This paper proposes an effective and efficient model for concrete crack detection. The presented work consists of two modules: multi-view image feature extraction and multi-task crack region detection. Specifically, multiple visual features (such as texture, edge, etc.) of image regions are calculated, which can suppress various background noises (such as illumination, pockmark, stripe, blurring, etc.). With the computed multiple visual features, a novel crack region detector is advocated using a multi-task learning framework, which involves restraining the variability for different crack region features and emphasizing the separability between crack region features and complex background ones. Furthermore, the extreme learning machine is utilized to construct this multi-task learning model, thereby leading to high computing efficiency and good generalization. Experimental results of the practical concrete images demonstrate that the developed algorithm can achieve favorable crack detection performance compared with traditional crack detectors.

Detecting cracks within reinforced concrete is still a challenging problem, owing to the complex disturbances from the background noise. In this work, we advocate a new concrete crack damage detection model, based upon multilayer sparse feature representation and an incremental extreme learning machine (ELM), which has both favorable feature learning and classification capabilities. Specifically, by cropping and using a sliding window operation and image rotation, a large number of crack and non-crack patches are obtained from the collected concrete images. With the existing image patches, the defect region features can be quickly calculated by the multilayer sparse ELM autoencoder networks. Then, the online incremental ELM classified network is used to recognize the crack defect features. Unlike the commonly-used deep learning-based methods, the presented ELM-based crack detection model can be trained efficiently without tediously fine-tuning the entire-network parameters. Moreover, according to the ELM theory, the proposed crack detector works universally for defect feature extraction and detection. In the experiments, when compared with other recently developed crack detectors, the proposed concrete crack detection model can offer outstanding training efficiency and favorable crack detecting accuracy.

In the field of non-destructive testing (NDT) for concrete structures, the traditional air-coupled impact-echo technology often has the problems of complex operation and low efficiency. In order to solve these problems, this study uses Comsol software to establish a finite element model (FEM) of the concrete structure with different void sizes and obtains the variation rule of peak frequency. The recognition property of the concrete void based on peak frequency is proposed, which is explained and validated by relevant theory and experiments. The results show that compared with the depth of the void, the influence of the void width on the peak frequency increases significantly. When the void width is greater than 0.3 m, the peak frequency of the sound wave decreases with the increase in the width, and the change is obvious. This paper describes the applicability of concrete void depth less than 0.4 m for the air-coupled method and, when the concrete void depth is less than 0.4 m, the peak frequency can be used to effectively identify void widths greater than 0.3 m. The research results will be beneficial to void detection of concrete structures such as tunnel lining and pavements.

The identification of maximum bearing friction is critical to working performance assessment of bridge sliding bearings. The friction-displacement hysteresis model was used for the bearing working performance (BWP) assessment. In this study, the bearing longitudinal displacement (BLD) hysteresis model is established for the sliding bearing system, introducing bearing friction and vehicle longitudinal effect. A novel approach for BWP assessment is presented using alternating vehicle longitudinal excitation. First, bearing friction and vehicle longitudinal effect were introduced to establish the hysteresis model of BLD. Subsequently, the evaluation index and the assessment approach were proposed for BWP assessment using the alternating vehicle longitudinal excitation. Finally, the assessment approach for BWP was applied to a real-world railway bridge. The results show that temperature-displacement relationship model for BWP assessment is unapplicable under significant vehicle longitudinal effects. On the contrary, the BLD induced by alternating vehicle longitudinal excitation can identify the degradation of the BWP when vehicle longitudinal excitation overcomes maximum bearing friction.