Accurately forecasting peak particle velocity(PPV)during blasting operations plays a crucial role in mitigating vibration-related hazards and preventing economic losses.This research introduces an approach to PPV pred...Accurately forecasting peak particle velocity(PPV)during blasting operations plays a crucial role in mitigating vibration-related hazards and preventing economic losses.This research introduces an approach to PPV prediction by combining conventional empirical equations with physics-informed neural networks(PINN)and optimizing the model parameters via the Particle Swarm Optimization(PSO)algorithm.The proposed PSO-PINN framework was rigorously benchmarked against seven established machine learning approaches:Multilayer Perceptron(MLP),Extreme Gradient Boosting(XGBoost),Random Forest(RF),Support Vector Regression(SVR),Gradient Boosting Decision Tree(GBDT),Adaptive Boosting(Adaboost),and Gene Expression Programming(GEP).Comparative analysis showed that PSO-PINN outperformed these models,achieving RMSE reductions of 17.82-37.63%,MSE reductions of 32.47-61.10%,AR improvements of 2.97-21.19%,and R^(2)enhancements of 7.43-29.21%,demonstrating superior accuracy and generalization.Furthermore,the study determines the impact of incorporating empirical formulas as physical constraints in neural networks and examines the effects of different empirical equations,particle swarm size,iteration count in PSO,regularization coefficient,and learning rate in PINN on model performance.Lastly,a predictive system for blast vibration PPV is designed and implemented.The research outcomes offer theoretical references and practical recommendations for blast vibration forecasting in similar engineering applications.展开更多
Under circumstances in which both underground mining and open-pit mining are employed, the mining effects of two approaches will be superposed and the mining slope will receive several induced stress fields, which mak...Under circumstances in which both underground mining and open-pit mining are employed, the mining effects of two approaches will be superposed and the mining slope will receive several induced stress fields, which makes the sliding mechanism and deformation law of slope rock mass more complicated. This paper, targeting at the east slope of Antaibao Mine with the joint employment of underground mining and open-pit mining, aims to study the moving law of the slope rock mass and the damage mechanism to the overburden of the goaf by numerical simulation. It is supposed that models of possible damage to the slope could be explored for guidance to safety-production of the mine.展开更多
In order to explore the effect of loading rate on physical and mechanical properties of dihydrate gypsum,cyclic loading and unloading mechanical tests were carried out at different loading rates.Test results were anal...In order to explore the effect of loading rate on physical and mechanical properties of dihydrate gypsum,cyclic loading and unloading mechanical tests were carried out at different loading rates.Test results were analyzed from the aspects of stress-strain curve,energy distribution mode,damage law and failure mode of specimen.The main research results obtained in the thesis are as follows:with the increase of the loading rate,the peak value of specimen damage first increases rapidly,and then in-creases slowly,and there is a damage threshold.In the early stage of loading,the dissipated energy of the specimen accounts for about 70%of the total energy,most of the total energy input is converted into dissipated energy.The elastic energy density shows an increasing trend with the increase of the loading rate.The elastic energy density is the highest when the loading rate is 400 N/s,and more elastic energy can be stored.The ratio of elastic energy ue/u increases with the in-crease of loading rate and tends to be stable.The acoustic emission data show that the acoustic emission signals present a certain agglomeration phenomenon at the unloading point,and there is a“blank period”between the unloading point and the emergence of the next acoustic emission activity.In the early stage of specimen loading,friction-type acoustic emission is mainly generated.The cumulative ringing count when the load reaches the peak failure stress at low loading rate is more,indicating that low loading rate will produce more acoustic emission activities.With the increase of loading rate,the cumulative ringing number per unit time increases,indicating that the increase of loading rate accelerates the damage and failure of dihydrate gypsum near the peak value.The failure mode of gypsum specimens is shear failure,and the increase of loading rate of shear failure angle shows an increasing trend.The larger the loading rate is,the higher the strength of the specimen is.The more energy the press inputs during the loading process,the higher the energy absorbed by the unit volume specimen,which aggravates the development,expansion and penetration of the internal cracks of the specimen,resulting in the larger shear angle of the specimen.The test results provide a more comprehensive theoretical basis for the study of damage characteristics of dihydrate gypsum during cyclic loading and unloading.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.52409143)the Basic Scientific Research Fund of Changjiang River Scientific Research Institute for Central-level Public Welfare Research Institutes(Grant No.CKSF2025184/YT)the Hubei Provincial Natural Science Foundation of China(Grant No.2022CFB673).
文摘Accurately forecasting peak particle velocity(PPV)during blasting operations plays a crucial role in mitigating vibration-related hazards and preventing economic losses.This research introduces an approach to PPV prediction by combining conventional empirical equations with physics-informed neural networks(PINN)and optimizing the model parameters via the Particle Swarm Optimization(PSO)algorithm.The proposed PSO-PINN framework was rigorously benchmarked against seven established machine learning approaches:Multilayer Perceptron(MLP),Extreme Gradient Boosting(XGBoost),Random Forest(RF),Support Vector Regression(SVR),Gradient Boosting Decision Tree(GBDT),Adaptive Boosting(Adaboost),and Gene Expression Programming(GEP).Comparative analysis showed that PSO-PINN outperformed these models,achieving RMSE reductions of 17.82-37.63%,MSE reductions of 32.47-61.10%,AR improvements of 2.97-21.19%,and R^(2)enhancements of 7.43-29.21%,demonstrating superior accuracy and generalization.Furthermore,the study determines the impact of incorporating empirical formulas as physical constraints in neural networks and examines the effects of different empirical equations,particle swarm size,iteration count in PSO,regularization coefficient,and learning rate in PINN on model performance.Lastly,a predictive system for blast vibration PPV is designed and implemented.The research outcomes offer theoretical references and practical recommendations for blast vibration forecasting in similar engineering applications.
文摘Under circumstances in which both underground mining and open-pit mining are employed, the mining effects of two approaches will be superposed and the mining slope will receive several induced stress fields, which makes the sliding mechanism and deformation law of slope rock mass more complicated. This paper, targeting at the east slope of Antaibao Mine with the joint employment of underground mining and open-pit mining, aims to study the moving law of the slope rock mass and the damage mechanism to the overburden of the goaf by numerical simulation. It is supposed that models of possible damage to the slope could be explored for guidance to safety-production of the mine.
基金support from the National Natural Science Foundation of China,grant number 52174087.
文摘In order to explore the effect of loading rate on physical and mechanical properties of dihydrate gypsum,cyclic loading and unloading mechanical tests were carried out at different loading rates.Test results were analyzed from the aspects of stress-strain curve,energy distribution mode,damage law and failure mode of specimen.The main research results obtained in the thesis are as follows:with the increase of the loading rate,the peak value of specimen damage first increases rapidly,and then in-creases slowly,and there is a damage threshold.In the early stage of loading,the dissipated energy of the specimen accounts for about 70%of the total energy,most of the total energy input is converted into dissipated energy.The elastic energy density shows an increasing trend with the increase of the loading rate.The elastic energy density is the highest when the loading rate is 400 N/s,and more elastic energy can be stored.The ratio of elastic energy ue/u increases with the in-crease of loading rate and tends to be stable.The acoustic emission data show that the acoustic emission signals present a certain agglomeration phenomenon at the unloading point,and there is a“blank period”between the unloading point and the emergence of the next acoustic emission activity.In the early stage of specimen loading,friction-type acoustic emission is mainly generated.The cumulative ringing count when the load reaches the peak failure stress at low loading rate is more,indicating that low loading rate will produce more acoustic emission activities.With the increase of loading rate,the cumulative ringing number per unit time increases,indicating that the increase of loading rate accelerates the damage and failure of dihydrate gypsum near the peak value.The failure mode of gypsum specimens is shear failure,and the increase of loading rate of shear failure angle shows an increasing trend.The larger the loading rate is,the higher the strength of the specimen is.The more energy the press inputs during the loading process,the higher the energy absorbed by the unit volume specimen,which aggravates the development,expansion and penetration of the internal cracks of the specimen,resulting in the larger shear angle of the specimen.The test results provide a more comprehensive theoretical basis for the study of damage characteristics of dihydrate gypsum during cyclic loading and unloading.
