Explore the vast range of titles available.

Traditional methods on crack inspection for large infrastructures require a number of structural health inspection devices and instruments. They usually use the signal changes caused by physical deformations from cracks to detect the cracks, which is time-consuming and cost-ineffective. In this work, we propose a novel real-time crack inspection system based on unmanned aerial vehicles for real-world applications. The proposed system successfully detects and classifies various types of cracks. It can accurately find the crack positions in the world coordinate system. Our detector is based on an improved YOLOv4 with an attention module, which produces 90.02% mean average precision (mAP) and outperforms the YOLOv4-original by 5.23% in terms of mAP. The proposed system is low-cost and lightweight. Moreover, it is not restricted by navigation trajectories. The experimental results demonstrate the robustness and effectiveness of our system in real-world crack inspection tasks.

With the rapid development of unmanned aerial vehicle (UAV) remote sensing and deep learning, road crack detection has become an important component of road condition assessment and intelligent road maintenance. However, accurately detecting cracks from UAV images remains challenging due to complex background environments, slender crack structures, blurred boundaries, and irregular crack shapes and orientations. Traditional methods that rely solely on visual information often struggle to achieve stable and accurate detection performance under these conditions. To address these challenges, this paper proposes a Multimodal Crack Geometry-Consistent Network (MCGC-Net) for high-precision road crack detection in complex road scenes. First, a UAV-based multimodal road crack dataset with image-text annotations is constructed. Specifically, crack-related textual descriptions are automatically generated from crack annotations using predefined semantic templates, which summarize crack morphology, spatial distribution characteristics, and structural properties. These semantic descriptions provide high-level semantic prior information for crack representation learning. Second, a Multimodal Contrastive Semantic Gating module (MCSG) is introduced to leverage automatically generated crack semantic descriptions and in-batch image-text semantic differences to guide visual feature learning, thereby improving the discrimination between crack and non-crack regions under complex background conditions. Furthermore, a Crack-Aware Slenderness Loss (CASL) is proposed to explicitly constrain slenderness consistency between predicted boxes and ground-truth boxes, improving localization stability for slender crack targets. In addition, a KAN-based Nonlinear Channel Attention mechanism (KAN-CA) is introduced to enhance feature representation capability for complex crack structures. Experimental results demonstrate that the proposed MCGC-Net effectively improves crack detection accuracy and structural representation capability under complex road environments. The proposed method provides a practical and reliable solution for UAV-based intelligent road crack detection.

A novel output-only crack localization method is proposed for operating rotors based on an enhanced higher-order dynamic mode decomposition (HODMD), in which the nonlinear breathing crack-induced super-harmonic characteristic components from multiple vibration measurement points are simultaneously extracted to compose the corresponding super-harmonic transmissibility damage indexes. Firstly, the theoretical background of the HODMD is briefly reviewed. Secondly, the proposed crack localization method is dedicated which improving the HODMD for multivariate signals by casting the total least square method into standard HODMD and adaptively selecting the order parameter of Koopman approximation by optimizing the super-harmonic frequency vector. In addition, the super-harmonic characteristic components are evaluated and harnessed to derive the damage index based on super-harmonic transmissibility and fractal dimension. Finally, the proposed method is investigated and demonstrated by numerical simulations and experiments. Both numerical and experimental results show that the proposed method is powerful in realizing multi-crack localization for running rotors accurately and robustly in the case of no baseline information on intact rotors. Moreover, the interferences from commonly existing steps and misalignment can also be eliminated.

Crack detection is vital for maintaining hydraulic engineering infrastructure. However, achieving a balance between real-time processing and high precision in semantic segmentation models presents a significant challenge, especially given the intricate details of cracks and complex backgrounds. To tackle this issue, this paper proposes a real-time, high-precision crack segmentation model. Initially, a four-branch feature extraction structure is devised to capture the edge details of cracks, with a focus on enhancing segmentation accuracy. Subsequently, an image pyramid is constructed at the input end to feed small-scale samples into high-dimensional feature extraction branches, thereby reducing computational costs and improving segmentation speed. Finally, an effective feature fusion module is designed for the feature extraction structure to capture sufficient crack features and achieve precise crack localization. Extensive experiments validate the superior performance of the proposed method, with Pixel Accuracy, Recall, Intersection over Union, and F1 score reaching 68.45 % , 67.04 % , 51.22 % , and 67.74 % , respectively, while maintaining a modest parameter count of 13.12M. This model provides a reliable and efficient solution for the health monitoring and maintenance of hydraulic engineering.

The nonlinear interaction of longitudinal vibration and ultrasound in beams with cracks is investigated. The central focus is on the localization effect of this interaction, i.e., the locally enhanced nonlinear vibro-acoustic modulation. Both numerical and experimental investigations are undertaken. The finite element (FE) method is used to investigate different crack models, including the bi-linear crack, open crack, and breathing crack. A parametric study is performed considering different crack depths, locations, and boundary conditions in a two-dimensional beam model. The study shows that observed nonlinearities (i.e., nonlinear crack–wave modulations) are particularly strong in the vicinity of the crack, allowing not only for crack localization but also for the separation of the crack-induced nonlinearity from other sources of nonlinearity.

This study addresses the intricate challenge of detecting and localizing transverse cracks in rotors supported by active magnetic bearings (AMBs). Rotor systems in machinery demand accurate fault identification without halting operations, a task accomplished through signal-based analysis. Vibration signals, reflecting the mechanical state during operation, serve as valuable information sources for condition assessment. The significance of this study lies in its dual objectives: identification and localization of rotor cracks. Unlike existing techniques that often focus solely on crack identification, this work ventures into the challenging domain of precise localization. An innovative and novel proof-by-negation method is introduced, enabling the identification algorithm to pinpoint crack positions. This methodology offers a breakthrough by efficiently addressing the intricate problem of accurate localization within the dynamic rotor system. The study’s methodology involves a comprehensive approach, combining finite element modeling, synthetic vibration response generation, and advanced identification techniques. The algorithm’s efficacy is demonstrated through simulations using MATLAB-based finite element models, encompassing both conventionally supported and AMB-supported rotor configurations. Synthetic responses are extracted and processed to validate the algorithm’s effectiveness in identifying and localizing cracks. The results showcase the algorithm’s robustness and accuracy. In AMB-supported rotor systems, the algorithm successfully estimates key parameters such as crack stiffness and position. By manipulating a flag vector, the proof-by-negation approach accurately locates the crack along the rotor’s axis.

This study aims to reveal the control mechanism of key geometric parameters (flange thickness and flange edge thickness) of H-shaped cross-section on the bending performance of UHPC piles. Through conducting bending tests, combined with digital image correlation (DIC) technology and finite element simulation, the mechanical behavior was studied, and based on the principal strain field obtained from DIC, a strain field concentration index was proposed. The results show that: as the load ratio increases, the strain field concentration and the peak value of the mid-span principal strain continuously increase, and the crack evolution changes from dispersed development to localized control; near the limit state, the strain field concentration can reach approximately 0.28, and the peak value of the principal strain increases in an increasing trend, approximately 20% or more. Under the specific conditions of this test, in terms of ductility and energy absorption, when the flange thickness is constant, increasing the flange thickness of the web increases the energy absorption of the component by approximately 6% to 10%, while the ductility coefficient decreases by approximately 9% to 15%; when the web thickness is constant, increasing the flange thickness reduces the ductility coefficient by approximately 21% to 25%, and the energy absorption decreases by approximately 27% to 29%. The strain field concentration can effectively reflect the evolution process of the localization of bending cracks in H-shaped UHPC piles and can be used for quantitative analysis of their ductility degradation and energy absorption characteristics. It should be clarified that this study does not claim to isolate the effect of a single parameter.

Crack localization in running rotors is very important and full of challenges for machinery operation and maintenance. Characteristic deflection shapes or their derivatives based methods seem to be promising for crack localization in rotors. Despite the substantial advantages, several critical issues still need to be addressed to enhance the efficiency of this kind of method for practical applications. Two problems are considered in this work: 1. How to localize single or multiple cracks accurately avoiding the interference of commonly existing steps without baseline information on pristine rotors; 2. How to improve the crack localization performance under a noisy environment. To circumvent the issues, a novel baseline-free adaptive crack localization method is proposed based on data fusion of multiscale super-harmonic characteristic deflection shapes (SCDSs). In this method, crack induced asymmetry and nonlinearity of crack breathing are utilized to simultaneously eliminate the interference from the steps without a reference model. To enhance the noise robustness, the multiscale representations of SCDSs are made in Gaussian multiscale space, and Teager energy operator is applied to the multiscale SCDSs to amplify the crack induced singularities and construct the multiscale Teager super-harmonic characteristic deflection shapes (TSCDSs). Moreover, fractal dimension is designed as an evaluator to select the proper multiscale TSCDSs for data fusion adaptively. Then, a new damage index is derived for crack localization by Dempster-Shafer’s (D-S) evidence fusion of the adaptively selected multiscale TSCDSs. Finally, the feasibility and the effectiveness are verified by both numerical and experimental investigations.

Timely detection of defects is essential for ensuring safe and stable operation of concrete buildings. Automatic segmentation of concrete buildings’ surfaces is challenging due to the high diversity of crack appearance, the detailed information, and the unbalanced proportion of crack pixels and background pixels. In this work, the Double Feature Pyramid Network is designed for high-precision crack segmentation. Our work reached the state-of-the-art level in crack segmentation, with key contributions outlined as follows: firstly, considering the diversity of crack shapes, the network constructs a feature pyramid containing three feature extraction backbones to extract the global feature map with three scale input images. In particular, due to the biggest challenge being too much single-pixel crack area, the targeted feature pyramid based on the high-resolution is added to extract adequate shallow semantic information. Lastly, designing a cascade feature fusion unit to aggregate the extracted multi-dimensional feature maps and obtain the final prediction. Compared with existing crack detection methods, the superior performance of this method has been verified based on extensive experiments, with Pixel Accuracy of 65.99%, Intersection over Union of 44.71%, and Recall of 62.95%, providing a reliable and efficient solution for the health monitoring and maintenance of concrete structures. This work contributes to the advancement of research and practical applications in related fields, offering robust support for the monitoring and maintenance of concrete structures.

Purpose To address the impact of intrinsic material nonlinearity on closed crack detection in thin plates, a phase-velocity mismatching Lamb wave mixing technique is introduced. Methods By coaxially mixing two phase-velocity mismatching S 0 modes in opposite directions, both sum- and difference-frequency Lamb waves are produced. When there are no closed cracks, the sum- and difference-frequency components remain weak due to their nonlinear accumulation over propagation distance. When there is a closed crack, the modulation of the primary waves causes the crack to open and close, resulting in the “clapping” effect. The waveforms of the primary waves become distorted in the time domain after passing through the crack, significantly enhancing the sum- and difference-frequency components. Consequently, closed cracks can be accurately detected based on the variations in harmonic properties within the plate. The two newly generated sum- or difference-frequency Lamb waves propagate symmetrically around the closed crack, exhibiting equal group velocities, periods, and amplitudes. This symmetry enables the accurate localization of closed cracks by measuring the time difference of their arrival at the two ends of the plate. Finite element simulations are employed for closed crack detection and localization. Results Results indicate that the sum- and difference-frequency components caused from closed-crack contact acoustic nonlinearity (CAN) are much stronger than those produced by the intrinsic material nonlinearity. Furthermore, the acoustic nonlinear parameter associated with the sideband at the sum frequency increases with the length of the closed crack and decreases with the width of the closed crack. The proposed technique achieves an impressive closed crack localization accuracy of 1.2 mm. Conclusion The findings of this study provide a feasible method for detection and localization of closed cracks.