Soft Computing Techniques in Civil Engineering: Time Series Prediction

Soft Computing Techniques in Civil Engineering: Time Series Prediction

Juan L. Pérez, Juan R. Rabuñal, Fernando Martínez Abella
DOI: 10.4018/978-1-61520-893-7.ch010
(Individual Chapters)
No Current Special Offers


Soft computing techniques are applied to a huge quantity of problems spread in several areas of science. In this case, Evolutionary Computation (EC) techniques are applied, in concrete Genetic Programming (GP), to a temporary problem associated to the field of Civil Engineering. The case of study of this technique has been centered in the prediction, over time, of the behavior of the structural concrete in controlled conditions. Given the temporary nature of the case of study, it has been necessary to make several changes to the classical algorithm of GP, among whom it can be emphasized the incorporation of a new operator that gives the GP the ability to be able to solve problems with temporary behavior. The obtained results shown that the proposed method has succeeded in improving the adjustment to the current regulations about creep in the structural concrete.
Chapter Preview

Development System

Within Soft computing there are several strategies when it comes to deal with the solution of a certain problem. Soft computing is a group of techniques and methodologies that can work together to obtain in any case a flexible ability and adapted to situations of the real world (Zadeh, 1994). Its main advantage is the ability to make the most of the lack of precision, the uncertainty and the approximate reasoning to achieve strength and solutions without and excessive knowledge of the problem. The principle in which it is based is the one of designing the methods of calculus that lead to an acceptable solution through the search of an approximate solution to a given problem (Pal & Mitra, 1999).

A field where Soft Computing techniques can be applied is to the tasks of prediction, according to the type of prediction (generally classification or regression), several techniques exist to solve these tasks.

The fundamental objective that is pursued is the carrying out of prediction of the value that a certain data coming from the experimentation, that is, making symbolic regression about data. Regression uses the existing values to predict what other values are going to happen.

Complete Chapter List

Search this Book: