash thermography is a potentially promising QC technique because it is scalable to arbitrary structure size. However, the detection sensitivity of this method is limited by noise. We investigate separation of signal from noise in thermography images using several machine learning (ML) methods, including new spatial–temporal blind source separation and spatial–temporal sparse dictionary learning methods. Performance of the ML methods is benchmarked using thermography data obtained from imaging stainless steel 316L and Inconel 718 specimens produced by the LPBF method with imprinted calibrated porosity defects. The ML methods are ranked by F-score and execution runtime. The ML methods with higher accuracy require a longer runtime. However, this runtime is sufficiently short to perform QC within a realistic time frame.

中文翻译：

---

利用热成像图像的机器学习对增材制造的金属结构进行质量控制

高强度金属的增材制造 (AM) 目前基于激光粉末床融合 (LPBF) 工艺，该工艺会引入内部材料缺陷，例如孔隙和各向异性。质量控制 (QC) 需要对实际 AM 结构进行无损评估。闪光热成像是一种有潜力的 QC 技术，因为它可以扩展到任意结构尺寸。然而，这种方法的检测灵敏度受到噪声的限制。我们使用多种机器学习 (ML) 方法研究热成像图像中信号与噪声的分离，包括新的时空盲源分离和时空稀疏字典学习方法。ML 方法的性能是使用从 LPBF 方法生产的不锈钢 316L 和 Inconel 718 样品成像获得的热成像数据进行基准测试的，这些样品具有压印校准的孔隙度缺陷。ML 方法按 F 分数和执行运行时间排序。精度更高的机器学习方法需要更长的运行时间。然而，这个运行时间足够短，可以在现实的时间范围内执行 QC。