A novel approach to investigate the mechanical properties of the material for bridge health monitoring using convolutional neural network

Abstract

In the bridge structure, the main bearing element is the spans, which are directly subject to random and continuous loads, environmental influences, ageing, etc. These factors are easy to lead to material deterioration. Therefore, this study proposes a novel approach to investigate the mechanical properties of the material. The span of the bridge is the selected structure for investigation. This study focuses on the general evaluation of mechanical factors consistent with reality, so the following main factors are to be carried out. First, the viscoelastic model of material will be applied to set up and solve the governing differential equation of the beams with material characteristics involving the elastic modulus (E) and the viscous coefficient (C). The viscoelastic model is different from the traditional elastic model due to its non-linearity, reflecting the actual state of the structure. Second, the random vibration signal-based Loss Factor function (LF) calculation using the Power Spectral Density (PSD) to detect changes in structures. LF is a feature representing changes in material properties, including elasticity and viscosity, and is suitable for many types of bridge structures. Also, the paper uses Cubic Interpolation (CI) to generate a surface representing the LF distribution. This interpolation results in surfaces with respect to the LF values distributed by frequencies and spectral amplitudes. Finally, the LF distribution-based material investigation using Convolutional Neural Network (CNN) is proposed with high performance and accuracy. This study applies the proposed method to several bridges in Ho Chi Minh City, Vietnam. It demonstrates that LF is highly suitable for bridge health monitoring.

Keywords:

• Structural health monitoring
• loss factor function
• convolutional neural network
• cubic Interpolation
• deep learning
• bridge monitoring
• viscoelastic model
• material properties

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research is funded by Vietnam National University Ho Chi Minh City (VNU-HCM) under grant number C2021-20-06. The support of time and facilities from Ho Chi Minh City University of Technology (HCMUT) is also acknowledged.