best congress paper

A.I. Vision System for Automated Casting Quality Inspection

Aluminum die casting is a high-speed molding process in which molten aluminum is injected into a die under high pressure to produce high-quality and high-reliability products. This process involves multiple metallurgical steps, making quality control a challenging task. Currently, product inspection is carried out post-production manually, leading to a high percentage of scrap and, in worse scenarios, products with defects being shipped to customers. In this paper, we propose an automatic inspection system based on artificial intelligence (AI), specifically utilizing deep neural network-based computer vision technology, including the Vision Transformer for aluminum die casting surface defect detection. The system not only classifies products as good or defective but also provides defect location information through a defect mask, even without defect localization information in the training dataset. By implementing this automatic vision-based defect inspection system, we can enhance the speed, consistency, and scalability of defect detection while reducing the costs associated with human inspection and scrap rates. This approach ultimately improves product quality and customer satisfaction by preventing defective products from reaching customers.

Best paper Authors

  • Boxiang Zhang

    Boxiang Zhang is currently pursuing his PhD at Purdue University under the guidance of Prof. Xiaoming Wang. He earned his MS degree in ECE from the University of Southern California (USC) and his BS degree in ECE from Huazhong University of Science and Technology (HUST). His primary research interests lie in machine learning and computer vision.

  • Dr. Xiaoming Wang

    Dr. Xiaoming Wang has been working with aluminum alloys for about 30 years. He is an associate professor with Purdue University. Before joining Purdue University, he was providing technical support to diecasting companies in Hong Kong. He is a member of TMS Honors & Professional Recognition Committee and Board of Review of Metallurgical and Materials Transactions A and B. He has been organizing the annual symposia on Light Metal Technology for MS&T since 2016. Dr. Wang is actively participating in technical activities with NADCA. He received his PhD from the University of Leeds in the UK, MSc from Beijing University of Science and Technology, and BSc from Hefei University of Technology in China.

  • Baijian Yang

    Baijian Yang received his PhD in Computer Science from Michigan State University, and his MS and BS in Automation (EECS) from Tsinghua University. He is currently a professor at the Department of Computer and Information Technology, and a University Faculty Scholar at Purdue University. He served as a steering committee member of IEEE Cybersecurity Initiative between 2015 and 2017, and a board director of ATMAE from 2014-2016. His research interests include cybersecurity, data-driven security analytics, and applied machine learning.

  • Dr. Corey Vian

    Dr. Corey Vian has been in the aluminum industry for the past 12 years. He has held multiple engineering related roles and is currently the Manufacturing Engineering Manager for Advanced Engineering at Stellantis’ Kokomo Casting Plant. He is active in NADCA, where he is a current board member, research committee member, and Chapter 25 Treasurer; and is also a past recipient of NADCA’s Committee Member of the Year award. He earned his Bachelors, Masters, and PhD from Purdue University and continues to be a part of Purdue’s manufacturing related programs as a member of their Cast Metals Advisory Board and Industrial Advisory Council.