Concrete Defects Research Articles

Automated Hammering Inspection System With Multi-Copter Type Mobile Robot for Concrete Structures

For infrastructure health monitoring, defects in concrete are periodically inspected by hammering test. Conventional hammering inspection is manually conducted to detect internal concrete defects by recognizing the sounds generated from the hammer strike. Therefore, a robot-based hammering inspection system can realize the inspection automatically. However, those robots have several elements such as noise-resistant acoustic analysis, weight reduction of the robot, constant striking mechanism, and stable robot movement; so integrated research has not been achieved. This paper introduces a hammering inspection system using robot that solves these problems. In the proposed system, a multi-copter type mobile robot realizes a stable attitude on a structure using thrust force to press the robot body onto the structure surface, while a lightweight hammering mechanism constantly strikes a wall. During inspection, noises from multi-copter affect acoustic analysis. Therefore, the proposed method clarifies the features of hammering sound and propeller noise and analyzes hammering sounds. This developed hammering inspection system is the first to realize all functions required for comprehensive hammering inspection, and its accuracy to detect concrete defects from hammering sounds was 81.7% through the experiments.

Study on Applicability of Detection of Internal Cracks by Impact Echo Using Machine Learning

In this study, as a part of the comprehensive deterioration evaluation system for concrete structures by combining several diagnostic methods such as impact echo detection and infrared diagnosis, automatic judgement of concrete defects was attempted by machine learning of impact echo spectrogram. In machine learning, the impact echoes were transformed into spectrograms using the short-time Fourier transform, and supervised learning was performed using a convolutional neural network (CNN). This method can judge defects with the same accuracy as experienced engineers in the specimen with simulated defects buried in it. So, it was investigated the possibility of detecting micro cracks in concrete under conditions closer to real structures by this method. In the experiment, a reinforced concrete specimen with dimensions of 1800 x 1800 x 600 mm and the cover concrete of 70 mm was fabricated. Then, by electric corrosion of the specimen, the steel bars inside were corroded, and micro cracks were generated. Impact echoes were measured before and about every week after the start of electric corrosion. Then, machine learning was performed using the impact echo spectrograms before the start of electric corrosion and after internal cracks were determined to have occurred. The CNN obtained from this process was used to judge the impact echo spectrograms during the progress of electric corrosion. As a result, the area judged as defects became larger after the rapid growth of strain considered to be caused by the internal cracks. In addition, when the impact echo spectrograms with further electric corrosion were used as training data, the area judged as defect became smaller. From these results, this method was found to be capable of judging micro-cracks due to corrosion expansion of steel bars in the concrete.

Civil infrastructure defect assessment using pixel-wise segmentation based on deep learning

Nowadays, the number of aging civil infrastructures is growing world-wide and when concrete is involved, cracking and delamination can occur. Therefore, ensuring the safety and serviceability of existing civil infrastructure and preventing an inadequate level of damage have become some of the major issues in civil engineering field. Routine inspections and maintenance are then required to avoid leaving these defects unexplored and untreated. However, due to the limitations of on-field inspection resources and budget management efficiency, automation technology is needed to develop more effective and pervasive inspection processes. This paper presents a pixel-wise classification method to automatically detect and quantify concrete defects from images through semantic segmentation network. The proposed model uses Deeplabv3+ network with weights initialized from pre-trained neural networks. The comparison study among the performance of different deep neural network models resulted in ResNet-50 as the most suitable network for applications of civil infrastructure defects segmentation. A total of 1250 images have been collected from the Internet, on-field bridge inspections and Google Street View in order to build an invariant network for different resolutions, image qualities and backgrounds. A randomized data augmentation allowed to double the database and assign 2000 images for training and 500 images for validation. The experimental results show global accuracies for training and validation of 93.42% and 91.04%, respectively. The promising results highlighted the suitability of the model to be integrated in digitalized management system to increase the productivity of management agencies involved in civil infrastructure inspections and digital transformation.

Fusion of thermal and RGB images for automated deep learning based crack detection in civil infrastructure

Research has been continually growing toward the development of image-based structural health monitoring tools that can leverage deep learning models to automate damage detection in civil infrastructure. However, these tools are typically based on RGB images, which work well under ideal lighting conditions, but often have degrading performance in poor and low-light scenes. On the other hand, thermal images, while lacking in crispness of details, do not show the same degradation of performance in changing lighting conditions. The potential to enhance automated damage detection by fusing RGB and thermal images together within a deep learning network has yet to be explored. In this paper, RGB and thermal images are fused in a ResNET-based semantic segmentation model for vision-based inspections. A convolutional neural network is then employed to automatically identify damage defects in concrete. The model uses a thermal and RGB encoder to combine the features detected from both spectrums to improve its performance of the model, and a single decoder to predict the classes. The results suggest that this RGB-thermal fusion network outperforms the RGB-only network in the detection of cracks using the Intersection Over Union (IOU) performance metric. The RGB-thermal fusion model not only detected damage at a higher performance rate, but it also performed much better in differentiating the types of damage.

Sparse‐sensing and superpixel‐based segmentation model for concrete cracks

AbstractEfficient image‐recognition algorithms to classify the pixels accurately are required for the computer‐vision‐based inspection of concrete defects. This study proposes a deep learning‐based model called sparse‐sensing and superpixel‐based segmentation (SSSeg) for accurate and efficient crack segmentation. The model employed a sparse‐sensing‐based encoder and a superpixel‐based decoder and was compared with six state‐of‐the‐art models. An input pipeline of 1231 diverse crack images was specially designed to train and evaluate the models. The results indicated that the SSSeg achieved a good balance between the recognition correctness and completeness and outperformed other models in both accuracy and efficiency. The SSSeg also exhibited good resistance to the interference of surface roughness, dirty stains, and moisture. The increased depth and receptive field of sparse‐sensing units guaranteed the representability; meanwhile, structured sparse characteristics protected the network from overfitting. The lightweight superpixel‐based decoder omitted skip connections, which greatly reduced the computation and memory footprint and enlarged the input size in the inference.

Effect of different imaging modalities on the performance of a CNN: An experimental study on damage segmentation in infrared, visible, and fused images of concrete structures

This study investigates the semantic segmentation of common concrete defects when using different imaging modalities. One pre-trained Convolutional Neural Network (CNN) model was trained via transfer learning and tested to detect concrete defect indications, such as cracks, spalling, and potential subsurface defects. We compared the model's performance using datasets of visible, thermal, and fused images. In addition, the impact of using different image enhancement techniques, such as histogram equalization and resolution improvement, was investigated. The data was collected from four different concrete structures using four infrared cameras with distinct sensitivities and resolutions, with imaging campaigns conducted during autumn, summer, and winter. Although specific defects can be detected in monomodal images, the results demonstrated that a larger number of defect classes could be detected using fused images with the same viewpoint and resolution as the single-sensor image without significant loss of information. In addition, the output of one hypothesis test showed that the image enhancement techniques provided no significant improvement in the CNN performance for this case of study, even though they resulted in enhanced images with higher information content (entropy) than the original images.

Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition

Image/video based defect recognition is a crucial task in automating visual inspection of concrete structures. Although some progress has been made to automatically recognize defects in concrete structural images, significant challenges still exist. In this work, we propose a deep convolutional neural network architecture that embeds novel spatial-channel interaction based concurrent attention (SCA) for multi-target, multi-class defect recognition. SCA module stems from novel kernel salient feature (KSF) encoder that captures higher-order features with robust discriminative representation of concrete defects. KSF encoder incorporates kernelized convolution followed by dynamic routing operation to be used as the primary building block. The proposed CSDNet architecture is able to apportion higher weightage in defective regions while suppressing large background area (healthy region), thereby improving recognition performance of overlapping defects in concrete structures. Experimental results and ablation study on four large benchmark datasets show consistent superiority of our proposed network as compared to current state-of-the-art methodologies. This end-to-end trainable architecture can be augmented with unmanned aerial vehicles (UAVs) to monitor health of massive infrastructures to leverage high concrete defect recognition performance.

Compression performance analysis of multi-scale modified concrete based on response surface method

The natural multi-scale defects in concrete are important factors affecting the performance. To comprehensively improve the performance of concrete, a method of adding variety materials into concrete to improve the defects from nano-micron-millimeter scales is proposed, and carbon nanotubes (CNTs), calcium carbonate whiskers (CCW), PVA fiber, steel fiber and rubber particles are selected for tests. The whole tests are completed by the phased test method. Firstly, CNTs and CCW are added into concrete, and the optimal content scheme of CNTs and CCW is determined. On this basis, this study designed and completed the multi-scale modified concrete test that further added PVA fiber, steel fiber and rubber particles according to response surface method (RSM). Finally, combined with RSM, hybrid effect coefficient and scanning electron microscope (SEM), the multi-scale modified concrete test results are analyzed. The analysis results indicated that the regression equation established by RSM has high accuracy and can effectively predict concrete mechanical properties under different materials content. Steel fiber and PVA fiber can improve concrete performance, while rubber particles can improve the deformation capacity and reduce the peak stress and toughness. When the contents of CNTs, CCW, PVA fibers, steel fibers and rubber particles are 0.6 %, 6 %, 0.075 %, 1 % and 0 % respectively, the multi-scale modified concrete has the best mechanical properties.

3D reconstruction of concrete defects using optical laser triangulation and modified spacetime analysis

Automated investigation of concrete defects has attracted attention with well-developed computer vision techniques. However, most studies in defect reconstruction mainly focus on identifying and measuring defects on a two-dimensional surface. Few progresses have been made to explore the 3D reconstruction of concrete defects. This study describes an affordable optical laser triangulation system fusing a linear laser ray generator and a sports camera to reconstruct the concrete defects. The proposed system adopts a modified spacetime analysis approach to solve two critical imaging errors in typical laser triangulation approaches. By comparing the outputs of the proposed system and two typical laser triangulation approaches, the results show that the proposed system can eliminate the imaging errors and generate 3D reconstruction models of concrete defects with acceptable accuracy.

Artificial intelligence applications for proactive environmental monitoring and asset management

Two research studies have been implemented to explore the potential of applying artificial intelligence (AI) technologies in works projects and maintenance work of the Drainage Services Department (DSD) for enhancing the efficiency related to environmental monitoring and structural inspection, referred to as the AIEIA and AIBIM projects, respectively. In the AIEIA project, AI technologies were explored to assist observing bird behaviour that would likely be influenced by nearby DSD construction projects. A domain randomisation-enhanced model was built to detect great egrets and little egrets at Penfold Park, Hong Kong, achieving a mean average precision of 87.65%. The detection result was used to analyse the Penfold Park egretry behaviour. In the AIBIM project, AI technologies were used to facilitate the condition assessment of concrete defects in sewage treatment facilities. A classifier was developed with supervised learning for concrete defect detection, attaining recalls of 86.2% and 89.9% for the cracking and spalling classes. Another concrete defect anomaly detector was built using unsupervised learning, achieving balanced results with F2 measures of 85.2% and 76.0% for the cracking and spalling classes. The two research studies render valuable experience for the DSD to integrate AI-enabled analytics into future work to continuously improve the drainage services in Hong Kong.

Optimization on Ready-Mixed Concrete Dispatching Problem via Sliding Time Window Searching

The dispatching of ready-mixed concrete (RMC) is usually scheduled manually and difficult to meet the demand of construction sites. The inefficient dispatching plan causes concrete defects of discontinuous casting (cold joint formation) or long on-site queuing (concrete early hardening inside RMC truck). The RMC dispatching literature focus on optimizing the dispatching intervals to minimize RMC truck on-site queuing, system operation costs of RMC plant and construction sites, or tradeoff. The previous research methods include mixed-integer linear programming (MILP) and evolutionary algorithms. They have the limitations of providing optimal solutions or computation efficiency. This paper develops a Binary Linear programming with Sliding Time-Window (BLSTW) to overcome these limitations. The BLSTW model subtly determines the dispatch of RMC trucks through binary variables incorporated into sliding time window search approach. Two perspectives, from the RMC plant supplier and construction site demanders, are discussed respectively. Three case studies are conducted to verify the efficiency improvement of the developed model including one largescale example of 25 sites. The comparisons made with two cited results shows the superior of the developed model.

Application of deep learning in structural health management of concrete structures

Structural health management constitutes an essential factor in ensuring the durability of concrete structures. Cracks in concrete, reinforcement corrosion, alkali–silica reaction and efflorescence attacks are common concrete defects that can be identified visually. However, the detection and classification of these defects in concrete bridges and other high-rise concrete structures is a difficult and expensive process using manual approaches. In this research, a deep learning application is applied to detect and classify concrete defects. Concrete images from the public repository were used to create the explored database. The database was divided into training and validation subsets. The visual geometry group (Vgg19), neural search architecture (nasnetlarge) and residual inception block (vinceptionresnetv2) algorithms were used to analyse the images. The results of the overall performance show that the Vgg19 algorithm recorded higher accuracy in the detection and classification of concrete defects when compared to the nasnetlarge and inceptionresnetv2 algorithms. The efficiency of the proposed approach was evaluated using a new dataset containing images of concrete defects. The outcome of this research shows clearly that deep learning models could enhance the efficiency of concrete structural health monitoring in a multi-classification scenario.

A Wavelet Packet Transform and Convolutional Neural Network Method Based Ultrasonic Detection Signals Recognition of Concrete.

This paper proposes a new intelligent recognition method for concrete ultrasonic detection based on wavelet packet transform and a convolutional neural network (CNN). To validate the proposed data-based method, a case study is presented where the K-fold cross-validation was adopted to produce the performance analysis and classification experiments. Moreover, three evaluation indicators, precision, recall, and F-score, are calculated for analyzing the classification performance of the trained models. As a result, the obtained four-classifying CNN reaches more than 99% detection accuracy while the lowest recognition accuracy is not less than 92.5% on the testing dataset for the six-classifying CNN model. Compared with the existing stochastic configuration network (SCN) models, the presented method achieves the design objective with better recognition performance. The calculation results of the six-classifying and five-classifying models and related research clearly indicate the remaining challenging tasks for intelligent recognition algorithms in extracting features and classifying mass data from various concrete defects precisely and efficiently.

An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module.

Buildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, due to human physiology, the assessment limits the accuracy of image evaluation, making it more subjective rather than objective. Thus, in this study, a multivariant defect recognition technique was developed to efficiently assess the various structural health issues of concrete. The image dataset used was comprised of 3650 different types of concrete defects, including surface cracks, delamination, spalling, and non-crack concretes. The proposed scheme of this paper is the development of an automated image-based concrete condition recognition technique to categorize, not only non-defective concrete into defective concrete, but also multivariant defects such as surface cracks, delamination, and spalling. The developed convolution-based model multivariant defect recognition neural network can recognize different types of defects on concretes. The trained model observed a 98.8% defect detection accuracy. In addition, the proposed system can promote the development of various defect detection and recognition methods, which can accelerate the evaluation of the conditions of existing structures.

Stand-Alone Composite Attention Network for Concrete Structural Defect Classification

Automation in structural health monitoring involves a critical step of automatic classification of concrete defect images/videos. Although interdisciplinary research community in AI has responded with some progress, immense challenges are still involved because of the predominant overlapping nature of the defect classes, exacerbated by the large variations in their visual appearance. However, current methodologies mostly consider single-class nonoverlapping defects and emphasize equally over the entire image plane; thus unable to focus on specific defect regions for robust feature selection. Thereby, the classification performance gets degraded and the methodologies became less suitable for real-world scenarios. In this work, we propose a novel stand-alone composite attention network that automatically exerts higher emphasis on the defective regions and less emphasis on the healthy regions to recognize multitarget multiclass and single-class concrete structural defects. This architecture stems from the novel GFGA mechanism as the building block to capture minute local features from visually-similar defect classes. We then propose the MSAM that encompasses multiscale discriminative information to capture variations in image properties. The MSAM incorporates BMAM to obtain crucial channel-spatial descriptors making the overall architecture an end-to-end-trainable network. Extensive experimentation and analysis on three large concrete defect datasets show the superiority of our proposed network as compared to the current state-of-the-art methodologies.

Structural Performance of Reinforced Cement Concrete Beam with Sawdust

Sawdust materials are important for several reasons. They are cheap, lightweight, and have high insulation properties. Some of this material is incorporated into the concrete as part of the cement binder phase and as gravel. Micro-cracks and defects in concrete are responsible for the low tensile strength of concrete. This study proposes the use of sawdust as a partial replacement for fine aggregate. By volume, the sawdust gradually replaced the sand with a replacement percentage that varied from 0% to 100%. Nine reinforced concrete beams with a cross-section of 90 mm × 150 mm × 1000 mm (width × depth × length) and different replacement percentages were cast and tested after 28 days. All concrete beams are supported, with two simple supports at the ends of the beam and a loading point at the center of the beam to apply load gradually using 100 kN load cells and transverse frames. The addition of sawdust results in a reduction in the flexural strength of concrete beams. The flexural reinforced concrete beam test results were compared to the design strength calculated using British Standards. According to the results of the study, both the compressive and tensile strength of concrete decreased as sawdust content increased. The weight of the sawdust concrete mixture decreased with increased sawdust content. When the replacement percentage of sand was between 5% and 20%, the sawdust concrete mixture showed good results for the structural performance of the reinforced concrete beam.

Detection of Internal Defects in Concrete and Evaluation of a Healthy Part of Concrete by Noncontact Acoustic Inspection Using Normalized Spectral Entropy and Normalized SSE.

Non-destructive testing, with non-contact from a remote location, to detect and visualize internal defects in composite materials such as a concrete is desired. Therefore, a noncontact acoustic inspection method has been studied. In this method, the measurement surface is forced to vibrate by powerful aerial sound waves from a remote sound source, and the vibration state is measured by a laser Doppler vibrometer. The distribution of acoustic feature quantities (spectral entropy and vibrational energy ratio) is analyzed to statistically identify and evaluate healthy parts of concrete. If healthy parts in the measuring plane can be identified, the other part is considered to be internal defects or an abnormal measurement point. As a result, internal defects are detected. Spectral entropy (SE) was used to distinguish between defective parts and healthy parts. Furthermore, in order to distinguish between the resonance of a laser head and the resonance of the defective part of the concrete, spatial spectral entropy (SSE) was also used. SSE is an extension of the concept of SE to a two-dimensional measuring space. That is, based on the concept of SE, SSE is calculated, at each frequency, for spatial distribution of vibration velocity spectrum in the measuring plane. However, these two entropy values were used in unnormalized expressions. Therefore, although relative evaluation within the same measurement surface was possible, there was the issue that changes in the entropy value could not be evaluated in a unified manner in measurements under different conditions and environments. Therefore, this study verified whether it is possible to perform a unified evaluation for different defective parts of concrete specimen by using normalized SE and normalized SSE. From the experimental results using cavity defects and peeling defects, the detection and visualization of internal defects in concrete can be effectively carried out by the following two analysis methods. The first is using both the normalized SE and the evaluation of a healthy part of concrete. The second is the normalized SSE analysis that detects resonance frequency band of internal defects.

Fractal Analysis of Defects in Concrete under Elevated Temperatures

Fractal Analysis of Defects in Concrete under Elevated Temperatures

DETECTING CRACKS IN CONCRETE BASED ON IMAGES USING AMAZON WEB SERVICE REKOGNITION

Concrete is the basis for many structures in architecture and infrastructure. Under the influence of external factors and load from use, this material can be destroyed. At first, microcracks may form in the concrete, which grows into larger cracks over time. Detection of such cracks can be performed with the help of information technologies. Cloud technologies are gaining popularity today. Among the largest service providers in this direction is Amazon Web Service. There are many opportunities in this cloud environment for computing using artificial intelligence. In the work, the recognition of cracks in concrete is performed using the Amazon Web Service Rekognition. The images with the concrete crack and the corroded pipe are analyzed for label matches. Based on the given test and training images with defects, cracks are recognized using Amazon Rekognition Custom Labels. The main elements of the image are identified, namely concrete and cracks. As a result, the described recognition method can be used for the automatic detection of defects in concrete. Keywords : machine learning, concrete, crack, bounding box, label, cloud technologies.

A comparison study on Australia, Eurocode, and US reinforced concrete structure repair codes

Currently, there is no local standard on reinforced concrete structures repairing in Malaysia. The aim of this study is to discuss the similarities and differences of the reinforced concrete structure repair codes of Australia, Eurocode, and United States.In the methodology and work plan stage, preliminary decision for concrete repair is made after the structural assessment. Next, repair work is conducted in relation to the general planning. Lastly, repair products applied in the system are ensured to be mutually compatible in order to accept the repair work. According to the 11 principles listed in EN 1504-9, concrete damages are classified as concrete defects and corrosion on reinforced concrete structure. SA HB 84:2018 is using the fundamental principles of EN 1504 as the main reference. Similarly, all three codes highlight the reinforcement corrosion as the primary reason of concrete damage. The main difference between ACI 546R-14 and EN 1504 is ACI 546R-14 provides no principle for all intended uses in repair works. Two case studies of reinforced concrete structure repairing for irrigation control structures and low-cost flat building are discussed. The case studies reveal a possibility of combining the strengths of a selected standards in reinforced concrete structures repair works.