Multiple models soft sensing technique based on online clustering arithmetic for industry distillation

Aiming at the complex operation and composition online detection problem of the industrial distillation, a multiple model soft sensing based on clustering arithmetic is proposed in the paper in order to realize the online soft sensor. Firstly, the principal component analysis and correlation analysis are used to preprocess a large amount of data set in order to acquire proper modeling sample set. And then, the K-means clustering method was used to analyze the modeling data, the multiple models are established using the partial least squares method. The proposed soft-sensing method was used to predict the composition of the product Butadiene. Practical applications indicated the proposed method was useful for the online prediction of the product quality.