In cold regions,the dynamic compressive strength(DCS)of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering.Nevertheless,testing the dynamic strength under freeze-thaw wea...In cold regions,the dynamic compressive strength(DCS)of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering.Nevertheless,testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive.Therefore,this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques.Initially,a database of DCS for frozen-thawed rocks,comprising 216 rock specimens,was compiled.Three external load parameters(freeze-thaw cycle number,confining pressure,and impact pressure)and two rock parameters(characteristic impedance and porosity)were selected as input variables,with DCS as the predicted target.This research optimized the kernel scale,penalty factor,and insensitive loss coefficient of the support vector regression(SVR)model using five swarm intelligent optimization algorithms,leading to the development of five hybrid models.In addition,a statistical DCS prediction equation using multiple linear regression techniques was developed.The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes.A sensitivity analysis based on the cosine amplitude method has also been conducted.The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions.Among these models,the SVR model optimized with the chameleon swarm algorithm exhibited the best performance,with metrics indicating its effectiveness,including root mean square error(RMSE)﹦3.9675,mean absolute error(MAE)﹦2.9673,coefficient of determination(R^(2))﹦0.98631,and variance accounted for(VAF)﹦98.634.This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models.Notably,impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction.This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering.展开更多
For rapid and cost-effective hammer drilling,accurate prediction of rock impact response is crucial for designing optimal bits and maximising rock fragmentation.Current design optimisation workflows combine numerical ...For rapid and cost-effective hammer drilling,accurate prediction of rock impact response is crucial for designing optimal bits and maximising rock fragmentation.Current design optimisation workflows combine numerical simulations and experiments but often require numerous iterations to pinpoint the optimal design.Although physics-based models can potentially reduce experimental expenses,their significant computational demands present challenges when simulating the complex fragmentation dynamics during drill bit-rock interactions.This study introduces a data-driven artificial intelligence(AI)model,employing a multilayer perceptron(MLP)as a surrogate.The model leverages the hybrid finitediscrete element model(FDEM)as a powerful method in rock fracture mechanics to generate a sufficiently large training dataset.An automated workflow has been developed for generating the training data,comprising a pipeline that includes pre-processing,solving,and post-processing modules.Subsequently,the AI models were integrated into an optimisation framework alongside uncertainty quantification to demonstrate their potential in enhancing drilling efficiency through optimised bit design and operations.The MLP exhibits high accuracy in predicting key parameters,including rebound velocity,total crack length,quantities of fragments with different sizes and maximum contact force between rock and insert.Notably,this approach achieves real-time prediction compared to the 5-7 min simulation times of FDEM.Integrating this data-driven model into a design framework enables rapid assessment of different bit designs under various operational conditions.More broadly,this approach has the potential to impact other applications,such as digital twins,serving as a forward and inverse model for predicting rock type and optimising drilling performance.展开更多
Numerical simulations are widely used as a predictive tool to better understand complex air flows and pollution transport on the scale of individual buildings,city blocks,and entire cities.To improve prediction for ai...Numerical simulations are widely used as a predictive tool to better understand complex air flows and pollution transport on the scale of individual buildings,city blocks,and entire cities.To improve prediction for air flows and pollution transport,we propose a Variational Data Assimilation(VarDA)model which assimilates data from sensors into the open-source,finite-element,fluid dynamics model Fluidity.VarDA is based on the minimization of a function which estimates the discrepancy between numerical results and observations assuming that the two sources of information,forecast and observations,have errors that are adequately described by error covariance matrices.The conditioning of the numerical problem is dominated by the condition number of the background error covariance matrix which is ill-conditioned.In this paper,a preconditioned VarDA model is presented,it is based on a reduced background error covariance matrix.The Empirical Orthogonal Functions(EOFs)method is used to alleviate the computational cost and reduce the space dimension.Experimental results are provided assuming observed values provided by sensors from positions mainly located on roofs of buildings.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.42072309)the Knowledge Innovation Program of Wuhan-Basic Research(Grant No.2022020801010199)the Fundamental Research Funds for National University,China University of Geosciences(Wuhan)(Grant No.CUGDCJJ202217).
文摘In cold regions,the dynamic compressive strength(DCS)of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering.Nevertheless,testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive.Therefore,this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques.Initially,a database of DCS for frozen-thawed rocks,comprising 216 rock specimens,was compiled.Three external load parameters(freeze-thaw cycle number,confining pressure,and impact pressure)and two rock parameters(characteristic impedance and porosity)were selected as input variables,with DCS as the predicted target.This research optimized the kernel scale,penalty factor,and insensitive loss coefficient of the support vector regression(SVR)model using five swarm intelligent optimization algorithms,leading to the development of five hybrid models.In addition,a statistical DCS prediction equation using multiple linear regression techniques was developed.The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes.A sensitivity analysis based on the cosine amplitude method has also been conducted.The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions.Among these models,the SVR model optimized with the chameleon swarm algorithm exhibited the best performance,with metrics indicating its effectiveness,including root mean square error(RMSE)﹦3.9675,mean absolute error(MAE)﹦2.9673,coefficient of determination(R^(2))﹦0.98631,and variance accounted for(VAF)﹦98.634.This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models.Notably,impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction.This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering.
基金supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No.101006752(ORCHYD project).
文摘For rapid and cost-effective hammer drilling,accurate prediction of rock impact response is crucial for designing optimal bits and maximising rock fragmentation.Current design optimisation workflows combine numerical simulations and experiments but often require numerous iterations to pinpoint the optimal design.Although physics-based models can potentially reduce experimental expenses,their significant computational demands present challenges when simulating the complex fragmentation dynamics during drill bit-rock interactions.This study introduces a data-driven artificial intelligence(AI)model,employing a multilayer perceptron(MLP)as a surrogate.The model leverages the hybrid finitediscrete element model(FDEM)as a powerful method in rock fracture mechanics to generate a sufficiently large training dataset.An automated workflow has been developed for generating the training data,comprising a pipeline that includes pre-processing,solving,and post-processing modules.Subsequently,the AI models were integrated into an optimisation framework alongside uncertainty quantification to demonstrate their potential in enhancing drilling efficiency through optimised bit design and operations.The MLP exhibits high accuracy in predicting key parameters,including rebound velocity,total crack length,quantities of fragments with different sizes and maximum contact force between rock and insert.Notably,this approach achieves real-time prediction compared to the 5-7 min simulation times of FDEM.Integrating this data-driven model into a design framework enables rapid assessment of different bit designs under various operational conditions.More broadly,this approach has the potential to impact other applications,such as digital twins,serving as a forward and inverse model for predicting rock type and optimising drilling performance.
基金supported by the EPSRC Grand Challenge grant“Managing Air for Green Inner Cities”(MAGIC)EP/N010221/1.
文摘Numerical simulations are widely used as a predictive tool to better understand complex air flows and pollution transport on the scale of individual buildings,city blocks,and entire cities.To improve prediction for air flows and pollution transport,we propose a Variational Data Assimilation(VarDA)model which assimilates data from sensors into the open-source,finite-element,fluid dynamics model Fluidity.VarDA is based on the minimization of a function which estimates the discrepancy between numerical results and observations assuming that the two sources of information,forecast and observations,have errors that are adequately described by error covariance matrices.The conditioning of the numerical problem is dominated by the condition number of the background error covariance matrix which is ill-conditioned.In this paper,a preconditioned VarDA model is presented,it is based on a reduced background error covariance matrix.The Empirical Orthogonal Functions(EOFs)method is used to alleviate the computational cost and reduce the space dimension.Experimental results are provided assuming observed values provided by sensors from positions mainly located on roofs of buildings.
