Machine learning para predecir la calidad del secado de chapas en la industria de tableros contrachapados de Pinus radiata
DOI:
https://doi.org/10.22320/s0718221x/2024.46Keywords:
Algoritmos de aprendizaje supervisado, calidad de la madera, modelo predictivo, secado de chapas, optimización de procesosAbstract
El Aprendizaje automático o Machine learning es una herramienta que está siendo utilizada para optimizar procesos industriales de alta complejidad. En la industria de producción de paneles contrachapados, el secado de chapas es uno de los procesos más importantes ya que permite obtener productos con alta calidad. La naturaleza biológica y alta variabilidad estructural de la madera hace que su procesamiento industrial sea multivariado y difícil de controlar. La gran cantidad de variables presentes y la posibilidad cada vez más frecuente de medirlas en tiempo real están permitiendo la disponibilidad de una gran cantidad de datos. En la actualidad, el enfoque basado en datos y las técnicas de Inteligencia Artificial, específicamente Machine learning, pueden permitir enfoques robustos de predicción y de control. En la industria de procesos con altos niveles de automatización es posible viabilizar la toma de decisiones para predecir la calidad del producto, monitoreando las variables de control explicativas. El objetivo de este trabajo fue evaluar el comportamiento de tres algoritmos de Machine learning para predecir la calidad del proceso de secado de chapas a partir de un número considerable de variables de entrada capturadas de un proceso industrial real. Se utilizó la plataforma Weka y código Python. Se evaluaron los algoritmos: K-Nearest-Neighbor, eXtreme Gradient Boosting y Support Vector Machine. Se realizó reducción de variables y dimensionalidad de análisis de correlación y de componentes principales. Los resultados demostraron que eXtreme Gradient Boosting logró una precisión del 76 % en la predicción de resultados de calidad. Finalmente, se concluye que la metodología de ingeniería de datos y los algoritmos fueron eficientes para predecir los datos industriales.
Downloads
References
Abe, S. 2010. Variants of Support Vector Machines. In Springer (pp. 163-226). https://doi.org/10.1007/978-1-84996-098-4_4 DOI: https://doi.org/10.1007/978-1-84996-098-4_4
Acevedo, C.; Ramos-Maldonado, M.; Aguilera, C.; Monsalve-Lozano, D. 2015. Optimización 3D de patrones de corte para trozas de Pino radiata con cilindro central defectuoso. Maderas. Ciencia y Tecnología 17(2): 421-434. https://doi.org/10.4067/s0718-221x2015005000039 DOI: https://doi.org/10.4067/S0718-221X2015005000039
Alfaleh, A.; Ben, K.N.; Eldin, S.M.; Alturki, M.; Elbadawi, I.; Kumar, R. 2023. Predicting thermal conductivity and dynamic viscosity of nanofluid by employment of Support Vector Machines: A review. Energy Reports 10: 1259-1267. https://doi.org/10.1016/j.egyr.2023.08.001 DOI: https://doi.org/10.1016/j.egyr.2023.08.001
Aydin, I. 2014. Effects of veneer drying at high temperature and chemical treatments on equilibrium moisture content of plywood. Maderas. Ciencia y Tecnologia 16(4): 445-452. https://doi.org/10.4067/S0718-221X2014005000036 DOI: https://doi.org/10.4067/S0718-221X2014005000036
Aydin, I.; Colakoglu, G. 2005. Formaldehyde emission, surface roughness, and some properties of plywood as function of veneer drying temperature. Drying Technology 23(5): 1107-1117. https://doi.org/10.1081/DRT-200059142 DOI: https://doi.org/10.1081/DRT-200059142
Bressan, T.S.; Kehl de Souza, M.; Girelli, T.J.; Junior, F.C. 2020. Evaluation of machine learning methods for lithology classification using geophysical data. Computers and Geosciences 139: e104475. https://doi.org/10.1016/j.cageo.2020.104475 DOI: https://doi.org/10.1016/j.cageo.2020.104475
Chen, T.; Guestrin, C. 2016. XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17-August-2016, 785-794. https://doi.org/10.1145/2939672.2939785 DOI: https://doi.org/10.1145/2939672.2939785
Cortes, C.; Vapnik, V. 1995. Support-Vector Networks. Machine Learning 20: 273-297. http://dx.doi.org/10.1007/bf00994018 DOI: https://doi.org/10.1007/BF00994018
Cover, T.M.; Hart, P.E. 1952. Approximate formulas for the information transmitted bv a discrete communication channel. In IEEE Transactions on Information Theory 24:1. https://doi.org/10.1109/TIT.1967.1053945 DOI: https://doi.org/10.1109/TIT.1967.1053945
Demir, A. 2023. Determination of the effect of valonia tannin when used as a filler on the formaldehyde emission and adhesion properties of plywood with artificial neural network analysis. International Journal of Adhesion and Adhesives 123: e103346 https://doi.org/10.1016/j.ijadhadh.2023.103346 DOI: https://doi.org/10.1016/j.ijadhadh.2023.103346
Demirkir, C.; Colak, S.; Aydin, I. 2013. Some technological properties of wood-styrofoam composite panels. Composites Part B: Engineering 55: 513-517. https://doi.org/10.1016/j.compositesb.2013.07.024 DOI: https://doi.org/10.1016/j.compositesb.2013.07.024
Diez-Olivan, A.; Del Ser, J.; Galar, D.; Sierra, B. 2019. Data fusion and machine learning for industrial prognosis: Trends and perspectives towards Industry 4.0. Information Fusion 50: 92-111. https://doi.org/10.1016/j.inffus.2018.10.005 DOI: https://doi.org/10.1016/j.inffus.2018.10.005
Dogan, A. Birant, D. 2021. Machine learning and data mining in manufacturing. In Expert Systems with Applications 166: e114060. https://doi.org/10.1016/j.eswa.2020.114060 DOI: https://doi.org/10.1016/j.eswa.2020.114060
dos Santos-Freitas, M. M.; Barbosa, J. R.; dos Santos-Martins, E. M.; da Silva-Martins, L. H.; de Souza-Farias, F.; de Fátima-Henriques, L.; da Silva, N. 2022. KNN algorithm and multivariate analysis to select and classify starch films. Food Packaging and Shelf Life 34: e 100976. https://doi.org/10.1016/j.fpsl.2022.100976 DOI: https://doi.org/10.1016/j.fpsl.2022.100976
Duarte, T. 2023. Uso de técnicas de Machine Learning para predecir la calidad de tableros contrachapados. Habilitación Profesional de Ingeniería Civil Química, Universidad del Bío-Bío, Departamento Ingeniería en Madera. Concepción, Chile
Düntsch, I.; Gediga, G. 2019. Confusion Matrices and Rough Set Data Analysis. Journal of Physics: Conference Series 1229(1): e012055. https://doi.org/10.1088/1742-6596/1229/1/012055 DOI: https://doi.org/10.1088/1742-6596/1229/1/012055
Easaw, N.; Lee, W.S.; Lohiya, P.S.; Jalan, S.; Pradhan, P. 2023. Estimation of correlation matrices from limited time series data using machine learning. Journal of Computational Science 71: e102053. https://doi.org/10.1016/j.jocs.2023.102053 DOI: https://doi.org/10.1016/j.jocs.2023.102053
Ellis, J.L.; Alaiz-Moretón, H.; Navarro-Villa, A.; McGeough, E.J.; Purcell, P.; Powell, C. D.; O’Kiely, P.; France, J.; López, S. 2020. Application of meta-analysis and machine learning methods to the prediction of methane production from in vitro mixed ruminal micro-organism fermentation. Animals 10(4): e720. https://doi.org/10.3390/ani10040720 DOI: https://doi.org/10.3390/ani10040720
Foody, G.M.; Mathur, A. 2004. A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing 42(6): 1335-1343. https://doi.org/10.1109/TGRS.2004.827257 DOI: https://doi.org/10.1109/TGRS.2004.827257
Freund, Y.; Schapire, R.E. 1999. A Short Introduction to Boosting. Journal of Japanese Society for Artificial Intelligence 14(5): 771-780. http://www.yorku.ca/gisweb/eats4400/boost.pdf
Frey, U.J.; Klein, M.; Deissenroth, M. 2019. Modelling complex investment decisions in Germany for renewables with different machine learning algorithms. Environmental Modelling and Software 118: 61-75. https://doi.org/10.1016/j.envsoft.2019.03.006 DOI: https://doi.org/10.1016/j.envsoft.2019.03.006
Gatica-Neira, F.; Ramos-Maldonado, M. 2020. Public policies and networks for the development of 4.0 technologies in Chile. PAAKAT: Revista de Tecnología y Sociedad 19(10): 1-28. https://doi.org/10.32870/Pk.a10n19.475 DOI: https://doi.org/10.32870/Pk.a10n19.475
Gatica-Neira, F.; Ramos-Maldonado, M. 2022. Limits to the Productivity in Biobased Territorial SMEs. SAGE Open 12(2): 1-15. https://doi.org/10.1177/21582440221099294 DOI: https://doi.org/10.1177/21582440221099294
Gosselin, P.H.; Murray, N.; Jégou, H.; Perronnin, F. 2014. Revisiting the Fisher vector for fine-grained classification. Pattern Recognition Letters 49: 92-98. https://doi.org/10.1016/j.patrec.2014.06.011 DOI: https://doi.org/10.1016/j.patrec.2014.06.011
Gradov, D.V.; Yusuf, Y.O.; Ohjainen, J.; Suuronen, J.; Eskola, R.; Roininen, L.; Koiranen, T. 2022. Modelling of a continuous veneer drying unit of industrial scale and model-based ANOVA of the energy efficiency. Energy 244: e122673. https://doi.org/10.1016/j.energy.2021.122673 DOI: https://doi.org/10.1016/j.energy.2021.122673
He, H.; Zhang, W.; Zhang, S. 2018. A novel ensemble method for credit scoring: Adaption of different imbalance ratios. Expert Systems with Applications 98: 105-117. https://doi.org/10.1016/j.eswa.2018.01.012 DOI: https://doi.org/10.1016/j.eswa.2018.01.012
Jia, L.; Chu, J.; Ma, L.; Qi, X.; Kumar, A. 2019. Life cycle assessment of plywood manufacturing process in China. International Journal of Environmental Research and Public Health 16(11): e2037. https://doi.org/10.3390/ijerph16112037 DOI: https://doi.org/10.3390/ijerph16112037
Kehr, R. 2007. Evaluación de programas de secado continuo en Chapas de Pinus radiata D. Don. Tesis. Universidad Austral de Chile. Facultad de Ciencias Forestales. Valdivia, Chile
Koskinen, J.; Vaarala, T.; Alatalo, J.; Heikkilä, T. 2013. Automated Quality Classification of Wooden Parts for Flexible Manufacturing. Journal of Engineering Technology 2(1): 239-243. http://dx.doi.org/10.5176/2251-3701_2.1.60 DOI: https://doi.org/10.5176/2251-3701_2.1.60
Lagos-Biolley, L. 2023. Uso de Machine Learning para la optimización de cámaras de secado de chapas de Pino radiata. Habilitación Profesional de Ingeniería Civil en Industrias de la madera, Universidad del Bío-Bío. Departamento Ingeniería en Madera. Concepción, Chile.
Lu, G.; Zeng, L.; Dong, S.; Huang, L.; Liu, G.; Ostadhassan, M.; He, W.; Du, X.; Bao, C. 2023. Lithology identification using graph neural network in continental shale oil reservoirs: A case study in Mahu Sag, Junggar Basin, Western China. Marine and Petroleum Geology 150: e106168. https://doi.org/10.1016/j.marpetgeo.2023.106168 DOI: https://doi.org/10.1016/j.marpetgeo.2023.106168
Lu, Z.; Lin, F.; Ying, H. 2007. Design of decision tree via kernelized hierarchical clustering for multiclass support vector machines. Cybernetics and Systems 38(2): 187-202. https://doi.org/10.1080/01969720601139058 DOI: https://doi.org/10.1080/01969720601139058
Luque, A.; Carrasco, A.; Martín, A.; de las Heras, A. 2019. The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition 91: 216-231. https://doi.org/10.1016/j.patcog.2019.02.023 DOI: https://doi.org/10.1016/j.patcog.2019.02.023
Lutz, J. 1978. Wood Veneer: Log Selection, Cutting, and Drying. Forest Service U.S Department of Agriculture. Technical Bulletin 1577. https://ageconsearch.umn.edu/record/157864/files/tb1577.pdf
Manrique-Rojas, E. 2020. Machine Learning: análisis de lenguajes de programación y herramientas para desarrollo. Revista Ibérica de Sistemas e Tecnologias de Informação Edición no regular E28 Abril: 586-599.
Mehra, N.; Gupta, S. 2013. Survey on Multiclass Classification Methods. International Journal of Computer Science and Information Technologies 4(4): 572-576. https://www.ijcsit.com/docs/Volume%204/Vol4Issue4/ijcsit2013040408.pdf
Mihel, A.M.; Lerga, J.; Krvavica, N. 2024. Estimating water levels and discharges in tidal rivers and estuaries: Review of machine learning approaches. Environmental Modelling and Software 176: e106033. https://doi.org/10.1016/j.envsoft.2024.106033 DOI: https://doi.org/10.1016/j.envsoft.2024.106033
Minaei-Bidgoli, B.; Parvin, H.; Alinejad-Rokny, H.; Alizadeh, H.; Punch, W.F. 2014. Effects of resampling method and adaptation on clustering ensemble efficacy. Artificial Intelligence Review 41(1): 27-48. https://doi.org/10.1007/s10462-011-9295-x DOI: https://doi.org/10.1007/s10462-011-9295-x
Mobarak, M.H.; Mimona, M.A.; Islam, M.A.; Hossain, N.; Zohura, F.T.; Imtiaz, I.; Rimon, M. I. H. 2023. Scope of machine learning in materials research-A review. Applied Surface Science Advances 18: e100523. https://doi.org/10.1016/j.apsadv.2023.100523 DOI: https://doi.org/10.1016/j.apsadv.2023.100523
Moisan, R. 2007. Modelo de determinación de rendimiento para el proceso de elaboración de paneles en planta Nueva Aldea. http://repobib.ubiobio.cl/jspui/handle/123456789/2353
Nakamura, K. 2023. A practical approach for discriminating tectonic settings of basaltic rocks using machine learning. Applied Computing and Geosciences 19: e100132. https://doi.org/10.1016/j.acags.2023.100132 DOI: https://doi.org/10.1016/j.acags.2023.100132
Navarrete, C. 2020. Evaluación de método predictivo para variables de secado de chapas en planta de paneles Arauco Nueva Aldea. Habilitación Profesional de Ingeniería Civil Química. Universidad del Bío-Bío. Departamento Ingeniería en Madera. Concepción, Chile.
Özsahin, Ş.; Demir, A.; Aydin, İ. 2019. Optimization of Veneer Drying Temperature for the Best Mechanical Properties of Plywood via Artificial Neural Network. Journal of Anatolian Environmental and Animal Sciences 4(4): 589-597. https://doi.org/10.35229/jaes.635302 DOI: https://doi.org/10.35229/jaes.635302
Parvin, H.; Alinejad-Rokny, H.; Minaei-Bidgoli, B.; Parvin, S. 2013. A new classifier ensemble methodology based on subspace learning. Journal of Experimental and Theoretical Artificial Intelligence 25(2): 227-250. https://doi.org/10.1080/0952813X.2012.715683 DOI: https://doi.org/10.1080/0952813X.2012.715683
Parvin, H.; Mirnabibaboli, M.; Alinejad-Rokny, H. 2015. Proposing a classifier ensemble framework based on classifier selection and decision tree. Engineering Applications of Artificial Intelligence 37: 34-42. https://doi.org/10.1016/j.engappai.2014.08.005 DOI: https://doi.org/10.1016/j.engappai.2014.08.005
Penkova, T.G. 2017. Principal component analysis and cluster analysis for evaluating the natural and anthropogenic territory safety. Procedia Computer Science 112: 99-108. https://doi.org/10.1016/j.procs.2017.08.179 DOI: https://doi.org/10.1016/j.procs.2017.08.179
Pillay, T.; Cawthra, H.C.; Lombard, A.T. 2021. Integration of machine learning using hydroacoustic techniques and sediment sampling to refine substrate description in the Western Cape, South Africa. Marine Geology 440: e106599. https://doi.org/10.1016/j.margeo.2021.106599 DOI: https://doi.org/10.1016/j.margeo.2021.106599
Ramos-Maldonado, M.; Aguilera-Carrasco, C. 2021. Trends and Opportunities of Industry 4.0 in Wood Manufacturing Processes. In Engineered Wood Products for Construction. Intech Open. https://doi.org/10.5772/intechopen.99581 DOI: https://doi.org/10.5772/intechopen.99581
Rice, R. 1988. Mass transfer, creep and stress development during the drying of red oak. https://vtechworks.lib.vt.edu/bitstreams/68c1415d-0bf7-4743-a6af-ffed0ed4ea9b/download
Rokach, L. 2010. Ensemble-based classifiers. Artificial Intelligence Review 33(1-2): 1-39. https://doi.org/10.1007/s10462-009-9124-7 DOI: https://doi.org/10.1007/s10462-009-9124-7
Russell, S.J.; Norvig, P. 2021. Artificial intelligence: a modern approach. Pearson Educational Inc.. Fourth Edition. https://thuvienso.hoasen.edu.vn/bitstream/handle/123456789/8967/Contents.pdf?sequence=3
Sadrara, M.; Khorrami, M. K. 2023. Principal component analysis–multivariate adaptive regression splines (PCA-MARS) and back propagation-artificial neural network (BP-ANN) methods for predicting the efficiency of oxidative desulfurization systems using ATR-FTIR spectroscopy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 300: e 122944. https://doi.org/10.1016/j.saa.2023.122944 DOI: https://doi.org/10.1016/j.saa.2023.122944
Shalev-Shwartz, S.; Ben-David, S. 2014. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press. http://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning DOI: https://doi.org/10.1017/CBO9781107298019
Tabassum-Abbasi.; Abbasi, T.; Patnaik, P.; Ali, B.M.J.; Abbasi, S.A. 2023. Artificial intelligence-based optimization of a novel process for generating volatile fatty acid energy precursors from date palm waste. Biomass Conversion and Biorefinery https://doi.org/10.1007/s13399-023-04812-7 DOI: https://doi.org/10.1007/s13399-023-04812-7
Teihuel, J. 2007. Propuesta de alternativas de solución para el transporte de residuos de madera sólida en la industria de tableros contrachapados. Tesis, Universidad Austral de Chile, Facultad de Ciencias Forestales, Valdivia, Chile http://cybertesis.uach.cl/tesis/uach/2007/fift263p/doc/fift263p.pdf
Tharwat, A. 2016. Principal Component Analysis (PCA): An Overview. International Journal of Applied Pattern Recognition 3: 197-240. https://doi.org/10.1504/IJAPR.2016.079733 DOI: https://doi.org/10.1504/IJAPR.2016.10000630
Troncoso-Espinosa, F.H.; Avello-Betancur, Y.G.; Martinez-Flores, L.A. 2021. Prediction of cellulose sheet cutting using Machine Learning. Universidad Ciencia y Tecnología 25(110): 109-118. https://doi.org/10.47460/uct.v25i110.481 DOI: https://doi.org/10.47460/uct.v25i110.481
Turhan, K.; Serdar, B. 2013. Support vector machines in wood identification: The case of three Salix species from Turkey. Turkish Journal of Agriculture and Forestry 37(2): 249-256. https://doi.org/10.3906/tar-1205-47 DOI: https://doi.org/10.3906/tar-1205-47
Uniyal, S.; Purohit, S.; Chaurasia, K.; Rao, S.S.; Amminedu, E. 2022. Quantification of carbon sequestration by urban forest using Landsat 8 OLI and machine learning algorithms in Jodhpur, India. Urban Forestry and Urban Greening 67: e127445. https://doi.org/10.1016/j.ufug.2021.127445 DOI: https://doi.org/10.1016/j.ufug.2021.127445
Urra-González, C.; Ramos-Maldonado, M. 2023. A machine learning approach for plywood quality prediction. Maderas. Ciencia y Tecnología 25: e36. https://doi.org/10.4067/S0718-221X2023000100436 DOI: https://doi.org/10.4067/S0718-221X2023000100436
Venegas-Vásconez, D.; Arteaga-Pérez, L.E.; Aguayo, M.G.; Romero-Carrillo, R.; Guerrero, V.H.; Tipanluisa-Sarchi, L.; Alejandro-Martín, S. 2023. Analytical Pyrolysis of Pinus radiata and Eucalyptus globulus: Effects of Microwave Pretreatment on Pyrolytic Vapours Composition. Polymers 15(18): e3790. https://doi.org/10.3390/polym15183790 DOI: https://doi.org/10.3390/polym15183790
Wang, H.; Xu, P.; Zhao, J. 2022. Improved KNN algorithms of spherical regions based on clustering and region division. Alexandria Engineering Journal 61(5): 3571-3585. https://doi.org/10.1016/j.aej.2021.09.004 DOI: https://doi.org/10.1016/j.aej.2021.09.004
Wu, S.J.; Gebraeel, N.; Lawley, M.A.; Yih, Y. 2007. A neural network integrated decision support system for condition-based optimal predictive maintenance policy. IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans 37(2): 226-236. https://doi.org/10.1109/TSMCA.2006.886368 DOI: https://doi.org/10.1109/TSMCA.2006.886368
Zhao, S.; Chen, C.; Luo, Y. 2020. Probabilistic Principal Component Analysis Assisted New Optimal Scale Morphological Top-Hat Filter for the Fault Diagnosis of Rolling Bearing. IEEE Access 8: 156774-156791. https://doi.org/10.1109/ACCESS.2020.3019638 DOI: https://doi.org/10.1109/ACCESS.2020.3019638
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Los autores/as conservarán sus derechos de autor y garantizarán a la revista el derecho de primera publicación de su obra, el cuál estará simultáneamente sujeto a la Licencia de Reconocimiento de Creative Commons CC-BY que permite a terceros compartir la obra siempre que se indique su autor y su primera publicación esta revista.
