Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods o...Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods often face challenges such as indirect prediction,data sparsity,and data drift,which limit their accuracy and generalizability.This study develops an integrated method that combines a knowledge-driven method to directly compute distribution patterns of lithological components,which are used as a priori knowledge to guide the development of a data-driven method.Coupled Markov chain(CMC)and deep neural networks(DNNs)serve as the knowledge-driven and data-driven components,respectively.Additionally,a dynamic prediction strategy is proposed,where the model is continuously optimized as construction progresses and training samples accumulate,rather than being statically trained on post-construction data,as is common in data-driven methods.Finally,the proposed method is evaluated using a real-world project.The evaluation results show that the integrated method outperforms both individual data-and knowledge-driven methods,demonstrating higher predictive performance,greater stability,and greater robustness to data scarcity and data drift.Furthermore,the dynamic prediction strategy better captures the effects of gradual data accumulation and lithological spatial variability on prediction performance during construction,providing new insights for real-time prediction in practical tunneling applications.展开更多
Large-diameter drilling method is a prevalent method for preventing and controlling rock burst,and the spacing between the large-diameter drilling hole and anchoring hole is a critical factor influencing the roadway s...Large-diameter drilling method is a prevalent method for preventing and controlling rock burst,and the spacing between the large-diameter drilling hole and anchoring hole is a critical factor influencing the roadway stability and relief effectiveness.In this study,a mechanical model for optimal matching between the large-diameter drilling hole and anchoring hole was established following the principle of synergistic control.The influence of large-diameter drilling hole diameter on the optimal spacing under the synergistic relief effect was investigated by integrating theoretical analysis,numerical simulation,and field practice.The results suggest that the hole spacing achieved a synergistic effect in a certain range when the optimal hole spacing increased linearly with the hole diameter.For instance,when the anchoring hole diameter was 20 mm,an increase in the aperture ratio from 5 to 10 brought about an increase in the optimal spacing from 0.25 m to 0.45 m.Additionally,the vertical stress between the large-diameter drilling hole and anchor hole increased nonlinearly under the condition of constant pore ratio but varying hole spacing.Both excessively small and excessively large hole spacings were detrimental to the pressure relief effect.In the engineering practice,optimizing the hole spacing from 0.55 m to 0.45 m in the 1208 working face contributed to reducing coal body drilling cuttings and the roadway moving quantity by 33%and 19.2%,respectively.This demonstrates that the pressure relief-support reinforcement synergistic effect should be fully considered in optimization design.展开更多
[Objectives]This study was conducted to achieve rapid and accurate detection of protein content in rice with a particle size of 1.0 mm.[Methods]A multi-model fusion strategy was proposed on the basis of Stacking ensem...[Objectives]This study was conducted to achieve rapid and accurate detection of protein content in rice with a particle size of 1.0 mm.[Methods]A multi-model fusion strategy was proposed on the basis of Stacking ensemble learning.A base learner pool was constructed,containing Partial Least Squares(PLS),Support Vector Machine(SVM),Deep Extreme Learning Machine(DELM),Random Forest(RF),Gradient Boosting Decision Tree(GBDT),and Multilayer Perceptron(MLP).PLS,DELM,and Linear Regression(LR)were used as meta-learner candidates.Employing integer coding technology,systematic dynamic combinations of base learners and meta-learners were generated,resulting in a total of 40 non-repetitive fusion models.The optimal combination was selected through a comprehensive evaluation based on multiple assessment indicators.[Results]The combination"PLS-DELM-MLP-LR"(code 1367)achieved coefficients of determination of 0.9732 and 0.9780 on the validation set and independent test set,respectively,with relative root mean square errors of 2.35%and 2.36%,and residual predictive deviations of 6.1075 and 6.7479,respectively.[Conclusions]The Stacking fusion model significantly enhances the predictive accuracy and robustness of spectral quantitative analysis,providing an efficient and feasible solution for modeling complex agricultural product spectral data.展开更多
In physics,our expectations for system behavior are often guided by intuitive arithmetic.For systems composed of identical units,we anticipate synergy of the contributions from these units,where 1+1=2.Conversely,for s...In physics,our expectations for system behavior are often guided by intuitive arithmetic.For systems composed of identical units,we anticipate synergy of the contributions from these units,where 1+1=2.Conversely,for systems built from opposing units,we expect cancellation of their contributions,where 1-1=0.This intuitive arithmetic has long underpinned our understanding of physical properties of materials,from electronic transport to optical responses.However,scientific breakthroughs often occur when nature reveals ways to circumvent these seemingly fundamental rules,opening new possibilities that challenge our deepest assumptions about material behavior.展开更多
Tube thinning control without wrinkling occurring is a key problem urgently to be solved for improving the forming qualities in numerical control （NC） bending processes of large-diameter Al-alloy thin-walled tubes ...Tube thinning control without wrinkling occurring is a key problem urgently to be solved for improving the forming qualities in numerical control （NC） bending processes of large-diameter Al-alloy thin-walled tubes （AATTs）. It may be a way solving this problem to exert axial compression loads （ACL） on the tube end in the bending. Thus, this article establishes a three-dimensional （3D） elastic-plastic explicit finite element （FE） model for the bending under ACL and has its reliability verified. Through a multi-index orthogonal experiment design, a combination of process parameters, each expressed by a proper range, for this FE model is derived to overcome the compression instability on tube ends. By combining the FE model with a wrinkling energy prediction model, an in-depth study is conducted on the forming characteristics of large-diameter AATTs with small bending radii and it can be concluded that （1） The larger the tube diameters and the smaller the bending radii, the larger the induced tangent tension stress zones on tube intrados, by which the tube maximum tangent compression stress zones will be partitioned in the bending processes; thus, the smaller the ACL roles in decreasing thinning degrees and the larger the compression instability possibilities on tube ends. （2） The tube wrinkling possibilities under ACL are larger than without ACL acting in the earlier forming periods, and smaller in the later ones. （3） For the tubes with a size factor less than 80, the ACL roles in decreasing thinning degrees are stronger than in increasing wrinkling possibilities.展开更多
文摘董志塬地区位于黄土高原中心地带,滑坡灾害频发,亟需明确滑坡易发性分区,以支持该区域滑坡隐患的科学防控。因此,本文以董志塬为研究区,选取高程、坡向和NDVI等12个影响因素作为评价因子,基于频率比(frequency ratio,FR)模型,结合随机森林(random forest,RF)与人工神经网络(artificial neural network,ANN)模型开展滑坡静态易发性评价,并分析各因子对评价精度的贡献。结果表明,FRRF和FR-ANN模型的曲线下面积(area under the curve,AUC)值分别为0.922和0.918,表明FR-RF模型在董志塬滑坡易发性评价中的精度更高。坡度、坡向和道路密度对滑坡易发性的贡献率分别为16.7%、15.3%和1.4%。为克服地形复杂和数据更新滞后的问题,本文将FR-RF模型的易发性结果与InSAR Stacking结果相结合,将静态滑坡易发性评价精度由6.9%提升到8.1%。动态易发性结果表明,董志塬滑坡高易发区主要分布于河流沿岸,占总面积的6.5%,该区域的滑坡数量占总滑坡数的23.6%,滑坡密度15.7个/km^(2)。低易发区主要位于远离河流的中部区域,占总面积的81.7%,滑坡数量占总滑坡数的57.8%,滑坡密度4.7个/km^(2)。本研究通过融合InSAR Stacking方法,解决了静态滑坡易发性评价数据更新滞后问题,减少了假阴性错误,为传统滑坡易发性评价赋予了时效性,可以实现董志塬滑坡易发性动态评价,为灾害防治提供了重要数据支持。
基金supported by the Beijing Natural Science Foundation(Grant No.8252012)the National Natural Science Foundation of China(Grant No.52378475).
文摘Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods often face challenges such as indirect prediction,data sparsity,and data drift,which limit their accuracy and generalizability.This study develops an integrated method that combines a knowledge-driven method to directly compute distribution patterns of lithological components,which are used as a priori knowledge to guide the development of a data-driven method.Coupled Markov chain(CMC)and deep neural networks(DNNs)serve as the knowledge-driven and data-driven components,respectively.Additionally,a dynamic prediction strategy is proposed,where the model is continuously optimized as construction progresses and training samples accumulate,rather than being statically trained on post-construction data,as is common in data-driven methods.Finally,the proposed method is evaluated using a real-world project.The evaluation results show that the integrated method outperforms both individual data-and knowledge-driven methods,demonstrating higher predictive performance,greater stability,and greater robustness to data scarcity and data drift.Furthermore,the dynamic prediction strategy better captures the effects of gradual data accumulation and lithological spatial variability on prediction performance during construction,providing new insights for real-time prediction in practical tunneling applications.
基金Project(52274086)supported by the National Natural Science Foundation of ChinaProject(2024KJH069)supported by the Shandong Provincial Youth Innovation and Technology Support Program,ChinaProject(tstp20221126)supported by the Project of Taishan Scholar in Shandong Province,China。
文摘Large-diameter drilling method is a prevalent method for preventing and controlling rock burst,and the spacing between the large-diameter drilling hole and anchoring hole is a critical factor influencing the roadway stability and relief effectiveness.In this study,a mechanical model for optimal matching between the large-diameter drilling hole and anchoring hole was established following the principle of synergistic control.The influence of large-diameter drilling hole diameter on the optimal spacing under the synergistic relief effect was investigated by integrating theoretical analysis,numerical simulation,and field practice.The results suggest that the hole spacing achieved a synergistic effect in a certain range when the optimal hole spacing increased linearly with the hole diameter.For instance,when the anchoring hole diameter was 20 mm,an increase in the aperture ratio from 5 to 10 brought about an increase in the optimal spacing from 0.25 m to 0.45 m.Additionally,the vertical stress between the large-diameter drilling hole and anchor hole increased nonlinearly under the condition of constant pore ratio but varying hole spacing.Both excessively small and excessively large hole spacings were detrimental to the pressure relief effect.In the engineering practice,optimizing the hole spacing from 0.55 m to 0.45 m in the 1208 working face contributed to reducing coal body drilling cuttings and the roadway moving quantity by 33%and 19.2%,respectively.This demonstrates that the pressure relief-support reinforcement synergistic effect should be fully considered in optimization design.
文摘[Objectives]This study was conducted to achieve rapid and accurate detection of protein content in rice with a particle size of 1.0 mm.[Methods]A multi-model fusion strategy was proposed on the basis of Stacking ensemble learning.A base learner pool was constructed,containing Partial Least Squares(PLS),Support Vector Machine(SVM),Deep Extreme Learning Machine(DELM),Random Forest(RF),Gradient Boosting Decision Tree(GBDT),and Multilayer Perceptron(MLP).PLS,DELM,and Linear Regression(LR)were used as meta-learner candidates.Employing integer coding technology,systematic dynamic combinations of base learners and meta-learners were generated,resulting in a total of 40 non-repetitive fusion models.The optimal combination was selected through a comprehensive evaluation based on multiple assessment indicators.[Results]The combination"PLS-DELM-MLP-LR"(code 1367)achieved coefficients of determination of 0.9732 and 0.9780 on the validation set and independent test set,respectively,with relative root mean square errors of 2.35%and 2.36%,and residual predictive deviations of 6.1075 and 6.7479,respectively.[Conclusions]The Stacking fusion model significantly enhances the predictive accuracy and robustness of spectral quantitative analysis,providing an efficient and feasible solution for modeling complex agricultural product spectral data.
基金supported by the National Natural Science Foundation of China (Grant No.12374109)the National Key Research and Development Program of China (Grant No.2023YFA1406600)。
文摘In physics,our expectations for system behavior are often guided by intuitive arithmetic.For systems composed of identical units,we anticipate synergy of the contributions from these units,where 1+1=2.Conversely,for systems built from opposing units,we expect cancellation of their contributions,where 1-1=0.This intuitive arithmetic has long underpinned our understanding of physical properties of materials,from electronic transport to optical responses.However,scientific breakthroughs often occur when nature reveals ways to circumvent these seemingly fundamental rules,opening new possibilities that challenge our deepest assumptions about material behavior.
基金National Natural Science Foundation of China (59975076, 50175092)National Science Fund of China for Distinguished Young Scholars (50225518)
文摘Tube thinning control without wrinkling occurring is a key problem urgently to be solved for improving the forming qualities in numerical control （NC） bending processes of large-diameter Al-alloy thin-walled tubes （AATTs）. It may be a way solving this problem to exert axial compression loads （ACL） on the tube end in the bending. Thus, this article establishes a three-dimensional （3D） elastic-plastic explicit finite element （FE） model for the bending under ACL and has its reliability verified. Through a multi-index orthogonal experiment design, a combination of process parameters, each expressed by a proper range, for this FE model is derived to overcome the compression instability on tube ends. By combining the FE model with a wrinkling energy prediction model, an in-depth study is conducted on the forming characteristics of large-diameter AATTs with small bending radii and it can be concluded that （1） The larger the tube diameters and the smaller the bending radii, the larger the induced tangent tension stress zones on tube intrados, by which the tube maximum tangent compression stress zones will be partitioned in the bending processes; thus, the smaller the ACL roles in decreasing thinning degrees and the larger the compression instability possibilities on tube ends. （2） The tube wrinkling possibilities under ACL are larger than without ACL acting in the earlier forming periods, and smaller in the later ones. （3） For the tubes with a size factor less than 80, the ACL roles in decreasing thinning degrees are stronger than in increasing wrinkling possibilities.
