Evaluation of Damage Level for Ground Settlement Using the Convolutional Neural Network

Park, Sung-Sik; Tran, Van-Than; Doan, Nhat-Phi; Hwang, Keum-Bee

doi:10.1007/978-981-16-7160-9_128

Cited by 10 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning (DL) has in recent years gained significant traction in numerous domains for performing complex tasks, including computer vision, and speech recognition, natural language processing, and machine translation. It has outperformed traditional methods in some applications such as image classification [17][18][19][20], object detection [21][22][23], image segmentation [24,25], and time series forecasting [26][27][28]. DL is a data-driven approach that uses mathematical functions to map the examples of the input to that of the output without any manual intervention.…”

Section: Introductionmentioning

confidence: 99%

Investigation of crack segmentation and fast evaluation of crack propagation, based on deep learning

Tran,

Nguyen-Xuan,

Zhuang

2024

Front. Struct. Civ. Eng.

View full text Add to dashboard Cite

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering structures. Most traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing time. To address this issue, we explore the potential of deep learning (DL) to increase the efficiency of crack detection and forecasting crack growth. However, there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks vary. In the paper, we present DL models for identifying cracks, especially on concrete surface images, and for predicting crack propagation. Firstly, SegNet and U-Net networks are used to identify concrete cracks. Stochastic gradient descent (SGD) and adaptive moment estimation (Adam) algorithms are applied to minimize loss function during iterations. Secondly, time series algorithms including gated recurrent unit (GRU) and long short-term memory (LSTM) are used to predict crack propagation. The experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding results. For evaluation of crack propagation, GRU and LSTM are used as DL models and results show good agreement with the experimental data.

show abstract