Mixture of Elastic Net Experts and its Application to a Polymerization Batch Process

Soft sensors are widely applied in many industrial systems for predicting quality variables in real-time; examples of soft sensors applications can be found in pulp and paper mills, cement kilns, polymerization processes and so on. However, there are several peculiarities that make soft sensors development difficult in some processes. One of these characteristics is the multiple operating mode scenarios, which is characterized by different operating regions of process, e.g. summer-winter operation of a refinery, batch processes, etc. In this paper, a regularized version of mixture of expert models, based on elastic net regularization, is employed for predicting the acidity value, a quality indicator variable of process, in a batch polymerization process. The proposed method allowed the application of 27 experts to compose the final model and attaining better prediction performance when compared to other state-of-the-art algorithms. The proposed method is compared to the predictive modeling state-of-the-art methods, such as support vector machines (SVM), decision trees (DT), and the elastic net model (EN).