Figure 6 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
This paper proposes a novel pavement transverse crack detection model based on time–frequency analysis and convolutional neural networks. The accelerometer and smartphone installed in the vehicle collect the vibration response between the wheel and the road, such as pavement transverse cracks, manholes, and normal pavement. Since the original vibra...
Contexts in source publication
Context 1
... are differences in their measurement sensitivity and acquisition stability as well as sampling frequency depending on the type of accelerometer. Figure 6 shows samples data from three smartphone sensors and a professional sensor, which is to verify that the same feature spectrum can be obtained after the Time-frequency analysis even though there are differences in acquisition accuracy and range between different sensors. The placement of three mobile phones are approximately the same location on the seats during the experiment, but the sensitivity of the sampling is not same due to different data collection frequency. ...
Context 2
... placement of three mobile phones are approximately the same location on the seats during the experiment, but the sensitivity of the sampling is not same due to different data collection frequency. The amplitude of the different sensors is not the same as shown in Figure 6 when the vehicle passed on the same crack, and hence the vibration signal is not able to distinguish simply different types of signals. In contrast, the signal coherence and the sensitivity of the professional sensor is better. ...
Similar publications
Power Quality is the Major Concern in modern Electrical Distribution System. Supplying Un Interrupted Power to the customers is the first priority of distribution companies. In recent days, raise of un balanced loads the voltage levels are deviated, further causing many power quality issues. There is a constant need of monitoring the voltage, curre...
Partial Discharge (PD) signal denoising is very significant in analyzing its characteristics and its effect on high voltage insulation equipments. Mainly, the PD information is lost in the presence of various noises. The wavelet transform provides a better platform for PD signal pre and post processing. The wavelet adaptive thresholding denoising t...
Citations
... Tran and Roesler (2022) conducted a study to detect concrete joints in road pavements with shear wave transmission energy [5]. used an accelerometer to automatically detect transverse cracks in road pavements through a WT-CNN [6]. Damage detection of road pavements using various sensors can accurately detect damage, but there is a limit in its application to city or country locations. ...
It is important to maintain the safety of road driving by automatically performing a series of processes to automatically measure and repair damage to the road pavement. However, road pavements include not only damages such as longitudinal cracks, transverse cracks, alligator cracks, and potholes, but also various elements such as manholes, road marks, oil marks, shadows, and joints. Therefore, in order to separate categories that exist in various road pavements, in this paper, 13,500 digital, IR, and MSX images were collected and nine categories were automatically classified by DarkNet. The DarkNet classification accuracies of digital images, IR images, and MSX images are 97.4%, 80.1%, and 91.1%, respectively. The MSX image is a enhanced image of the IR image and showed an average of 6% lower accuracy than the digital image but an average of 11% higher accuracy than the IR image. Therefore, MSX images can play a complementary role if DarkNet classification is performed together with digital images. In this paper, a method for detecting the directionality of each crack through a two-dimensional wavelet transform is presented, and this result can contribute to future research on detecting cracks in pavements.
... In a similar vein, a study conducted in 2021 by researchers [2] reported a remarkable accuracy of 97.20% using a CNN-based approach. Their research focused on addressing one of the challenges in crack detectionlighting variations. ...
... (5) The training was terminated, and the test set was fed into the optimal model for testing. (6) The test results were the output. ...
Accurately extracting faulty sound signals from belt conveyor rollers within the high-noise environment of coal mine operations presents a formidable challenge. To address this issue, this study introduces an innovative fault diagnosis method that merges the variational modal de-composition (VMD) model with the Swin Transformer deep learning network model. First, the study employed the adaptive VMD method to eliminate intense noise from the original signal of the rollers, while also assessing the reconstruction accuracy of the VMD signal across different modal components. Subsequently, we delved into the impact of the parameter structure of the Swin Transformer network model on the fault diagnosis accuracy. Finally, the accuracy of the method was validated using a sound test dataset from the rollers. The results indicated that optimizing the K-value of the VMD method effectively reduced the noise in the reconstructed signal, and the Swin Transformer excelled in extracting both local and global features. Specifically, on the conveyor roller sound dataset, it was shown that, after the VMD reconstruction of the signal so that the highest Pearson correlation coefficient corresponded to a modal component of 3 and adjusting the parameters of the Swin Transformer coding layer, the combination of the VMD+Swin-S model achieved an accuracy of 99.36%, while the VMD+Swin-T model achieved an accuracy of 98.6%. Meanwhile, the accuracy of the VMD+Swin-S model was higher than that of the VMD + CNN model combination, with 95.4% accuracy, and the VMD+ViT model, with 97.68% accuracy. In the example application experiments, compared with other models the VMD+Swin-S model achieved the highest accuracy rate at all three speeds, with 98.67%, 98.32%, and 97.65%, respectively. Overall, this approach demonstrated high accuracy and robustness, rendering it an optimal choice for diagnosing conveyor belt roller faults within environments characterized by strong noise.
... This results in the local spectrum across a brief time window. The final transformation generates a two-dimensional function about time and frequency domains [23]. ...
Transverse cracking is thought of as the typical distress of asphalt pavements. A faster detection technique can provide pavement performance information for maintenance administrations. This paper proposes a novel vehicle-vibration-based method for transverse cracking detection. A theoretical model of a vehicle-cracked pavement vibration system was constructed using the d’Alembert principle. A testing system installed with a vibration sensor was put in and applied to a testing road. Then, parameter optimization of the Short-time Fourier transform (STFT) was conducted. Transverse cracking and normal sections were processed by the optimized STFT algorithm, generating two ideal indicators. The maximum power spectral density and the relative power spectral density, which were extracted from 3D time–frequency maps, performed well. It was found that the power spectral density caused by transverse cracks was above 100 dB/Hz. The power spectral density at normal sections was below 80 dB/Hz. The distribution of the power spectral density for the cracked sections is more discrete than for normal sections. The classification model based on the above two indicators had an accuracy, true positive rate, and false positive rate of 94.96%, 92.86%, and 4.80%, respectively. The proposed vehicle-vibration-based method is capable of accurately detecting pavement transverse cracking.
... The proposed method incorporated the connectivity of pixels for automatic pavement crack detection, for which the convolutional layers of the deep neural network were densely connected in a feed-forward manner to reuse features from multiple layers, and transposed convolution layers were considered for multiple level feature fusion. The other research studies on road damage/defect detection based on smartphone-captured images and different deep neural networks can be found in [187][188][189][190][191][192][193]. ...
Sensing is a critical and inevitable sector of structural health monitoring (SHM). Recently, smartphone sensing technology has become an emerging, affordable, and effective system for SHM and other engineering fields. This is because a modern smartphone is equipped with various built-in sensors and technologies, especially a triaxial accelerometer, gyroscope, global positioning system, high-resolution cameras, and wireless data communications under the internet-of-things paradigm, which are suitable for vibration- and vision-based SHM applications. This article presents a state-of-the-art review on recent research progress of smartphone-based SHM. Although there are some short reviews on this topic, the major contribution of this article is to exclusively present a comprehensive survey of recent practices of smartphone sensors to health monitoring of civil structures from the perspectives of measurement techniques, third-party apps developed in Android and iOS, and various application domains. Findings of this article provide thorough understanding of the main ideas and recent SHM studies on smartphone sensing technology.
... Cui (2021) proposed digital intangible cultural heritage management (DLICHM) using a deep-learning algorithm to analyse damaged images and image reconstruction [22]. This deep-learning algorithm for automatic damage detection has been applied not only to heritage buildings but also to other infrastructures [23][24][25]. To detect each damage, deep-learning algorithms and machine-learning algorithms, including CNN algorithms, are used [26,27]. ...
In the era of the first Industrial Revolution, many buildings were built with red bricks, and the heritage buildings built at that time are more than 100 years old. In these old heritage buildings, damage is bound to occur due to chemical and physical effects. Technologies such as automatic damage detection can effectively manage damage, but they can be affected by other categories present in heritage buildings. Therefore, this paper proposes a CNN algorithm that can automatically detect cracks and damage that occur in heritage buildings, as well as multi-label classification, such as doors, windows, arches, artwork, brick walls, stonewalls, and vents. A total of 2400 thermal infrared images are collected for 8 categories and automatic classification was performed using the CNN algorithm. The average precision and average sensitivity for the eight categories of heritage buildings are 97.72% and 97.43%, respectively. This paper defines the causes of misclassification as the following two causes: misclassification by multiple objects and misclassification by the perception of the CNN algorithm.
... Deep learning is becoming one of the most advanced pixel-level target segmentation methods in road condition inspection, as it learns from large-scale data and requires little human involvement during training. Convolutional Neural Network (CNN), a deep learning method, has been gradually utilized in road crack detection and segmentation [11], [12]. For example, Bang et al. [13] used ResNet-152 to classify cracks and the outcome resulted in a precision of 0.78 and recall of 0.72. ...
Pavement crack segmentation using deep learning methods can improve crack segmentation accuracy, but in many cases the training dataset is lacking or uneven, making it insufficient to train an accurate segmentation model. In this work, an integrated APC-GAN and AttuNet framework is proposed as an automated pavement surface crack pixel-level segmentation solution for small training datasets. First, an Automated Pavement Crack Generative Adversarial Network (APC-GAN) is designed for the pavement cracks data as an image augmentation method, which is modified and improved from a traditional Deep Convolutional Generative Adversarial Network (DCGAN). Then, a novel pixel-level semantic segmentation structure, Attention modified U-Net (AttuNet), is proposed by introducing the attention module into the convolutional network structure. In order to assess the performance of our proposed framework, an open-source dataset DeepCrack is used, which only contains 300 training images. The results show that our proposed APC-GAN could augment the datasets by producing more clear and distinct pavement images than DCGAN and the generated images could feature more diversity than traditional image augmentation methods. APC-GAN demonstrated higher accuracy than DCGAN and traditional image augmentation methods. Apparently, our proposed APC-GAN and AttuNet framework gains the highest value in the evaluation metrices, including recall, F1 score, mean Intersection over Union (mIoU) and mean Pixel Accuracy (mPA) among all models including U-Net, DeepLabv3, FCN, and LRASPP.
... But due to the various forms and complex causes of damage, it is difficult to determine the quantitative description of damage conditions. Therefore, how to objectively and scientifically describe the pavement damage condition and how to adopt the detection and evaluation methods to take into account the accuracy of the evaluation results and the simplicity of data collection have become common problems to be solved [8][9][10][11]. ...
Pavement will inevitably be damaged in the process of use; pavement damage detection and assessment are an important part of maintenance management. In order to prevent road diseases, it is necessary to fix the road cracks and implement automatic road crack inspection and monitoring. In this paper, the automatic identification of road cracks is realized by constructing the Mask R-CNN model. The labeled area can be segmented by pixels and positioned at the original data by integrating the image data used for training and the labeled data into a network model. The effect of the training model can be improved by increasing the number of data sets, the pixel of the fracture image, the background of the fracture, and the marking method of the fracture type. The validity and accuracy of the test results were characterized by RPN bounding-box loss, classification loss, mask loss, and total loss.
... In addition, neural networks have begun to be used for image denoising. Liu, F. et al. [11,12] used a method based on wavelet transform and deep networks image classification to improve the classification accuracy of topographic images. Singh, A. [13] used a backpropagation algorithm for training in MLP-ANN to achieve good denoising of images without prior knowledge of the degradation model. ...
Photographing images is used as a common detection tool during the process of bridge maintenance. The edges in an image can provide a lot of valuable information, but the detection and extraction of edge details are often affected by the image noise. This study proposes an algorithm for wavelet transform to denoise the image before edge detection, which can improve the signal-to-noise ratio of the image and retain as much edge information as possible. In this study, four wavelet functions and four decomposition levels are used to decompose the image, filter the coefficients and reconstruct the image. The PSNR and MSE of the denoised images were compared, and the results showed that the sym5 wavelet function with three-level decomposition has the best overall denoising performance, in which the PSNR and MSE of the denoised images were 23.48 dB and 299.49, respectively. In this study, the canny algorithm was used to detect the edges of the images, and the detection results visually demonstrate the difference between before and after denoising. In order to further evaluate the denoising performance, this study also performed edge detection on images processed by both wavelet transform and the current widely used Gaussian filter, and it calculated the Pratt quality factor of the edge detection results, which were 0.53 and 0.47, respectively. This indicates that the use of wavelet transform to remove noise is more beneficial to the improvement of the subsequent edge detection results.
... A basic CNN architecture includes a convolutional layer, a pooling layer, and a fully connected layer [9,10,12,13]. CNN performs as an encoder to capture significant Fig. 8 Basic LSTM cells Fig. 9 The architecture of the LSTM Acta Geotechnica characteristics, enabling it to discriminate without requiring complicated rules. The objective of the convolution process is to extract the distinguishing characteristics of the input data. ...
... and DL model Figures 12,13,14 and 15 demonstrate the recording of the TPE hyperparameter tuning process for the typical ML models, ensemble ML models, boosting-based ML models and DL models, respectively, where the scatter points were the test accuracy with each different input hyperparameter, and the 'best accuracy' indicated the optimal accuracy of the current trial. As the trials updated, the color of the scattered points changed from gray to black. ...
In this paper, field construction data from the Singapore Metro Line project were used to study the mapping relationship and establish the prediction model between TBM operation data and the ground condition ahead of the excavation face. The study presents a multi-classifier competition mechanism to construct ten separate classifiers, including logistic regression, support vector machine, random forest, extremely randomized trees, adaptive boosting machine, extreme gradient boosting (Xgboost), light gradient boosting (LightGBM), categorical boosting, long short-term memory and convolutional neural network. The acquired data were used to select 28 key TBM operating parameters by a correlation-based feature selection method, and the selected parameters in the stabilization phase after removing the outliers were calculated as the input to the classifier, and a relatively balanced training set was obtained by the synthetic minority oversampling technique. The hyperparameters of each classifier were optimized using tree Parzen estimator Bayesian optimization. The prediction results show that LightGBM presents the best results among ten different machine and deep learning algorithms with an accuracy of 96.22%, precision of 96.94%, recall of 97.33% and F1-score of 97.33%. In addition, the effect of the input parameters of the LightGBM model on the prediction accuracy of the model was analyzed using Shapley additive explanations, and the effect of sample imbalance on the prediction performance was discussed.
