Seeing Structural Failure Before it Happens: An Image-Based Physics-Informed Neural Network (PINN) for Spaghetti Bridge Load Prediction

2025-10-27

AI Summary

This study addresses the spaghetti bridge load-bearing prediction task under data scarcity—only 100 experimental samples—where structural failure risk identification is challenging and physical consistency is weak. We propose a Physics-Informed Kolmogorov–Arnold Network (PIKAN), which embeds mechanical priors (e.g., equilibrium equations and material constitutive relations) into a universal function approximation framework, while integrating geometric features extracted via computer vision for end-to-end modeling. Compared to standard Physics-Informed Neural Networks (PINNs), PIKAN achieves significantly improved generalization under limited data and enhanced physical interpretability. On the test set, it attains R² = 0.9603 and MAE = 10.50 units. The model has been deployed in an interactive web platform enabling real-time load-capacity prediction from user-input structural parameters. This work establishes a reliable, interpretable, data-driven paradigm for experimental pedagogy and rapid prototyping assessment of lightweight structures.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Structured Learning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Physics Informed Neural Networks (PINNs) are gaining attention for their ability to embed physical laws into deep learning models, which is particularly useful in structural engineering tasks with limited data. This paper aims to explore the use of PINNs to predict the weight of small scale spaghetti bridges, a task relevant to understanding load limits and potential failure modes in simplified structural models. Our proposed framework incorporates physics-based constraints to the prediction model for improved performance. In addition to standard PINNs, we introduce a novel architecture named Physics Informed Kolmogorov Arnold Network (PIKAN), which blends universal function approximation theory with physical insights. The structural parameters provided as input to the model are collected either manually or through computer vision methods. Our dataset includes 15 real bridges, augmented to 100 samples, and our best model achieves an $R^2$ score of 0.9603 and a mean absolute error (MAE) of 10.50 units. From applied perspective, we also provide a web based interface for parameter entry and prediction. These results show that PINNs can offer reliable estimates of structural weight, even with limited data, and may help inform early stage failure analysis in lightweight bridge designs. The complete data and code are available at https://github.com/OmerJauhar/PINNS-For-Spaghetti-Bridges.

Problem

• Predict spaghetti bridge load limits using physics-informed neural networks
• Estimate structural failure modes with limited experimental data
• Combine computer vision and physical laws for weight prediction

Innovation

• Physics-informed neural network predicts spaghetti bridge failure
• Novel PIKAN architecture blends physics with function approximation
• Computer vision and manual inputs enhance structural parameter collection