A cable tension identification technology using percussion sound

Qingzhao Kong,Guowei Wang,Wensheng Lu,Cheng Yuan 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.3

The loss of cable tension for civil infrastructure reduces structural bearing capacity and causes harmful deformation of structures. Currently, most of the structural health monitoring (SHM) approaches for cables rely on contact transducers. This paper proposes a cable tension identification technology using percussion sound, which provides a fast determination of steel cable tension without physical contact between cables and sensors. Notably, inspired by the concept of tensioning strings for piano tuning, this proposed technology predicts cable tension value by deep learning assisted classification of "percussion" sound from tapping a steel cable. To simulate the non-linear mapping of human ears to sound and to better quantify the minor changes in the high-frequency bands of the sound spectrum generated by percussions, Mel-frequency cepstral coefficients (MFCCs) were extracted as acoustic features to train the deep learning network. A convolutional neural network (CNN) with four convolutional layers and two global pooling layers was employed to identify the cable tension in a certain designed range. Moreover, theoretical and finite element methods (FEM) were conducted to prove the feasibility of the proposed technology. Finally, the identification performance of the proposed technology was experimentally investigated. Overall, results show that the proposed percussion-based technology has great potentials for estimating cable tension for <i>in-situ</i> structural safety assessment.

Monitoring moisture content of timber structures using PZT-enabled sensing and machine learning

Qingzhao Kong,Lin Chen,Hai-Bei Xiong,Yufeng He,Xiuquan Li 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.4

Timber structures are susceptible to structural damages caused by variations in moisture content (MC), inducing severe durability deterioration and safety issues. Therefore, it is of great significance to detect MC levels in timber structures. Compared to current methods for timber MC detection, which are time-consuming and require bulky equipment deployment, Lead Zirconate Titanate (PZT)-enabled stress wave sensing combined with statistic machine learning classification proposed in this paper show the advantage of the portable device and ease of operation. First, stress wave signals from different MC cases are excited and received by PZT sensors through active sensing. Subsequently, two non-baseline features are extracted from these stress wave signals. Finally, these features are fed to a statistic machine learning classifier (i.e., naive Bayesian classification) to achieve MC detection of timber structures. Numerical simulations validate the feasibility of PZT-enabled sensing to perceive MC variations. Tests referring to five MC cases are conducted to verify the effectiveness of the proposed method. Results present high accuracy for timber MC detection, showing a great potential to conduct rapid and long-term monitoring of the MC level of timber structures in future field applications.

Grouting compactness monitoring of concrete-filled steel tube arch bridge model using piezoceramic-based transducers

Feng, Qian,Kong, Qingzhao,Tan, Jie,Song, Gangbing Techno-Press 2017 Smart Structures and Systems, An International Jou Vol.20 No.2

The load-carrying capacity and structural behavior of concrete-filled steel tube (CFST) structures is highly influenced by the grouting compactness in the steel tube. Due to the invisibility of the grout in the steel tube, monitoring of the grouting progress in such a structure is still a challenge. This paper develops an active sensing approach with combined piezoceramic-based smart aggregates (SA) and piezoceramic patches to monitor the grouting compactness of CFST bridge structure. A small-scale steel specimen was designed and fabricated to simulate CFST bridge structure in this research. Before casting, four SAs and two piezoceramic patches were installed in the pre-determined locations of the specimen. In the active sensing approach, selected SAs were utilized as actuators to generate designed stress waves, which were detected by other SAs or piezoceramic patch sensors. Since concrete functions as a wave conduit, the stress wave response can be only detected when the wave path between the actuator and the sensor is filled with concrete. For the sake of monitoring the grouting progress, the steel tube specimen was grouted in four stages, and each stage held three days for cement drying. Experimental results show that the received sensor signals in time domain clearly indicate the change of the signal amplitude before and after the wave path is filled with concrete. Further, a wavelet packet-based energy index matrix (WPEIM) was developed to compute signal energy of the received signals. The computed signal energies of the sensors shown in the WPEIM demonstrate the feasibility of the proposed method in the monitoring of the grouting progress.

A deep learning-based vision enhancement method for UAV assisted visual inspection of concrete cracks

Yanzhi Qi,Cheng Yuan,Qingzhao Kong,Bing Xiong,Peizhen Li 국제구조공학회 2021 Smart Structures and Systems, An International Jou Vol.27 No.6

Implementing unmanned aerial vehicles (UAVs) on concrete surface-crack inspection leads to a promising visual crack detection approach. One of the challenges for automated field visual cracking inspection is image degradation caused by the rain or fog and motion blur during data acquisition. The present study combines two deep neural networks to address the image degradation problem. By using the Variance of Laplacian algorithm for quantifying image clarity, the proposed deep neural networks can remarkably enhance the sharpness of the degraded images. After vision enhancement process, Mask Region Convolutional Neutral Network (Mask R-CNN) was developed to perform automated crack identification and segmentation. Results show a 8~13% enhancement in prediction accuracy compared to the degraded images, indicating that the proposed deep learning-based vision enhancement method can effectivey identify and segment concrete surface cracks from photos captured by UAVs.

Damage monitoring of variable cross-section region in a column-drilled shaft assembly using smart aggregates

Jie Tan,Mahadi Masud,Xiaoming Qin,Cheng Yuan,Qingzhao Kong,Y.L.Mo 국제구조공학회 2021 Smart Structures and Systems, An International Jou Vol.28 No.5

Pier column, as the most critical load-bearing member of bridge, can bear multiple loads including axial forces,shear forces, bending moments, etc. The varied cross section at the column interface and bearing platform or drilled shaft leads to harmful stress concentration that can potentially compromise the structural integrity. In order to improve the ductility of bridge structure, a pier column is often designed with a variable cross-section region to dissipate energy through plastic deformation. For better understanding the health condition of pier column in its service life, it is of great significance to obtain the damage severity information in the variable cross-section region. This study utilizes an active sensing method enabled by distributed Lead Zirconate Titanate (PZT)-based Smart Aggregate (SA) sensors to monitor the damage initiation and development near the bottom of a pier column. Crack damage in variable cross-section region functions as a stress relief that attenuates propagating stress wave energy between SA pairs. Both the numerical and experimental results show that the reduction ratio of the stress wave energy is consistent with the crack development, thus validating the reliability of the investigated approach. SA-based technology can be used as a potential tool to provide early warning of damage in variable cross-section region of bridge structures.

A three-stage deep-learning-based method for crack detection of high-resolution steel box girder image

Ying Zhou,Shiqiao Meng,Zhiyuan Gao,Bin He,Qingzhao Kong 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted highresolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The <i>Recall</i> reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The <i>IoU</i> of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The <i>IoU</i> of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the <i>IoU</i> by 2.9%. In general, our method is of great significance for crack detection.