A data mining approach to process optimization without an explicit quality function

TY - JOUR

T1 - A data mining approach to process optimization without an explicit quality function

AU - Chong, Il Gyo

AU - Albin, Susan L.

AU - Jun, Chi Hyuck

N1 - Funding Information: We would like to thank the Departmental Editor and anonymous referees for their helpful comments. The work by Chi-Hyuck Jun was partially supported by the KOSEF through the National Core Research Center for System BioDynamics at POSTECH. Funding Information: Susan L. Albin is a Professor and Director of the Graduate Program in the Department of Industrial and Systems Engineering at Rutgers University. Her research interests lie in quality engineering, multivariate process control, multivariate optimization, and stochastic modeling. Her work has been applied in areas including semiconductor manufacturing, plastics recycling, food processing, materials processing, and medical devices. Her research has been supported by the NSF, FAA, DOD, Exxon, the Army and industrial companies. She received her doctorate from Columbia University. Currently she is the Secretary of INFORMS, the Institute for Operations Research and the Management Sciences, and is also a Fellow of the IIE. She is Focused Issues Editor of IIE Transactions—Quality and Reliability Engineering and has served as Associate Editor for Management Science.

PY - 2007/8

Y1 - 2007/8

N2 - In process optimization, the setting of the process variables is usually determined by estimating a function that relates the quality to the process variables and then optimizing this estimated function. However, it is difficult to build an accurate function from process data in industrial settings because the process variables are correlated, outliers are included in the data, and the form of the functional relation between the quality and process variables may be unknown. A solution derived from an inaccurate function is normally far from being optimal. To overcome this problem, we use a data mining approach. First, a partial least squares model is used to reduce the dimensionality of the process and quality variables. Then the process settings that yield the best output are identified by sequentially partitioning the reduced process variable space using a rule induction method. The proposed method finds an optimal setting from historical data without constructing an explicit quality function. The proposed method is illustrated with two examples obtained from steel making processes. We also show, through simulation, that the proposed method gives more stable results than estimating an explicit function even when the form of the function is known in advance.

AB - In process optimization, the setting of the process variables is usually determined by estimating a function that relates the quality to the process variables and then optimizing this estimated function. However, it is difficult to build an accurate function from process data in industrial settings because the process variables are correlated, outliers are included in the data, and the form of the functional relation between the quality and process variables may be unknown. A solution derived from an inaccurate function is normally far from being optimal. To overcome this problem, we use a data mining approach. First, a partial least squares model is used to reduce the dimensionality of the process and quality variables. Then the process settings that yield the best output are identified by sequentially partitioning the reduced process variable space using a rule induction method. The proposed method finds an optimal setting from historical data without constructing an explicit quality function. The proposed method is illustrated with two examples obtained from steel making processes. We also show, through simulation, that the proposed method gives more stable results than estimating an explicit function even when the form of the function is known in advance.

KW - Data mining

KW - Multicollinearity

KW - Partial least squares (PLS)

KW - Patient rule induction method (PRIM)

KW - Process optimization

UR - http://www.scopus.com/inward/record.url?scp=34249940628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249940628&partnerID=8YFLogxK

U2 - https://doi.org/10.1080/07408170601142668

DO - https://doi.org/10.1080/07408170601142668

M3 - Article

SN - 0740-817X

VL - 39

SP - 795

EP - 804

JO - IIE Transactions (Institute of Industrial Engineers)

JF - IIE Transactions (Institute of Industrial Engineers)

IS - 8

ER -