Hb. Hwarng et Nf. Hubele, BACKPROPAGATION PATTERN RECOGNIZERS FOR (X)OVER-BAR CONTROL CHARTS - METHODOLOGY AND PERFORMANCE, Computers & industrial engineering, 24(2), 1993, pp. 219-235
The pattern recognition algorithm presented here is based on the perce
ption that, as automated data collection becomes more widespread in ma
nufacturing processes, the monitoring of control charts will be perfor
med by computer-based algorithms. These algorithms will have to detect
unnatural patterns to assist in the correction of assignable causes.
The work currently being performed in addressing the application of pa
ttern recognition to control charts is directed toward answering this
need. In this paper, a control chart pattern recognition methodology b
ased on the back-propagation algorithm, a neural computing theory, is
presented. This classification algorithm, suitable for real-time stati
stical process control, evaluates observations routinely collected for
control charting to determine whether a pattern, such as a trend or c
ycle, exists in the data. The foundation of the algorithm is based on
the neural network concepts of constructing and training a network in
the types of patterns to be detected. These concepts mimic the trained
operator's ability to detect patterns. Here, the pattern recognizer i
s trained and tested with the consideration of Type I error (finding a
pattern where none existed) as well as Type II error (failing to dete
ct a known pattern). Performance measures sensitive to these types of
errors are used to evaluate the algorithm's performance on an extensiv
e series of simulated patterns of control chart data. This approach is
promising because of its flexible training and high-speed computation
.