2021
DOI: 10.3390/app112110264
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of Shield Machine Attitude Based on Various Artificial Intelligence Technologies

Abstract: The shield machine attitude (SMA) is the most important parameter in the process of tunnel construction. To prevent the shield machine from deviating from the design axis (DTA) of the tunnel, it is of great significance to accurately predict the dynamic characteristics of SMA. We establish eight SMA prediction models based on the data of five earth pressure balance (EPB) shield machines. The algorithms adopted in the models are four machine learning (ML) algorithms (KNN, SVR, RF, AdaBoost) and four deep learni… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 31 publications
(9 citation statements)
references
References 56 publications
0
9
0
Order By: Relevance
“…Kong Xiangxun [12] proposed a prediction method based on random forest and selected geological conditions and shield operation data as features to establish a prediction model to achieve thrust prediction. Xiao Haohan [13] established eight simple moving average (SMA) prediction models K-nearest neighbors (KNN), Support vector regression (SVR), Random Forest (RF), Adaptive Boosting (AdaBoost), Backpropagation Neural Network (BPNN), CNN, LSTM, and GRU for comparison, and indirectly realized thrust prediction. At present, predictive control is also widely used in ground settlement and possible risks during shield machine construction [14][15][16][17][18].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Kong Xiangxun [12] proposed a prediction method based on random forest and selected geological conditions and shield operation data as features to establish a prediction model to achieve thrust prediction. Xiao Haohan [13] established eight simple moving average (SMA) prediction models K-nearest neighbors (KNN), Support vector regression (SVR), Random Forest (RF), Adaptive Boosting (AdaBoost), Backpropagation Neural Network (BPNN), CNN, LSTM, and GRU for comparison, and indirectly realized thrust prediction. At present, predictive control is also widely used in ground settlement and possible risks during shield machine construction [14][15][16][17][18].…”
Section: Introductionmentioning
confidence: 99%
“…The prediction models built by the above methods can all give the prediction parameters for the next moment, but they are based on a large amount of data-driven, which leads to a long training time for the model due to a large amount of data and does not satisfy the requirement of real-time prediction. In addition, the structure and input characteristics of the thrust prediction model in the literature [12,13]are relatively simple and do not consider the input of other relevant tunneling parameters.…”
Section: Introductionmentioning
confidence: 99%
“…To ensure the advance in accordance with the established route and control the deformation of tunnel excavation, it is important to adjust the shield attitude in time 1 . The control of shield propulsion attitude should be paid more attention to 2 . The unreasonable control of shield attitude may seriously affect the safety and quality of tunnel construction 3 .…”
Section: Introductionmentioning
confidence: 99%
“…Therefore, many scholars have conducted research on TBMAP prediction. Xiao et al [16] established eight prediction models of shield machine attitude based on the data from five earth pressure balance shield machines and obtained two best algorithms, the LSTM and GRU with EVS > 0.9 and RMSE < 1.5. Fu et al [17] proposed the deep learning model with a graph convolutional network and long short-term memory, which can predict the vertical and horizontal deviations at the articulation and tail of TBM with high accuracy.…”
Section: Introductionmentioning
confidence: 99%