Design optimization of ANN-based pattern recognizer for multivariate quality control
In manufacturing industries, process variation is known to be 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 or known as multivariate. Proc...
| Váldodahkki: | |
|---|---|
| Materiálatiipa: | Oahppočájánas |
| Giella: | English English English |
| Almmustuhtton: |
2013
|
| Fáttát: | |
| Liŋkkat: | http://eprints.uthm.edu.my/1983/1/24p%20MUHAMAD%20FAIZAL%20ABDUL%20JAMIL.pdf http://eprints.uthm.edu.my/1983/2/MUHAMAD%20FAIZAL%20ABDUL%20JAMIL%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/1983/3/MUHAMAD%20FAIZAL%20ABDUL%20JAMIL%20WATERMARK.pdf |
| Čoahkkáigeassu: | In manufacturing industries, process variation is known to be 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 or known as multivariate. Process monitoring refers to the identification of process
status either it is running within a statistically in-control or out-of-control condition, while
process diagnosis refers to the identification of the source variables of out-of-control process.
The traditional statistical process control (SPC) charting scheme are known to be effective in
monitoring aspects, but they are lack of diagnosis. In recent years, the artificial neural
network (ANN) based pattern recognition schemes has been developed for solving this issue.
The existing ANN model recognizers are mainly utilize raw data as input representation,
which resulted in limited performance. In order to improve the monitoring-diagnosis
capability, in this research, the feature based input representation shall be investigated using
empirical method in designing the ANN model recognizer. |
|---|