A Fault Detection System for an Autocorrelated Process Using SPC/EPC/ANN and SPC/EPC/SVM Schemes
The Statistical Process Control (SPC) chart is effective in detecting process faults. One important assumption for using the traditional SPC charts requires that the plotted observations are independent to each other. However, the assumption of independent observations is not typically applicable in practice. When the observations are auto-correlated, the false alarms are increased, and these improper signals can result in a misinterpretation. Therefore, the use of Engineering Process Control (EPC) has been proposed to overcome this difficulty. Although EPC is able to compensate for the effects of faults, it decreases the monitoring capability of SPC. This study proposes the combination of SPC, EPC and Artificial Neural Network (SPC/EPC/ANN) and SPC, EPC and Support Vector Machine (SPC/EPC/SVM) mechanisms to solve this problem.