Composite Materials Technology: Neural Network Applications
Features
- Fills the knowledge gap in the field of neural network applications in composite materials
- Discusses the detection of internal defects in composite structures using neural networks
- Covers the prediction of mechanical behavior of composites using neural networks
- Explores the design and analysis of composite materials
- Presents materials and manufacturing process selection using neural networks, including back propagation type neural networks
Summary
Artificial neural networks (ANN) can provide new insight into the study of composite materials and can normally be combined with other artificial intelligence tools such as expert system, genetic algorithm, and fuzzy logic. Because research on this field is very new, there is only a limited amount of published literature on the subject.
Compiling information from diverse sources, Composite Materials Technology: Neural Network Applications fills the void in knowledge of these important networks, covering composite mechanics, materials characterization, product design, and other important aspects of polymer matrix composites.
Light weight, corrosion resistance, good stiffness and strength properties, and part consolidation are just some of the reasons that composites are useful in areas including civil engineering and structure, chemical processing, management, agriculture, space study, and manufacturing. ANN has already been used to carry out design prediction, mechanical property prediction, and selection processes in the evolution of composites, but although it has already been used with great success in various branches of scientific and technological research, it is still in the nascent stage of its development.
Featuring contributions from leading researchers throughout the world, this book is divided into four parts, starting with an introduction to neural networks and a review of existing literature on the subject. The text then covers structural health monitoring and damage detection in composites, addresses mechanical properties, and discusses design, analysis, and materials selection. Training, testing, and validation of experimental data were carried out to optimize the results presented in the book.
This book will be an important aid to researchers as they work on the future implementation of ANN in industries such as aerospace, automotive, marine, sporting goods, furniture, and electronics and communication.
Table of Contents
Application of Artificial Neural Network in Composites Materials, M. Hasan, M.E. Hoque, and S.M. Sapuan
Neural Network Approaches for Defect Detection in Composite Materials, T. D’Orazio, M. Leo, and C. Guaragnella
The Use of Artificial Neural Networks in Damage Detection and Assessment in Polymeric Composite Structures, S. John, A. Kesavan, and I. Herszberg
Damage Identification and Localization of Carbon Fiber-Reinforced Plastic Composite Plate Using Outlier Analysis and Multilayer Perceptron Neural Network, F. Mustapha, S.M. Sapuan, K. Worden, and G. Manson
Damage Localization of Carbon Fiber–Reinforced Plastic Composite and Perspex Plates Using Novelty Indices and the Cross-Validation Set of Multilayer Perceptron Neural Network, F. Mustapha, S.M. Sapuan, K. Worden, and G. Manson
Impact Damage Detection in a Composite Structure Using Artificial Neural Network, S. Mahzan and W. J. Staszewski
Artificial Neural Networks for Predicting the Mechanical Behavior of Cement-Based Composites after 100 Cycles of Aging, E.M. Bezerra, C.A.R. Brito, Jr., A.C. Ancelotti, Jr., and L.C. Pardini
Fatigue Life Prediction of Fiber-Reinforced Composites UsingArtificial Neural Networks, H. El Kadi and Y. Al-Assaf
Optimizing Neural Network Prediction of Composite Fatigue Life Under Variable Amplitude Loading Using Bayesian Regularization, M.I.P. Hidayat and P.S.M. M. Yusoff
Free Vibration Analysis and Optimal Design of the Adhesively Bonded Composite Single Lap and Tubular Lap Joints, M.K. Apalak
Determining Initial Design Parameters by Using Genetically Optimized Neural Network Systems, I.N. Tansel, M. Demetgul, and R.L. Sierakowski
Development of a Prototype Computational Framework for Selection of Natural Fiber-Reinforced Polymer Composite Materials Using Neural Network, S.M. Sapuan and I.M. Mujtaba
Index
Author Bio(s)
S. M. Sapuan is a professor of composite materials and the head of the Department of Mechanical and Manufacturing Engineering, Universiti Putra Malaysia (UPM). He is the vice president and honorary member of Asian Polymer Association; fellow of Institute of Materials, Malaysia; life fellow, International Biographical Association; life member, Institute of Energy, Malaysia; member, Society of Automotive Engineers International; member, International Association of Engineers; member, Plastics and Rubber Institute, Malaysia; and a professional engineer. He has published more than 200 papers in refereed journals, more than 200 papers in conferences/seminars, and six books in engineering.
I. M. Mujtaba is a professor of computational process engineering in the School of Engineering, Design and Technology at the University of Bradford, UK. He is a fellow of the IChemE, a chartered chemical engineer, and a chartered scientist. Professor Mujtaba is actively involved in many research areas like dynamic modeling, simulation, optimization, and control of batch and continuous chemical processes with specific interests in distillation, industrial reactors, refinery processes, and desalination. He has published more than 110 technical papers in major engineering journals, international conference proceedings, and books.
