The surrogate model serves as an efficient simulation tool during the slope parameter inversion process.However,the creep constitutive model integrated with dynamic damage evolution poses challenges in development of ...The surrogate model serves as an efficient simulation tool during the slope parameter inversion process.However,the creep constitutive model integrated with dynamic damage evolution poses challenges in development of the required surrogate model.In this study,a novel physics knowledge-based surrogate model framework is proposed.In this framework,a Transformer module is employed to capture straindriven softening-hardening physical mechanisms.Positional encoding and self-attention are utilized to transform the constitutive parameters associated with shear strain,which are not directly time-related,into intermediate latent features for physical loss calculation.Next,a multi-layer stacked GRU(gated recurrent unit)network is built to provide input interfaces for time-dependent intermediate latent features,hydraulic boundary conditions,and water-rock interaction degradation equations,with static parameters introduced via external fully-connected layers.Finally,a combined loss function is constructed to facilitate the collaborative training of physical and data loss,introducing time-dependent weight adjustments to focus the surrogate model on accurate deformation predictions during critical phases.Based on the deformation of a reservoir bank landslide triggered by impoundment and subsequent restabilization,an elasto-viscoplastic constitutive model that considers water effect and sliding state dependencies is developed to validate the proposed surrogate model framework.The results indicate that the framework exhibits good performance in capturing physical mechanisms and predicting creep behavior,reducing errors by about 30 times compared to baseline models such as GRU and LSTM(long short-term memory),meeting the precision requirements for parameter inversion.Ablation experiments also confirmed the effectiveness of the framework.This framework can also serve as a reference for constructing other creep surrogate models that involve non-time-related across dimensions.展开更多
The stability of reservoir bank slopes during the impoundment period has become a critical issue in the construction and operation of large-scale hydropower projects.A predictive and early warning method for reservoir...The stability of reservoir bank slopes during the impoundment period has become a critical issue in the construction and operation of large-scale hydropower projects.A predictive and early warning method for reservoir bank slopes is proposed,based on slip resistance stability evolution analysis.Using a refined three-dimensional numerical calculation model of the bank slope,the creep damage model is employed for simulation and analysis,enabling the derivation of stress field and strain field evolution from bank slope excavation to the long-term impoundment period.Subsequently,for the stress field of the bank slope at any given moment,the safety factors of the sliding blocks are determined by using the multigrid method and vector sum method.Accordingly,the evolutionary law of the sliding safety factor for the bank slope can be derived.By integrating the long-term stability evolution trend of the slope with specific engineering practices,the safety factors for graded warning can be determined.Based on the time correspondence,the graded warning moment and the deformation warning index for slope measurement points can be determined.In this study,the proposed method is applied to the left bank slope of the Jinping I Hydropower Station.The results indicate that from excavation to June 2022,the left bank slope exhibits a strong correlation with excavation elevation and the number of reservoir water cycles.The initial,maximum,and minimum safety factors are 2.01,3.07,and 1.58,respectively.The deep fracture SL44-1 serves as the primary stress-bearing slip surface of the left bank slope,while the safety margin of the fault f42-9 and lamprophyre X is slightly insufficient.Based on the long-term stability evolution trend of the slope and in accordance with relevant standards,the safety factors for graded warning indicators—K_(w1),K_(w2),K_(w3),and K_(w4)—are determined as 1.350,1.325,1.300,and 1.275,respectively.Correspondingly,the estimated warning times are 12/30/2066,12/30/2084,and 12/30/2120.Accordingly,the deformation graded warning indexes for slope measurement points are established.展开更多
In tunnel construction,tunnel boring machine(TBM)tunnelling typically relies on manual experience with sub-optimal control parameters,which can easily lead to inefficiency and high costs.This study proposed an intelli...In tunnel construction,tunnel boring machine(TBM)tunnelling typically relies on manual experience with sub-optimal control parameters,which can easily lead to inefficiency and high costs.This study proposed an intelligent decision-making method for TBM tunnelling control parameters based on multiobjective optimization(MOO).First,the effective TBM operation dataset is obtained through data preprocessing of the Songhua River(YS)tunnel project in China.Next,the proposed method begins with developing machine learning models for predicting TBM tunnelling performance parameters(i.e.total thrust and cutterhead torque),rock mass classification,and hazard risks(i.e.tunnel collapse and shield jamming).Then,considering three optimal objectives,(i.e.,penetration rate,rock-breaking energy consumption,and cutterhead hob wear),the MOO framework and corresponding mathematical expression are established.The Pareto optimal front is solved using DE-NSGA-II algorithm.Finally,the optimal control parameters(i.e.,advance rate and cutterhead rotation speed)are obtained by the satisfactory solution determination criterion,which can balance construction safety and efficiency with satisfaction.Furthermore,the proposed method is validated through 50 cases of TBM tunnelling,showing promising potential of application.展开更多
Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are g...Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are generated,reflecting the interaction between the TBM system and surrounding rock,and these data can be used to evaluate the rock mass quality.This study proposed a stacking ensemble classifier for the real-time prediction of the rock mass classification using TBM operation data.Based on the Songhua River water conveyance project,a total of 7538 TBM tunnelling cycles and the corresponding rock mass classes are obtained after data preprocessing.Then,through the tree-based feature selection method,10 key TBM operation parameters are selected,and the mean values of the 10 selected features in the stable phase after removing outliers are calculated as the inputs of classifiers.The preprocessed data are randomly divided into the training set(90%)and test set(10%)using simple random sampling.Besides stacking ensemble classifier,seven individual classifiers are established as the comparison.These classifiers include support vector machine(SVM),k-nearest neighbors(KNN),random forest(RF),gradient boosting decision tree(GBDT),decision tree(DT),logistic regression(LR)and multilayer perceptron(MLP),where the hyper-parameters of each classifier are optimised using the grid search method.The prediction results show that the stacking ensemble classifier has a better performance than individual classifiers,and it shows a more powerful learning and generalisation ability for small and imbalanced samples.Additionally,a relative balance training set is obtained by the synthetic minority oversampling technique(SMOTE),and the influence of sample imbalance on the prediction performance is discussed.展开更多
The strict definition and logical description of the concept of structure stability and failure are presented. The criterion of structure stability is developed based on plastic complementary energy and its variation....The strict definition and logical description of the concept of structure stability and failure are presented. The criterion of structure stability is developed based on plastic complementary energy and its variation. It is presented that the principle of minimum plastic complementary energy is the combination of structure equilibrium, coordination condition of deformation and constitutive relationship. Based on the above arguments, the deformation reinforcement theory is developed. The structure global stability can be described by the relationship between the global degree of safety of structure and the plastic complementary energy. Correspondingly, the new idea is used in the evaluations of global stability, anchorage force of dam-toe, fracture of dam-heel and treatment of faults of high arch dams in China. The results show that the deformation reinforcement theory provides a uniform and practical theoretical framework and a valuable solution for the analysis of global stability, dam-heel cracking, dam-toe anchorage and reinforcement of faults of high arch dams and their foundations.展开更多
The time-dependent behavior of the left bank abutment slope at Jinping I hydropower station has a major influence on the normal operation and long-term safety of the hydropower station. To solve this problem, a geomec...The time-dependent behavior of the left bank abutment slope at Jinping I hydropower station has a major influence on the normal operation and long-term safety of the hydropower station. To solve this problem, a geomechanical model containing various faults and weak structural planes is established, and numerical simulation is conducted under normal water load condition using FLAC3D, incorporating creep model proposed based on thermodynamics with internal state variables theory. The creep deformations of the left bank abutment slope are obtained, and the changes of principal stresses and deformations of the dam body are analyzed. The long-term stability of the left bank abutment slope is evaluated according to the integral curves of energy dissipation rate in domain and its derivative with respect to time, and the non-equilibrium evolution rules and the characteristic time can also be determined using these curves. Numerical results show that the left bank abutment slope tends to be stable in a global sense, and the stress concentration is released. It is also indicated that more attention should be paid to some weak regions within the slope in the long-term deformation process.展开更多
The rigid-body limit equilibrium method cannot reflect the actual stress distribution in a rock mass,and the finite-element-based strength reduction method also has some problems with respect to convergence.To address...The rigid-body limit equilibrium method cannot reflect the actual stress distribution in a rock mass,and the finite-element-based strength reduction method also has some problems with respect to convergence.To address these problems,a multi-grid method was adopted in this study to establish a structural grid for finite element computation and a slip surface grid for computing slope stability safety factors.This method can be used to determine the stability safety factor for any slip surface or slide block through a combination of nonlinear finite element analysis and limit equilibrium analysis.An ideal elastic–plastic incremental analysis method based on the Drucker–Prager yield criterion was adopted in the nonlinear finite element computation.Elasto-plastic computation achieves good convergence for both small load steps and large load steps and can increase computation precision to a certain extent.To increase the scale and accuracy of the computation,TFINE,a finite element parallel computation program,was used to analyze the influence of grid density on the accuracy of the computation results and was then applied to analysis of the stability of the Jinping high slope.A comparison of the results with results obtained using the rigid-body limit equilibrium method showed that the slope stability safety factors determined using finite element analysis were greater than those obtained using the rigid-body limit equilibrium method and were in better agreement with actual values because nonlinear stress adjustment was considered in the calculation.展开更多
Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a ...Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a novel encoder–decoder structure,CrackRecNet,for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture.An image acquisition equipment is designed based on a camera,3-dimensional printing(3DP)bracket and two laser rangefinders.A tunnel concrete structure crack(TCSC)image data set,containing images collected from a double-shield tunnel boring machines(TBM)tunnel in China,was established.Through data preprocessing operations,such as brightness adjustment,pixel resolution adjustment,flipping,splitting and annotation,2880 image samples with pixel resolution of 448×448 were prepared.The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs.In the experiments,the proposed CrackRecNet showed better prediction performance than U-Net,TernausNet,and ResU-Net.This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.41961134032).
文摘The surrogate model serves as an efficient simulation tool during the slope parameter inversion process.However,the creep constitutive model integrated with dynamic damage evolution poses challenges in development of the required surrogate model.In this study,a novel physics knowledge-based surrogate model framework is proposed.In this framework,a Transformer module is employed to capture straindriven softening-hardening physical mechanisms.Positional encoding and self-attention are utilized to transform the constitutive parameters associated with shear strain,which are not directly time-related,into intermediate latent features for physical loss calculation.Next,a multi-layer stacked GRU(gated recurrent unit)network is built to provide input interfaces for time-dependent intermediate latent features,hydraulic boundary conditions,and water-rock interaction degradation equations,with static parameters introduced via external fully-connected layers.Finally,a combined loss function is constructed to facilitate the collaborative training of physical and data loss,introducing time-dependent weight adjustments to focus the surrogate model on accurate deformation predictions during critical phases.Based on the deformation of a reservoir bank landslide triggered by impoundment and subsequent restabilization,an elasto-viscoplastic constitutive model that considers water effect and sliding state dependencies is developed to validate the proposed surrogate model framework.The results indicate that the framework exhibits good performance in capturing physical mechanisms and predicting creep behavior,reducing errors by about 30 times compared to baseline models such as GRU and LSTM(long short-term memory),meeting the precision requirements for parameter inversion.Ablation experiments also confirmed the effectiveness of the framework.This framework can also serve as a reference for constructing other creep surrogate models that involve non-time-related across dimensions.
基金supported by the National Natural Science Foundation of China(Grant No.41961134032).
文摘The stability of reservoir bank slopes during the impoundment period has become a critical issue in the construction and operation of large-scale hydropower projects.A predictive and early warning method for reservoir bank slopes is proposed,based on slip resistance stability evolution analysis.Using a refined three-dimensional numerical calculation model of the bank slope,the creep damage model is employed for simulation and analysis,enabling the derivation of stress field and strain field evolution from bank slope excavation to the long-term impoundment period.Subsequently,for the stress field of the bank slope at any given moment,the safety factors of the sliding blocks are determined by using the multigrid method and vector sum method.Accordingly,the evolutionary law of the sliding safety factor for the bank slope can be derived.By integrating the long-term stability evolution trend of the slope with specific engineering practices,the safety factors for graded warning can be determined.Based on the time correspondence,the graded warning moment and the deformation warning index for slope measurement points can be determined.In this study,the proposed method is applied to the left bank slope of the Jinping I Hydropower Station.The results indicate that from excavation to June 2022,the left bank slope exhibits a strong correlation with excavation elevation and the number of reservoir water cycles.The initial,maximum,and minimum safety factors are 2.01,3.07,and 1.58,respectively.The deep fracture SL44-1 serves as the primary stress-bearing slip surface of the left bank slope,while the safety margin of the fault f42-9 and lamprophyre X is slightly insufficient.Based on the long-term stability evolution trend of the slope and in accordance with relevant standards,the safety factors for graded warning indicators—K_(w1),K_(w2),K_(w3),and K_(w4)—are determined as 1.350,1.325,1.300,and 1.275,respectively.Correspondingly,the estimated warning times are 12/30/2066,12/30/2084,and 12/30/2120.Accordingly,the deformation graded warning indexes for slope measurement points are established.
基金supported by the National Natural Science Foundation of China(Grant No.52179105)China Postdoctoral Science Foundation(Grant No.2024M762193)。
文摘In tunnel construction,tunnel boring machine(TBM)tunnelling typically relies on manual experience with sub-optimal control parameters,which can easily lead to inefficiency and high costs.This study proposed an intelligent decision-making method for TBM tunnelling control parameters based on multiobjective optimization(MOO).First,the effective TBM operation dataset is obtained through data preprocessing of the Songhua River(YS)tunnel project in China.Next,the proposed method begins with developing machine learning models for predicting TBM tunnelling performance parameters(i.e.total thrust and cutterhead torque),rock mass classification,and hazard risks(i.e.tunnel collapse and shield jamming).Then,considering three optimal objectives,(i.e.,penetration rate,rock-breaking energy consumption,and cutterhead hob wear),the MOO framework and corresponding mathematical expression are established.The Pareto optimal front is solved using DE-NSGA-II algorithm.Finally,the optimal control parameters(i.e.,advance rate and cutterhead rotation speed)are obtained by the satisfactory solution determination criterion,which can balance construction safety and efficiency with satisfaction.Furthermore,the proposed method is validated through 50 cases of TBM tunnelling,showing promising potential of application.
基金funded by the National Natural Science Foundation of China(Grant No.41941019)the State Key Laboratory of Hydroscience and Engineering(Grant No.2019-KY-03)。
文摘Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are generated,reflecting the interaction between the TBM system and surrounding rock,and these data can be used to evaluate the rock mass quality.This study proposed a stacking ensemble classifier for the real-time prediction of the rock mass classification using TBM operation data.Based on the Songhua River water conveyance project,a total of 7538 TBM tunnelling cycles and the corresponding rock mass classes are obtained after data preprocessing.Then,through the tree-based feature selection method,10 key TBM operation parameters are selected,and the mean values of the 10 selected features in the stable phase after removing outliers are calculated as the inputs of classifiers.The preprocessed data are randomly divided into the training set(90%)and test set(10%)using simple random sampling.Besides stacking ensemble classifier,seven individual classifiers are established as the comparison.These classifiers include support vector machine(SVM),k-nearest neighbors(KNN),random forest(RF),gradient boosting decision tree(GBDT),decision tree(DT),logistic regression(LR)and multilayer perceptron(MLP),where the hyper-parameters of each classifier are optimised using the grid search method.The prediction results show that the stacking ensemble classifier has a better performance than individual classifiers,and it shows a more powerful learning and generalisation ability for small and imbalanced samples.Additionally,a relative balance training set is obtained by the synthetic minority oversampling technique(SMOTE),and the influence of sample imbalance on the prediction performance is discussed.
基金Supported by the China National Funds for Distinguished Young Scientists (50925931)the Special Funds for Major State Basic Research Projects (2009CB724604)
文摘The strict definition and logical description of the concept of structure stability and failure are presented. The criterion of structure stability is developed based on plastic complementary energy and its variation. It is presented that the principle of minimum plastic complementary energy is the combination of structure equilibrium, coordination condition of deformation and constitutive relationship. Based on the above arguments, the deformation reinforcement theory is developed. The structure global stability can be described by the relationship between the global degree of safety of structure and the plastic complementary energy. Correspondingly, the new idea is used in the evaluations of global stability, anchorage force of dam-toe, fracture of dam-heel and treatment of faults of high arch dams in China. The results show that the deformation reinforcement theory provides a uniform and practical theoretical framework and a valuable solution for the analysis of global stability, dam-heel cracking, dam-toe anchorage and reinforcement of faults of high arch dams and their foundations.
文摘The time-dependent behavior of the left bank abutment slope at Jinping I hydropower station has a major influence on the normal operation and long-term safety of the hydropower station. To solve this problem, a geomechanical model containing various faults and weak structural planes is established, and numerical simulation is conducted under normal water load condition using FLAC3D, incorporating creep model proposed based on thermodynamics with internal state variables theory. The creep deformations of the left bank abutment slope are obtained, and the changes of principal stresses and deformations of the dam body are analyzed. The long-term stability of the left bank abutment slope is evaluated according to the integral curves of energy dissipation rate in domain and its derivative with respect to time, and the non-equilibrium evolution rules and the characteristic time can also be determined using these curves. Numerical results show that the left bank abutment slope tends to be stable in a global sense, and the stress concentration is released. It is also indicated that more attention should be paid to some weak regions within the slope in the long-term deformation process.
基金The research reported in this paper was supported by the National Natural Science Foundation of China(Grant Nos.50823005 and 50709014)subsidized by China National Funds for Distinguished Young Scientists(Grant No.50925931).
文摘The rigid-body limit equilibrium method cannot reflect the actual stress distribution in a rock mass,and the finite-element-based strength reduction method also has some problems with respect to convergence.To address these problems,a multi-grid method was adopted in this study to establish a structural grid for finite element computation and a slip surface grid for computing slope stability safety factors.This method can be used to determine the stability safety factor for any slip surface or slide block through a combination of nonlinear finite element analysis and limit equilibrium analysis.An ideal elastic–plastic incremental analysis method based on the Drucker–Prager yield criterion was adopted in the nonlinear finite element computation.Elasto-plastic computation achieves good convergence for both small load steps and large load steps and can increase computation precision to a certain extent.To increase the scale and accuracy of the computation,TFINE,a finite element parallel computation program,was used to analyze the influence of grid density on the accuracy of the computation results and was then applied to analysis of the stability of the Jinping high slope.A comparison of the results with results obtained using the rigid-body limit equilibrium method showed that the slope stability safety factors determined using finite element analysis were greater than those obtained using the rigid-body limit equilibrium method and were in better agreement with actual values because nonlinear stress adjustment was considered in the calculation.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.52179105 and 41941019)Science and Technology Innovation Project of Quanmutang Engineering.
文摘Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels.The development of computer vision has greatly promoted structural health monitoring.This study proposes a novel encoder–decoder structure,CrackRecNet,for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture.An image acquisition equipment is designed based on a camera,3-dimensional printing(3DP)bracket and two laser rangefinders.A tunnel concrete structure crack(TCSC)image data set,containing images collected from a double-shield tunnel boring machines(TBM)tunnel in China,was established.Through data preprocessing operations,such as brightness adjustment,pixel resolution adjustment,flipping,splitting and annotation,2880 image samples with pixel resolution of 448×448 were prepared.The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs.In the experiments,the proposed CrackRecNet showed better prediction performance than U-Net,TernausNet,and ResU-Net.This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.
