Evolutionary Computing in Advanced Manufacturing (Wiley-Scrivener)
Manoj Tiwari, Jenny A. Harding
Format: PDF / Kindle (mobi) / ePub
This book presents and explains evolutionary computing in the context of manufacturing problems.
The complexity of real-life advanced manufacturing problems often cannot be solved by traditional engineering or computational methods. As a result, researchers and practitioners have proposed and developed in recent years new strands of advanced, intelligent techniques and methodologies.
Evolutionary computing approaches are introduced in the context of a wide range of manufacturing activities, and through the examination of practical problems and their solutions, readers will gain confidence to apply these powerful computing solutions.
The initial chapters introduce and discuss the well established evolutionary algorithm, to help readers to understand the basic building blocks and steps required to successfully implement their own solutions to real-life advanced manufacturing problems. In the later chapters, modified and improved versions of evolutionary algorithms are discussed.
• Provides readers with a solid basis for understanding the development of mathematical models for production and manufacturing-related issues;
• Explicates the mathematical models and various evolutionary algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Algorithm (ACO);
• Helps scholars, researchers, and practitioners in understanding both the fundamentals and advanced aspects of computational intelligence in production and manufacturing.
The volume will interest manufacturing engineers in academia and industry as well as IT/Computer Science specialists involved in manufacturing. Students at MSc and PhD levels will find it very rewarding as well.
About the authors
Manoj Tiwari is based at the Indian Institute of Technology, Kharagpur. He is an acknowledged research leader and has worked in the areas of evolutionary computing, applications, modeling and simulation of manufacturing system, supply chain management, planning and scheduling of automated manufacturing system for about 20 years.
Jenny A. Harding joined Loughborough University in 1992 after working in industry for many years. Her industrial experience includes textile production and engineering, and immediately prior to joining Loughborough University, she spent 7 years working in R&D at Rank Taylor Hobson Ltd., manufacturers of metrology instruments. Her experience is mostly in the areas of mathematics and computing for manufacturing.
cases. FMSs can respond to the changing demand but the system configuration remains intact, whereas RMSs can undergo changes in system configuration to meet the requirements. The observed difference between the physical configuration of FMS and RMS is that FMS generally has a general purpose CNC machine and programmable automations as compared to the customized CNC machines and reconfigurable machine tools in RMS. Reconfiguration could be implemented in soft (logical) form or hard (physical)
approach, Journal Manufacturing Technology Management, 8, pp. 735-744. 76 EVOLUTIONARY COMPUTING IN ADVANCED MANUFACTURING Jiao, J., Tseng, M. M., Ma, Q., and Zou, Y, 2000, Generic bill-of-materials-andoperations for high-variety production management, Concurrent Engineering, 8 (4), pp. 297-321. Krishnan, V., and Gupta, S., 2001, Appropriateness and impact of platform based product development, Management Science, 47 (1), pp. 52-68. Lamothe J., Hadj-Hamou, K., and Aldanondo, M., 2006, An
decision structure which includes: part type selection, machine loading, part input sequencing and operation. Liang and Dutta (1992) developed 98 EVOLUTIONARY COMPUTING IN ADVANCED MANUFACTURING an integrated approach to solve the job selection, tool allocation and machine loading problem, but their approach was limited to only small sized problems. Guerrero et al. (1999) considered the entire production route instead of individual operations and used this approach to solve the tool
Horizon) over utilized time on machine m under utilized time on machine m set of operations for job / set of machines for performing oth operation of job j available time on machine m for performing oth operation of job / required time by machine m for performing oth operation of job / remaining time on machine m for performing oth operation of job / tool_av M jom available tool slots on machine m for performing oth operation of job; tool_req M jom required tool slots by machine m for
milling, drilling, polishing, washing, or assembly These work stations are connected with the guide path network by pick-up/delivery (P/D) points where AGVs transfer the unfinished material (as shown in the Figure 8.1). For efficient performance of the advanced manufacturing system, optimal design and control of the AGVs system should be adopted (Maza and Castagna , 2005). The design and control processes of AGVs involve many issues and can be divided in three levels: 1. Strategic 2. Tactical and