Prediction of Peak Ground Acceleration (PGA) using Artificial Neural Networks
نویسندگان
چکیده
In this paper, the probable range of the horizontal component of peak ground acceleration (PGA) is predicted as a function of focal depth, earthquake magnitude and epicentral distance, using artificial neural network (ANN). Three different ANN architectures (namely Feed Forward, Back Propagation and Radial Bias Networks) are used to develop the model. The three models are then compared, to decide which model gives better prediction. The model gives better result for earthquakes having focal depth less than 50km, magnitude greater than 4 and epicentral distance less than 300 km.Traditionally regression analysis and other mathematical models are used for the data analysis of the past earthquake data, to develop equations for PGA. In this study an attempt is made to develop a model with the help of Artificial Neural Networks for predicting the probable range for PGA. Thus an attempt is done to replace the traditional methods by the faster artificial intelligence techniques. Hence the two different fields, Seismology and Earthquake Engineering are gelled with the AI techniques for faster and better computational results. Peak ground acceleration (PGA) is a determining factor that must be considered while designing the earthquake resistant structures. With growing urbanization, there is tremendous increase in the population density in earthquake prone areas, which in turn is increasing the demand for earthquake resistant structures.
منابع مشابه
A Comparison of ANFIS and ANN for the Prediction of Peak Ground Acceleration in Indian Himalayan Region
Peak ground acceleration (PGA) plays an important role in assessing effects of earthquakes on the built environment, persons, and the natural environment. It is a basic parameter of seismic wave motion based on which earthquake resistant building design and construction are made. The level of damage is, among other factors, directly proportional to the severity of the ground acceleration, and i...
متن کاملFEASIBILITY OF PSO-ANFIS-PSO AND GA-ANFIS-GA MODELS IN PREDICTION OF PEAK GROUND ACCELERATION
In the present study, two new hybrid approaches are proposed for predicting peak ground acceleration (PGA) parameter. The proposed approaches are based on the combinations of Adaptive Neuro-Fuzzy System (ANFIS) with Genetic Algorithm (GA), and with Particle Swarm Optimization (PSO). In these approaches, the PSO and GA algorithms are employed to enhance the accuracy of ANFIS model. To develop hy...
متن کاملA neural network approach for attenuation relationships: An application using strong ground motion data from Turkey
This paper presents an application of neural network approach for the prediction of peak ground acceleration (PGA) using the strong motion data from Turkey, as a soft computing technique to remove uncertainties in attenuation equations. A training algorithm based on the Fletcher–Reeves conjugate gradient back-propagation was developed and employed for three sample sets of strong ground motion. ...
متن کاملSeismic Amplification of Peak Ground Acceleration, Velocity, and Displacement by Two-Dimensional Hills
There are valuable investigations on the amplification effects of the topography on the seismic response in the frequency domain; however, a question is that how one can estimate the amplification of time domain peak ground acceleration (PGA), peak ground velocity (PGV), and peak ground displacement (PGD) over the topographic structures. In this study, the numerical approach has been used for t...
متن کامل