Image based statistical process monitoring via partial first order stochastic dominance

Abstract

The continuously evolving digitalized manufacturing industry is pushing quality engineers to face new and complex challenges. Quality data formats are evolving from simple univariate or multivariate characteristics to big data streams consisting of sequences of images and videos in the visible or infrared range; manufacturing processes are moving from series production to more and more customized applications. In this framework, novel methods are needed to monitor and keep under statistical control the process. This study presents two novel process monitoring techniques that rely on the partial first order stochastic dominance (PFOSD) concept, applicable to in-line analysis of video image data aiming at signaling out-of-control process states. Being non-parametric, they allow dealing with complex underlying dynamics and wildly varying distributions that represent the natural process conditions. A motivating case study in metal additive manufacturing is presented, where the proposed methodology enables the in-line and in-situ detection of anomalous patterns in thermal videos captured during the production of zinc samples. Performances are investigated and compared in the presence of both simulated and real data.

Keywords:

• additive manufacturing; image analysis; laser powder bed fusion; statistical process monitoring;stochastic dominance
• thermal images

Supplementary material

The data set used in the real case study in section “Real data application” is available to download in Figshare at the url: https://doi.org/10.6084/m9.figshare.14829033

Acknowledgments

We would like to thank the editor and the two anonymous referees, whose valuable comments and suggestions improved significantly the manuscript. This work was supported by the project SIADD: Soluzioni Innovative per la qualitá e la sostenibilitá dei processi di ADDitive manufacturing (Novel solutions for quality and sustainability of AM processes)-MIUR PON MIUR “Ricerca e Innovazione.”

Additional information

Notes on contributors

Panagiotis Tsiamyrtzis

Panagiotis Tsiamyrtzis is Associate Professor in the Department of Mechanical Engineering of Politecnico di Milano. He received his BSc degree in Mathematics from the Aristotle University of Thessaloniki, Greece and the MSc and PhD degrees in Statistics from the School of Statistics at University of Minnesota, USA. His primary research interests are in two areas. The first is Statistical Process Control/Monitoring (SPC/M), where most of his work is performed from a Bayesian perspective. The second is in statistical problems in affective computing, where as a member of the Computational Physiology Lab at University of Houston, he has been working in monitoring and analyzing numerous physiological variables in human based experiments, like stress detection, face recognition, deception detection and others.

Marco Luigi Giuseppe Grasso

Marco Luigi Giuseppe Grasso is Assistant Professor in the Department of Mechanical Engineering of Politecnico di Milano. He got both his MSc in Aerospace Engineering and his PhD in Mechanical Engineering at Politecnico di Milano. The framework of his research consists of statistical process monitoring of manufacturing processes via signal data analysis, statistical learning and data mining techniques. The core of his research is carried out at the AddMe Lab, the laboratory of the Department of Mechanical Engineering focused on Additive Manufacturing technologies, with a focus on in-situ sensing and monitoring of laser and electron beam powder bed fusion processes.

Bianca Maria Colosimo

Bianca Maria Colosimo is Professor in the Department of Mechanical Engineering of Politecnico di Milano, where she is Deputy-Head of the Department. She received her MSc and PhD (cum Laude) in Industrial Engineering from Politecnico di Milano. Her research interest is mainly in the area of complex data modeling monitoring and control, with special attention to surface point clouds, signal, images and video data in advanced manufacturing applications, additive manufacturing among the others. She is Editor-in-Chief of the Journal of Quality Technology, member of the QSR Advisory Board at INFORMS, Council member of ENBIS, member of the Implementation Support Group of the Manufuture-EU, member of the CLC South of the European Institute of Innovation & Technology (EIT) on Manufacturing. She is included among the top 100 Italian woman scientists in STEM – (https://100esperte.it/search?id=170).