Neural network based data-driven predictor: Case study on clinker quality prediction

Abstract

Soft sensors are key solutions in process industries. Important parameters which are difficult or cost a lot to measure can be predicted using soft sensors. In this paper neural network based clinker quality predictor is developed. The predictor genuinely estimates LSF, SM, AM and C₃S values.
There is a time delay while physically measuring clinker quality parameters. This can be avoided and quick control action can be taken by predicting the parameters. Many neural network based predictors have been developed in different application areas. However, this paper has its own new contribution. First it has developed data synthesis strategy. Besides, multiple and advanced neural network architectures are used to get improved result. Moreover, it is of the first kind for the selected case (Mugher cement factory).

Key words: Soft sensor, neural network, clinker quality prediction.