Structural damage detection using deep learning and FE model updating techniques

Area of Science:

• Structural Engineering
• Computational Mechanics
• Artificial Intelligence

Background:

• Structural damage detection is crucial for safety and maintenance.
• Traditional methods like damage detection and finite element model updating have limitations.
• Analytical approaches face challenges in complex structural problems.

Purpose of the Study:

• To develop a novel methodology for structural damage detection.
• To accurately identify the location and extent of structural damage.
• To leverage artificial intelligence for complex damage analysis.

Main Methods:

• Utilizing finite element model updating to create a reference model reflecting structural characteristics.
• Generating training data for various damage scenarios based on the reference model.
• Employing artificial intelligence networks for damage identification.

Main Results:

• The developed methodology enables precise identification of structural damage.
• The approach effectively overcomes limitations of traditional analytical methods.
• Artificial intelligence networks successfully learn to detect damage from trained data.

Conclusions:

• The proposed AI-driven methodology offers a robust solution for structural damage detection.
• Model updating combined with AI provides an effective way to analyze structural integrity.
• This approach enhances the ability to assess and manage structural health.