Pattern recognition for bivariate process mean shifts using feature-based artificial neural network

Masood, Ibrahim and Hassan, Adnan (2012) Pattern recognition for bivariate process mean shifts using feature-based artificial neural network. International Journal Advanced Manufacturing Technology . ISSN 0268-3768

[img]
Preview
PDF
1231Kb

Official URL: http://dx.doi.org/10.1007/s00170-012-4399-2

Abstract

In multivariate quality control, the artificial neural networks (ANN)-based pattern recognition schemes generally performed better for monitoring bivariate process mean shifts and provided more efficient information for diagnosing the source variable(s) compared to the traditional multivariate statistical process control charring. However, these schemes revealed disadvantages in term of reference bivariate pattern in identifying the joint effect and exeess false alarms in identifying stable process condition. In this study, feature-based ANN scheme was investigated for recognizing bivariate correlated patterns. Feature based input representation was utilized into an ANN training and testing towards strengthening discrimination capability between bivariate normal and bivariate mean shift patterns. Besides indicating an effective diagnosis capability in dealing with low correlation bivariate pattern, the proposed scheme promotes a smaller network size and better monitoring capability as compared to the raw data-based ANN scheme.

Item Type:Article
Uncontrolled Keywords:artificial neural networks; bivariate emulated pattem; process monitoring and diagnosis; statistical features; pattern recognition
Subjects:Q Science > QA Mathematics > QA76 Computer software
T Technology > TA Engineering (General). Civil engineering (General) > TA329-348 Engineering mathematics. Engineering analysis
Divisions:Faculty of Mechanical and Manufacturing Engineering > Department of Manufacturing and Industrial Engineering
ID Code:3883
Deposited By:Normajihan Abd. Rahman
Deposited On:16 Aug 2013 16:49
Last Modified:22 Jan 2015 08:33

Repository Staff Only: item control page