On-line SPC with consideration of learning curve

Authors:
Ling Yang;Yuh-Rau Wang;Suzanne Pai
Affiliations:
Department of Marketing and Logistics Management, St. John's University, 499, Sec. 4, Tam King Road, Tamsui, Taipei 251, Taiwan, ROC;Department of Computer Science and Information Engineering, St. John's University, 499, Sec. 4, Tam King Road, Tamsui, Taipei 251, Taiwan, ROC;Department of Marketing and Logistics Management, St. John's University, 499, Sec. 4, Tam King Road, Tamsui, Taipei 251, Taiwan, ROC
Venue:
Computers and Industrial Engineering
Year:
2009

Citing 5
Cited 0

Quality improvement and learning in productive systems

Management Science
Toward a Theory of Continuous Improvement and the Learning Curve

Management Science
An Empirical Examination of Dynamic Quality-Based Learning Models

Management Science
Behind the Learning Curve: Linking Learning Activities to Waste Reduction

Management Science
Lot sizing for an imperfect production process with quality corrective interruptions and improvements, and reduction in setups

Computers and Industrial Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work identifies a link between on-line statistical process control (SPC) and the learning effect for the process standard deviation (PSD) caused by the quality improvement (QI) program. The learning curve (LC) is used to describe and forecast, and the exponentially weighted root mean square control chart is used to monitor the progress in reducing PSD. A modification of the quality control chart (QCC) that considers LC of PSD is proposed. The reduction rate of PSD may be large during the initial stage of the QI program, and influences QCC construction. Simulation is used to compare the shift-detecting ability of the Shewhart-X@? control chart and EWMA-X@? control chart, without- and with- consideration of LC. The EWMA-X@? chart with consideration of LC performs best. In comparison, the Shewhart-X@? chart without LC consideration has almost no shift-detecting ability when the shift magnitude of the process mean is small, leading to rendering quality control ineffective.