الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 155 |  |  |
| | | from | 155 | | |
Abstract
Process monitoring in the process industries has been of great practical importance. Early detection of faults is critical in avoiding product quality deterioration to develop process monitoring schemes that can be applied to complex process systems. Statistical Process Control (SPC) charts are powerful tools that are used to improve quality, increase uniformity and minimize production costs in manufacturing. The control chart may indicate an out-of-control condition either when one or more points fall beyond the control limits or when the plotted points exhibit some nonrandom pattern of behavior. The problem is one of pattern recognition that is, recognizing systematic or nonrandom patterns on the control chart and identifying the reason for this behavior. The presence of abnormal (unnatural) patterns indicates that a process is affected by assignable causes, and corrective actions should be taken. The ability to interpret a particular pattern in terms of assignable causes requires experience and knowledge of the process. The abnormal patterns can occur in a process irrespective of the process being a univariate or multivariate one. This work describes a proposed framework for SPC chart pattern recognition, using the Artificial Neural Networks (ANNs). The proposed framework works to recognize set of subclasses of multivariate control chart abnormal patterns, identify the responsible variable(s) and classify the abnormal pattern parameters. The performance of the proposed approach has been evaluated using a numerical example and real case study. The numerical and graphical results are presented which demonstrate that the approach performs effectively in the multivariate control chart pattern recognition. In addition, accurately identifies and classifies the parameters of the errant variable(s). Key Words: Multivariate Statistical Process Control (MSPC) – Control Charts – Artificial Neural Networks (ANNs).