Proposition of a New Fault Detection Method Using Independent Component Analysis and Support Vector Machine for Developing of High Predictive Soft Sensor

Abstract

Soft sensors are widely used to estimate a process variable which is difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes of state of chemical plants. In order to cope with this problem, a regression model can be updated. However, if the model is updated with abnormal data, the predictive ability can deteriorate. In this paper, we propose a new fault detection and classification method using independent component analysis (ICA) and support vector machine (SVM). This method, named ICA-SVM, was applied to the soft sensor in order to increase fault detection ability and predictive accuracy. It is conceivable that we could comprehend the state of a plant by using the ICA-SVM model and estimate the objective variable by the regression model, updating it appropriately. We analyzed real industrial data to confirm the fault detection ability and predictive accuracy of the proposed method. First, we verified the fault detection ability, and then showed that the proposed method achieved higher predictive accuracy than the traditional one.