Finite element model updating using computationalintelligence techniques: applications to structural dynamics

FEM updating allows FEMs to be tuned better to reflect measured data. It can be conducted using two different statistical frameworks: the maximum likelihood approach and Bayesian approaches. This book applies both strategies to the field of structural mechanics, using vibration data. Computational intelligencetechniques including: multi-layer perceptron neural networks; particle swarm and GA-based optimization methods; simulated annealing; response surface methods; and expectation maximization algorithms, are proposed to facilitate the updating process. Based on these methods, the most appropriate updated FEM is selected, a problem that traditional FEM updating has not addressed. This is found to incorporate engineering judgment into finite elements through the formulations of prior distributions. Case studies, demonstrating the principles testthe viability of the approaches, and. by critically analysing the state of the art in FEM updating, this book identifies new research directions." Shows the reader advanced methods for tuning finite element simulations to measured data Dual use of expectation maximization and response surface methods compensates for computational complexity Robust optimisation techniques reconcile localwith global models INDICE: Introduction to Finite Element Model Updating.- Finite Element Model Updating Using Neural Networks.- Maximum Likelihood Approach to Finite Element Model Updating.- Finite Element Model Updating Using Evolutionary Optimization Techniques: Genetic Algorithms and Particle Swarm Optimization.- Finite Element Model Updating Using Simulated Annealing.- Finite Element Model Updating Using Response Surface Method.- Bayesian Approach to Finite Element Model Updating.- Model Selection in Finite Element Model Updating.- Expectation Maximization Algorithm for Finite Element Model Updating.- Damage Detection Using Finite Element Model Updating.

• ISBN: 978-1-84996-322-0
• Editorial: Springer
• Encuadernacion: Cartoné
• Páginas: 247
• Fecha Publicación: 10/06/2010
• Nº Volúmenes: 1
• Idioma: Inglés