Affiliation:
1. Department of Mechanical Engineering, School of Engineering , 174277 Aalto University , Espoo , Finland
2. Department of Energy , 4415 Lappeenranta University of Technology , Lappeenranta , Finland
Abstract
Abstract
Thermo-mechanical Pulping (TMP) is one of the most energy-intensive industries where most of the electrical energy is consumed in the refining process. This paper proposes the energy-saving refining optimization strategy by integrating the machine learning algorithm and heuristic optimization method. First, refining specific energy consumption (RSEC) and pulp quality identification models are developed using Artificial Neural Networks. In the second step, the developed identification models are incorporated with the Genetic algorithm to minimize the total refining specific energy consumption while maintaining the same pulp quality. Simulation results prove that a deep multilayer perceptron neural network is a powerful tool for creating refining energy and quality identification models with the model correlation coefficients of 0.97, 0.94, 0.92, and 0.67 for the first-stage RSEC, second-stage RSEC, final pulp fiber length, and freeness prediction, respectively. Findings confirm that the average total RSEC reduction of 14 % is achievable by utilizing the proposed optimization method.
Subject
General Materials Science,Forestry
Reference40 articles.
1. Bajpai, P. Pulp and Paper Industry: Energy Conversion. Elsevier, 2016.
2. Bajpai, P. Biermann’s Handbook of Pulp and Paper: Raw Material and Pulp Making. Third edition. Elsevier, Kanpur, India, 2018.
3. Batchelor, W., Kjell-Arve, K., Ouellet, D. (1994) Refining and the development of fibre properties. Nord. Pulp Pap. Res. J. 14(4):285–291.
4. Bergstra, J., Bengio, Y. (2012) Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13:281–305.
5. Bhardwaj, N.K., Hoang, V., Nguyen, K.L. (2007) A comparative study of the effect of refining on physical and electrokinetic properties of various cellulosic fibres. Bioresour. Technol. 98(8):1647–1654.
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献