Downstream performance prediction for a manufacturing system using neural networks and six-sigma improvement techniques

Intelligent techniques have been applied in a range of industrial environments [Meziane F, Vadera S, Kobbacy K, Proudlove N. Intelligent systems in manufacturing: current developments and future prospects. Integrated Manuf Syst 2000;11(4):218-38; Stephanopoulos G, Han C. Intelligent systems in process engineering: a review. Comput Chem Eng, 1996;20 (6-7):743-91; Johnston AB, Maguire LP, McGinnity TM. Using business improvement techniques to inform the optimisation of production cycle time: an industrial case study. Proceedings of the IEEE SMC UK-RI Chapter conference 2004 on intelligent cybernetic systems. September 7-8, 2004 ISSN:1744-9189; Proudlove NC, Vadera S, Kobbacy KAH. Intelligent management systems in operations: A review. J Oper Res Soc, 1998;49(7):682-99] although their implementation is not the first choice of many process engineers. In contrast process engineers in a diverse range of manufacturing environments regularly deploy business improvement techniques, such as the six-sigma methodology. Such techniques aim to control and subsequently identify the relationship between the process inputs and outputs so that a process engineer can more accurately predict how the process output shall perform based on the system inputs. Factors such as cost reduction, automatic process control or simply process prediction may be the defining factors in establishing prediction models. In this paper the authors use as a case study the manufacture of hard disc drives, from the developing of the read-write head to the recording media and the overall construction of the hard disc drive with its controlling mechanisms. Each of these stages are separate and complex-processing elements and integral to the functionality of the end product. In addition each of these stages of manufacturing may take days or weeks to complete and be processed in separate facilities and/or countries. This paper reports on the application of intelligent system techniques to improve the downstream performance prediction within this manufacturing environment. The application is guided by a six-sigma methodology to obtain improved performance. The results highlight that significant downstream prediction accuracy can be obtained using this hybrid approach.

[1]  G. W. Ng.  application of Neural Networks to Adaptive Control of Nonlinear Systems , 1997 .

[2]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[3]  Khairy A.H. Kobbacy,et al.  Intelligent systems in manufacturing: current developments and future prospects , 2000 .

[4]  Margaret A. Nemeth,et al.  Basic Statistics : Tools for Continuous Improvement , 1990 .

[5]  J. Weiner,et al.  Fundamentals and applications , 2003 .

[6]  Sangit Chatterjee,et al.  A Pareto-like effect in regression ? , 1998 .

[7]  Scott Tonidandel,et al.  Sample size and power calculations in repeated measurement analysis , 2001, Comput. Methods Programs Biomed..

[8]  Timon C. Du,et al.  Applying Six-Sigma to Supplier Development , 2004 .

[9]  Cl Huang,et al.  The construction of production performance prediction system for semiconductor manufacturing with artificial neural networks , 1999 .

[10]  Peter S. Pande,et al.  The Six Sigma Way Team Fieldbook: An Implementation Guide for Process Improvement Teams , 2001 .

[11]  Kostas S. Metaxiotis,et al.  Expert systems in production planning and scheduling: A state-of-the-art survey , 2002, J. Intell. Manuf..

[12]  Fugee Tsung,et al.  A DMAIC approach to printed circuit board quality improvement , 2004 .

[13]  R Guh.  IntelliSPC: a hybrid intelligent tool for on-line economical statistical process control , 1999 .

[14]  Daniel J. Ehrlich,et al.  Emerging technologies for in situ processing , 1988 .

[15]  John C. Mallinson.  Magneto-Resistive Heads: Fundamentals and Applications , 1995 .

[16]  Chen Nianyi,et al.  Artificial neural network prediction of the band gap and melting point of binary and ternary compound semiconductors , 1998 .

[17]  Leslie W. Flott.  Six-sigma controversy , 2000 .

[18]  Chonghun Han,et al.  Intelligent systems in process engineering : A review , 1996 .

[19]  J. D. Tate,et al.  Comparison of partial least squares regression and multi-layer neural networks for quantification of nonlinear systems and application to gas phase Fourier transform infrared spectra , 2003 .

[20]  Forrest W. Breyfogle,et al.  Implementing Six Sigma: Smarter Solutions Using Statistical Methods , 1999 .

[21]  N C Proudlove,et al.  Intelligent management systems in operations: a review , 1998, J. Oper. Res. Soc..

[22]  Wolfgang Rosenstiel,et al.  Error Classification and Yield Prediction of Chips in Semiconductor Industry Applications , 2000, Neural Computing & Applications.

[23]  Prasad K. Yarlagadda,et al.  Development of a hybrid neural network system for prediction of process parameters in injection moulding , 2001 .