Concrete Surface Crack Research Articles

A comparison of deep convolutional neural networks for image-based detection of concrete surface cracks

The aim of this paper is to compare the performance of four deep convolutional neural networks in the problem of image-based automated detection of concrete surface cracks in the case of a small dataset. This crack detection problem is treated as a binary classification problem, and it is solved by training a deep convolutional neural network on the small dataset. In this context, overfitting during training was the main issue to cope with and various techniques were applied to overcome this issue. The results of the experiments suggest that the best approach for this problem is to use the pretrained convolutional base of a large pretrained convolutional neural network as an automatic feature extraction method and adding a new binary classifier on top of the convolutional base. Then, at the training the new classifier and fine-tuning the last few layers of the pretrained network take place at the same time. The classification accuracy of the best deep convolutional neural network on the testing set is about 94%.

Anisotropic diffusion based denoising on concrete images and surface crack segmentation

Purpose Health monitoring of concrete is one of the important tasks in the structural health monitoring. The life of any infrastructure relies on the quality of the concrete. The computer vision-based methods are very useful to identify the structural defects. The identification of minor cracks in the noisy concrete image is complex. The purpose of this paper is to denoise the concrete crack images and also segment the cracks. Design/methodology/approach The novelty of the proposed work lies on the usage of anisotropic diffusion filter in the noisy concrete images. Initially anisotropic diffusion filter is applied to smoothen the concrete images. Adaptive threshold and gray level-based edge stopping constant are used in the diffusion process. The statistical six sigma-based method is utilized to segment the cracks from smoothened concrete images. Findings The proposed method is compared with five state-of-the-art-methods with the performance metrics of mean square error, peak signal to noise ratio and mean structural similarity. The experimental results highlight the advantages of the proposed method. Originality/value The novelty of the proposed work lies on the usage of anisotropic diffusion filter in the noisy concrete images. This research work gives the scope for structural damage evaluation by the automation techniques.

Detect concrete cracks based on OTSU algorithm with differential image

Aiming at the detection of concrete surface cracks, based on digital image processing technology, OTSU algorithm is processed based on differential image. First, the Gaussian filter is acted on the original image to obtain the smoothed image. Then the smoothed image is subtracted by the original image, the differential image is obtained. According to the OTSU algorithm, the optimal threshold on the differential image was calculated. As the characteristic cracks are a few pixels and with lower grey values, the pixels whose grey values are less than the mean value of the whole image to get the best threshold value were only calculated. Finally, remove the background noise based on the morphologic noise reduction to obtain the binary image of the crack. The experimental results show that the cracks can be discerned in complex backgrounds.

Correction to: Evaluation of surface cracks of bending concrete using a fully non-contact air-coupled nonlinear ultrasonic technique

The article Evaluation of surface cracks of bending concrete using a fully non-contact air-coupled nonlinear ultrasonic technique, written by Jun Chen, Chenglong Yang and Quanquan Guo, was originally published online without open access.

Behavioural Study of Concrete Surface Crack Filling Conditions on Surface Rayleigh Wave

In the recent studies of concrete surface crack non-destructive test (NDT), the environmental factors are seldom to be taken into assessment consideration using Rayleigh wave (R-wave) propagation method. Dust, fine sand or water that accumulated in the concrete surface cracks might potentially affect the behaviour of R-wave when it propagated through the cracks. In this study, the effects of filling conditions in concrete surface crack to the properties of R-wave were examined. The targeted parameters that used for studying the behaviour of R-wave are the arrival time of R-wave and its corresponding amplitude. Numerical simulations were conducted for determining the changes of R-wave amplitudes and arrival time when it propagated through a concrete model with a surface crack which containing various filling conditions. Sand and charcoal powder were the materials used for filling the concrete cracks. The results of numerical simulations were then justified by experimental measurements. The comparison between the results of numerical simulation and experimental measurement generated a conclusion where R-wave arrival time and its corresponding amplitude is independent from the predefined filling conditions of concrete surface crack.

The Algorithm of Concrete Surface Crack Detection Based on the Genetic Programming and Percolation Model

Because of the impact of the variation in different concrete surface images, such as the heterogeneity of the detection environment, uneven illumination, stains, the block, and water leakage, the existing crack detection algorithms cannot detect the real crack quickly and effectively. In this paper, a genetic algorithm based on genetic programming (GP) and percolation model is proposed. This method involves three steps. First, the cracks are pre-extracted by the image processing model of GP. Second, the crack tip is calculated after the crack skeleton is extracted. With the endpoint as the anchor point, high speed, and high precision percolation are used to detect the cracks with small width accurately. Concurrently, the fracture unit areas are scanned for connection. Finally, the pre-extracted cracks are connected with the cracks detected by the percolation, and the mass interference area is removed to obtain the real cracks on the concrete surface. The simulation results show that the concrete surface crack detection algorithm based on the GP and percolation model can effectively combine both of their advantages. The algorithm proposed in this paper can detect real concrete surface cracks accurately and effectively with strong robustness.

Correlation of Surface Cracks of Concrete due to Corrosion and Bond Strength (between Steel Bar and Concrete)

The current experimental study presents the results of bond strength loss (steel bar concrete) due to the corrosion damage of steel bar specimens, semiembedded in concrete, at various times of exposure to corrosive environment. In this case, a correlation was made between the width of the surface cracks of concrete caused by reinforcing steel corrosion and bond strength for different distances between stirrups and different cover thickness of concrete. The study indicates close relationship between the width of surface cracking, the percentage mass loss of embedded reinforcing bar, the distance between stirrups, and the cover thickness. In addition, mathematical predictive models of bond strength loss of corroded specimens were proposed. The model outcomes showed that the cracking development on concrete surface up to a width of 1.6 mm is accompanied by an exponential reduction of bond strength loss between steel reinforcement and concrete. Furthermore, the investigation has shown that the increase of transverse reinforcement (stirrups) percentage and the cover thickness play a significant role in durability of reinforced concrete elements and in bond strength maintenance between rebar and concrete.

A methodology framework for retrieval of concrete surface crack′s image properties based on hybrid model

Regular concrete surface crack inspection is critical since cracks are one of the earliest signs of deteriorating in concrete structures. With recent digital imaging and processing techniques, computer vision-based inspection shows huge potential in this field. A novel image processing framework for automatically retrieving multiple crack properties from concrete surface images is proposed. The framework includes (1) a crack extraction algorithm which combines edge detecting and seed growing; (2) a skeleton optimizing method which contains short branch deleting and polyline approximation algorithm; (3) a hybrid crack model which classifies crack segments into disc-shaped and bar-shaped parts based on their skeleton topological information, and (4) a triad labelling method that indicates the interrelationships between different cracks. Contrast experiments showed that the proposed segmentation method can extract more complete crack segments. Real image experiments indicated that the framework is effective and helpful for subsequent concrete structure health assessment.

Deep Belief Network and its application for Detection of Concrete Surface Cracks

Deep Belief Network and its application for Detection of Concrete Surface Cracks

Concrete surface crack detection with the improved pre-extraction and the second percolation processing methods.

Monitoring the instantaneous and changing concrete surface condition is paramount to cost-effectively managing tunnel assets. In practice, detecting cracks efficiently and accurately is a very challenging task due to concrete blebs, stains, and illumination over the concrete surface. Unclear and tiny cracks cannot be detected effectively. In this paper, we proposed an ultra-efficient crack detection algorithm (CrackHHP) and an improved pre-extraction and second percolation process based on the percolation model to address these issues. Our contributions are shown as follows: 1) apply the overlapping grids and weight-based, redefined pixel value to obtain the candidate dark pixel image while preserving the cracks. 2) introduce the second percolation processing to generate a high-accuracy crack detection algorithm, which can connect the tiny fractures and detect the tiny cracks. 3) construct a high-efficiency and high-accuracy crack detection algorithm combining the improved pre-extraction and the second percolation process. The experimental results demonstrate that CrackHHP can significantly improve the efficiency and accuracy of crack detection.

Evaluation of surface cracks of bending concrete using a fully non-contact air-coupled nonlinear ultrasonic technique

In this paper, a fully non-contact second harmonic generation (SHG) technique using a pair of air-coupled ultrasonic transducers is developed and the feasibility of the technique is investigated through the evaluation of surface cracks of concrete beams subjected to the bending load. The reliability of developed technique is subsequently validated by comparing the non-contact nonlinear ultrasonic measurements with measurement results based on contact-type sensors, where the coefficient of variation of non-contact measurements is averagely about 46% of the contact measurements. The defined nonlinear parameter is found to have a monotonically increasing trend with the growth of concrete crack, and the nonlinear parameter corresponding to the largest crack increases about 7 times from its initial value corresponding to the sample in intact state. In contrast, the increase of linear parameter namely the time-of-flight of surface wave is only about 40%. The difference as high as one order of magnitude verifies the high sensitivity of developed air-coupled SHG technique. With consideration of the easily removable characteristic of air-coupled ultrasonic measurements, the developed SHG technique could be promising for the large scale quality control of concrete structures in engineering practice.

Mesoscale model for cracking of concrete cover induced by reinforcement corrosion

Cracking of concrete cover induced by reinforcement corrosion is a critical issue for life-cycle design and maintenance of reinforced concrete structures. However, the critical degree of corrosion, based on when the concrete surface cracks, is usually hard to predict accurately due to the heterogeneity inherent in concrete. To investigate the influence of concrete heterogeneity, a modified rigid-body-spring model, which could generate concrete sections with randomly distributed coarse aggregates, has been developed to study the corrosion-induced cracking process of the concrete cover and the corresponding critical degree of corrosion. In this model, concrete is assumed to be a three-phase composite composed of coarse aggregate, mortar and an interfacial transition zone (ITZ), and the uniform corrosion of a steel bar is simulated by applying uniform radial displacement. Once the relationship between radial displacement and degree of corrosion is derived, the critical degree of corrosion can be obtained. The mesoscale model demonstrated its validity as it predicted the critical degree of corrosion and cracking patterns in good agreement with analytical solutions and experimental results. The model demonstrates how the random distribution of coarse aggregate results in a variation of critical degrees of corrosion, which follows a normal distribution. A parametric study was conducted, which indicates that both the mean and variation of critical degree of corrosion increased with the increase of concrete cover thickness, coarse aggregates volume fraction and decrease of coarse aggregate size. In addition, as tensile strength of concrete increased, the average critical degree of corrosion increased while its variation almost remained unchanged.

Dynamic analysis of an immersed tunnel in Izmir

The original design of the planned Izmir Bay Immersed Tube Tunnel, considered it to be a continuous subsea tunnel for the whole length of about 7.6 km. But this was later changed into having 2 shorter tubes of 2.7 km long each connected thru’ a 2.2 km long artificial island created in the middle of the bay from the excess dredged material, a concept which also reduces costs and increases efficiency. This island will serve as a venue for the 2025 Expo Exhibition, which Izmir city will apply to organize in the future. Reason for the research study was to provide a preliminary design, using a dynamic analysis, during the current pre-feasibility stage, of the immersed tunnel to show whether it can be built across the Izmir Bay. This paper takes into account the new alignment and presents the results of a 2-D dynamic analysis conducted of the prefabricated 100m long tunnel elements, sitting within a backfilled dredged ditch, dug after the recommended ground improvement was carried out. Analyses considered staged construction and the results showed that: Tunnel units and its surrounding soils inside the dredged ditch act together to provide a better earthquake response with a damping effect of the earthquake force; Tunnel units do not float to the sea surface, but continued to stay inside the dredged ditch and applied positive stresses to the foundations during the design earthquakes. As there was no floating, there was no need for anchoring the tunnel to ditch bottom; Tunnel units and immersion joints (made of specified strong elastomer material) continued to stay in compression longitudinally and provided a superb water-tightness level; There were no risky (un-tolerable) ground deformations during, after striking of the design earthquakes. Total vertical and differential displacements of the tunnel units and in the surrounding soils were all at acceptable levels; Concrete surface crack widths occurring in the tunnel units, during striking of the design earthquakes were also found to be allowable. Study results show that the tunnel elements can withstand Mw=7 short duration ( 10 sec) earthquakes without major damages to their structure

A non-uniform corrosion model and meso-scale fracture modelling of concrete

Corrosion-induced concrete cracking is a significant durability problem for reinforced concrete structures. Considerable research has been carried out in the last few decades to understand and model the expansion mechanism of the corrosion products around the reinforcing bar and simulate the cracking behaviour of the concrete cover. In this paper, a new corrosion model based on non-uniform corrosion expansion is formulated and validated against experimental data. A meso-scale fracture model, consisting of aggregates, cement paste/mortar and ITZ, is established for the cases of both middle and side reinforcing bars. Under the developed corrosion and concrete fracture model, the cracking phenomena of the concrete cover are accurately simulated. It has been found that the non-uniform corrosion model can be used to express the realistic corrosion rust progression around the reinforcing bar, with the best accuracy. It has also been found that some microcracks occur before they are connected to form the dominating discrete crack which usually appears on the concrete surface. Moreover, the effects of the corrosion variables, as well as other key material and geometric parameters, on surface cracking of concrete are investigated.

A Brief Review and a New Graph-Based Image Analysis for Concrete Crack Quantification

This paper surveys development using image-based methods for crack analysis in the last two-decade (2002–2016).This study aimed to extract and quantify the individual cracks in concrete surfaces, using a new automated image-based system. In general, an individual crack can appear in concrete structures as one of the three common configurations including longitudinal, transverse, and diagonal cracks. These kinds of cracks propagate inherently as linear, and may be involved in branching and spalling at some point of the original path. The main contribution of this work is twofold. First, the main mother crack is extracted using the graph theory and simulates the crack group proportionally. Second, the exact width of cracks can be measured automatically. The procedure has been automated in this study to calculate the individual crack characteristics including the length, average width, and orientation. Furthermore, the analytical results are presented as the distribution of accurate width variations along the length of the skeleton, maximum crack width and its location on the crack and graph. The results indicated that the proposed image-based crack quantification method can accurately measure changing the crack characteristics like width along it. It is demonstrated that the proposed method is applicable and shows good performance in conventional assessment of distressed concrete surfaces.

Image analysis method for crack distribution and width estimation for reinforced concrete structures

Abstract Crack observation is important for evaluating the structural performance and safety of reinforced concrete (RC) structures. Most of the existing image-based crack detection methods are based on edge detection algorithms, which detect cracks that are wide enough to present dark areas in the obtained images. Cracks initiate as thin cracks, generally having width less than the width of a pixel in images; such cracks are generally undetectable by edge detection-based methods. An image analysis method is proposed to observe the development and distribution of thin cracks on RC surfaces; it also allows estimation of crack widths. Image matching based on optical flow and subpixel is employed to analyze slight concrete surface displacements. Camera calibration is included to eliminate perspective effects and lens distortion. Geometric transformation is adopted so that cameras do not need to be perpendicular to the observed surface or specified positions. Formulas are proposed to estimate the width of shear crack opening. The proposed method was then applied to a cyclic test of an RC structure. The crack widths and their development analyzed by the image analysis were verified with human inspection in the test. In addition, concrete surface cracks that appeared at a very early stage of the test could be observed by the proposed method before they could be detected by the naked eye. The results thus demonstrate that the proposed image analysis method offers an efficient way applicable not only for structural tests but also for crack-based structural-health-monitoring applications.

Effect of Steel Fiber and Different Environments on Flexural Behavior of Reinforced Concrete Beams

The main kind of deterioration in marine Reinforced Concrete (RC) structures and other infrastructures is steel bar corrosion due to cracks in concrete surfaces, which leads to the reduction of the load carrying capacity, ductility, and structural safety. It seems that steel fibers can reduce and delay the cracking, and increase the flexural strength and ductility of marine RC structures. To do so, in marine atmosphere and the tidal zone of the Oman Sea and fresh water, the flexural behavior of beams containing Plain Concrete (PC), Concrete with Steel fiber Reinforcement (SFRC), RC, Concrete with Steel fiber, and bar Reinforcement ((R+S)C) at 28, 90 and 180 days were determined. Beams were 99 un-cracked and pre-cracked beams, with dimensions of 200 × 200 × 750 mm. Based on results and at 180 days, the flexural strength and toughness of pre-cracked (R+S)C beams were 22%–43% higher than the pre-cracked RC beams. The effect of steel fiber on the increment of load capacity and the toughness of pre-cracked RC beams were approximately the same. By addition of steel fiber to un-cracked RC beams, load capacity and toughness were increased up to 20%. The load capacity and toughness in marine atmosphere and tidal zone were approximately 15% lower than the fresh water condition.

A feasibility study on real-time evaluation of concrete surface crack repairing using embedded piezoceramic transducers

Surface cracking in large-scale concrete structures are inevitable, and some cracks shall be repaired to prevent further structural damages. Various methods of repairing surface cracks in concrete structures have been studied, however, evaluation of repairing of those cracks, especially through real time means, have not much been reported. In this paper, a feasibility study was performed on evaluation of repairing concrete surface crack in real-time using embedded piezoceramic-based transducers, called Smart Aggregates (SA). Using the active sensing approach, a pair of SAs in a concrete structure can communicate through generating and detecting stress wave. In the experimental study, three concrete beam specimens were investigated. In each specimen, four smart aggregates were embedded in the beam with two designed surface cracks. Subsequently, these two cracks were repaired by using mortar and Carbon Fiber Reinforced Polymer (CFRP) sheet. Due to interfacial properties among the three different interfacial conditions: the healthy concrete structure, the concrete structure with a crack, and the concrete structure with a repaired crack, the stress wave attenuation characteristics differ. The received signals of SAs among those three interfacial conditions were compared in time domain. In addition, a wavelet packet-based energy analysis was performed to quantitatively indicate the energy value of the received signal. Experimental results shows that the signal energy values computed by the wavelet packet-based energy analysis has potential to determine the crack occurrence in concrete structures and to help evaluate the repair effects.

Crack Detection in Concrete Tunnels Using a Gabor Filter Invariant to Rotation

In this article, a system for the detection of cracks in concrete tunnel surfaces, based on image sensors, is presented. Both data acquisition and processing are covered. Linear cameras and proper lighting are used for data acquisition. The required resolution of the camera sensors and the number of cameras is discussed in terms of the crack size and the tunnel type. Data processing is done by applying a new method called Gabor filter invariant to rotation, allowing the detection of cracks in any direction. The parameter values of this filter are set by using a modified genetic algorithm based on the Differential Evolution optimization method. The detection of the pixels belonging to cracks is obtained to a balanced accuracy of 95.27%, thus improving the results of previous approaches.

Continuous-wave Laser Thermography for Concrete Crack Evaluation under Moving Conditions

This paper presents a continuous-wave laser thermography (CLT) technique for concrete surface crack evaluation under moving conditions. The CLT technique is able to visualize and quantify surface cracks on moving concrete structures by generating a continuous-wave laser source and capturing infrared images at a fixed spatial point. Although the CLT system has spatially limited field of view, it can inspect the entire region of interest (ROI) of the moving target structure. To precisely quantify surface cracks, the data acquired from the entire ROI are integrated and subsequently processed by developing an instantaneous crack evaluation algorithm. In this study, concrete specimens with various macro- andmicro-cracks are specially prepared and used to validate the proposed CLT technique. The test results reveal that various cracks are successfully visualized and quantified within 3% error ratio.