Design and implementation of a generic nonconformance tracking and recovery (GINTR) system

Nonconformance tracking and recovery remains a major issue in large complex manufacturing systems due to the complexity of manufacturing processes, diversity of parts, high density of nonconformances, and fuzziness of nonconformance information. In addition, the existing nonconformance tracking and recovery systems are usually special purpose systems. They lack the capabilities to migrate to new working domains and integrate with other systems. This research proposes a comprehensive approach to nonconformance tracking and recovery. In conjunction with the soft computing and case-based reasoning (CBR) technologies, a generic intelligent system is designed to address the nonconformance tracking and diagnosis problem. A system built under such a comprehensive approach can track the nonconformance with multiple causes as well as limited knowledge and provide timely diagnostic recovery. A prototype of the GINTR system has been developed using the Microsoft .NET technology, which is considered as the next generation distributed computing paradigm. The prototype system developed is generic, fault tolerant, and agile. It can be adapted to diverse complex manufacturing environments with minimum difficulty.

[1]  Sankar K. Pal,et al.  Soft Computing in Case Based Reasoning , 2000, Springer London.

[2]  Simon C. K. Shiu,et al.  A Tutorial on Case Based Reasoning , 2000, Soft Computing in Case Based Reasoning.

[3]  K. Srinivasan,et al.  FDAS: architecture and implementation , 1992 .

[4]  Moti Schneider,et al.  Matching attributes in a fuzzy case based reasoning , 1999, 18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397).

[5]  Matthew MacDonald.  Microsoft .NET Distributed Applications: Integrating XML Web Services and .NET Remoting , 2003 .

[6]  L. P. Khoo,et al.  A fuzzy-based genetic approach to the diagnosis of manufacturing systems , 2000 .

[7]  Philip D. Wasserman,et al.  Advanced methods in neural computing , 1993, VNR computer library.

[8]  Kesheng Wang,et al.  Using B-spline neural network to extract fuzzy rules for a centrifugal pump monitoring , 2001, J. Intell. Manuf..

[9]  P. Roth.  MISSING DATA: A CONCEPTUAL REVIEW FOR APPLIED PSYCHOLOGISTS , 1994 .

[10]  Yu Zhang,et al.  An integration architecture for process manufacturing systems , 2002, Int. J. Comput. Integr. Manuf..

[11]  Chrissanthi Angeli,et al.  A Model-Based Method for an Online Diagnostic Knowledge-Based System , 2001, Expert Syst. J. Knowl. Eng..

[12]  K. Srinivasan,et al.  SDAS: A Knowledge-based Framework for Analyzing Defects in Apparel Manufacturing , 1994 .

[13]  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).

[14]  Young-Geun Han,et al.  The Internet‐based virtual machining system using CORBA , 2002 .

[15]  Anil Varma,et al.  ICARUS: design and deployment of a case-based reasoning system for locomotive diagnostics , 1999 .

[16]  Chrissanthi Angeli,et al.  Fault Prediction and Compensation Functions in a Diagnostic Knowledge-Based System for Hydraulic Systems , 1999, J. Intell. Robotic Syst..

[17]  S. H. Cheraghi,et al.  Fuzzy defect avoidance system (FDAS) for product defect control , 2004 .

[18]  Jie Zhang,et al.  Agent- and CORBA-Based Application Integration Platform for an Agile Manufacturing Environment , 2003 .

[19]  G. K. Griffith,et al.  The quality technician's handbook , 1986 .