Data-mining approach to production control in the computer-integrated testing cell

This paper presents a data-mining-based production control approach for the testing and rework cell in a dynamic computer-integrated manufacturing system. The proposed competitive decision selector (CDS) observes the status of the system and jobs at every decision point, and makes its decision on job preemption and dispatching rules in real time. The CDS equipped with two algorithms combines two different knowledge sources, the long-run performance and the short-term performance of each rule on the various status of the system. The short-term performance information is mined by a data-mining approach from large-scale training data generated by simulation with data partition. A decision tree-based module generates classification rules on each partitioned data that are suitable for interpretation and verification by users and stores the rules in the CDS knowledge bases. Experimental results show that the CDS dynamic control is better than other common control rules with respect to the number of tardy jobs.

[1]  Thomas R. Rohleder,et al.  An evaluation of scheduling heuristics for dynamic single-processor scheduling with early/tardy costs , 1996 .

[2]  Walter J. Trybula,et al.  Surface Mount Technology , 1999 .

[3]  Michael J. Magazine,et al.  Generalized preemption models for single-machine dynamic scheduling problems , 1997 .

[4]  Peter Mertens,et al.  Combining knowledge-based systems and simulation to solve rescheduling problems , 1996, Decis. Support Syst..

[5]  Marijke F. Augusteijn,et al.  Performance evaluation of texture measures for ground cover identification in satellite images by means of a neural network classifier , 1995, IEEE Trans. Geosci. Remote. Sens..

[6]  Gregory Piatetsky-Shapiro,et al.  The KDD process for extracting useful knowledge from volumes of data , 1996, CACM.

[7]  Averill M. Law,et al.  Simulation Modeling and Analysis , 1982 .

[8]  Randall P. Sadowski,et al.  Introduction to Simulation Using Siman , 1990 .

[9]  Michael J. Shaw,et al.  Learning-based scheduling in a flexible manufacturing flow line , 1994 .

[10]  E. D. Perfecto,et al.  MCM-D/C yield improvements through effective diagnostics , 1999 .

[11]  Chris J McDonald,et al.  New tools for yield improvement in integrated circuit manufacturing: can they be applied to reliability? , 1999 .

[12]  J. Neter,et al.  Applied linear statistical models : regression, analysis of variance, and experimental designs , 1974 .

[13]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[14]  Yuehwern Yih,et al.  Auto-bias selection for developing learning-based scheduling systems , 1999 .

[15]  Reha Uzsoy,et al.  A review of production planning and scheduling models in the semiconductor industry , 1994 .

[16]  Markus Ettl,et al.  Sojourn Time and Waiting Time Distributions for M/GI/1 Queues with Preemption-Distance Priorities , 1994, Oper. Res..

[17]  Douglas B. Bock,et al.  A Comparison of Due Date Setting, Resource Assignment, and Job Preemption Heuristics for the Multiproject Scheduling Problem* , 1990 .

[18]  Howard H. Manko,et al.  Soldering handbook for printed circuits and surface mounting : design, materials, processes, equipment, trouble-shooting, quality, economy, and line management , 1986 .

[19]  Yuehwern Yih,et al.  Simulation comparison of collaboration protocol-based testing models , 2001 .

[20]  Han Hoogeveen,et al.  On-line scheduling on a single machine: maximizing the number of early jobs , 2000, Oper. Res. Lett..

[21]  C. McGreavy,et al.  Automatic Classification for Mining Process Operational Data , 1998 .

[22]  K. S. Desai,et al.  Improving yields through effective diagnostics: A MCM-D/C example , 1998, Proceedings. 1998 International Conference on Multichip Modules and High Density Packaging (Cat. No.98EX154).

[23]  Tsu-Shuan Chang,et al.  Multiobjective scheduling for IC sort and test with a simulation testbed , 1998, ICMTS 1998.

[24]  Frederic Duvivier.  Automatic detection of spatial signature on wafermaps in a high volume production , 1999, Proceedings 1999 IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems (EFT'99).

[25]  Edward Anderson,et al.  Two new rules to minimize tardiness in a job shop , 1990 .

[26]  G. Soda,et al.  Data Categorization Using Decision Trellises , 1999, IEEE Trans. Knowl. Data Eng..

[27]  Yuehwern Yih,et al.  Statistical analysis of factors influencing the performance of the timeout-based testing model , 2003 .

[28]  Louis Wehenkel.  Machine-Learning Approaches to Power-System Security Assessment , 1997, IEEE Expert.

[29]  Carla E. Brodley,et al.  Temporal sequence learning and data reduction for anomaly detection , 1998, CCS '98.

[30]  Michael J. Shaw,et al.  Adaptive scheduling in dynamic flexible manufacturing systems: a dynamic rule selection approach , 1997, IEEE Trans. Robotics Autom..

[31]  Jose A. Ventura,et al.  A neural network approach for defect identification and classification on leather fabric , 2000, J. Intell. Manuf..

[32]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[33]  Shigeo Abe,et al.  Function approximation based on fuzzy rules extracted from partitioned numerical data , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[34]  Hongjun Lu,et al.  Effective Data Mining Using Neural Networks , 1996, IEEE Trans. Knowl. Data Eng..

[35]  Nina F. Thornhill,et al.  Experiences of statistical quality control with BP Chemicals, Grangemouth , 1999 .

[36]  Yuehwern Yih,et al.  An intelligent controller for manufacturing cells , 1996 .