A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Seismic Response Prediction of RC Buildings Using Artificial Neural Network
The study presented in this work deals with the seismic response of reinforced concrete (RC) structures subjected to earthquake motion using an Artificial Neural Network (ANN). The strong ground motion may lead to catastrophic failure of buildings or their components. Therefore, it is necessary to analyze the structure with seismic loads and to predict the damaged state of buildings. Here, an RC structure with different heights is subjected to a wide range of earthquake motions, and time history analysis is carried out to obtain the structure's seismic response, which is further used as the dataset in training ANN. Then ANN is constructed using MATLAB software from the dataset collected. The architecture of ANN is composed of three layers—the input layer, hidden layer, and output layer. The input layer consists of structural parameters such as structural configuration, the height of the structure, etc., and seismic parameters such as duration, Peak Ground Acceleration (PGA), Peak Ground Velocity (PGV), epicentral distance, etc. The maximum story drift ratio and maximum displacement are the output layers of ANN. The optimum input parameters which give the least error and maximum accuracy were identified to predict the dynamic response of the RC multistoried buildings.
Seismic Response Prediction of RC Buildings Using Artificial Neural Network
The study presented in this work deals with the seismic response of reinforced concrete (RC) structures subjected to earthquake motion using an Artificial Neural Network (ANN). The strong ground motion may lead to catastrophic failure of buildings or their components. Therefore, it is necessary to analyze the structure with seismic loads and to predict the damaged state of buildings. Here, an RC structure with different heights is subjected to a wide range of earthquake motions, and time history analysis is carried out to obtain the structure's seismic response, which is further used as the dataset in training ANN. Then ANN is constructed using MATLAB software from the dataset collected. The architecture of ANN is composed of three layers—the input layer, hidden layer, and output layer. The input layer consists of structural parameters such as structural configuration, the height of the structure, etc., and seismic parameters such as duration, Peak Ground Acceleration (PGA), Peak Ground Velocity (PGV), epicentral distance, etc. The maximum story drift ratio and maximum displacement are the output layers of ANN. The optimum input parameters which give the least error and maximum accuracy were identified to predict the dynamic response of the RC multistoried buildings.
Seismic Response Prediction of RC Buildings Using Artificial Neural Network
Lecture Notes in Civil Engineering
Marano, Giuseppe Carlo (editor) / Rahul, A. V. (editor) / Antony, Jiji (editor) / Unni Kartha, G. (editor) / Kavitha, P. E. (editor) / Preethi, M. (editor) / Menon, U. Abhijit (author) / Nair, Deepthy S. (author)
International Conference on Structural Engineering and Construction Management ; 2022 ; Angamaly, India
2022-10-30
11 pages
Article/Chapter (Book)
Electronic Resource
English
Artificial Neural Network Application for Predicting Seismic Damage Index of Buildings in Malaysia
| DOAJ | 2012
Seismic Response Modeling of Multi-Story Buildings Using Neural Networks
| British Library Online Contents | 1994
Artificial Neural Network-Based Prediction of Wind Pressure Coefficients on Buildings
| Springer Verlag | 2021
Seismic Damage Prediction of Multistory Brick Buildings Based on RBF Neural Network Model
| Trans Tech Publications | 2010