Waste reduction via image classification algorithms: beyond the human eye with an AI-based vision

Abstract

Modern manufacturing is the world's largest and most automated industrial sector. The rise of Industry 4.0 technologies such as Big Data, Internet of Things (IoT) devices, and Machine Learning has enabled a better connection with machines and factory systems. Data harvesting allowed for a more seamless and comprehensive implementation of the knowledge-based decision-making process. New models that provide a competitive edge must be created by combining the Lean paradigm with the new technologies of Industry 4.0. This paper presents novel computer-based vision models for automated detection and classification of damaged packages from intact packages. In high-volume production environments, the package manual inspection process through the human eye consumes inordinate amounts of time poring over physical packages. Our proposed three different computer-based vision approaches detect damaged packages to prevent them from moving to shipping operations that would otherwise incur waste in the form of wasted operating hours, wasted resources and lost customer satisfaction. The proposed approaches were carried out on a data set consisting of package images and achieved high precision, accuracy, and recall values during the training and validation stage, with the resultant trained YOLO v7 model.

KEYWORDS:

• Lean manufacturing
• waste reduction
• machine learning
• Industry 4.0
• image classification

Acknowledgements

Mohammad Shahin took care of conceptualisation, methodology, data collection, investigation, drafting the original manuscript, and reviewing and editing it. Ali Hosseinzadeh took care of investigation, and the proposed methodology and editing. Hamed Bouzary took care of final revisions and edits. Awni Shahin contributed to the statistical testing. F. Frank Chen contributed in resources, and supervision. Lastly, all authors reviewed and gave their approval for the final version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The reported research work received partial financial support from U.S. Office of Naval Research MEEP Program (Award Number: N00014-19-1-2728), U.S. Department of Energy/NNSA (Award Number: DE-NA0004003), as well as from the Lutcher Brown Distinguished Chair Professorship fund of the University of Texas at San Antonio.

Notes on contributors

Mohammad Shahin

Mohammad Shahin received his Ph.D. degree in Mechanical Engineering from the University of Texas at San Antonio. Mohammad Shahin is a knowledgeable scholar in data-driven solutions via applied machine learning across various business and industry applications, including enterprise management & operations, business process management, healthcare, decision science, cybersecurity, and manufacturing systems. In addition, Mohammad Shahin has an interest in the integration of Industry 4.0 and 5.0 (Artificial Intelligence Systems in particular) into Lean manufacturing systems. Mohammad Shahin has years of teaching experience in different areas of engineering coupled with a track record of scholarly work and publication. Mohammad Shahin has also co-worked on writing and submitting proposals to different funding sources.

F. Frank Chen

F. Frank Chen is Lutcher Brown Distinguished Chair in Advanced Manufacturing at the University of Texas at San Antonio where he founded the Center for Advanced Manufacturing and Lean Systems and served as the center director. Before joining UT-San Antonio, he was with Virginia Tech as John Lawrence Endowed Professor at the Grado Department of Industrial and Systems Engineering there he founded the Center for High Performance Manufacturing. He was with Caterpillar Technical Center as Senior Manufacturing Systems Engineer and as Project Manager before returning to academia in 1991. He received the 1996 NSF Presidential Faculty Fellows (PFF/PECASE) Award at the White House, with current research interests in cloud manufacturing, defense manufacturing, and applications of lean tools and techniques in various manufacturing and service industries. He is an elected Fellow of the Society of Manufacturing Engineers (SME) and the Institute of Industrial and Systems Engineers (IISE).

Ali Hosseinzadeh

Ali Hosseinzadeh received his MSc degree in Mechanical Engineering from Ozyegin University. He is currently a Ph.D. student at the University of Texas at San Antonio. His current research interests include Lean manufacturing, the implementation of artificial intelligence in advanced manufacturing systems, cybersecurity, and the optimisation of manufacturing processes and systems.

Hamed Bouzary

Hamed Bouzary received his M.Sc. degree from K.N. Toosi University of Technology, Iran and his Ph.D. from University of Texas at San Antonio. He is currently a Data Scientist at General Motors. His research interests are centred around realisation of smart manufacturing through implementing novel data-driven methodologies at the product, process and system levels. He has been involved in several projects related to cloud manufacturing, applications of AI in manufacturing, and cyber-physical systems supported by U.S. funding agencies, including U.S. National Science Foundation, and U.S. Department of Defense, and U.S. Department of Energy. He is a recipient of the IISE’s Engineering Lean & Six Sigma 2019 conference’s Outstanding Paper Award as well.

Awni Shahin

Awni Shahin is a full professor at Mut’ah University in Jordan. He received his Ph.D. degree in Special Education with a minor in Quantitative Analysis from the University of Jordan. His research interests are in the field of data analytics and special education.