ADVANCED ANALYTICS APPLIED TO PROBLEM SOLVING TECHNIQUE ON A PULP MILL

Authors

  • Felipe De Carli
  • R. I.G. Mejia
  • Guilherme A.T. De Araújo

DOI:

https://doi.org/10.52292/j.laar.2019.355

Keywords:

Lean manufacturing, Problem solving, Advanced analytics, Process modelling, Pulp mill

Abstract

In this article, advanced analytics will be applied to the lean 8 step problem solving technique aiming to increase the data analysis reliability. The modelling techniques consider in this work are boosted and bagging decision trees, artificial neural networks, relief and stepwise regression. The proposal is validated by the evaluation of a bleaching process problem on a pulp mill. The high pressure events on bleaching washer feeding stage resulted on bleaching non planned shutdowns. The lean 8 steps problem solving technique allied to advanced analytics modeling tools reduced the high pressure events on 63%. As a result, the plant reduced its loss of production due to bleaching plant and allowed to increase the pulp production rate. On this example the relief, decision trees and stepwise regression algorithms proved to be a well-tuned packet for problem solving in a pulp mill.

Downloads

Published

2019-07-31

Issue

Vol. 49 No. 3 (2019): Latin American Applied Research

Section

Control and Information Processing

License

Once a paper is accepted for publication, the author is assumed to have transferred its copyright to the Publisher. The Publisher will not, however, put any limitation on the personal freedom of the author to use material from the paper in other publications. From September 2019 it is required that authors explicitly sign a copyright release form before their paper gets published. The Author Copyright Release form can be found here