Prediction of mechanical strength of cork under compression using machine learning techniques

Abstract In this study, the accuracy of mathematical techniques such as multiple linear regression, clustering, decision trees (CART) and neural networks was evaluated to predict Young’s modulus, compressive stress at 30% strain and instantaneous recovery velocity of cork. Physical properties, namely test direction, density, porosity and pore number, as well as test direction were used as input. The better model was achieved when a classification problem was performed. Only compressive stress at 30% strain can be predicted with neural networks with an error rate of about 20%. The prediction of Young’s modulus and instantaneous recovery velocity led to unacceptably high error rates due to the heterogeneity of the material.

[1]  Şükrü Özşahin,et al.  Comparison of artificial neural network and multiple linear regression models to predict optimum bonding strength of heat treated woods , 2014 .

[2]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[3]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[4]  Pasi Fränti,et al.  K-means⁎: Clustering by gradual data transformation , 2014, Pattern Recognit..

[5]  Helena Pereira,et al.  Effect of quality, porosity and density on the compression properties of cork , 2008, Holz als Roh- und Werkstoff.

[6]  Helena Pereira,et al.  Prediction of tension properties of cork from its physical properties using neural networks , 2015, European Journal of Wood and Wood Products.

[7]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[8]  Hany El Kadi,et al.  Modeling the mechanical behavior of fiber-reinforced polymeric composite materials using artificial neural networks—A review , 2006 .

[9]  Mehdi Ahmadi,et al.  Unsupervised acoustic emission data clustering for the analysis of damage mechanisms in glass/polyester composites , 2012, Materials & Design.

[10]  P. J. García Nieto,et al.  Support vector machines and neural networks used to evaluate paper manufactured using Eucalyptus globulus , 2012 .

[11]  N. Altinkok,et al.  Neural network approach to prediction of bending strength and hardening behaviour of particulate reinforced (Al-Si-Mg)-aluminium matrix composites , 2004 .

[12]  M. A. Fortes,et al.  Rate effects on the compression and recovery of dimensions of cork , 1988 .

[13]  Mohammad Firuz Ramli,et al.  Artificial neural network modeling of the water quality index for Kinta River (Malaysia) using water quality variables as predictors. , 2012, Marine pollution bulletin.

[14]  M. Ashby,et al.  Cellular solids: Structure & properties , 1988 .

[15]  Fábio A. O. Fernandes,et al.  Modelling impact response of agglomerated cork , 2014 .

[16]  Helena Pereira,et al.  Tensile properties of cork in the tangential direction: Variation with quality, porosity, density and radial position in the cork plank , 2010 .

[17]  Michael H. Kutner.  Applied Linear Statistical Models , 1974 .

[18]  Ahmet Tortum,et al.  Neural networks analysis of compressive strength of lightweight concrete after high temperatures , 2013 .

[19]  M. J. Jiménez-Come,et al.  An automatic pitting corrosion detection approach for 316L stainless steel , 2014 .

[20]  Francisco García Fernández,et al.  MOE prediction in Abies pinsapo Boiss. timber: Application of an artificial neural network using non-destructive testing , 2009 .

[21]  J. García-Olmo,et al.  Discriminant Analysis of Geographical Origin of Cork Planks and Stoppers by Near Infrared Spectroscopy , 2012 .

[22]  M. Ashby,et al.  The structure and mechanics of cork , 1981, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[23]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[24]  Pascal Reynaud,et al.  Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si–B–C] composites exhibiting different tensile behaviours. Part II: Unsupervised acoustic emission data clustering , 2008 .

[25]  Jianhong Wu,et al.  Data clustering - theory, algorithms, and applications , 2007 .

[26]  Jana Hajslova,et al.  Traceability of honey origin based on volatiles pattern processing by artificial neural networks. , 2009, Journal of chromatography. A.

[27]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[28]  João F. Mano,et al.  The viscoelastic properties of cork , 2002 .

[29]  M. L. Andrade,et al.  Classification and regression trees (CARTs) for modelling the sorption and retention of heavy metals by soil. , 2009, Journal of hazardous materials.

[30]  Raşit Köker,et al.  Neural network based prediction of mechanical properties of particulate reinforced metal matrix composites using various training algorithms , 2007 .

[31]  Helena Pereira,et al.  Effect of density on the compression behaviour of cork , 2014 .

[32]  P. J. García Nieto,et al.  Turbidity Prediction in a River Basin by Using Artificial Neural Networks: A Case Study in Northern Spain , 2013, Water Resources Management.

[33]  George A. F. Seber,et al.  Linear regression analysis , 1977 .

[34]  Fábio A. O. Fernandes,et al.  Static and dynamic mechanical response of different cork agglomerates , 2015 .

[35]  Raşit Köker,et al.  Modelling of the prediction of tensile and density properties in particle reinforced metal matrix composites by using neural networks , 2006 .

[36]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[37]  Helena Pereira,et al.  Tensile properties of cork in axial stress and influence of porosity, density, quality and radial position in the plank , 2011, European Journal of Wood and Wood Products.

[38]  Helena Pereira,et al.  Cork : biology, production and uses , 2007 .

[39]  Vanda Oliveira,et al.  Variability of the compression properties of cork , 2014, Wood Science and Technology.