類神經網路在品質管制上之應用:非隨機性變化之偵測

The Application of Artificial Neural Network to Quality Control : Recognition of Nonrandom patterns

謝昆霖(Shau-Hwa Ow)

指導教授 ： 鄭春生

元智大學/工程學院/工業工程與管理學系/碩士(1994年)

摘要

在製程管制中辨認管制圖中之非隨機性模型是一件重要的工作。這些非隨
機性模型，表示製程是受到一些可歸屬原因的影響所造成的，一旦製程出
現這些非隨機性模型，則需要去做一些矯正製程的動作。本研究提出一個
以模組化網路為基礎的非隨機性模型辨認程序。本研究是以模擬數據來訓
練和評估類神經網路。由多項評估指標來看，本研究所建立之模組化類神
經網路可以有效地辨認管制圖之非隨機性模型，而且其成效也較倒傳遞網
路為優。

關鍵字

多變量統計製程管制 ； 類神經網路 ； 平均連串長度

並列摘要

Control chart pattern recognition is an important aspect of
statistical process control(SPC). The presence of
unnatural patterns indicates that a process is affected by
assignable causes, and corrective actions should be taken.
This paper describes one type of pattern recognition
procedure based on modural neural network architectures. The
pattern recognition procedure were developed to take the
advantage of the fact that a particular unnatural pattern is
often associated with a set of assignable causes. Th e
performances of the proposed pattern recognition procedure
were evaluated through Monte Carlo simulations on the basis of
appropriate performance measures. An extensive evaluation
indicates that the proposed pattern recognition procedure
could recgnize multiple unnatural patterns for which they
were trained. The results also indicat that modular network
performance is batter than that of backpropagation neural
network.

並列關鍵字

Multivariate quality control ； artificial neural network ； average run length