Knowledge Refinement for Engineering Knowledge Management

Engineering design is a knowledge-intensive process, including conceptual design, detailed design, engineering analysis, assembly design, process design, and performance evaluation. Each of these tasks involves various aspects of knowledge and experience. They are the most valuable sources for capitalizing enterprise knowledge and know-how on building enterprise memory, which may become part of enterprise assets. Therefore, capturing and representing product design information, design intents, and underlining design knowledge for later reuse is the basis of and one of the key tasks in engineering knowledge management. This study develops an approach for engineering knowledge refinement to facilitate engineering knowledge management. This approach is basically a refinement process that includes the steps of knowledge capture, knowledge representation and storage, and knowledge compilation. This study involves the development of a semantic graph for describing product-related information, design intent and know-how, a tag-based scheme for representing various types of captured product information and engineering knowledge, a case-based representation for a designed entity, and the design of a knowledge compilation model and algorithm. The objective of this study can be achieved by performing the following tasks: (i) developing an engineering knowledge management framework, (ii) establishing an engineering knowledge refinement process, (iii) developing levels of knowledge representation schemes, and(iv) implementing engineering knowledge refinement mechanisms.

[1]  Susan Craw,et al.  Knowledge refinement to debug and maintain a tablet formulation system , 1997, Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence.

[2]  Xavier Boucher,et al.  A Decision Support System for a Concurrent Design of Cable Harnesses: Conceptual Approach and Implementation , 1998 .

[3]  Yuh-Min Chen,et al.  Computer-aided feature-based design for net shape manufacturing , 1997 .

[4]  Edward M. Riseman,et al.  Dynamic-Scene and Motion Analysis Using Passive Sensors - Part 1: A Qualitative Approach , 1992, IEEE Expert.

[5]  M.A. Boyd,et al.  Development of automated computer-aided diagnostic systems using FMECA-based knowledge capture methods , 1998, Annual Reliability and Maintainability Symposium. 1998 Proceedings. International Symposium on Product Quality and Integrity.

[6]  Yuh-Min Chen,et al.  Distributed engineering change management for allied concurrent engineering , 2002, Int. J. Comput. Integr. Manuf..

[7]  S. Krishna,et al.  Requirements engineering: problem domain knowledge capture and the deliberation process support , 1999, Proceedings. Tenth International Workshop on Database and Expert Systems Applications. DEXA 99.

[8]  John F. Sowa,et al.  Conceptual Structures: Information Processing in Mind and Machine , 1983 .

[9]  Yan Jin,et al.  An Agent-Based Decision Network for Concurrent Engineering Design , 2001, Concurr. Eng. Res. Appl..

[10]  Xiaoqing Liu,et al.  An expert system building tool supporting knowledge compilation and management , 1993, Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93).

[11]  K.R. Levi,et al.  An explanation-based-learning approach to knowledge compilation: a Pilot's Associate application , 1992, IEEE Expert.

[12]  Shigenobu Kobayashi,et al.  Knowledge compilation and refinement for fault diagnosis , 1991, IEEE Expert.

[13]  Jae-Won Lee,et al.  ADTEP: An Agent-Based Decision-Supporting System for Taguchi Experiment Planning , 2001, Concurr. Eng. Res. Appl..

[14]  Anthony N. Godwin,et al.  Analysis of the STEP standard data access interface using formal methods , 1995 .

[15]  C. Tong,et al.  The nature and significance of knowledge compilation , 1991, IEEE Expert.

[16]  George Q. Huang,et al.  Computer aids for engineering change control , 1998 .

[17]  Yuh-Min Chen,et al.  Methodology and system framework for knowledge management in allied concurrent engineering , 2005, Int. J. Comput. Integr. Manuf..

[18]  John F. Sowa,et al.  Conceptual Structures: Current Practices , 1994, Lecture Notes in Computer Science.

[19]  Jesse C. Jones,et al.  The Engineering Design Process , 1993 .

[20]  T. Bylander.  A simple model of knowledge compilation , 1991, IEEE Expert.

[21]  H. Nakamura,et al.  Knowledge refinement approach through incorporating case-based knowledge in maintenance engineer scheduling AI system , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[22]  Daniele Theseider Dupré,et al.  Local Reasoning and Knowledge Compilation for Efficient Temporal Abduction , 2002, IEEE Trans. Knowl. Data Eng..

[23]  Kikuo Fujita,et al.  Agent-Based Distributed Design System Architecture for Basic Ship Design , 1999 .

[24]  C. Chen,et al.  IREF-an interactive theory-driven knowledge refinement tool , 1991, [1991] Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application.

[25]  William E. Lorensen,et al.  Object-Oriented Modeling and Design , 1991, TOOLS.

[26]  Keith A Lichti,et al.  Knowledge capture model for expert systems development , 1993, Proceedings 1993 The First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems.

[27]  Z. Chai,et al.  A model of the knowledge compilation , 1993, Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation.

[28]  R.M. Keller,et al.  Applying knowledge compilation techniques to model-based reasoning , 1991, IEEE Expert.

[29]  Jami J. Shah,et al.  Functional requirements and conceptual design of the feature-based modelling system , 1988 .

[30]  Ken G. McIntosh.  Engineering Data Management: A Guide to Successful Implementation , 1995 .

[31]  D. C. Anderson,et al.  Geometric reasoning in feature-based design and process planning , 1990, Comput. Graph..

[32]  Y. Tachibana,et al.  A technical analysis expert system with knowledge refinement mechanism , 1991, Proceedings First International Conference on Artificial Intelligence Applications on Wall Street.