To Improve Machining Fixture Design: A Case Based Reasoning Paradigm

Fixture design is a complex and an experience based process without any throughout numerical theory behind. Proper fixture design could improve the quality of products and reduce the cost as well as required time of manufacturing; consequently the modern manufacturing environment requires suitable design systems to achieve appropriate fixtures. In this paper to obtain an acceptable machining fixture design, a case-based reasoning method with developed retrieval system is proposed. In order toincrease the effectiveness of the case based reasoning (CBR) retrieval system some formulae are derived which are able to measure similarity between symbolic attributes.This method references previous design cases to help designers for a new case in an easy manner.By using this method the designer can solve the faced fixture problem by finding the most similar work piece to the query case accurately and quickly by means of a hybrid retrieval system. A case study to validate the methodis performed using this method to present the applicability of this method. According to case studies result, this method can work properly in fixture design for prismatic parts. Comparing to the current CBR methods in fixture design, the proposed method in this research is faster and easier regarding to reduce reliance on the designer experience and being done in one step.

[1]  Hui Wang,et al.  Case based reasoning method for computer aided welding fixture design , 2008, Comput. Aided Des..

[2]  K. Rong,et al.  Computer-Aided Fixture Design , 1999 .

[3]  A. Senthil Kumar,et al.  Conceptual Design of Fixtures Using Machine Learning Techniques , 2000 .

[4]  Yingguang Li,et al.  A feature-based fixture design methodology for the manufacturing of aircraft structural parts , 2011 .

[5]  Jahau Lewis Chen,et al.  A modular fixture design system based on case-based reasoning , 1995 .

[6]  Andrew Y. C. Nee,et al.  Expert fixture-design system for an automated manufacturing environment , 1992, Comput. Aided Des..

[7]  Yang Jiang,et al.  Applying RBR and CBR to develop a VR based integrated system for machining fixture design , 2011, Expert Syst. Appl..

[8]  Celso Kazuyuki Morooka,et al.  Case-based system: indexing and retrieval with fuzzy hypercube , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[9]  Mohsen Hamedi,et al.  Intelligent Fixture Design through a Hybrid System of Artificial Neural Network and Genetic Algorithm , 2005, Artificial Intelligence Review.

[10]  Andrew Y. C. Nee,et al.  Advanced Fixture Design for FMS , 1995 .

[11]  K. C. Seow,et al.  Conceptual Design of Fixtures using Genetic Algorithms , 1999 .

[12]  Satyandra K. Gupta,et al.  Machining feature-based similarity assessment algorithms for prismatic machined parts , 2006, Comput. Aided Des..

[13]  Peyman Salah,et al.  A Neural Network Based Method for Cost Estimation 63/20kV and 132/20kV Transformers , 2012 .

[14]  Y. Kang,et al.  Computer‐aided fixture design verification , 2002 .

[15]  Iain M. Boyle,et al.  CAFixD: A Case-Based Reasoning Fixture Design Method. Framework and Indexing Mechanisms , 2006, J. Comput. Inf. Sci. Eng..