Over the years, many methods have been developed to predict settlement of shallow foundations on cohesionless soils. However, methods that have the desired degree of accuracy and consistency have not yet been developed. In this book, one of the most common artificial intelligence techniques, i.e. artificial neural networks (ANNs), is investigated for settlement prediction. A number of issues in relation to ANN construction, optimisation and validation are investigated, and guidelines for improving ANN performance are developed. Settlement analysis is often affected by considerable levels of uncertainties that are usually ignored by traditional methods. In this book, probabilistic solutions based on deterministic ANN settlement predictions are developed so that the uncertainties associated with the settlement analysis are considered. A set of probabilistic design charts that provide the designer with the level of risk associated with predicted settlements are produced and presented. This book is intended for civil engineering postgraduates, civil engineers working in modelling and geotechnical engineers working in design of foundations.
Senior Lecturer of Geotechnical Engineering at Curtin University of Technology, Perth City, Australia. He gained his BSc and MSc from Cairo University, Egypt, and his PhD from The University of Adelaide, Australia. He is a member of Institution of Engineers, Australia, and American Society of Civil Engineers.
Über den Autor
Senior Lecturer of Geotechnical Engineering at Curtin University of Technology, Perth City, Australia. He gained his BSc and MSc from Cairo University, Egypt, and his PhD from The University of Adelaide, Australia. He is a member of Institution of Engineers, Australia, and American Society of Civil Engineers.
Klappentext
Over the years, many methods have been developed to predict settlement of shallow foundations on cohesionless soils. However, methods that have the desired degree of accuracy and consistency have not yet been developed. In this book, one of the most common artificial intelligence techniques, i.e. artificial neural networks (ANNs), is investigated for settlement prediction. A number of issues in relation to ANN construction, optimisation and validation are investigated, and guidelines for improving ANN performance are developed. Settlement analysis is often affected by considerable levels of uncertainties that are usually ignored by traditional methods. In this book, probabilistic solutions based on deterministic ANN settlement predictions are developed so that the uncertainties associated with the settlement analysis are considered. A set of probabilistic design charts that provide the designer with the level of risk associated with predicted settlements are produced and presented. This book is intended for civil engineering postgraduates, civil engineers working in modelling and geotechnical engineers working in design of foundations.
