Prediction of mechanical strength of cork under compression using machine learning techniques |
| |
| Affiliation: | 1. Department of Natural Resources and Environmental Eng., University of Vigo, 36310 Vigo, Spain;2. Instituto Politécnico de Castelo Branco, Escola Superior Agrária, Apartado 119, 6001-909 Castelo Branco, Portugal;3. Centro de Estudos Florestais, Instituto Superior de Agronomia, Universidade de Lisboa, Tapada da Ajuda, 1349-017 Lisboa, Portugal;4. Centro Universitario de la Defensa, Academia General Militar, 50090 Zaragoza, Spain;1. Instituto de Tecnología de los Materiales (ITM), Universidad Politècnica de València (UPV), Camino de Vera S/N, 46022 Valencia, Spain;2. Departamentd’Enginyeria Química, Escola Tècnica Superior d’Enginyeria, Universitat de València, Av. de la Universitat, s/n, 46100, Burjassot, Spain;3. School of Chemical Science and Engineering, Fibre and Polymer Technology, KTH – Royal Institute of Technology, Teknikrigen 56-58, SE-10044, Stockholm, Sweden;4. Department of Materials Science and Technology, Faculty of Science, Prince of Songkla University, Songkhla, 90112, Thailand;1. bime – Bremen Institute for Mechanical Engineering, University of Bremen, Am Biologischen Garten 2, 28359 Bremen, Germany;2. University of Applied Sciences Bremen, Faculty 5, Neustadtswall 30, 28199 Bremen, Germany;1. Universidade de Lisboa, Instituto Superior de Agronomia, Centro de Estudos Florestais (CEF), Tapada da Ajuda, P-1349-017 Lisboa, Portugal;2. Amorim & Irmãos, R&D Department, Rua de Meladas 380, P.O. Box 20, Mozelos 4536-902, Portugal |
| |
| 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. |
| |
| Keywords: | Cork Mechanical properties Neural network Multiple linear regression CART Cluster |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
