Narrow Results

The main environmental factors that interfere with asphalt pavement crack detection include shadows from ambient light of different intensities, trees, signboards, railings, etc. Traditional crack detection methods usually eliminate the effect of light during pre-processing or improve the recognition results by local consistency and light normalization during image segmentation. However, the current methods can only improve the image brightness uniformity and cannot completely eliminate the effect of light, so the usual methods are only effective when the image brightness uniformity is good. So, this study puts out an approach to improving images. Machine learning is used to suggest a method for detecting cracks in asphalt pavement, with the help of an attention mechanism, using photos of real roads as the experimental dataset. Experiments show that the method can preprocess image data well and enhance the robustness of training in machine learning structures. Test results show that our method can be well applied to practical testing work.

Deep learning artificial intelligence (AI) is a booming area in the research field. It allows the development of end-to-end models to predict outcomes based on input data without the need for manual extraction of features. This paper aims for evaluating the automatic crack detection process that is used in identifying the cracks in building structures such as bridges, foundations or other large structures using images. A hybrid approach involving image processing and deep learning algorithms is proposed to detect automatic cracks in structures. As cracks are detected in the images they are segmented using a segmentation process. The proposed deep learning models include a hybrid architecture combining Mask R-CNN with single layer CNN, 3-layer CNN, and8-layer CNN. These models utilizes depth wise convolution with varying dilation rates for efficiently extracting diversified features from the crack images. Further, performance evaluation shows that Mask R-CNN with a single layer CNN achieves an accuracy of 97.5% on a normal dataset and 97.8% on a segmented dataset. The Mask R-CNN with 2-layer convolution resulted in an accuracy of 98.32% on a normal dataset and 98.39% on a segmented dataset. The Mask R-CNN with 8-layers convolution achieves an accuracy of 98.4% on a normal dataset and 98.75% on a segmented dataset. The proposed Mask R-CNN have proved its feasibility in detecting cracks in huge building and structures.

Structural inherent dynamic characteristics would change when damage occurs, and this fact is the theoretical basis of damage detection method based on vibration features. As one of structural inherent properties, frequency response function (FRF) contains rich information and has more potential in damage detection. On the basis of crack detection researches, a new method based on the change of FRF is proposed in this paper. First, the single-degree-of-freedom (SDOF) system is used to illustrated the change of dynamic features caused by cracks represented by changing stiffness, and it is found that the change of stiffness leads to the obvious nonlinear variation of frequency response function curvature (FRFC) and frequency response function curvature differentiation (FRFCD) near the natural frequency. To describe this phenomenon, the Pearson correlation coefficient is employed to analyze correlation relationship of FRF, FRFC and FRFCD between the undamaged and the damaged system. The results demonstrate that absolute values of these coefficients approach from 1 to 0 with the increase of stiffness change. The rail with cracks is taken as the research object, and relationships between the crack size and the correlation coefficients of FRF, FRFC and FRFCD are investigated through the combination of finite element simulation and frequency response experiment. The correlation coefficients of FRF, FRFC and FRFCD are close to 1 when the structure is intact. When cracks occur, the absolute value of the correlation coefficient will gradually trend from 1 to 0, and the sensitivity of FRFCD correlation coefficient to crack is much higher than that of FRF and FRFC. The selection of calculated frequency bands containing different modes and the damping of the structure would affect the absolute value of FRFCD correlation coefficient, but will not change the characteristics of high sensitivity of FRFCD and the relationship between the coefficient and crack size. Besides, noise signals would enhance the nonlinear relationship between responses of intact structure and the structure with cracks, and the FRFCD correlation coefficient value is influenced accordingly.