Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularl...Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.展开更多
The Huayangchuan ore belt is located in the western segment of Xiaoqinling Orogen in the southern margin of the North China Craton(NCC),and hosts voluminous magmatism and significant U-REE-Mo-Cu-Fe polymetallic minera...The Huayangchuan ore belt is located in the western segment of Xiaoqinling Orogen in the southern margin of the North China Craton(NCC),and hosts voluminous magmatism and significant U-REE-Mo-Cu-Fe polymetallic mineralization.However,geochronological framework of the various mineralization phases in this region is poorly understood.Here,we present new Re-Os isochron ages on magnetite from the Caotan Fe deposit(2 675 ± 410 Ma,MSWD = 0.55),and on pyrite from the Jialu REE deposit(2 127 ± 280 Ma,MSWD = 1.9) and Yuejiawa Cu deposit(418 ± 23 Ma,MSWD =11.5),and Re-Os weighted average model age on pyrite from the Taoyuan Mo-U deposit(235 ± 14 Ma,MSWD = 0.17).These ages,combined with regional geology and mineralization ages from other deposits,suggest that mineralization in the Huayangchuan ore belt lasted from the Neoarchean to the Late Mesozoic.The mineralization corresponds to regional tectono-magmatic events,including the Neoarchean alkali magmatism(REE mineralization),Paleoproterozoic plagioclase-amphibolite emplacement(Fe mineralization),Paleoproterozoic pegmatite magmatism(U mineralization),Paleozoic Shangdan oceanic slab subduction-related arc magmatism(Cu mineralization),Early Mesozoic Paleo-Tethys Ocean subduction-related arc magmatism(Mo-U mineralization),and Late Mesozoic Paleo-Pacific oceanic plate subduction direction change-related Mo(-Pb) mineralization.We proposed that the Huayangchuan ore belt has undergone prolonged metallogenic evolution,and the magmatism and associated mineralization were controlled by regional geodynamic events.展开更多
A growing body of evidence shows that climate change can alter the phenology of plants and animals. In this study long-term data from the UK Environmental Change Network （ECN） were analyzed to investigate whether th...A growing body of evidence shows that climate change can alter the phenology of plants and animals. In this study long-term data from the UK Environmental Change Network （ECN） were analyzed to investigate whether there has been a change in the phenology of the ground beetle Pterostichus madidus （Fabricius, 1775）. Pitfall trap data were available from 12 ECN sites across the United Kingdom, most of which have been in operation for more than 15 years. Weather and vegetation datasets were also utilized. Pitfall trap lines were categorized to eight vegetation types. Trend analysis over time was carried out first using all the available dates of capture events, then the datasets grouped by vegetation type and site. Shifts in high-activity periods were also analyzed. P madidus appearance dates advanced significantly at seven sites and in five vegetation types. Peak activity advanced at two sites. At one site the timing of activity became significantly later. The last day of activity did not change significantly, supporting the theory that the cessation of the activity period is more likely to be controlled by photoperiod than temperature. The relationships between phenological variables and climatic factors were also investigated. Howe＇ver, no significant correlations were detected. These results demonstrate that between 1992 and 2008, phenology ofP madidus at seven sites from the eight analyzed has changed. Global warming may be driving these changes and future work will investigate underlying processes.展开更多
It is helpful to improve the seismic design theory of long-span continuous bridges for studying the seismic performance of each cantilever construction state.Taking the Bridge 1 in the north of Changbai-Mountain inter...It is helpful to improve the seismic design theory of long-span continuous bridges for studying the seismic performance of each cantilever construction state.Taking the Bridge 1 in the north of Changbai-Mountain international tourism resort as an example,the authors studied it in shutdown phase and the cantilever construction process,established the simulation model by using Midas / civil,and analyzed time-history of each construction stage for the bridge.The study shows that long-span bridge cantilever construction in northeastern China can be divided into two-year tasks for construction(suspending in winter).It is needed to think about seismic stability of the cantilever position in shut-down phase of winter.The effect of longitudinal vibration is the most disadvantageous influence to bridge,and its calculation results can provide reference for seismic design of similar bridges in the future.展开更多
文摘Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.
基金financially supported by the Academician Workstation of Sino Shaanxi Nuclear Industry Group(Nos.ZSH-YS190101 and ZSH-YS180101)Major Project of Basic and Applied Basic Research in Guangdong Province(No.2019B030302013)。
文摘The Huayangchuan ore belt is located in the western segment of Xiaoqinling Orogen in the southern margin of the North China Craton(NCC),and hosts voluminous magmatism and significant U-REE-Mo-Cu-Fe polymetallic mineralization.However,geochronological framework of the various mineralization phases in this region is poorly understood.Here,we present new Re-Os isochron ages on magnetite from the Caotan Fe deposit(2 675 ± 410 Ma,MSWD = 0.55),and on pyrite from the Jialu REE deposit(2 127 ± 280 Ma,MSWD = 1.9) and Yuejiawa Cu deposit(418 ± 23 Ma,MSWD =11.5),and Re-Os weighted average model age on pyrite from the Taoyuan Mo-U deposit(235 ± 14 Ma,MSWD = 0.17).These ages,combined with regional geology and mineralization ages from other deposits,suggest that mineralization in the Huayangchuan ore belt lasted from the Neoarchean to the Late Mesozoic.The mineralization corresponds to regional tectono-magmatic events,including the Neoarchean alkali magmatism(REE mineralization),Paleoproterozoic plagioclase-amphibolite emplacement(Fe mineralization),Paleoproterozoic pegmatite magmatism(U mineralization),Paleozoic Shangdan oceanic slab subduction-related arc magmatism(Cu mineralization),Early Mesozoic Paleo-Tethys Ocean subduction-related arc magmatism(Mo-U mineralization),and Late Mesozoic Paleo-Pacific oceanic plate subduction direction change-related Mo(-Pb) mineralization.We proposed that the Huayangchuan ore belt has undergone prolonged metallogenic evolution,and the magmatism and associated mineralization were controlled by regional geodynamic events.
文摘A growing body of evidence shows that climate change can alter the phenology of plants and animals. In this study long-term data from the UK Environmental Change Network （ECN） were analyzed to investigate whether there has been a change in the phenology of the ground beetle Pterostichus madidus （Fabricius, 1775）. Pitfall trap data were available from 12 ECN sites across the United Kingdom, most of which have been in operation for more than 15 years. Weather and vegetation datasets were also utilized. Pitfall trap lines were categorized to eight vegetation types. Trend analysis over time was carried out first using all the available dates of capture events, then the datasets grouped by vegetation type and site. Shifts in high-activity periods were also analyzed. P madidus appearance dates advanced significantly at seven sites and in five vegetation types. Peak activity advanced at two sites. At one site the timing of activity became significantly later. The last day of activity did not change significantly, supporting the theory that the cessation of the activity period is more likely to be controlled by photoperiod than temperature. The relationships between phenological variables and climatic factors were also investigated. Howe＇ver, no significant correlations were detected. These results demonstrate that between 1992 and 2008, phenology ofP madidus at seven sites from the eight analyzed has changed. Global warming may be driving these changes and future work will investigate underlying processes.
文摘It is helpful to improve the seismic design theory of long-span continuous bridges for studying the seismic performance of each cantilever construction state.Taking the Bridge 1 in the north of Changbai-Mountain international tourism resort as an example,the authors studied it in shutdown phase and the cantilever construction process,established the simulation model by using Midas / civil,and analyzed time-history of each construction stage for the bridge.The study shows that long-span bridge cantilever construction in northeastern China can be divided into two-year tasks for construction(suspending in winter).It is needed to think about seismic stability of the cantilever position in shut-down phase of winter.The effect of longitudinal vibration is the most disadvantageous influence to bridge,and its calculation results can provide reference for seismic design of similar bridges in the future.
