Soft Measurement Model of Raw Meal Decomposition Ratio Based on Data Driven for Raw Meal Calcination Process

Abstract

In cement raw meal calcination process, the raw meal decomposition ratio(hereinafter referred to as RMDR) is an important quality index, and the cement raw meal is decomposed in the calciner because of varying boundary conditions and manual offline detection period of two hour. The product quality index is low and it is easy to cause the preheater C5 (i.e., the No. 5 preheater) feeding tube to be blocked. To solve above problem, a soft measurement model of raw meal decomposition ratio was proposed based on mechanism and hierarchical S kernel function. This model for raw meal calcination process consists of five modules, namely an outlier detection based on KL divergence density ratio, a raw meal decomposition ratio model based on mechanism model, a raw meal decomposition ratio model based on hierarchical S kernel function, an offline detection model, and a coordination factor based on fuzzy model. The actual application results shows that the model proposed can select right sub-model according to current operating conditions, and far from fault condition by the practical application results.