Deep learning technologies for shield tunneling: Challenges and opportunities

Automation in Construction, Год журнала: 2023, Номер 154, С. 104982 - 104982

Опубликована: Июнь 27, 2023

Язык: Английский

---

Feedback on a shared big dataset for intelligent TBM Part I: Feature extraction and machine learning methods

Underground Space, Год журнала: 2023, Номер 11, С. 1 - 25

Опубликована: Март 22, 2023

This review summarizes the research outcomes and findings documented in 45 journal papers using a shared tunnel boring machine (TBM) dataset for performance prediction efficiency optimization learning methods. The big was collected during Yinsong water diversion project construction China, covering excavation of 20 km-section with 199 items monitoring metrics taken an interval one second. were result call contributions TBM contest 2019 covered variety topics related to intelligent TBM. comprises two parts. Part I is concerned data processing, feature extraction, methods applied by contributors. finds that data-driven knowledge-driven approaches extracting important features various authors are diversified, requiring further studies achieve commonly accepted criteria. techniques cleaning amending raw adopted contributors summarized, indicating some highlights such as importance sufficiently high frequency acquisition (higher than 1 second), classification standardization preprocessing process, appropriate selections cycle. both supervised unsupervised have been utilized researchers. ensemble deep found wide applications. individual contributors, including structures algorithm, selection hyperparameters, model validation approaches.

Язык: Английский

---

Attitude deviation prediction of shield tunneling machine using Time-Aware LSTM networks

Transportation Geotechnics, Год журнала: 2024, Номер 45, С. 101195 - 101195

Опубликована: Янв. 28, 2024

Язык: Английский

---

Long-term safety evaluation of soft rock tunnel structure based on knowledge decision-making and data-driven models

Computers and Geotechnics, Год журнала: 2024, Номер 169, С. 106244 - 106244

Опубликована: Март 20, 2024

Язык: Английский

---

Multisource information fusion for real-time prediction and multiobjective optimization of large-diameter slurry shield attitude

Reliability Engineering & System Safety, Год журнала: 2024, Номер 250, С. 110305 - 110305

Опубликована: Июнь 24, 2024

Язык: Английский

---

Prediction of shield machine attitude parameters based on decomposition and multi-head attention mechanism

Automation in Construction, Год журнала: 2025, Номер 171, С. 105973 - 105973

Опубликована: Янв. 18, 2025

Язык: Английский

---

Long-term forecasting of shield tunnel position and attitude deviation using the 1DCNN-informer method

Engineering Science and Technology an International Journal, Год журнала: 2025, Номер 63, С. 101957 - 101957

Опубликована: Янв. 30, 2025

Язык: Английский

---

Epoxy composite reinforced with jute/basalt hybrid – Characterisation and performance evaluation using machine learning techniques

Composites Part C Open Access, Год журнала: 2024, Номер 14, С. 100453 - 100453

Опубликована: Март 22, 2024

Epoxy resins, prized for their versatile properties, are derived from bio-based materials, contributing to sustainability and eco-friendliness in both production application. This study focuses on the application of gradient boosting machine learning techniques field machining predict surface roughness also contour based experimental validation numerical results. The turning experiments, conducted via Taguchi's L27 array, aimed explore effects depth cut, feed rate, spindle speed. Higher speeds, lower rates, shallower cuts led smoother surfaces turned jute/basalt epoxy composites. Machine models (Gradient Boosting Machine, AdaBoost, XGBoost) were then used roughness. Amongst these, XGBoost outperformed GBM exhibiting maximum average prediction errors 3.78 % 2.24 %, respectively. accurately predicted 2D contours that closely matched training test cases. Orthogonal Matrix identified minimum values as 0.773 μm (experimental), 0.800 (GBM), 0.880 (AdaBoost), 0.774 (XGBoost). All achieved at 1500 rpm speed, 0.05 mm/rev 0.3 mm cut.

Язык: Английский

---

Novel rockburst prediction criterion with enhanced explainability employing CatBoost and nature-inspired metaheuristic technique

Underground Space, Год журнала: 2024, Номер 19, С. 101 - 118

Опубликована: Июнь 13, 2024

Rockburst is a major challenge to hard rock engineering at great depth. Accurate and timely assessment of rockburst risk can avoid unnecessary casualties property losses. Despite the existence various methods for assessment, there remains an urgent need comprehensive reliable criterion that easy both apply interpret. Developing new based on simple parameters potentially fill this gap. With its advantages, facilitate more effective efficient prediction potential, thereby contributing significantly enhancing safety measures. In paper, combined with internal external factors rockburst, four control variables (i.e., integrity index, stress brittleness elastic energy index) were selected be incorporated into rockburstability index (RBSI). Based 116 sets cases, potential was accurately quantified predicted using categorical boosting (CatBoost) model nature-inspired metaheuristic African vultures optimization algorithm (AVOA). performance validation, achieved highest accuracy 95.45%, verifying reliability effectiveness proposed RBSI criterion. Additionally, interpretive method applied analyze variable influence criterion, facilitating explanation predictions analysis formula's robustness under different conditions. general, compared existing involving relevant indicators, newly enhances prediction, it effectively swiftly evaluate preliminary rockburst. Lastly, graphical user interface developed provide clear visualization potential.

Язык: Английский

---

Prediction of the tunnelling advance speed of a super-large-diameter shield machine based on a KF-CNN-BiGRU hybrid neural network

Measurement, Год журнала: 2024, Номер 230, С. 114517 - 114517

Опубликована: Март 24, 2024

Язык: Английский

---