TITLE:
Research on Structural Damage Identification Method Based on Convolutional Neural Network
AUTHORS:
Zongchao Liu, Shuai Teng, Shaodi Wang
KEYWORDS:
Convolutional Neural Network, Structural Damage Recognition, Simply Supported Beams, Modal Strain Energy, Finite Element Simulation
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.15 No.11,
November
17,
2025
ABSTRACT: Structural damage identification is a critical task in civil engineering for ensuring the safety and serviceability of infrastructures. Traditional methods often rely on manually selected features from vibration data, which may lack sensitivity to incipient or localized damage. In recent years, convolutional neural networks (CNNs) have demonstrated remarkable capability in automatically extracting discriminative features from raw data, providing a powerful data-driven alternative for structural health monitoring. This paper proposes a novel structural damage identification method based on a CNN framework. Numerical simulations of the free vibration of a simply supported beam were conducted using the finite element method. The modal strain energy of the first-order element was collected as the primary damage-sensitive feature. Through batch automatic calculation, a comprehensive dataset encompassing various damage scenarios—including different locations and severity levels—was efficiently generated to serve as training, validation, and testing samples for the network. The proposed CNN model was specifically designed and implemented in MATLAB to adapt to the characteristics of the structural damage detection data. This study systematically verifies the recognition performance of the CNN from three key aspects: identification of single damage location, quantification of damage severity at a single location, and detection of multiple damage locations. The results indicate that the CNN can not only accurately identify the location of structural damage with high precision but also achieve a considerable level of accuracy in quantifying the degree of damage, demonstrating its strong potential for comprehensive damage assessment in engineering structures.