Application of Genetic Algorithms Coupled with Neural Networks to Optimization of Reinforced Concrete Footings
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2016, Vol 4, Issue 4
Abstract
This paper first applies genetic algorithms to optimally design reinforced concrete isolated footings subjected to concentric loading. Based on the ACI Building Code, constraints are built by considering wide-beam and punching shears, bending moment, allowable soil pressure, the development length for deformed bars and clear distance between deformed bars. Design variables consist of the width, length and thickness of the footing and the number of bars in the long and short directions, all of which are discrete. The objective function is to minimize the cost of steel and concrete in the footing. There are totally 144 cases of reinforced concrete isolated footings considered. The optimal results are randomly divided into three groups for the use of neural networks: training data, validation data and testing data. Two kinds of artificial neural networks are employed in this paper: two-layer feedforward backpropagation networks and radial basis networks. Linear regression analysis between the network outputs and targets of the testing data is performed to judge the accuracy of the neural networks. Numerical results show that the feedforward backpropagation network is very effective and has high accuracy with the correlation coefficients and the slope of the regression line being close to one and the y-intercept close to zero. Besides, it is better than the radial basis networks and needs much fewer neurons in the hidden layer.
Authors and Affiliations
Jiin-Po Yeh, Shu-Yu Yeh
Keywords
Related Articles
- EP ID EP277212
- DOI 10.14738/tmlai.44.2150
- Views 78
- Downloads 0
Stock Recommendations using Bio-Inspired Computations on Social Media
The tremendous growth of the social networks has paved way for social interactions of investing communities about a company�s stock performance. Investors are able to share their comments on stocks using social media pla...
A Dynamic Clustering Approach for Maximizing Scalability in Wireless Sensor Networks
Scalability is an important and crucial issue which in routing protocols for Wireless Sensor Networks (WSNs). In this paper, we present an approach to achieving a balanced energy consumption rate using dynamic clustering...
Support Vector Machine Regression and Artificial Neural Network for Channel Estimation of LTE Downlink in High-Mobility Environments
In this paper we apply and assess the performance of support vector machine regression (SVR) and artificial neural network (ANN) channel estimation algorithms to the reference signal structure standardized for LTE Downli...
Body Temperature Patterns in Captive Barbary Striped Grass Mousse (Lemniscomysbarbarus): Influence of Photoperiod and Sex Steroids
The Barbary striped grass mouse (Lemniscomys Barbarus) has been described as a diurnal and photoperiodic rodent, but no reliable data exist on the daily and seasonal rhythmicity of body temperature (Tb). In this study, T...
Collective Behavior Bees for Solving HW/SW Partitioning and Scheduling Problems in RSoC
In the codesign domain, many hardware and software techniques must be developed to satisfy specific constraints in terms of computation time, area, performance, power consumption, etc. This paper introduces an automatic...