Process monitoring and fault detection method based on independent component analysis

Multivariate statistical process control(MSPC) are based upon the assumption that the observed data must be subject to normal probability distribution, which sometimes can not be satisfied in many industrial applications. Independent component analysis(ICA) is a recently developed method, which can overcome the need of the data distribution. In this paper, a new method is introduced for process monitoring and fault detection based on ICA method. Use ICA to extract the independent components, use I-2, Ie(2) and SPE charts for fault detection. At last, the simulation results of fractional distillation process monitoring reveals this method is very effective.