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

Transportation Geotechnics, Journal Year: 2024, Volume and Issue: 45, P. 101195 - 101195

Published: Jan. 28, 2024

Language: Английский

---

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

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 169, P. 106244 - 106244

Published: March 20, 2024

Language: Английский

---

Flood susceptibility prediction using tree-based machine learning models in the GBA

Sustainable Cities and Society, Journal Year: 2023, Volume and Issue: 97, P. 104744 - 104744

Published: June 25, 2023

Language: Английский

---

Machine learning approach for predicting compressive strength in foam concrete under varying mix designs and curing periods

Smart Construction and Sustainable Cities, Journal Year: 2023, Volume and Issue: 1(1)

Published: Nov. 10, 2023

Abstract Efforts to reduce the weight of buildings and structures, counteract seismic threat human life, cut down on construction expenses are widespread. A strategy employed address these challenges involves adoption foam concrete. Unlike traditional concrete, concrete maintains standard composition but excludes coarse aggregates, substituting them with a agent. This alteration serves dual purpose: diminishing concrete’s overall weight, thereby achieving lower density than regular creating voids within material due agent, resulting in excellent thermal conductivity. article delves into presentation statistical models utilizing three different methods—linear (LR), non-linear (NLR), artificial neural network (ANN)—to predict compressive strength These formulated based dataset 97 sets experimental data sourced from prior research endeavors. comparative evaluation outcomes is subsequently conducted, leveraging benchmarks like coefficient determination ( R 2 ), root mean square error (RMSE), absolute (MAE), aim identifying most proficient model. The results underscore remarkable effectiveness ANN evident model’s value, which surpasses that LR model by 36% 22%. Furthermore, demonstrates significantly MAE RMSE values compared both NLR models.

Language: Английский

---

A Novel Real-Time Torque Prediction of EPB Shield in Mixed Ground Using Machine Learning Method Based on Geological Knowledge Fusion

Journal of Construction Engineering and Management, Journal Year: 2025, Volume and Issue: 151(3)

Published: Jan. 13, 2025

Language: Английский

---

A multi-stage learning method for excavation torque prediction of TBM based on CEEMD-EWT-BiLSTM hybrid network model

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116766 - 116766

Published: Jan. 1, 2025

Language: Английский

---

Deformation and protection of tunnels influenced by excavation dewatering in soft soil strata with leaky aquifers

Tunnelling and Underground Space Technology, Journal Year: 2025, Volume and Issue: 159, P. 106468 - 106468

Published: Feb. 12, 2025

Language: Английский

---

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

Measurement, Journal Year: 2024, Volume and Issue: 230, P. 114517 - 114517

Published: March 24, 2024

Language: Английский

---

TBM disc cutter wear prediction using stratal slicing and IPSO-LSTM in mixed weathered granite stratum

Tunnelling and Underground Space Technology, Journal Year: 2024, Volume and Issue: 148, P. 105745 - 105745

Published: April 10, 2024

Monitoring the wear status of cutters is important for safe and sustainable shield construction cost management. In this paper, an innovative stratal slicing method proposed to convert segmented discrete uniaxial compressive strength (UCS) test data into a sequential dataset by combining it with geological profile. The not only accurately represents changing strata conditions but also differentiates working disc in various cutterhead areas on excavation face. Its sequence characteristics can be better combined operational parameters time-series models real-time prediction. Furthermore, particle swarm optimization (PSO) algorithm was improved adding variable inertia weights elimination mechanisms, which effectively optimised hyperparameters long short-term memory (LSTM) model. applied field tunnelling case collected from Guangzhou Metro Line 18 railway. results show that UCS obtained using improve prediction accuracy compared traditional methods models. particular, IPSO + LSTM horizontal summation obtain most accurate has capability. With method, modelling approach generally applicable more complex ground larger diameters.

Language: Английский

---

Water quality prediction using LSTM with combined normalizer for efficient water management

Desalination and Water Treatment, Journal Year: 2024, Volume and Issue: 317, P. 100183 - 100183

Published: Jan. 1, 2024

Predicting water quality is a significant area of study in the field smart technology, since it may provide valuable assistance managing and mitigating pollution. Due to increasing global population need for effective methods agriculture irrigation, there continuous increase demand water, which lead scarcity resources. Consequently, management systems have been created with objective enhancing effectiveness management. Nevertheless, conventional prediction models mostly use data-driven approaches only depend on diverse sensor data. In recent research, deep learning algorithms extensively used due their robust ability map highly nonlinear connections while maintaining acceptable computational efficiency. Therefore, LSTM-CN model presented this paper integrates benefits three normalisation calculation methods: z-score, Interval, Max. This allows adaptive processing multi-factor data preserving data's inherent characteristics. Ultimately, collaborates codec learn characteristics generate accurate results. When compared existing terms various parameters proposed achieves 99.3% accuracy,95% precision, 93.6% recall, 18% MSE 11.45% RMSE.

Language: Английский

---