Authors:
Muhammad Kamran

Addresses:
Department of Computer Science and Technology, Blantyre, Scotland, United Kingdom.

Abstract:

Structural Health Monitoring (SHM) plays an important role in ensuring that bridges remain reliable and safe throughout their service life. Traditional inspection practices provide useful information, but they may not detect early deterioration, which can later lead to costly repairs or safety issues. This study proposes an AI-enabled SHM framework that uses IoT-based sensor measurements and machine learning to identify signs of structural degradation. The system integrates historical vibration, strain, and temperature data from the Vänersborg Bridge with project-level information from the BIM-AI dataset, including cost performance, schedule status, safety indicators, and monitoring records. Two datasets were therefore used: One representing actual sensor readings from a movable bridge, and the other capturing project-specific attributes that relate to operational and safety risks. In this framework, aberrant circumstances are classified, and the likelihood of problems such as structural flaws, cost deviations, or timetable delays is estimated using machine learning techniques. The proposed approach supports proactive and data-driven bridge management. By combining IoT technologies with AI-based analysis, SHM systems can provide more timely and reliable damage detection, support better maintenance planning, and enhance overall infrastructure safety.

Keywords: Structural Health Monitoring; Traditional Inspection; Service Life; Vänersborg Bridge; Policy Validation; Project-Level Information; BIM-AI Dataset; Machine-Learning Techniques.

Received on: 09/06/2025, Revised on: 14/08/2025, Accepted on: 15/10/2025, Published on: 07/03/2026

DOI: 10.69888/FTSIS.2026.000667

FMDB Transactions on Sustainable Intelligence and Security, 2026 Vol. 1 No. 1, Pages: 53–81

• Views : 63
• Downloads : 12

Download PDF