Shield machine position prediction and anomaly detection during tunnelling in loess region using ensemble and deep learning algorithms

Bai, Xuedong; Cheng, Wen-Chieh; Wu, Bin; Li, Ge; Ong, Danny

doi:10.1007/s11440-023-01902-8

Cited by 9 publications

(1 citation statement)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The establishment of the multi-step intelligent predictive model of shield position is conducive to providing technical guidance for shield drivers to eliminate the interference of unfavorable experiences and make accurate control operations in time. It can effectively prevent the shield machine from deviating from the designed tunnel axis and ensure the safety and efficiency of the construction process [3,4].…”

Section: Introductionmentioning

confidence: 99%

Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU

Liu,

Zhang,

Mengting

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Realizing automatic control of shield machine tunneling attitude is a challenging problem. Realizing multi-step intelligent prediction for attitude and position is an important prerequisite for solving this problem in the tunneling process with complex and varied geological environments. In this paper, a multi-step intelligent predictive scheme based on beluga whale optimization-convolutional neural network-Long Short-term memory-gated recurrent unit (BWO-CNN-LSTM-GRU) is proposed for shield machine position attitude. First, Pearson correlation analysis is utilized to determine the input feature variables from the construction data and temporalize the input features. Subsequently, CNN-LSTM-GRU predictive models are established for the six positional parameters, separately. Among them, CNN performs feature extraction on the input variables, and LSTM-GRU realizes the predictions for the target positional parameters. In the end, the optimization of the convolutional layer dimension, the number of convolutional layers, iterations, the learning rate, the number of neurons in the LSTM layer and GRU layer of each position predictive model is performed on the basis of BWO, separately, and the best hyperparameters found are built into a BWO-CNN-LSTM-GRU position predictive model, which realizes the multi-step intelligent predictions for the shield machine’s position. The proposed approach is examined by utilizing the Beijing Metro Line 10. The results show that the predictive deviation of the position predictive model is within 3 mm, and the positional trajectory points obtained on the basis of the predicted values and the 3D coordinate system are highly coincident with the actual trajectory points. Therefore, the approach provides a more accurate predictive result for shield attitude and position and can provide a decision-making scheme for further realizing the coordinated autonomous control of shield machine.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU

Liu,

Zhang,

Mengting

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Biopolymer-assisted enzyme-induced carbonate precipitation for immobilizing Cu ions in aqueous solution and loess

Xie,

Cheng,

Wang

et al. 2023

Environ Sci Pollut Res

Self Cite

View full text Add to dashboard Cite

Wastewater, discharged in copper (Cu) mining and smelting, usually contains a large amount of Cu 2+ .Immobilizing Cu 2+ in aqueous solution and soils is deemed crucial in preventing its migration into surrounding environments. In recent years, the enzyme-induced carbonate precipitation (EICP) has been widely applied to Cu immobilization. However, the effect of Cu 2+ toxicity denatures and even inactivates the urease. In the present work, the biopolymer-assisted EICP technology was proposed. The inherent mechanism affecting Cu immobilization was explored through a series of test tube experiments and soil column tests. Results indicated that 4 g/L chitosan may not correspond to a higher immobilization e ciency because it depends as well on surrounding pH conditions. The use of Ca 2+ not only prevented the nucleation of the urease with Cu 2+ by the electrostatic repulsion but reduced the potential for Cu 2+ to migrate into nearby environments when malachite and azurite minerals are wrapped by calcite minerals. The species of carbonate precipitation that are recognized in the numerical simulation supported the above claim. On the other hand, UC1 (urease and chitosan colloid) and UC2 (urea and calcium source) grouting reduced the effect of Cu 2+ toxicity by transforming the exchangeable state-Cu into the carbonate combination state-Cu. The side effect, induced by 4 g/L chitosan, promoted the copper-ammonia complex formation in the shallow ground, while the acidic environments in the deep ground prevented Cu 2+ from coordinating with soil minerals. These badly degraded the immobilization e ciency. The Raman spectroscopy and XRD test results tallied with the above results. The ndings shed light on the potential of applying the biopolymer-assisted EICP technology to Cu-contaminated water bodies and sites remediation.

show abstract

Applying the first microcapsule-based self-healing microbial-induced calcium carbonate materials to prevent the migration of Pb ions

Xue,

Cheng,

Wang

et al. 2023

Environmental Research

View full text Add to dashboard Cite

Shield machine position prediction and anomaly detection during tunnelling in loess region using ensemble and deep learning algorithms

Cited by 9 publications

References 62 publications

Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU

Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU

Biopolymer-assisted enzyme-induced carbonate precipitation for immobilizing Cu ions in aqueous solution and loess

Applying the first microcapsule-based self-healing microbial-induced calcium carbonate materials to prevent the migration of Pb ions

Contact Info

Product

Resources

About