Nondestructive Quantitative Measurement for Precision Quality Control in Additive Manufacturing Using Hyperspectral Imagery and Machine Learning

Measuring the purity of the metal powder is essential to maintain the quality of additive manufacturing products. Contamination is a significant concern, leading to cracks and malfunctions in the final products. Conventional assessment methods focus more on physical integrity rather than material composition and can be time-consuming. By capturing spectral data from a wide frequency range along with the spatial information, hyperspectral imaging (HSI) can detect minor differences in terms of temperature, moisture, and chemical composition to tackle this challenge. In this article, we explore the application of HSI in conjunction with machine learning for nondestructive inspection of metal powders. By employing near-infrared and visible HSI cameras, we introduce the utilization of HSI for this purpose. We delve into the technical challenges encountered and present detailed solutions through three case studies, including the establishment of a spectral dictionary, contamination detection, and band selection analysis. Our experimental results demonstrate the immense potential of HSI and its synergy with machine learning for nondestructive testing in powder metallurgy, particularly in meeting the requirements of industrial manufacturing environments.