The explosive growth of lithium-ion battery literature has led to severe knowledge overload,challenging researchers'ability to efficiently extract structured information.While large language models(LLMs)offer cons...The explosive growth of lithium-ion battery literature has led to severe knowledge overload,challenging researchers'ability to efficiently extract structured information.While large language models(LLMs)offer considerable potential for automating this task,their practical application in scientific domains is nonetheless constrained by high application programming interface(API)costs and computational resources required for fine-tuning.To address these limitations,a cognition-enhanced instruction framework(CEIF)is proposed,wherein a high-performance teacher model(such as DeepSeek-R1)provides dynamic feedback,prompt refinement,and training data optimization to guide the learning process of low-parameter models.Experimental results demonstrate that the low-parameter models(6B-9B)optimized via the CEIF achieve approximately 85%accuracy in battery literature extraction tasks,approaching the performance of GPT-4 while requiring only a single NVIDIA RTX 3090 GPU.Furthermore,the emergence of an"Aha moment"characterized by rapid performance improvement during specialized learning is observed,offering novel theoretical insights for the design and optimization of domainspecific models.展开更多
Because the last closed flux-surface （LCFS） finally determines the shape of plasma cross-section, and the shaping of plasma is a key issue directly related with lots of the hot subjects of an advanced tokamak（AT） ...Because the last closed flux-surface （LCFS） finally determines the shape of plasma cross-section, and the shaping of plasma is a key issue directly related with lots of the hot subjects of an advanced tokamak（AT） and of a reactor, e. g., the control on the current density, equilibrium, scrapeoff layer（SOL）, aspects of edge particle and energy, high plasma kinetic energy, and of course, the MHD instability suppression, the further studies on the LCFS related subjects, e. g., its determination, flux loss, etc., are still tokamak research. It equilibrium, poloidal needed for present is also important to get precise LCFS-related equilibrium or configuration properties for the controls on an AT and for the understandings on the underlying basic physical issues in a discharge.展开更多
本文研究了一个包含波动CISK(Convective Instability of the Second Kind)机制的扰动方程数值模式中,基本气流对低频振荡数值模拟的影响。结果显示,当基本气流为纬向均匀风场U时,振荡周期随U的增加而减小:当U取2 m s-1时,周期从50～60 ...本文研究了一个包含波动CISK(Convective Instability of the Second Kind)机制的扰动方程数值模式中,基本气流对低频振荡数值模拟的影响。结果显示,当基本气流为纬向均匀风场U时,振荡周期随U的增加而减小:当U取2 m s-1时,周期从50～60 d减小到30 d;当U减小到-1 m s-1时,振荡周期增加为70～80 d。这是由于低频振荡是从西向东传播,西风基本气流能加快扰动东传,反之东风基本气流会抑制扰动东传,使振荡周期增加。同时,模式中的边界层顶出现误差时,模拟结果会有敏感的响应。若边界层顶取值比标准值高,对流加热反馈作用过大,出现扰动增长过快的现象,传播到80°～90°E附近时,扰动不再继续传播,而是无限增长;而边界层顶取值比标准值低时,对流加热反馈过小,扰动增长小且衰减加快,扰动传播不远便耗散到零,扰动循环周期表现为热源的周期。展开更多
基金supported by the National Natural Science Foundation of China(NSFC)under grant numbers of 52277222,52406256,and 52177217the Shanghai Science and Technology Development Fund under grant number 22ZR14445000the Artificial Intelligence for Research Paradigm Reform Enabling Discipline Leapfrog Program Project Funding Grant。
文摘The explosive growth of lithium-ion battery literature has led to severe knowledge overload,challenging researchers'ability to efficiently extract structured information.While large language models(LLMs)offer considerable potential for automating this task,their practical application in scientific domains is nonetheless constrained by high application programming interface(API)costs and computational resources required for fine-tuning.To address these limitations,a cognition-enhanced instruction framework(CEIF)is proposed,wherein a high-performance teacher model(such as DeepSeek-R1)provides dynamic feedback,prompt refinement,and training data optimization to guide the learning process of low-parameter models.Experimental results demonstrate that the low-parameter models(6B-9B)optimized via the CEIF achieve approximately 85%accuracy in battery literature extraction tasks,approaching the performance of GPT-4 while requiring only a single NVIDIA RTX 3090 GPU.Furthermore,the emergence of an"Aha moment"characterized by rapid performance improvement during specialized learning is observed,offering novel theoretical insights for the design and optimization of domainspecific models.
基金Supported by the National Natural Science Foundation of China（10175022）, and Sichuan Provincial Youth Foundation for Science and Technology （04zp026-032）
文摘Because the last closed flux-surface （LCFS） finally determines the shape of plasma cross-section, and the shaping of plasma is a key issue directly related with lots of the hot subjects of an advanced tokamak（AT） and of a reactor, e. g., the control on the current density, equilibrium, scrapeoff layer（SOL）, aspects of edge particle and energy, high plasma kinetic energy, and of course, the MHD instability suppression, the further studies on the LCFS related subjects, e. g., its determination, flux loss, etc., are still tokamak research. It equilibrium, poloidal needed for present is also important to get precise LCFS-related equilibrium or configuration properties for the controls on an AT and for the understandings on the underlying basic physical issues in a discharge.
文摘本文研究了一个包含波动CISK(Convective Instability of the Second Kind)机制的扰动方程数值模式中,基本气流对低频振荡数值模拟的影响。结果显示,当基本气流为纬向均匀风场U时,振荡周期随U的增加而减小:当U取2 m s-1时,周期从50～60 d减小到30 d;当U减小到-1 m s-1时,振荡周期增加为70～80 d。这是由于低频振荡是从西向东传播,西风基本气流能加快扰动东传,反之东风基本气流会抑制扰动东传,使振荡周期增加。同时,模式中的边界层顶出现误差时,模拟结果会有敏感的响应。若边界层顶取值比标准值高,对流加热反馈作用过大,出现扰动增长过快的现象,传播到80°～90°E附近时,扰动不再继续传播,而是无限增长;而边界层顶取值比标准值低时,对流加热反馈过小,扰动增长小且衰减加快,扰动传播不远便耗散到零,扰动循环周期表现为热源的周期。
