Use of Artificial Neural Network based Prediction of Optimum Case of Multistory Buildings by using Structural Response

This research presents a hybrid civil engineering and computer science approach for the efficient structural analysis of multistory buildings subjected to seismic forces. A total of ten distinct building models labeled NS and BD1 to BD9 were developed using structural analysis software, incorporating Response Spectrum Analysis and varying concrete grades (M25 and M30). A grade change scenario was introduced in slab components at different floor levels, with resulting horizontal displacements extracted as key response parameters. These outputs served as critical input for two Python based Artificial Neural Network (ANN) models: one using a Feed Forward algorithm and the other using Back Propagation, both integrated with Artificial Intelligence (AI) and Machine Learning (ML). Preprocessing tasks such as data normalization, cleaning and missing value treatment were performed using Pandas and NumPy. Model training and validation were conducted using TensorFlow and scikit learn, employing 200 epoches for optimal learning. Performance evaluation using Mean Squared Error (MSE) and R² score revealed exceptional accuracy, from this the ANN model achieving an MSE of 0 and R² of 1. Among the building cases analyzed, the ANN approach successfully identified the most structurally efficient configuration with minimum displacements in both UX and UY directions. This methodology not only enhances computational speed and accuracy compared to conventional practices but also promotes data driven decision making for cost effective and optimized structural design. The research underscores the applicability of ANN embedded with AI &ML techniques in building engineering and opens pathways for broader multidisciplinary implementations.