Advanced energy-saving optimization strategy in thermo-mechanical pulping by machine learning approach
Source abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Lignin and Wood Chemistry · Optimization and Packing Problems · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, School of Engineering , 174277 Aalto University , Espoo , Finland
Department of Energy , 4415 Lappeenranta University of Technology , Lappeenranta , Finland
Funding
Academy of Finland
References (40)
Show source-provided references
1. Bajpai, P. Pulp and Paper Industry: Energy Conversion. Elsevier, 2016.10.1016/B978-0-12-811099-7.00002-2 ↗
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):285–291.10.3183/npprj-1999-14-04-p285-291 ↗
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):1647–1654.10.1016/j.biortech.2006.05.040 ↗
6. Browne, B.T., Miles, K., Mcdonald, D., Wood, J., Browne, T. (2004) Multivariate analysis of seasonal pulp quality variations in a TMP mill. Pulp Pap. Can. 105(10):35–39.
7. Ciesielski, K., Olejnik, K. (2014) Application of Neural Networks for Estimation of Paper Properties Based on Refined Pulp Properties. Fibres Text. East. Eur. 5(107):126–132.
8. Elahimehr, A., Olson, J.A., Martinez, D.M. (2018) Understanding LC refining: The effect of plate pattern and refiner operation. Nord. Pulp Pap. Res. J. 28(3):386–391.10.3183/npprj-2013-28-03-p386-391 ↗
9. Fuhr, B.J., Henry, D., Leary, G., Smith, G. (1998) Seasonal variations at a mechanical newsprint mill. Pulp Pap. Can. 99(2):45–49.
10. Gao, Y., Huang, F., Rajbhandari, V., Li, K., Zhou, Y. (2009) Effect of separate refining and co-refining of bctmp/kp on paper properties. Pulp Pap. Can. 110(6):28–33.
11. Gharehkhani, S., et al. (2015) Basic effects of pulp refining on fiber properties – A review. Carbohydr. Polym. 115:785–803.10.1016/j.carbpol.2014.08.047 ↗
12. Hagan, M.T., Menhaj, M.B. (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 5(6):2–6.10.1109/72.329697 ↗
13. Harinath, E., Biegler, L., Dumont, G. (2013) Predictive optimal control for thermo-mechanical pulping processes with multi-stage low consistency refining. J. Process Control 23(7):1001–1011.10.1016/j.jprocont.2013.05.005 ↗
14. Harinath, E., Biegler, L.T., Dumont, G.A. (2011) Control and optimization strategies for thermo-mechanical pulping processes: Nonlinear model predictive control. J. Process Control 21(4):519–528.10.1016/j.jprocont.2011.01.009 ↗
15. Hong, G., Ma, C., Chen, H., Chuang, K., Chang, C., Su, T. (2011) Energy flow analysis in pulp and paper industry. Energy 36(5):3063–3068.10.1016/j.energy.2011.02.051 ↗
16. Hubbe, M.A., Heitmann, J.A. (2007) Review of factors affecting the release of water from cellulosic fibers during paper manufacture. BioResources 2(3):500–533.10.15376/biores.2.3.500-533 ↗
17. International Energy Agency. Tracking industrial energy efficiency and CO2 emissions. OECD/IEA, Paris, 2007.
18. Jang, H., Topal, E. (2013) Optimizing overbreak prediction based on geological parameters comparing multiple regression analysis and artificial neural network. Tunn. Undergr. Space Technol. 38:161–169.10.1016/j.tust.2013.06.003 ↗
19. Kerekes, R. (1990) Characterization of pulp refiners by a C-factor. Nord. Pulp Pap. Res. J. 5(1):3–8.10.3183/npprj-1990-05-01-p003-008 ↗
20. Kerekes, R., Olson, J. (2003) Perspectives on fibre length reduction in refining. In: Proceedings of 7th PIRA international refining conference & exhibition.
21. Li, B., Li, H., Zha, Q., Bandekar, R., Alsaggaf, A., Ni, Y. (2011) Review: Effects of wood quality and refining process on TMP pulp and paper quality. BioResources 6(3):3569–3584.10.15376/biores.6.3.Li ↗
22. Marquardt, D. (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J. Appl. Math. 11(2):431–441.10.1137/0111030 ↗
23. Musavi, M.T., Coughlin, D.R., Qiao, M. (1995) Prediction of wood pulp K with radial basis function neural network. In: Proceedings of ISCAS’95 – International Symposium on Circuits and Systems. pp. 1716–1719.10.1109/ISCAS.1995.523743 ↗
24. Oliveira, M., Almada-lobo, B. (2012) Integrated pulp and paper mill planning and scheduling. Comput. Ind. Eng. 63(1):1–12.10.1016/j.cie.2012.01.008 ↗
25. Paradis, M.A., Genco, J.M., Bousfield, D.W., Hassler, J.C. (2002) Determination of drainage resistance coefficients under known shear rate. Tappi J. 1(8):12–18.
26. Perrusquía, A., Yu, W. (2021) Neurocomputing Identification and optimal control of nonlinear systems using recurrent neural networks and reinforcement learning: An overview. Neurocomputing 438:145–154.10.1016/j.neucom.2021.01.096 ↗
27. Persson, J., Berntsson, T. (2009) Influence of seasonal variations on energy-saving opportunities in a pulp mill. Energy 34(10):1705–1714.10.1016/j.energy.2009.07.023 ↗
28. Pulkkinen, I. From eucalypt fiber distributions to technical properties of paper. Aalto University, Espoo, 2010.
29. Sainlez, M., Heyen, G. (2013) Comparison of supervised learning techniques for atmospheric pollutant monitoring in a Kraft pulp mill. J. Comput. Appl. Math. 246:329–334.10.1016/j.cam.2012.06.026 ↗
30. Sandberg, C., Ferritsius, O., Ferritsius, R. (2021) Mechanical pulping Energy efficiency in mechanical pulping – definitions and considerations. Nord. Pulp Pap. Res. J. 36(3):425–434.10.1515/npprj-2021-0013 ↗
31. Schmidhuber, J. (2015) Deep learning in neural networks: An overview. Neural Netw. 61:85–117.10.1016/j.neunet.2014.09.003 ↗
32. Schwartz, H., Chang, G., Liu, Y., Phung, T. (1996) A method of modeling, predicting and controlling TMP pulp properties. In: Proceeding of the 1996 IEEE International Conference on Control Applications. pp. 846–851.10.1109/CCA.1996.558977 ↗
33. Seth, R., Page, D. (1988) Fiber properties and tearing resistance. Tappi J. 71(2):103–107.
34. Simula, O., Alhoniemi, E. (2006) SOM based analysis of pulping process data. In: International Work-Conference on Artificial Neural Networks. pp. 567–577.10.1007/BFb0100524 ↗
35. Talebjedi, B., Behbahaninia, A. (2021) Availability analysis of an Energy Hub with CCHP system for economical design in terms of Energy Hub operator. J. Build. Eng. 33:101564.10.1016/j.jobe.2020.101564 ↗
36. Talebjedi, B., Khosravi, A., Laukkanen, T., Holmberg, H., Vakkilainen, E., Syri, S., (2020) Energy Modeling of a Refiner in Thermo-Mechanical Pulping Process Using ANFIS Method. Energies 13(19):5113. https://doi.org/10.3390/en13195113.10.3390/en13195113 ↗
37. Talebjedi, B., Laukkanen, T., Holmberg, H., Vakkilainen, E., Syri, S., (2021) Energy Efficiency Analysis of the Refining Unit in Thermo-Mechanical Pulp Mill. Energies 14(6):1664. https://doi.org/10.3390/en14061664.10.3390/en14061664 ↗
38. Talebjedi, B., Laukkanen, T., Holmberg, H., Vakkilainen, E., Syri, S. (2021) Energy simulation and variable analysis of refining process in thermo-mechanical pulp mill using machine learning approach. Math. Comput. Model. Dyn. Syst. 27(1):562–585.10.1080/13873954.2021.1990967 ↗
39. Tian, H., Prakash, J., Zavala, V.M., Olson, J.A., Gopaluni, R.B. (2020) A tractable approximation for stochastic MPC and application to mechanical pulping processes. Comput. Chem. Eng. 141:106977.10.1016/j.compchemeng.2020.106977 ↗
40. Wang, Y., Elhag, T. (2007) A comparison of neural network, evidential reasoning and multiple regression analysis in modelling bridge risks. Expert Syst. Appl. 32(2):336–348.10.1016/j.eswa.2005.11.029 ↗