Modeling and Optimization of Fiber Quality and Energy Consumption during Refining Based on Adaptive Neuro-fuzzy Inference System and Subtractive Clustering

Yunbo Gao, Jun Hua, Liping Cai, Guangwei Chen, Na Jia, Liangkuan Zhu, Hui Wang

Abstract


Refining is a critical step in the manufacturing of medium-density fiberboard (MDF). To ensure fiber quality and control of the energy consumption during refining, proper production parameters, such as feeding screw revolution speed (SR), accumulated chip height (CH), opening ratio of the discharge valve (OV), and content of Chinese poplar (CP), are vital. These parameters were monitored and recorded in an MDF mill to investigate the relationships between the parameters and the fiber quality and energy consumption. In this study, fuzzy models of the fiber quality and the energy consumption during refining were established based on subtractive clustering and an adaptive neuro-fuzzy inference system (ANFIS). The fiber quality and energy consumption models demonstrated high prediction accuracy because their predictive mean relative errors were as low as 4.14% and 6.72%, respectively. The errors of fiber quality were optimized using the simulated annealing method, and the input parameters were obtained. Based on the energy consumption model, the minimum energy consumption was 41.51 kWh/t, on the premise of the minimum requirement of fiber quality. This study can be a guideline for MDF production management to improve fiberboard quality and reduce energy consumption.

Keywords


Fiber quality; Energy consumption; Refining; Fuzzy model; ANFIS; Subtractive clustering

Full Text: PDF

Welcome to BioResources! This online, peer-reviewed journal is devoted to the science and engineering of biomaterials and chemicals from lignocellulosic sources for new end uses and new capabilities. The editors of BioResources would be very happy to assist you during the process of submitting or reviewing articles. Please note that logging in is required in order to submit or review articles. Martin A. Hubbe, (919) 513-3022, hubbe@ncsu.edu; Lucian A. Lucia, (919) 515-7707, lucian.lucia@gmail.com URLs: bioresourcesjournal.com; http://ncsu.edu/bioresources ISSN: 1930-2126