Earticle

초록

영어

In this study, the path planning problem in 3D automated optical inspection (AOI) machines is considered. In the problem, the primary objective is finding a path that minimizes the total working time among all possible paths for the camera. In 3D AOI machines, a very precise level of image processing has to be performed when inspecting the mounted components on printed circuit boards (PCBs). Therefore, both the routing time of the camera path and the image processing time have to be considered when calculating the total working time of the camera in the AOI machines. In this paper, we propose efficient heuristic algorithms that can find the paths that have the shortest total working times. The performances of the proposed methods primarily depend on the NEH-based procedure, which is one of our proposed improvement procedures. We introduce several construction and improvement procedures, and select the best combination as our proposed approach. The results of computational experiments conducted on real data to evaluate the performance of our proposed approach show that our proposed methods improve on the original path planning performances. In addition, tests done on randomly generated data indicate that our proposed approach is superior to other benchmark approaches, including metaheuristic algorithms, in terms of computing time and performance measures.

목차

Abstract
 1. Introduction
 2. Problem Description
  2.1. Path planning problem
  2.2. Solution representation
 3. Proposed Methods
  3.1. Construction procedures
  3.2. Improvement procedures
  3.3. Proposed combinations
 4. Computational Experiments
  4.1. Test results for real data
  4.2. Test results for generated data
 5. Conclusion
 Acknowledgements
 References

키워드

저자

• Geun-Cheol Lee [ Konkuk University, College of Business Administration, South Korea ]
• SungKuk Choi [ InterClone Corporation, South Korea ]
• DeokHwa Hong [ Koh Young Technology, R&D/Vision Engineer Group, South Korea ]
• Seong-Hoon Choi [ Sangmyung University, Department of Management Engineering, South Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605