Zhong Qu^1,*, Guoqing Mu¹, Bin Yuan²

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 255-273, 2024, DOI:10.32604/cmes.2024.048175 - 16 April 2024

Abstract Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning, with convolutional neural networks (CNN) playing an important role in this field. However, as the performance of crack detection in cement pavement improves, the depth and width of the network structure are significantly increased, which necessitates more computing power and storage space. This limitation hampers the practical implementation of crack detection models on various platforms, particularly portable devices like small mobile devices. To solve these problems, we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature… More > Graphic Abstract

Shan Xu^1,*, Huadu Tang¹, Ding Wang¹, Ruiguang Zhu¹, Liwei Wang¹, Shengwang Hao¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.27, No.4, pp. 1-3, 2023, DOI:10.32604/icces.2023.09930

Abstract Damage evaluation is an important index for the evaluation of buildings health. To provide a rapid crack evaluation in practical applications, a crack identification and damage evaluation via deep learning framework is proposed in this paper. We built a combined dataset from Kaggle and site photos. A pre-trained U-net model is used to perform the training of model. With updated weights, the identification of cracks could be performed on non-labelled photos. More >

Shorouq Alshawabkeh, Li Wu^*, Daojun Dong, Yao Cheng, Liping Li, Mohammad Alanaqreh

CMC-Computers, Materials & Continua, Vol.77, No.1, pp. 63-77, 2023, DOI:10.32604/cmc.2023.042183 - 31 October 2023

Abstract Pavement crack detection plays a crucial role in ensuring road safety and reducing maintenance expenses. Recent advancements in deep learning (DL) techniques have shown promising results in detecting pavement cracks; however, the selection of relevant features for classification remains challenging. In this study, we propose a new approach for pavement crack detection that integrates deep learning for feature extraction, the whale optimization algorithm (WOA) for feature selection, and random forest (RF) for classification. The performance of the models was evaluated using accuracy, recall, precision, F1 score, and area under the receiver operating characteristic curve (AUC).… More >

Wenyang Tang^1,2, Cong Liu^1,*, Bo Zhang²

Energy Engineering, Vol.120, No.11, pp. 2667-2681, 2023, DOI:10.32604/ee.2023.040743 - 31 October 2023

Abstract Harsh working environments and wear between blades and other unit components can easily lead to cracks and damage on wind turbine blades. The cracks on the blades can endanger the shafting of the generator set, the tower and other components, and even cause the tower to collapse. To achieve high-precision wind blade crack detection, this paper proposes a crack fault-detection strategy that integrates Gated Residual Network (GRN), a fusion module and Transformer. Firstly, GRN can reduce unnecessary noisy inputs that could negatively impact performance while preserving the integrity of feature information. In addition, to gain… More >

Yalong Yang^1,2,3, Wenjing Xu^1,2,3, Yinfeng Zhu⁴, Liangliang Su^1,2,3,*, Gongquan Zhang^1,2,3

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.1, pp. 761-773, 2023, DOI:10.32604/cmes.2023.027010 - 23 April 2023

Abstract As a current popular method, intelligent detection of cracks is of great significance to road safety, so deep learning has gradually attracted attention in the field of crack image detection. The nonlinear structure, low contrast and discontinuity of cracks bring great challenges to existing crack detection methods based on deep learning. Therefore, an end-to-end deep convolutional neural network (AttentionCrack) is proposed for automatic crack detection to overcome the inaccuracy of boundary location between crack and non-crack pixels. The AttentionCrack network is built on U-Net based encoder-decoder architecture, and an attention mechanism is incorporated into the… More >

Hong-Hu Chu¹, Muhammad Rizwan Saeed², Javed Rashid^3,4,*, Muhammad Tahir Mehmood⁵, Israr Ahmad⁶, Rao Sohail Iqbal⁴, Ghulam Ali¹

CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 1863-1881, 2023, DOI:10.32604/cmc.2023.035287 - 06 February 2023

Abstract The increasing global population at a rapid pace makes road traffic dense; managing such massive traffic is challenging. In developing countries like Pakistan, road traffic accidents (RTA) have the highest mortality percentage among other Asian countries. The main reasons for RTAs are road cracks and potholes. Understanding the need for an automated system for the detection of cracks and potholes, this study proposes a decision support system (DSS) for an autonomous road information system for smart city development with the use of deep learning. The proposed DSS works in layers where initially the image of… More >

M. J. Anitha^1,*, R. Hemalatha²

Computer Systems Science and Engineering, Vol.46, No.1, pp. 1183-1200, 2023, DOI:10.32604/csse.2023.031888 - 20 January 2023

Abstract Detection of cracks at the early stage is considered as very constructive since precautionary steps need to be taken to avoid the damage to the civil structures. Moreover, identifying and classifying the severity level of cracks is inevitable in order to find the stability of buildings. Hence, this paper proposes an efficient strategy to classify the cracks into fine, medium, and thick using a novel bilayer crack detection algorithm. The bilayer crack detection algorithm helps in extracting the requisite features from the crack for efficient classification. The proposed algorithm works well in the dark background… More >

Jianwei Yuan¹, Xinli Song^1,*, Huaijian Pu², Zhixiong Zheng³, Ziyang Niu³

CMC-Computers, Materials & Continua, Vol.74, No.3, pp. 6485-6503, 2023, DOI:10.32604/cmc.2023.035165 - 28 December 2022

Abstract Regular inspection of bridge cracks is crucial to bridge maintenance and repair. The traditional manual crack detection methods are time-consuming, dangerous and subjective. At the same time, for the existing mainstream vision-based automatic crack detection algorithms, it is challenging to detect fine cracks and balance the detection accuracy and speed. Therefore, this paper proposes a new bridge crack segmentation method based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+ network framework. First, the improved lightweight MobileNet-v2 network and dilated separable convolution are integrated into the original DeeplabV3+ network to improve… More >

R. Saveeth^1,*, S. Uma Maheswari²

Intelligent Automation & Soft Computing, Vol.34, No.2, pp. 983-1000, 2022, DOI:10.32604/iasc.2022.023455 - 03 May 2022

Abstract In the aerospace industry, composite materials are becoming more common. The presence of a crack in an aircraft makes it weaker and more dangerous, and it can lead to complete fracture and catastrophic failure. To predict the position and depth of a crack, various methods have been developed. For aircraft repair, crack diagnosis is extremely important. Even then, due to uncertainties arising from sources such as environmental conditions, packing, and intrinsic material property changes, accurate diagnosis in real engineering applications remains a challenge. Deep learning (DL) approaches have demonstrated powerful recognition potential in a variety… More >

Honggeun Ji^1,2, Jina Kim³, Syjung Hwang⁴, Eunil Park^1,4,*

Intelligent Automation & Soft Computing, Vol.34, No.1, pp. 593-607, 2022, DOI:10.32604/iasc.2022.024405 - 15 April 2022

Abstract Cracks affect the robustness and adaptability of various infrastructures, including buildings, bridge piers, pavement, and pipelines. Therefore, the robustness and the reliability of automated crack detection are essential. In this study, we conducted image segmentation using various crack datasets by applying the advanced architecture of U-Net. First, we collected and integrated crack datasets from prior studies, including the cracks in buildings and pavements. For effective localization and detection of cracks, we used U-Net-based neural networks, ResU-Net, VGGU-Net, and EfficientU-Net. The models were evaluated by the five-fold cross-validation using several evaluation metrics including mean pixel accuracy… More >