Intelligent use of data to optimize compressive strength of cellulose-derived composites |
| |
| Affiliation: | 1. Materials Processing Simulation Laboratory (MPS-LAB), School of Materials Science and Engineering, Iran University of Science and Technology (IUST), Narmak, Tehran, Iran;2. Reservoir Engineering Systems, Petroleum Engineering Dept., Main Office Building of National Iranian South Oil Company (NISOC), Ahvaz, Iran;1. Department of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, No. 111 Ren’ai Road, Suzhou Industrial Park Suzhou, Jiangsu Province, P.R. China;2. School of Electronic and Information Engineering, Suzhou University of Science and Technology, No. 1 Ke Rui Road, Suzhou High-Tech Zone, Suzhou, Jiangsu Province, P.R. China;3. School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, West Hi-Tech Zone, 611731 Chengdu, Sichuan, P.R. China;1. School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China;2. School of Electronic Information, Wuhan University, Wuhan 430072, China;1. College of Information Technology, Jiangxi University of Finance and Economics, Nanchang 330013, China;2. School of Statistics, Jiangxi University of Finance and Economics, Nanchang 330013, China;3. Research Center of Applied Statistics, Jiangxi University of Finance and Economics, Nanchang 330013, China;1. School of Software Engineering, Chongqing University, Chongqing 400044, PR China;2. School of Computing, National University of Singapore, Singapore 117417, Singapore;3. School of Information Science and Engineering, Lanzhou University, Gansu 730000, PR China;4. Faculty of Computer and Information Science, Southwest University, Chongqing 400715, PR China;5. Faculty of Engineering, The University of Sydney, Sydney 2006, Australia;1. Federal University of Technology (UTFPR), Elect. Eng. Dept., Av. Alberto Carazzai, 1640, 86300-000 Cornélio Procópio, PR, Brazil;2. Federal University of São Carlos (UFSCAR), Rodovia Washington Luís, km 235 – SP 310, 13565-905 São Carlos, SP, Brazil;1. School of Computer and Software Engineering, Xihua University, Chengdu 610039, China;2. School of Digital Media, Jiangnan University, Wuxi 214122, China |
| |
| Abstract: | Two soft-computing techniques are implemented to model and optimize the compressive strength of carbon/polymer composites. Artificial neural network is used to establish a relationship between the uniaxial compressive strength of fabricated materials and the most significant processing parameters. To put together a database, three different types of wood are carbonized at various heat treatment temperatures, in specific pyrolysis time periods. Compression tests are then conducted at room temperature on the composites, at a constant strain rate. The collected data of compressive strength and the related fabrication parameters are used as sets of data for training a neural network. A nested cross validation scheme is used to ensure the efficiency of the network. Results are indicative of a very good network, which generalizes very well. Next, an attempt is made to optimize the compressive behavior of the composites by controlling carbonization temperature, time and also starting material type with the aid of a genetic algorithm coupled with the trained network. The optimization system yields promising results, significantly enhancing the compressive strength. The validity of the optimal experiment, as proposed by the soft-computing system, is verified by subsequent laboratory testing. |
| |
| Keywords: | Carbon/polymer composites Compressive strength Hybrid soft computing Neural network Genetic algorithm |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
