On-Line Soft Sensor for Polyethylene Process with Multiple Production Grades

Since the online measurement of melt index (MI) of polyethylene is difficult, a virtual sensor model is desirable. However, a polyethylene process usually produces products with multiple grades. The relations between process and quality variables are highly nonlinear. In addition, a virtual sensor model in the real plant process with many inputs has to deal with the collinearity and the time-varying issues. A new recursive algorithm, which models the multivariable, time-varying and nonlinear system, is presented. Principal component analysis (PCA) is used to eliminate the collinearity. Fuzzy c-means (FCM) and fuzzy Takagi-Sugeno (FTS) modeling are used to decompose the nonlinear system into several linear subsystems. The effectiveness of the proposed method is demonstrated using the real plant data from a polyethylene process.