A Predictive Model of Sinter Chemical Composition and Its Application

It is necessary to predict sinter quality in order to realize optimization of technology parameters in sintering process. A predictive model is proposed by combining hybrid Takagi-Sugeno fuzzy model and particle swarm optimization algorithm to predict the quality indexes (FeO content and basicity R) of the finished sinter mineral. The gray relation analysis (GRA) method is used to analyze the factors influencing finished sinter quality. The simulation shows that the method can optimize the structure parameters of the T-S fuzzy model and shorten the learning time. The predictive model was tested by actual industrial data and a relatively satisfactory prediction result was obtained