Optimal Design for Mechanical Properties of Composite with Combination of Genetic Algorithm and Artificial Neural Network

Fan Wei Zhang; Song Bang Zhou; Yue Zhang; Da Hai Zhang; Zhong Ping Li

doi:10.4028/www.scientific.net/KEM.368-372.1645

Paper Titles

Microstructure and Thermal Shock Resistance of LaPO₄-ZrO₂
p.1633

Preparation and Characterization of Coated ZnO Nanoparticles
p.1636

Effect of Heat Treatment on Specific Surface Area of Si-C-O Fibers
p.1639

Prediction of the Properties of an Alumina Green Body Using an Artificial Neural Network by a New PSO-Gain Backpropagation Algorithm
p.1642

Optimal Design for Mechanical Properties of Composite with Combination of Genetic Algorithm and Artificial Neural Network
p.1645

Strength Model of Melt-Growth Composite Ceramics
p.1648

Enhanced Mechanism of Fracture Toughness in Cannon Bone
p.1651

Damage Model and Failure Stress of Ceramic Particle Ni Base Alloy Composite
p.1654

Damage Finite Element Analysis of Nano- Composite Ceramics
p.1657

HomeKey Engineering MaterialsKey Engineering Materials Vols. 368-372Optimal Design for Mechanical Properties of...

Optimal Design for Mechanical Properties of Composite with Combination of Genetic Algorithm and Artificial Neural Network

Abstract:

Improved genetic algorithm, combined with artificial neural network, is present for the optimal design of 2.5D braided composite. Dispersal simulation data, including maximal stresses and elastics properties, are adopted by artificial neural network for the calculation of strength property. Based on calculation method of strength mentioned above and other calculation models for other mechanical properties, genetic algorithm is employed for the design of structure parameters of 2.5D braided composite, such as wrap fiber density, fill fiber density and interface strength. These structure optimal parameters are finally optimized for practical application.