No abstract

With the continuous development of the social economy, road traffic plays an increasingly significant role in the national economy and people's lives. Traffic has become one of the important infrastructures for people's daily travel and economic construction in my country, and it is the key to reflecting the economic development of a region. During the long-term operation of expressways, various types of diseases will occur. In order to solve the problem that traditional pavement crack detection, a pavement crack detection method based on image processing under complex background is proposed. A pavement crack image segmentation model based on semantic segmentation is built, and cracks in highresolution crack images are extracted by using the pavement image segmentation model. The results show that, compared with the existing algorithms, the pro-posed algorithm has a better detection effect and stronger generalization ability in complex road scenes.

Bridges suffer damage throughout their lives due to variations in the performance of the materials, loads, and other uncontrollable factors. During the service period of the structure, the key parts will continue to accumulate damage and defects trapped, affecting the safety of its use. Therefore, structural health monitoring is important for engineering structures. In this work, the numerical and experimental verifications are used to verify the effectiveness of the wavelet packet energy curvature difference (WPECD) method in identifying structural damage, the beam body replaced by the bridge model is used to simulate the two damage levels. In this work the damage level increases from 5% to 20%. The acceleration response of each point in intact and damaged states was tested, and the WPECD method was used to identify the damage, and the effect of the number of decomposition layers and the wavelet function on the Knot identification effect were studied. The results of the presented method show that the WPECD technique is more effective for damage, and sensitive in small lesions (5%), it can also be effectively identified. It shows that the method is effective and can be applied to practical engineering.

Damage causes the dynamic structural responses of civil engineering structures to change from linear to nonlinear. It can be challenging to break down signals and identify features, mainly when the data is generated by a nonlinear system and is nonstationary. Under heavy loads and during routine operations, civil structures have been seen to exhibit nonlinear dynamic characteristics. To assess progressive damage, it is necessary to characterize the time-varying attribute of the structure’s nonlinearity and consider how the frequency and amplitude contents of nonstationary vibration responses change over time. The properties of a nonstationary signal cannot be properly described by either time analysis or frequency analysis alone. When measured data include structural damage occurrences, it is critical to extract as much information about the damage as possible from the data. To create a reliable damage detection method that captures damage progression using vibration data gathered by sensors, this work examines the instantaneous frequency (IF) representation utilizing time-frequency distributions of the energy density domain based on short-time Fourier transform, wavelet transform, Hilbert-Huang transform, Wigner-Ville distribution, and synchrosqueezed transform. Each technique capability is validated using various experimental data. It is found that both the synchrosqueezed transform and Wigner distribution proved to be the best performance in terms of IF tracking and showed particular promise due to their spectral energy concentration with the synchrosqueezing transform outdoing other techniques in terms of computation precision.