Optimization control system for nitrifying process

Abstract

The nitrifying process is an important step in dinitrochlorobenzene production. This paper presented an optimization control system to implement the modeling, optimization, and control of the nitrifying process. Models for predicting the quality of nitrifying process are derived and implemented using improved back-propagation neural networks, and an algorithm combining c-means clustering, genetic, and chaos approaches for the optimization of the operating parameters of the nitrifying process is presented. The results of actual runs demonstrate the validity of the system.