Prediction of Disc Cutter Life During Shield Tunneling with AI via the Incorporation of a Genetic Algorithm into a GMDH-Type Neural Network

Engineering, Journal Year: 2020, Volume and Issue: 7(2), P. 238 - 251

Published: Sept. 2, 2020

Disc cutter consumption is a critical problem that influences work performance during shield tunneling processes and directly affects the change decision. This study proposes new model to estimate disc life (Hf) by integrating group method of data handling (GMDH)-type neural network (NN) with genetic algorithm (GA). The efficiency effectiveness GMDH structure are optimized GA, which enables each neuron search for its optimum connections set from previous layer. With proposed model, monitoring including database, consumption, geological conditions, operational parameters can be analyzed. To verify case in China presented database adopted illustrate excellence hybrid model. results indicate predicts high accuracy. sensitivity analysis reveals penetration rate (PR) has significant influence on life. this beneficial both planning construction stages tunneling.

Language: Английский

---

Real-time analysis and regulation of EPB shield steering using Random Forest

Automation in Construction, Journal Year: 2019, Volume and Issue: 106, P. 102860 - 102860

Published: June 13, 2019

Language: Английский

---

Risk assessment of mega-city infrastructures related to land subsidence using improved trapezoidal FAHP

The Science of The Total Environment, Journal Year: 2019, Volume and Issue: 717, P. 135310 - 135310

Published: Nov. 25, 2019

Language: Английский

---

State-of-the-Art Review of Machine Learning Applications in Constitutive Modeling of Soils

Archives of Computational Methods in Engineering, Journal Year: 2021, Volume and Issue: 28(5), P. 3661 - 3686

Published: Jan. 5, 2021

Language: Английский

---

Real-time prediction of shield moving trajectory during tunnelling

Acta Geotechnica, Journal Year: 2022, Volume and Issue: 17(4), P. 1533 - 1549

Published: Feb. 4, 2022

Language: Английский

---

Intelligent Monitoring System for Deep Foundation Pit Based on Digital Twin

Buildings, Journal Year: 2025, Volume and Issue: 15(3), P. 366 - 366

Published: Jan. 24, 2025

Underground space development has significantly increased the depth, scale, and complexity of foundation pit engineering. However, monitoring systems lack mechanical analysis models fail to predict control construction risks. Additionally, model could not be updated based on on-site observed data, leading inaccurate predictions. This study proposes a DT modeling framework for pits, which is used simulate, predict, risks associated with entire excavation process. Consequently, framework, (DTFPM) was established using updating algorithms. summarizes identifies key parameters pits. A parametric algorithm ABAQUS (v2020) developed drive process within seconds. Furthermore, an inverse optimization genetic algorithms (GA) real-time deformation employed update elastic modulus soil. The supports parallel computing can converge 10 generations. prediction error after reduced 10%. Finally, authors applied DTFPM establish intelligent system. focus predictive warnings current step model. analyzes Beijing project case verify effectiveness system, demonstrating practical application proposed method. results showed that accurately simulate behavior pit. system provide more timely accurate safety warnings. method potentially contribute pits in future, both theoretically practically.

Language: Английский

---

Flood risk assessment of metro systems in a subsiding environment using the interval FAHP-FCA approach

Sustainable Cities and Society, Journal Year: 2019, Volume and Issue: 50, P. 101682 - 101682

Published: June 25, 2019

Language: Английский

---

A critical evaluation of machine learning and deep learning in shield-ground interaction prediction

Tunnelling and Underground Space Technology, Journal Year: 2020, Volume and Issue: 106, P. 103593 - 103593

Published: Sept. 28, 2020

Language: Английский

---

Evaluation of soil liquefaction using AI technology incorporating a coupled ENN / t-SNE model

Soil Dynamics and Earthquake Engineering, Journal Year: 2019, Volume and Issue: 130, P. 105988 - 105988

Published: Dec. 3, 2019

Language: Английский

---

Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms

Geoscience Frontiers, Journal Year: 2020, Volume and Issue: 12(1), P. 441 - 452

Published: March 21, 2020

Compression index Cc is an essential parameter in geotechnical design for which the effectiveness of correlation still a challenge. This paper suggests novel modelling approach using machine learning (ML) technique. The performance five commonly used algorithms, i.e. back-propagation neural network (BPNN), extreme (ELM), support vector (SVM), random forest (RF) and evolutionary polynomial regression (EPR) predicting comprehensively investigated. A database with total number 311 datasets including three input variables, initial void ratio e0, liquid limit water content wL, plasticity Ip, one output variable first established. Genetic algorithm (GA) to optimize hyper-parameters ML average prediction error 10-fold cross-validation (CV) sets set as fitness function GA enhancing robustness models. results indicate that models outperform empirical formulations lower error. RF yields lowest followed by BPNN, ELM, EPR SVM. If ranges variables are large enough, BPNN recommended predict Cc. Furthermore, if distribution continuous, model best one. Otherwise, small. predicted correlations between show great agreement physical explanation.

Language: Английский

---