A novel soft-sensor model which incorporates PCA （principal component analysis）, RBF （Radial Basis Function） networks, and MSA （Multi-scale analysis）, is proposed to infer the properties of manufactured products from real process variables. PCA is carried out to select the most relevant process features and to eliminate the correlations of input variables; multi-scale analysis is introduced to acquire much more information and to reduce uncertainty in the system; and RBF networks are used to characterize the nonlinearity of the process. A prediction of the melt index （MI）, or quality of polypropylene produced in an actual industrial process, is taken as a case study. Research results show that the proposed method provides promising prediction reliability and accuracy.
Internal thermally coupled distillation column(ITCDIC) is a frontier in energy saving distillation research. In this paper, the optimal assessment on the energy saving and the operating cost for ITCDIC of nonideal mixture is explored. An evaluating method is proposed, and the pertinent optimization model is then derived. The ethanol-water system is studied as an illustrative example. The optimization results show that the maximum energy saving in ITCDIC process is about 35% and the maximum operating cost saving in ITCDIC process is about 30%,as compared with a conventional distillation column(CDIC) under the minimum reflux ratio operating; the optimal operating pressure of the rectifying section is found to be around 0.25 MPa; the effects of the feed composition,operating pressure and the heat transfer rate on operation are also found and analyzed. It is revealed that ITCDIC process possesses high energy saving potential and promising economical prospect.
Prediction of melt index （MI）, the most important parameter in determining the product＇s grade and quality control of polypropylene produced in practical industrial processes, is studied. A novel soft-sensor model with principal component analysis （PCA）, radial basis function （RBF） networks, and multi-scale analysis （MSA） is proposed to infer the MI of manufactured products from real process variables, where PCA is carried out to select the most relevant process features and to eliminate the correlations of the input variables, MSA is introduced to a^quire much more information and to reduce the uncertainty of the system, and RBF networks are used to characterize the nonlinearity of the process. The research results show that the proposed method provides promising prediction reliability and accuracy, and supposed to have extensive application prospects in propylene polymerization processes.
