Vinay Agrawal

Applications of Soft Computing in Civil Engineering: A Review

field of engineering is a creative one. The problems encountered in this field are generally unstructured and imprecise influenced by intuitions and past experiences of a designer. The conventional methods of computing relying on analytical or empirical relations become time consuming and labor intensive when posed with real life problems. To study, model and analyze such problems, approximate computer based Soft Computing techniques inspired by the reasoning, intuition, consciousness and wisdom possessed by a human beings are employed. In contrast to conventional computing techniques which rely on exact solutions, soft computing aims at exploiting given tolerance of imprecision, the trivial and uncertain nature of the problem to yield an approximate solution to a problem in quick time. Soft Computing being a multi-disciplinary field uses a variety of statistical, probabilistic and optimization tools which complement each other to produce its three main branches viz., Neural Networks, Genetic Algorithms and Fuzzy Logic. The review paper presents the applications of two major Soft Computing techniques viz., Artificial Neural Networks and Genetic Algorithms in the field of Civil Engineering, which to some extent has replaced the time consuming conventional techniques of computing with intelligent and time saving computing tools.

Modeling slump of ready mix concrete using genetically evolved artificial neural networks

Artificial neural networks (ANNs) have been the preferred choice for modeling the complex and nonlinear material behavior where conventional mathematical approaches do not yield the desired accuracy and predictability. Despite their popularity as a universal function approximator and wide range of applications, no specific rules for deciding the architecture of neural networks catering to a specific modeling task have been formulated.The research paper presents a methodology for automated design of neural network architecture, replacing the conventional trial and error technique of finding the optimal neural network. The genetic algorithms (GA) stochastic search has been harnessed for evolving the optimum number of hidden layer neurons, transfer function, learning rate, and momentum coefficient for backpropagation ANN. The methodology has been applied for modeling slump of ready mix concrete based on its design mix constituents, namely, cement, fly ash, sand, coarse aggregates, admixture, and water-binder ratio. Six different statistical performance measures have been used for evaluating the performance of the trained neural networks. The study showed that, in comparison to conventional trial and error technique of deciding the neural network architecture and training parameters, the neural network architecture evolved through GA was of reduced complexity and provided better prediction performance.