Optimal online forecasting system for propylene polymerization production process based on weighted combination learning

Abstract

The invention discloses an optimal online forecast system for propylene polymerization production process based on weighted combination learning, which is used for quality inspection of polypropylene production products. The optimal online forecast model based on weighted combination learning includes phase space reconstruction , PCA principal component analysis module, support vector machine module, model update module, cuckoo search algorithm optimization module, Adaboost module. The invention predicts the melting index of an important quality index in the polypropylene production process on-line, overcomes the shortcomings of traditional chemical instruments, such as large measurement time lag and low measurement accuracy, and realizes on-line measurement, strong optimization and promotion ability, strong anti-noise interference ability, and high precision.

Description

technical field [0001] The invention relates to the field of quality detection of the polymerization process and the field of data-driven modeling, in particular to an optimal online forecast system for the propylene polymerization production process based on weighted combination learning. Background technique [0002] Polypropylene is a thermoplastic resin produced by propylene polymerization. The most important downstream product of propylene, 50% of the world's propylene and 65% of my country's propylene are used to make polypropylene. It is one of the five general-purpose plastics. are closely related to daily life. Polypropylene is the fastest growing general-purpose thermoplastic resin in the world, second only to polyethylene and polyvinyl chloride in total. In order to make my country's polypropylene products have market competitiveness, develop impact copolymer products, random copolymer products, BOPP and CPP film materials, fibers, and non-woven fabrics with good ...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the current existing propylene polymerization production process, which are not high in measurement accuracy and easily affected by human factors, the purpose of the present invention is to provide an online measurement with fast forecasting speed, automatic model update, strong anti-interference ability, and high accuracy. Gao Optimal online prediction system for melt index in propylene polymerization production process based on weighted combination learning

Images