Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Wang, Xiao; Lu, Hongfang; Wei, Xinjiang; Wei, Gang; Behbahani, Seyed Saleh; Iseley, Tom

doi:10.1109/access.2020.3004995

Cited by 42 publications

(23 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The path of undersea tunnels enters the seabed from the land, passes under the seabed, and moves outward to the land. Owing to this physical structure, undersea tunnels have an "U" shape [21]- [24]. Therefore, ordinary road tunnels do not have complicated longitudinal slope changes.…”

Section: Division Of Entrance and Exit Sections Of The Undersea Tunnelmentioning

confidence: 99%

“…According to Figure 4 and Figure 5, the calculation formula for the fitting curve of the visual adaptation time and illuminance difference of the driver at the entrance and exit of the undersea tunnel can be expressed as in formulas ( 22) and ( 23 denote the illumination difference at the entrance and exit sections (lux), respectively. According to these calculation formulas, the model to calculate the length of the entrance and exit sections of the undersea tunnel can be obtained, as shown in formulas (24) and (25), respectively:…”

Section: Figure5 Curve Of the Drivers' Visual Adaptation Time At The Exit Of The Undersea Tunnelmentioning

confidence: 99%

See 1 more Smart Citation

Modeling and Verification of the Length of the Entrance and Exit Sections of an Undersea Tunnel

et al. 2021

View full text Add to dashboard Cite

At present, there is no standard or research to define the specific length of the entrance and exit sections of an undersea tunnel. In combination with the unique longitudinal slope of the undersea tunnel and the change in the illumination difference, the lengths of the lane change, transition and adaptation sections of the entrance and exit sections of the undersea tunnel were theoretically deduced, and a model for the entrance and exit sections lengths was established. Considering the Qingdao Jiaozhou Bay undersea tunnel as an experimental subject, the accuracy of the model of the entrance and exit section lengths was verified using two methods. The results indicated that the lengths of the entrance and exit sections of undersea tunnels change with changes in the factors such as the illumination, vehicle speed, and slope. In the case of the Qingdao Jiaozhou Bay undersea tunnel, when the vehicle passes the undersea tunnel at a speed of 70 km/h on a sunny day, according to the studied model, the entrance and exit sections of the undersea tunnel are 146.7 m and 157.1 m long, respectively. The entrance and exit section lengths of the undersea tunnel, determined using test method 1 and test method 2 are 151.0m, 153.6m and 161.0m, 148.9m, respectively. The absolute errors between the results of the model and test method 1 and 2 are less than 10%. These findings indicate that the model for the entrance and exit section lengths of undersea tunnels is reasonably accurate.

show abstract

Section: Division Of Entrance and Exit Sections Of The Undersea Tunnelmentioning

confidence: 99%

Section: Figure5 Curve Of the Drivers' Visual Adaptation Time At The Exit Of The Undersea Tunnelmentioning

confidence: 99%

Modeling and Verification of the Length of the Entrance and Exit Sections of an Undersea Tunnel

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, some shortcomings of ANN are also revealed. The network structures and the ability to deal with problems of ANN are two manifestations of its characteristics, and the corresponding pros and cons of ANN are listed in Table 1 according to the literature [26].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Application of Artificial Neural Networks in Construction Management: Current Status and Future Directions

et al. 2021

View full text Add to dashboard Cite

Artificial neural networks (ANN) exhibit excellent performance in complex problems and have been increasingly applied in the research field of construction management (CM) over the last few decades. However, few papers draw up a systematic review to evaluate the state-of-the-art research on ANN in CM. In this paper, content analysis is performed to comprehensively analyze 112 related bibliographic records retrieved from seven selected top journals published between 2000 and 2020. The results indicate that the applications of ANN of interest in CM research have been significantly increasing since 2015. Back-propagation was the most widely used algorithm in training ANN. Integrated ANN with fuzzy logic/genetic algorithm was the most commonly employed way of addressing the CM problem. In addition, 11 application fields and 31 research topics were identified, with the primary research interests focusing on cost, performance, and safety. Lastly, challenges and future directions for ANN in CM were put forward from four main areas of input data, modeling, application fields, and emerging technologies. This paper provides a comprehensive understanding of the application of ANN in CM research and useful reference for the future.

show abstract

“…Research on the application of deep learning technology to tunnel quality inspection [16] has gradually increased in recent years, but most of the studies are on the surface of tunnels or highways, and there are relatively few quality inspections on the interior of tunnel linings [17]. During the construction and operation of the tunnel, various defects will appear inside the lining.…”

Section: Introductionmentioning

confidence: 99%

Recognition Method of Tunnel Lining Defects Based on Deep Learning

Жу

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The defect identification of tunnel lining is a task with a lot of tasks and time-consuming work, and currently, it mainly relies on manual operation. This paper takes the ground-penetrating radar image of the internal defects of the lining as the research object, and chooses the popular VGG16, ResNet34 convolutional neural network (CNN) to build the automatic recognition model for comparative study, and proposes an improved ResNet34 defect-recognition model. In this paper, SGD and Adam training algorithms are used to update network parameters, and the PyTorch depth framework is used to train the network. The test results show that the ResNet34 network has faster convergence speed, higher accuracy rate, and shorter training time than the VGG16 network. The ResNet34 network using the Adam algorithm can achieve 99.08% accuracy. The improved ResNet34 network can achieve an accuracy of 99.25%, and at the same, reduce the parameter amount by 4.22% compared with the ResNet34 network, which can better identify defects in the lining. The research in this paper shows that the deep learning method can provide new ideas for the identification of tunnel lining defects.

show abstract

Application of Artificial Neural Network in Tunnel Engineering: A Systematic Review

Cited by 42 publications

References 84 publications

Modeling and Verification of the Length of the Entrance and Exit Sections of an Undersea Tunnel

Modeling and Verification of the Length of the Entrance and Exit Sections of an Undersea Tunnel

Application of Artificial Neural Networks in Construction Management: Current Status and Future Directions

Recognition Method of Tunnel Lining Defects Based on Deep Learning

Contact Info

Product

Resources

About