A system for knowledge-based process planning |
| |
| Affiliation: | 1. William James Center for Research, ISPA-Instituto Universitário, Rua Jardim do Tabaco, n° 34, 1149-041, Lisboa, Portugal;2. Instituto Universitário de Lisboa (ISCTE-IUL), Cis-IUL, Edifício ISCTE, Av. das Forças Armadas, 1649-026, Lisbon, Portugal;3. Departamento de Psicologia, Centro de Investigação em Educação e Psicologia (CIEP), Escola de Ciências Sociais, Universidade de Évora, Rua da Barba Rala, 1, 7005-345, Évora, Portugal;4. School of Business and Management, Queen Mary University of London, Francis Bancroft Building, Mile End Road, London, E1 4NS, United Kingdom;5. University of Oslo, Postboks 1094, Blindern, 0317, Oslo, Norway;1. System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, China;2. Digital Manufacturing and Design Centre, Singapore University of Technology and Design, Singapore 487372, Singapore;3. Department of Mechanical and Aerospace Engineering, Monash University, Clayton, Victoria 3800, Australia;4. The G. W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA;1. Shandong Provincial Key Lab of Wireless Communication Technologies, School of Information Science and Engineering, Shandong University, Qingdao 266237, China;2. Department of Communication Engineering, Al-Neelain University, Khartoum 11114, Sudan;3. Department of Information and Communication Engineering, Inha University, Incheon 22212, South Korea |
| |
| Abstract: | We describe the application of problem solving, knowledge based methods in creating process plans in manufacturing. The planner presented - called TOLTEC - is designed for experiential domains and bases its operation on the use of cases in a dynamic memory environment. We will describe the way TOLTEC creates process plans by utilizing previous experiences, dynamic clustering of its memories and dynamic constraint generation and by shifting its focus of attention to different features of the workpiece by using importance values. Also, we will present how TOLTEC learns by modifying its memories according to new experiences and how it helps bridge some of the gap between design and manufacturing by detecting design errors.The emphasis in this paper is more on the application aspects of our system and the examples presented will demonstrate the abilities of TOLTEC to design process plans, detect design errors, predict manufacturing errors, recover from planning errors, handle multiple branching solutions and improve its performance by utilizing learning techniques. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
