B. Talebjedi, T. Laukkanen, H. Holmberg, E. Lut, S. Syri
{"title":"Energy simulation and variable analysis of refining process in thermo-mechanical pulp mill using machine learning approach","authors":"B. Talebjedi, T. Laukkanen, H. Holmberg, E. Lut, S. Syri","doi":"10.1080/13873954.2021.1990967","DOIUrl":null,"url":null,"abstract":"ABSTRACT Data from two thermo-mechanical pulp mills are collected to simulate the refining process using deep learning. A multilayer perceptron neural network is utilized for pattern recognition of the refining variables. Results show the impressive capability of artificial intelligence methods in refining energy simulation so that the correlation coefficient of 98% is accessible. A comprehensive parametric study has been made to investigate the effect of refining disturbance variables, plate gap and dilution water on refining energy simulation. The generated model reveals the non-linear hidden pattern between refining variables, which can be used for optimal refining control strategy. Considering the disturbance variables’ effect in refining energy simulation, model accuracy could increase by 15%. Removing the plate gape from predictive variables reduces the simulation determination coefficient by up to 25% in both mills, while the mentioned value for removing dilution water is 9–17% in mill 1 and about 35% in mill 2.","PeriodicalId":49871,"journal":{"name":"Mathematical and Computer Modelling of Dynamical Systems","volume":"27 1","pages":"562 - 585"},"PeriodicalIF":1.8000,"publicationDate":"2021-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mathematical and Computer Modelling of Dynamical Systems","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1080/13873954.2021.1990967","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 6
Abstract
ABSTRACT Data from two thermo-mechanical pulp mills are collected to simulate the refining process using deep learning. A multilayer perceptron neural network is utilized for pattern recognition of the refining variables. Results show the impressive capability of artificial intelligence methods in refining energy simulation so that the correlation coefficient of 98% is accessible. A comprehensive parametric study has been made to investigate the effect of refining disturbance variables, plate gap and dilution water on refining energy simulation. The generated model reveals the non-linear hidden pattern between refining variables, which can be used for optimal refining control strategy. Considering the disturbance variables’ effect in refining energy simulation, model accuracy could increase by 15%. Removing the plate gape from predictive variables reduces the simulation determination coefficient by up to 25% in both mills, while the mentioned value for removing dilution water is 9–17% in mill 1 and about 35% in mill 2.
期刊介绍:
Mathematical and Computer Modelling of Dynamical Systems (MCMDS) publishes high quality international research that presents new ideas and approaches in the derivation, simplification, and validation of models and sub-models of relevance to complex (real-world) dynamical systems.
The journal brings together engineers and scientists working in different areas of application and/or theory where researchers can learn about recent developments across engineering, environmental systems, and biotechnology amongst other fields. As MCMDS covers a wide range of application areas, papers aim to be accessible to readers who are not necessarily experts in the specific area of application.
MCMDS welcomes original articles on a range of topics including:
-methods of modelling and simulation-
automation of modelling-
qualitative and modular modelling-
data-based and learning-based modelling-
uncertainties and the effects of modelling errors on system performance-
application of modelling to complex real-world systems.