About The Project
Final Year Project at FAST-NUCES
Project Overview
This project focuses on predicting the failure load capacity of spaghetti bridges using Physics-Informed Neural Networks (PINN). By combining traditional physics-based modeling with modern machine learning techniques, we've developed a system that can accurately predict how much load a spaghetti bridge can support before failure based on its design parameters.
The application allows users to either upload an image of a spaghetti bridge design or input specific parameters to receive failure load predictions. This tool can be valuable for educational purposes, engineering competitions, and structural design studies.
The project demonstrates the power of combining domain knowledge from physics with the flexibility and learning capabilities of neural networks, resulting in more accurate and physically consistent predictions.
Institution
National University of Computer & Emerging Sciences
FAST Peshawar Campus
Combining physical laws with neural networks to create more accurate and physically consistent predictions.
Using advanced image processing techniques to extract structural features from spaghetti bridge images.
The findings from this research can be applied to real-world structural analysis, potentially improving safety and efficiency in construction.