A fuzzy-rough case-based learning approach for intelligent die design

Tacit knowledge plays an important role in stamping die design, but it is hard to be mined and reused. This paper presents a fuzzy-rough approach of mining rules from existing successful die designs, which improves learning capability of intelligent stamping die design systems. The core of the learning mechanism includes: (1) a feature-based case representation, (2) fuzzification of feature attributes, (3) a fuzzy classification method to partition the cases into clusters based on similarities, (4) a rough set theory-based approach to compute attribute reduct and mine rules. A case base containing 53 bending features was used to test the proposed approach. 38 If-Then rules were mined after computing, and these rules could preserve the basic properties of the origin decision table. The results show that this approach can speed up the retrieval process of the case-based systems and reduce the difficulties in acquiring and updating rules for the rule-based systems.

[1]  Ian D. Watson,et al.  Case-based reasoning is a methodology not a technology , 1999, Knowl. Based Syst..

[2]  Srinath Perera,et al.  A hierarchical case representation using context guided retrieval , 1998, Knowl. Based Syst..

[3]  Zone-Ching Lin,et al.  Application of a neural network machine learning model in the selection system of sheet metal bending tooling , 1996, Artif. Intell. Eng..

[4]  Mohsen Rezayat,et al.  Knowledge-based product development using XML and KCs , 2000, Comput. Aided Des..

[5]  O. W. Salomons,et al.  Review of research in feature-based design , 1993 .

[6]  Ann Heylighen,et al.  A case base of Case-Based Design tools for architecture , 2001, Comput. Aided Des..

[7]  Zone-Ching Lin,et al.  Application of Petri Net in the planning of a shearing-cut and bending progressive die workstation , 2001 .

[8]  Li Pheng Khoo,et al.  A rough set approach to the treatment of continuous-valued attributes in multi-concept classification for mechanical diagnosis , 2001, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[9]  Cad En,et al.  Research of Knowledge Discovery Method in Supporting Stamping Process Design , 2003 .

[10]  David Leake,et al.  Integrating diverse information resources in a case-based design environment , 1999 .

[11]  Manfred Geiger,et al.  Classification problems in manufacturing of sheet metal parts , 1997 .

[12]  Ruan Xue-yu.  K-Nearest Neighbors-based case retrieve strategy for injection product design , 2006 .

[13]  Manfred Geiger,et al.  Three kinds of case-based learning in sheet metal manufacturing , 1991 .

[14]  L. P. Khoo,et al.  A rough set approach to design concept analysis in a design chain , 2005 .

[15]  Li Zheng,et al.  An Intelligent Feature-Based Design for Stamping System , 2001 .

[16]  Z. Pawlak.  Rough set approach to knowledge-based decision support , 1997 .

[17]  Tzung-Pei Hong,et al.  An XML implementation process model for enterprise applications , 2004, Comput. Ind..

[18]  Juan M. Corchado,et al.  Applying Rough Sets Reduction Techniques to the Construction of a Fuzzy Rule Base for Case Based Reasoning , 2004, IBERAMIA.

[19]  Ge Wang,et al.  Intelligent Classification of the Drop Hammer Forming Process Method , 2001 .

[20]  Amit Konar,et al.  Artificial Intelligence and Soft Computing: Behavioral and Cognitive Modeling of the Human Brain , 1999 .

[21]  Peter Hodgson,et al.  Design, Implementation and Use of a Knowledge Acquisition Tool for Sheet Metal Forming , 2004 .

[22]  George-Christopher Vosniakos,et al.  Logic programming for process planning in the domain of sheet metal forming with progressive dies , 2005, J. Intell. Manuf..

[23]  Yinghong Peng,et al.  Knowledge acquisition from metal forming simulation , 2006 .

[24]  Aleksander Øhrn,et al.  Discernibility and Rough Sets in Medicine: Tools and Applications , 2000 .