Artificial Intelligence–Driven Predictive Systems for Civil Engineering: Advancing Smart Infrastructure and Structural Health Insights
TL;DR
These studies propose an artificial intelligence driven predictive monitoring framework of vibration based structural health assessment under real conditions including where the labelled damage data is unavailable to validate that the proposed framework allows for interpretable, scalable and data-driven predictive monitoring.
Abstract
Structural health information from continuous monitoring of vibration makes an important contribution to the development of a proactive approach to the management of civil infrastructure. These studies propose an artificial intelligence driven predictive monitoring framework of vibration based structural health assessment under real conditions including where the labelled damage data is unavailable. Structural behavior is evaluated according to baseline referenced deviation based on physics informed vibration features. A Structural Deviation Index is introduced to quantify deviation where median values range from the baseline measurements 0.42-0.45 to 3.68-3.92 in later monitoring tests representing progressive structural change. One-Class Support Vector Machine deviation scores reveal a corresponding deviation from close to zero to -0.76 which indicates that the classifier is highly sensitive to deviation in early stages. Band-limited spectral energy and dominant frequency are the most influential indicators with the value of permutation importance up to 0.231 and correlation coefficients up to 0.78, according to explainability analysis. The results validate that the proposed framework allows for interpretable, scalable and data-driven predictive monitoring. The study is an illustration of the possibilities of artificial intelligence to facilitate early warning, decision-making and smart infrastructure management with continuous structural health assessment.