September, 13 2017
David Steinberg
Data for process monitoring now comes from diverse collection and sensor modalities. Often this results in rich data that presents interesting challenges for on-line monitoring. This article, by Grasso et al., looks at image data produced by a machine vision system. The particular focal area for this article is “additive manufacturing” (AM) – the use of 3D printing technology for producing parts. There is growing use of AM to produce complex parts. In particular for metal components, there are large potential advantages over casting. The article looks at a system based on selective laser melting (SLM), one of the key technologies for metal AM. Although SLM technology has improved in recent years, process capability is still a major issue that must be resolve for it to make a full industrial breakthrough. In AM, parts are built up in layers and different kinds of defect may occur throughout the process. In some cases, defects propagate from one layer to the following ones leading to a job failure. In other cases, they are hardly visible or detectable by inspecting the final part, as they may affect only the internal structure or structural features that are difficult to measure. Ideally, in-process monitoring methods will be able to rapidly detect and locate defect onsets during the SLM process. This article makes important progress toward developing statistical monitoring techniques for SLM. The authors propose a method for detection and spatial identification of defects during the production process that exploits a machine vision system in the visible range. A statistical descriptor of the image data is developed that uses principal component analysis to reduce the dimension of the data. The method is shown to be useful for identifying defective areas of a layer. Cluster analysis is then used to identify similar images and provides a basis for automated defect detection. The performance of the method is illustrated via a real case study in SLM including both simple and complicated geometries.
In-Process Monitoring of Selective Laser Melting: Spatial Detection of Defects Via Image Data Analysis
Grasso, M., Laguzza, V., Semararo, Q. and Colosimo, B.M.
Journal of Manufacturing Science and Engineering, May 2017