Title: Augmenting statistical quality control with machine learning techniques: an overview
Authors: Aikaterini Fountoulaki; Nikos Karacapilidis; Manolis Manatakis
Addresses: Industrial Management and Information Systems Lab, MEAD, University of Patras, Rion-Patras 26500, Greece. ' Industrial Management and Information Systems Lab, MEAD, University of Patras, Rion-Patras 26500, Greece. ' Department of Mechanical Engineering and Aeronautics, University of Patras, Rion-Patras 26500, Greece
Abstract: This paper attempts to provide practical insights to issues related to the enrichment of statistical quality control (SQC) systems with machine learning (ML). It reports on ML techniques that have already augmented the major SQC methods, comments on their advantages and disadvantages and identifies areas of improvement that could delineate future work directions. Three major SQC methods are considered: acceptance sampling, statistical process control and experimental design. The work reported in this paper reveals that ML techniques can significantly augment SQC systems.
Keywords: statistical quality control; machine learning; acceptance sampling; statistical process control; experimental design; industrial quality systems; system improvements; business; systems research.
DOI: 10.1504/IJBSR.2011.043162
International Journal of Business and Systems Research, 2011 Vol.5 No.6, pp.610 - 626
Published online: 22 Apr 2015 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article