Pattern recognition for manufacturing process variation using statistical features artificial neural network

Abdullah, Abdul Aziz (2015) Pattern recognition for manufacturing process variation using statistical features artificial neural network. Masters thesis, Universiti Tun Hussein Onn Malaysia.

[img]
Preview
PDF
1029Kb

Abstract

In manufacturing industries, process variation is known to be a major source of poor quality. As such, process monitoring and diagnosis is critical towards continuous quality improvement. This becomes more challenging when involving two or more correlated variables (multivariate).The traditional statistical process control (SPC) charting schemes are known to be effective in monitoring aspect but nevertheless, they are lack of diagnosis. In recent years, the control chart pattern recognition (CCPR) schemes have been developed for solving this issue. Design consideration involved the modeling of manufacturing process data to select input representation based on raw data. Proper design of artificial neural network (ANN) model is important in developing an effective CCPR scheme. In this research, the multivariate model ANN pattern recognizer, namely Statistical Features – ANN was investigated in monitoring and diagnosing process variation in manufacturing of hard disc drive component. The finding suggests that the scheme was effective to be applied in various types of process variation such as loading error, offsetting tool, and inconsistent pressure in clamping fixture.

Item Type:Thesis (Masters)
Subjects:T Technology > TS Manufactures > TS155-194 Production management. Operations management
ID Code:7691
Deposited By:Normajihan Abd. Rahman
Deposited On:29 Feb 2016 16:34
Last Modified:29 Feb 2016 16:34

Repository Staff Only: item control page