A novel distribution-free hybrid regression model for manufacturing process efficiency improvement
share
This work is motivated by a particular problem in a modern paper manufacturing industry, in which maximum efficiency of the process fiber-filler recovery equipment, also known as Krofta supracell, is desired. As a by-product of the paper manufacturing process, a lot of unwanted materials along with valuable fibers and fillers come out as waste materials. The job of an efficient Krofta supracell is to separate the unwanted materials from the valuable ones so that fibers and fillers can be reused in the manufacturing process. In this work, we introduce a novel hybridization of regression trees (RT) and artificial neural networks (ANN), we call it as hybrid RT-ANN model, to solve the problem of low recovery percentage of the supracell. This model is used to achieve the goal of improving supracell efficiency, viz., gain in percentage recovery. In addition, theoretical results for universal consistency of the proposed model are given with the optimal choice of number of nodes in the model. Experimental findings show that the proposed distribution-free hybrid RT-ANN model achieves greater accuracy in predicting Krofta recovery percentage than other conventional regression models for solving the Krofta efficiency problem.
READ FULL TEXT
