Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme

Monitoring and diagnosis of mean shifts in manufacturing processes become more challenging when involving two or more correlated variables. Unfortunately, most of the existing multivariate statistical process control schemes are only effective in rapid detection but suffer high false alarm. This is...

Full description

Bibliographic Details
Main Authors:	Masood, Ibrahim, Ali, Rasheed Majeed, Mohd Solihin, Nurul Adlihisam, Elewe, Adel Muhsin
Format:	Article
Published:	Asian Research Publishing Network (ARPN) 2016
Subjects:	TJ1-162 Mechanical engineering and machinery
Online Access:	http://www.arpnjournals.org/jeas/research_papers/rp_2016/jeas_0616_4518.pdf http://www.arpnjournals.org/jeas/research_papers/rp_2016/jeas_0616_4518.pdf

id	uthm-10029
recordtype	eprints
spelling	uthm-100292018-08-13T03:31:48Z Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme Masood, Ibrahim Ali, Rasheed Majeed Mohd Solihin, Nurul Adlihisam Elewe, Adel Muhsin TJ1-162 Mechanical engineering and machinery Monitoring and diagnosis of mean shifts in manufacturing processes become more challenging when involving two or more correlated variables. Unfortunately, most of the existing multivariate statistical process control schemes are only effective in rapid detection but suffer high false alarm. This is referred to as imbalanced performance monitoring. The problem becomes more complicated when dealing with small mean shift particularly in identifying the causable variables. In this research, a scheme that integrated the control charting and pattern recognition technique has been investigated toward improving the quality control (QC) performance. Design considerations involved extensive simulation experiments to select input representation based on raw data and statistical features, recognizer design structure based on individual and Statistical Features-ANN models, and monitoring-diagnosis approach based on single stage and two stages techniques. The study focuses on correlated process mean shifts for cross correlation function, ρ = 0.1, 0.5, 0.9, and mean shift, μ = ± 0.75 ~ 3.00 standard deviations. Among the investigated design, an Integrated Multivariate Exponentially Weighted Moving Average with Artificial Neural Network scheme provides superior performance, namely the Average Run Length for grand average ARL1 = 7.55 ̴ 7.78 ( for out-of-control) and ARL0 = 4λ1.03 (small shifts) and 524.80 (large shifts) in control process and the grand average for recognition accuracy (RA) = λ6.36 ̴ λ8.74. This research has provided a new perspective in realizing balanced monitoring and accurate diagnosis of correlated process mean shifts. Asian Research Publishing Network (ARPN) 2016-06 Article PeerReviewed http://www.arpnjournals.org/jeas/research_papers/rp_2016/jeas_0616_4518.pdf Masood, Ibrahim and Ali, Rasheed Majeed and Mohd Solihin, Nurul Adlihisam and Elewe, Adel Muhsin (2016) Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme. ARPN Journal of Engineering and Applied Sciences, 11 (12). pp. 7806-7812. ISSN 18196608 http://eprints.uthm.edu.my/10029/
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Tun Hussein Onn Malaysia
building	UTHM Institutional Repository
collection	Online Access
topic	TJ1-162 Mechanical engineering and machinery
spellingShingle	TJ1-162 Mechanical engineering and machinery Masood, Ibrahim Ali, Rasheed Majeed Mohd Solihin, Nurul Adlihisam Elewe, Adel Muhsin Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
description	Monitoring and diagnosis of mean shifts in manufacturing processes become more challenging when involving two or more correlated variables. Unfortunately, most of the existing multivariate statistical process control schemes are only effective in rapid detection but suffer high false alarm. This is referred to as imbalanced performance monitoring. The problem becomes more complicated when dealing with small mean shift particularly in identifying the causable variables. In this research, a scheme that integrated the control charting and pattern recognition technique has been investigated toward improving the quality control (QC) performance. Design considerations involved extensive simulation experiments to select input representation based on raw data and statistical features, recognizer design structure based on individual and Statistical Features-ANN models, and monitoring-diagnosis approach based on single stage and two stages techniques. The study focuses on correlated process mean shifts for cross correlation function, ρ = 0.1, 0.5, 0.9, and mean shift, μ = ± 0.75 ~ 3.00 standard deviations. Among the investigated design, an Integrated Multivariate Exponentially Weighted Moving Average with Artificial Neural Network scheme provides superior performance, namely the Average Run Length for grand average ARL1 = 7.55 ̴ 7.78 ( for out-of-control) and ARL0 = 4λ1.03 (small shifts) and 524.80 (large shifts) in control process and the grand average for recognition accuracy (RA) = λ6.36 ̴ λ8.74. This research has provided a new perspective in realizing balanced monitoring and accurate diagnosis of correlated process mean shifts.
format	Article
author	Masood, Ibrahim Ali, Rasheed Majeed Mohd Solihin, Nurul Adlihisam Elewe, Adel Muhsin
author_facet	Masood, Ibrahim Ali, Rasheed Majeed Mohd Solihin, Nurul Adlihisam Elewe, Adel Muhsin
author_sort	Masood, Ibrahim
title	Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
title_short	Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
title_full	Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
title_fullStr	Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
title_full_unstemmed	Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme
title_sort	diagnosis of bivariate process variation using an integrated mspc-ann scheme
publisher	Asian Research Publishing Network (ARPN)
publishDate	2016
url	http://www.arpnjournals.org/jeas/research_papers/rp_2016/jeas_0616_4518.pdf http://www.arpnjournals.org/jeas/research_papers/rp_2016/jeas_0616_4518.pdf
first_indexed	2018-09-05T11:55:42Z
last_indexed	2018-09-05T11:55:42Z
_version_	1610768493949485056

Diagnosis of bivariate process variation using an integrated MSPC-ANN scheme

Similar Items