A Coupled Thermal-Hydraulic-Mechanical Nonlinear Model for Fault Water Inrush

Liu, Weitao; Zhao, Jiyuan; Nie, Ruiai; Liu, Yuben; Du, Yanhui

doi:10.3390/pr6080120

Cited by 13 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model combines the particle swarm optimization algorithm and the gated recurrent unit model in the spark streaming framework. Liu et al [26] proposed a coupled thermal-hydraulic-mechanical nonlinear model for predict and warn of water inrush in mines. Finally, Kong et al [27] proposed a fault diagnosis model using a particle swarm optimization algorithm to optimize the structure of a B-spline network, aiming to improve the prediction accuracy of nonlinear time series.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Li,

Jin,

Dogani

et al. 2024

Processes

View full text Add to dashboard Cite

The reliable operation of industrial equipment is imperative for ensuring both safety and enhanced production efficiency. Machine learning technology, particularly the Light Gradient Boosting Machine (LightGBM), has emerged as a valuable tool for achieving effective fault warning in industrial settings. Despite its success, the practical application of LightGBM encounters challenges in diverse scenarios, primarily stemming from the multitude of parameters that are intricate and challenging to ascertain, thus constraining computational efficiency and accuracy. In response to these challenges, we propose a novel innovative hybrid algorithm that integrates an Arithmetic Optimization Algorithm (AOA), Simulated Annealing (SA), and new search strategies. This amalgamation is designed to optimize LightGBM hyperparameters more effectively. Subsequently, we seamlessly integrate this hybrid algorithm with LightGBM to formulate a sophisticated fault warning system. Validation through industrial case studies demonstrates that our proposed algorithm consistently outperforms advanced methods in both prediction accuracy and generalization ability. In a real-world water pump application, the algorithm we proposed achieved a fault warning accuracy rate of 90%. Compared to three advanced algorithms, namely, Improved Social Engineering Optimizer-Backpropagation Network (ISEO-BP), Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN), and Grey Wolf Optimizer-Light Gradient Boosting Machine (GWO-LightGBM), its Root Mean Square Error (RMSE) decreased by 7.14%, 17.84%, and 13.16%, respectively. At the same time, its R-Squared value increased by 2.15%, 7.02%, and 3.73%, respectively. Lastly, the method we proposed also holds a leading position in the success rate of a water pump fault warning. This accomplishment provides robust support for the timely detection of issues, thereby mitigating the risk of production interruptions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Li,

Jin,

Dogani

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

“…When the failure area is connected with the fracture of the hidden fault, a water injection channel is formed. Liu et al [3] established the thermal nonlinear hydraulic mechanical coupling model of fault water inrush, studied the water-rock-water interaction, and predicted the fault water inrush. The governing equations of coupled THM model are established by coupling particle transport equation, nonlinear flow equation, mechanical equation, and heat transfer equation.…”

Section: Introductionmentioning

confidence: 99%

Groundwater Inrush Control and Parameters Optimization of Curtain Grouting Reinforcement for the Jingzhai Tunnel

Gan

Zhou³

et al. 2021

Geofluids

View full text Add to dashboard Cite

Based on the systematic study on the characteristics of water and mud inrush during the excavation of Jingzhai tunnel, the mechanism of water inrush seepage transformation caused by excavation disturbance is analyzed. By means of electromagnetic geophysical prospecting, the potential water bearing area of the tunnel was analyzed. The constitutive model of rock mass and grouting parameters are considered in the numerical simulation. The law of tunnel crack initiation and expansion under different curtain grouting parameters is proposed. The characteristics of seepage water inrush caused by excavation are described. It is considered that there are three stages in the seepage characteristics of tunnel: incubation, sudden, and stable. Numerical simulation was used to analyze the crack propagation track and water inflow characteristics under the grouting thickness of 3 m, 5 m, and 7 m. When the curtain grouting thickness was 3 m, the fracture field penetrated the curtain grouting area. The dominant seepage channel is formed, which greatly increases the probability of water inrush. When the curtain thickness is 5~7 m, the expansion of the crack zone can be controlled basically, so that the fracture and water bearing rock layer cannot form a seepage channel. At last, the grouting scheme of 6 m thick grouting and 20 m advanced grouting was selected, and the water seepage was reduced by 83%.

show abstract

“…The presented permeability model considered the rock failure process, including elastic, damaged, cracked, and crack closure stage, which is an important improvement for water inrush model in fracture rock. Moreover, a number of models considering the thermal effect and other factors were also developed to evaluate the water inrush, e.g., water inrush outlet model (Zhang et al 2015) and thermal-hydraulic-mechanical (THM) coupled model (Liu et al 2018c). Most of these studies focused on the water and mud inrush mechanism from the perspective of rock mechanics.…”

Section: Introductionmentioning

confidence: 99%

Prediction of water–mud inrush hazard from weathered granite tunnel by an improved seepage erosion model

Liu

et al. 2021

Bull Eng Geol Environ

View full text Add to dashboard Cite

During tunnel construction, water and mud inrush disasters from completely weathered granite usually lead to the serious casualties and economic losses. Predicting these disasters are vital to the safety construction. Considering the critical erosion condition and flow pattern variation at the three stages (Darcy, rapid, and stable flow stages), a seepage erosion model is developed to perform the coupling analysis of water and mud inrush evolution. The model is shown to have favorable accuracy in real-time predicting the erosion region, ground settlement region, and the main hydraulic parameters (i.e., permeability, water inflow, and mud inflow) by comparison with the laboratory tests and field investigations. Then, effects of the model parameters (i.e., particle diameter, erosion coefficient, and ground permeability) on the water and mud inrush are investigated. Results show that (1) with the decreasing particle diameter, the permeability and the water and mud inflow increase gradually. (2) The erosion coefficient mainly affects the evolution rate and time of the water and mud inrush disaster.(3) The water and mud inrush can be controlled when the ground permeability decreased to the 0.2 time of the initial value. The research findings and the proposed model can provide the reference for the water inrush prevention in a similar project.

show abstract

A Coupled Thermal-Hydraulic-Mechanical Nonlinear Model for Fault Water Inrush

Cited by 13 publications

References 17 publications

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Groundwater Inrush Control and Parameters Optimization of Curtain Grouting Reinforcement for the Jingzhai Tunnel

Prediction of water–mud inrush hazard from weathered granite tunnel by an improved seepage erosion model

Contact Info

Product

Resources

About