期刊文献+
共找到181篇文章
< 1 2 10 >
每页显示 20 50 100
A Fusion Neutron Source Driven Sub-Critical Nuclear Energy System: A Way for Early Application of Fusion Technology 被引量:11
1
作者 吴宜灿 《Plasma Science and Technology》 SCIE EI CAS CSCD 2001年第6期1085-1092,共8页
This paper proposes a sub-critical nuclear energy system driven by fusion neutron source, FDS, which can be used to transmute long-lived radioactive wastes and to produce fissile nuclear fuel as a way for early applic... This paper proposes a sub-critical nuclear energy system driven by fusion neutron source, FDS, which can be used to transmute long-lived radioactive wastes and to produce fissile nuclear fuel as a way for early application of fusion technology. The necessity and feasibility to develop that system in China are illustrated on the basis of prediction of the demand of energy source in the first half of the 21th century, the status of current fission energy supply and the progress in fusion technology in the world. The characteristics of fusion neutron driver and the potential for transmutation of long-lived nuclear wastes and breeding of fissile nuclear fuel in a blanket are analyzed. A scenario of development steps is proposed. 展开更多
关键词 A Way for Early Application of fusion Technology A fusion Neutron Source driven Sub-Critical Nuclear Energy System
在线阅读 下载PDF
Neutronics Optimization of LiPb-He Dual-Cooled Fuel Breeding Blanket for the Fusion-Driven sub-critical System 被引量:1
2
作者 郑善良 吴宜灿 《Plasma Science and Technology》 SCIE EI CAS CSCD 2002年第4期1421-1428,共8页
The concept of the liquid Li17Pb83 and Helium gas dual-cooled Fuel Breeding Blanket (FBB) for the Fusion-Driven sub-critical System (FDS) is presented and analyzed. Taking self-sustaining tritium (TBR >1.05) and an... The concept of the liquid Li17Pb83 and Helium gas dual-cooled Fuel Breeding Blanket (FBB) for the Fusion-Driven sub-critical System (FDS) is presented and analyzed. Taking self-sustaining tritium (TBR >1.05) and annual output of 100 kg or more fissile 239Pu (FBR > 0.238) as objective parameters, and based on the three-dimensional Monte Carlo neutron-photon transport code MCNP/4A, a neutronics-optimizated calculation of different cases was carried out and the concept is proved feasible. In addition, the total breeding ratio ( BR = TBR + FBR ) is listed corresponding to different cases. 展开更多
关键词 NEUTRONICS fusion - driven sub-exitical system LiPb-He dual-coded fuel breeding blanket
在线阅读 下载PDF
Implosion Plasma Driven Fusion Pellet of Inertial Confinement(A Short Memorandum)
3
作者 Rahele Zadfathollah Seyed Kamal Mousavi Balgehshiri +2 位作者 Ali Zamani Paydar Masoud J.Moghaddam Bahman Zohuri 《Journal of Energy and Power Engineering》 2023年第1期15-26,共12页
The implosion plasma drive fusion pellet of inertial confinement is a concept related to nuclear fusion,a process in which atomic nuclei combine to form heavier nuclei,releasing a large amount of energy in the process... The implosion plasma drive fusion pellet of inertial confinement is a concept related to nuclear fusion,a process in which atomic nuclei combine to form heavier nuclei,releasing a large amount of energy in the process.The implosion plasma drive fusion pellet is a potential fuel source for achieving controlled nuclear fusion.ICF(inertial confinement fusion)is a technique used to achieve fusion by compressing a small target containing fusion fuel to extremely high densities and temperatures using lasers or other methods.The implosion plasma drive fusion pellet concept involves using a small pellet of deuterium and tritium(two isotopes of hydrogen)as fusion fuel,and then rapidly heating and compressing it using a pulsed power system.The implosion process creates a high-pressure plasma that ignites the fusion reactions,releasing energy in the form of neutrons and charged particles.The resulting energy can be captured and used for power generation.This technology is still in the experimental stage,and significant research and development is required to make it commercially viable.However,it has the potential to provide a virtually limitless source of clean energy with no greenhouse gas emissions or long-term radioactive waste.Be that as it may,ICF has to get exact control of the implosion process,mitigate insecurities,and create modern materials and advances to resist the extraordinary conditions of the combined response. 展开更多
关键词 Plasma fusion plasma driven fusion magnetic reconnection TOKAMAK magnetic confinement fusion ICF
在线阅读 下载PDF
Thermal Physics and Statistical Mechanics Driven Inertial Confinement Fusion(ICF)Inducing a Controlled Thermonuclear Energy
4
作者 Bahman Zohuri Farahnaz Behgounia Masoud J.Moghaddam 《Journal of Energy and Power Engineering》 2021年第1期20-38,共19页
In the 1970s,scientists began experimenting with powerful laser beams to compress and heat the hydrogen isotopes to the point of fusion,a technique called ICF(Inertial Confinement Fusion).In the“direct drive”approac... In the 1970s,scientists began experimenting with powerful laser beams to compress and heat the hydrogen isotopes to the point of fusion,a technique called ICF(Inertial Confinement Fusion).In the“direct drive”approach to ICF,powerful beams of laser light are focused on a small spherical pellet containing micrograms of deuterium and tritium.The rapid heating caused by the laser“driver”makes the outer layer of the target explode.In keeping with Isaac Newton’s Third Law“For every action,there is an equal and opposite reaction”,the remaining portion of the target is driven inwards in a rocket-like implosion,causing compression of the fuel inside the capsule and the formation of a shock wave,which further heats the fuel in the very center and results in a self-sustaining burn.The fusion burn propagates outward through the cooler,outer regions of the capsule much more rapidly than the capsule can expand.Instead of magnetic fields,the plasma is confined by the inertia of its own mass—hence the term inertial confinement fusion.A similar process can be observed on an astrophysical scale in stars and the terrestrial uber world,that have exhausted their nuclear fuel,hence inertially or gravitationally collapsing and generating a supernova explosion,where the results can easily be converted to induction of energy in control forms for a peaceful purpose(i.e.,inertial fusion reaction)by means of thermal physics and statistical mechanics behavior of an ideal Fermi gas,utilizing Fermi-Degeneracy and Thomas-Fermi theory.The fundamental understanding of thermal physics and statistical mechanics enables us to have a better understanding of Fermi-Degeneracy as well as Thomas-Fermi theory of ideal gas,which results in laser compressing matter to a super high density for purpose of producing thermonuclear energy in way of controlled form for peaceful shape and form i.e.CTR(Controlled Thermonuclear Reaction).In this short review,we have concentrated on Fundamental of State Equations by driving them as it was evaluated in book Statistical Mechanics written by Mayer,J.and Mayer,M.in this article. 展开更多
关键词 RENEWABLE nonrenewable source of energy fusion reactors super high density matter laser driven fusion energy Fermi-Degeneracy Thomas-Fermi theory return on investment total cost of ownership
在线阅读 下载PDF
Laser-initiated p-^(11)B fusion reactions in petawatt high-repetition-rate laser facilities
5
作者 M.Scisciò G.Petringa +43 位作者 Z.Zhu M.R.D.Rodrigues M.Alonzo P.L.Andreoli F.Filippi Fe.Consoli M.Huault D.Raffestin D.Molloy H.Larreur D.Singappuli T.Carriere C.Verona P.Nicolai A.McNamee M.Ehret E.Filippov R.Lera J.A.Pérez-Hernández S.Agarwal M.Krupka S.Singh V.Istokskaia D.Lattuada M.La Cognata G.L.Guardo S.Palmerini G.Rapisarda K.Batani M.Cipriani G.Cristofari E.Di Ferdinando G.Di Giorgio R.De Angelis D.Giulietti J.Xu L.Volpe M.D.Rodríguez-Frías L.Giuffrida D.Margarone D.Batani G.A.P.Cirrone A.Bonasera Fa.Consoli 《Matter and Radiation at Extremes》 2025年第3期58-74,共17页
Driving of the nuclear fusion reaction p+^(11)B3α+8.7 MeV under laboratory conditions by interaction between high-power laser pulses and matter has become a popular field of research,owing to its numerous potential a... Driving of the nuclear fusion reaction p+^(11)B3α+8.7 MeV under laboratory conditions by interaction between high-power laser pulses and matter has become a popular field of research,owing to its numerous potential applications:as an alternative to deuterium-tritium for fusion energy production,astrophysics studies,and alpha-particle generation for medical treatment.One possible scheme for laser-driven p-^(11)B reactions is to direct a beam of laser-accelerated protons onto a boron(B)sample(the so-called“pitcher-catcher”scheme).This technique has been successfully implemented on large high-energy lasers,yielding hundreds of joules per shot at low repetition.We present here a complementary approach,exploiting the high repetition rate of the VEGA III petawatt laser at CLPU(Spain),aiming at accumulating results from many interactions at much lower energy,to provide better control of the parameters and the statistics of the measurements.Despite a moderate energy per pulse,our experiment allowed exploration of the laser-driven fusion process with tens(up to hundreds)of laser shots.The experiment provided a clear signature of the reactions involved and of the fusion products,accumulated over many shots,leading to an improved optimization of the diagnostics for experimental campaigns of this type.In this paper,we discuss the effectiveness of laser-driven p-11B fusion in the pitcher-catcher scheme,at a high repetition rate,addressing the challenges of this experimental scheme and highlighting its critical aspects.Our proposed methodology allows evaluation of the performance of this scheme for laser-driven alpha particle production and can be adapted to high-repetition-rate laser facilities with higher energy and intensity. 展开更多
关键词 petawatt laser p b reactions nuclear fusion reaction pitcher catcher scheme fusion energy alpha particle production high repetition rate laser driven fusion
在线阅读 下载PDF
Effect of laser spot size on fusion neutron yield in laser-deuterium cluster interactions 被引量:1
6
作者 陈光龙 卢海洋 +4 位作者 王成 刘建胜 李儒新 倪国权 徐至展 《Chinese Physics B》 SCIE EI CAS CSCD 2008年第6期2124-2129,共6页
The effect of the laser spot size on the neutron yield of table-top nuclear fusion from explosions of a femtosecond intense laser pulse heated deuterium clusters is investigated by using a simplified model, in which t... The effect of the laser spot size on the neutron yield of table-top nuclear fusion from explosions of a femtosecond intense laser pulse heated deuterium clusters is investigated by using a simplified model, in which the cluster size distribution and the energy attenuation of the laser as it propagates through the cluster jet are taken into account. It has been found that there exists a proper laser spot size for the maximum fusion neutron yield for a given laser pulse and a specific deuterium gas cluster jet. The proper spot size, which is dependent on the laser parameters and the cluster jet parameters, has been calculated and compared with the available experimental data. A reasonable agreement between the calculated results and the published experimental results is found. 展开更多
关键词 CLUSTERS femtosecond intense laser pulse table-top laser driven nuclear fusion
原文传递
Ultrahigh Acceleration of Plasma Blocks by Nonlinear Forces for Side-On Laser Ignition of Solid Density Fusion Fuel
7
作者 Heinrich HORA George H. MILEY +6 位作者 HE Xiantu ZHENG Wudi Paraskevas LALOUSIS Istvan FLDES Sandor SZATMARI Stavros MOUSTAIZIS Reynaldo CASTILLO 《Plasma Science and Technology》 SCIE EI CAS CSCD 2013年第5期420-424,共5页
A fundamental difference of very high intensity laser interaction with plasmas from solid targets appears with lasing at picosecond (ps) pulse durations in contrast to pulses of nanosec-onds (ns). This can be seen... A fundamental difference of very high intensity laser interaction with plasmas from solid targets appears with lasing at picosecond (ps) pulse durations in contrast to pulses of nanosec-onds (ns). This can be seen from the more than 10,000 times higher acceleration with ps pulse du-rations than with thermal pressure determined interaction. A ps pulse duration produces instantly acting high-efficiency nonlinear (ponderomotive) electrodynamic force dominated acceleration in contrast to heating with longer pulses. The ps pulses accelerate high-density plasma blocks. This can be used by a new scheme of side-on driven laser fusion with generating a flame ignition in uncompressed fusion fuel of solid density resulting in a reaction velocity of more than 2000 km/s for DT. 展开更多
关键词 laser driven fusion fast ignition nonlinear (ponderomotive) force ultrahighacceleration
在线阅读 下载PDF
Analysis of Fusion Process Model—Case Study
8
作者 Rupinder Kaur Jyotsna Sengupta 《Journal of Software Engineering and Applications》 2012年第3期119-128,共10页
Fusion Process Model is a software process model to enhance the software development process. Fusion process model have five fundamental phases and one fusion process controller to control and co-ordinate the overall ... Fusion Process Model is a software process model to enhance the software development process. Fusion process model have five fundamental phases and one fusion process controller to control and co-ordinate the overall development process. Fusion Process Model uses 3C-Model to generalize the process of solving the problem in each phase. 3C-Model, which helps in implementing component based development approach and provides firmer control over the software development process. Because of the component driven approach, the risk associated with cost and time is limited to component only and ensure the overall quality of software system, reduce the development cost and time by considering the changing requirements of customer, risk assessment, identification, evaluation and composition of relative concerns at each phase of development process. We have implemented Fusion Process Model to the design of a real world information system and evaluated this implementation with the initial project estimation. 展开更多
关键词 fusion PROCESS MODEL 3C-Model PROCESS MODEL COMPONENT driven Approach
暂未订购
A New Approach to Software Development Fusion Process Model
9
作者 Rupinder Kaur Jyotsna Sengupta 《Journal of Software Engineering and Applications》 2010年第10期998-1004,共7页
There are several software process models that have been proposed and are based on task involved in developing and maintaining software product. The large number of software projects not meeting their expectation in t... There are several software process models that have been proposed and are based on task involved in developing and maintaining software product. The large number of software projects not meeting their expectation in terms of functionality, cost, delivery schedule and effective project management appears to be lacking. In this paper, we present a new software fusion process model, which depicts the essential phases of a software project from initiate stage until the product is retired. Fusion is component based software process model, where each component implements a problem solving model. This approach reduces the risk associated with cost and time, as these risks will be limited to a component only and ensure the overall quality of software system by considering the changing requirements of customer, risk assessment, identification, evaluation and composition of relative concerns at each phase of development process. 展开更多
关键词 PROCESS MODEL fusion PROCESS MODEL COMPONENT driven Development APPROACH 3C-Model
暂未订购
钢结构疲劳的“模-数”融合驱动理论模型与性能确定方法——以腐蚀疲劳问题为例 被引量:1
10
作者 张清华 唐琨 +3 位作者 崔闯 马燕 袁晓鹏 李亚鹏 《土木工程学报》 北大核心 2025年第7期1-13,27,共14页
数据源和表征指标单一导致的信息维度不足,是制约钢结构疲劳性能研究的关键问题。文章结合钢结构数智化工程发展的迫切需求和数字技术的最新进展,提出钢结构疲劳的“模-数”(“模型试验-数字仿真”)融合驱动的理论模型与性能确定方法,... 数据源和表征指标单一导致的信息维度不足,是制约钢结构疲劳性能研究的关键问题。文章结合钢结构数智化工程发展的迫切需求和数字技术的最新进展,提出钢结构疲劳的“模-数”(“模型试验-数字仿真”)融合驱动的理论模型与性能确定方法,以严重威胁钢结构安全的腐蚀疲劳问题作为示例,研究并讨论理论模型和方法应用的具体问题。确定腐蚀疲劳表征指标,提出信息提取方法;基于腐蚀焊接接头点云形貌以及断裂力学裂纹扩展理论,构建了数据驱动与物理驱动融合模型,通过调整数据与物理驱动损失函数的权重配比,建立适用的物理信息神经网络(PINN)模型。设计并完成中性盐雾腐蚀试验和疲劳试验,以腐蚀形貌点云数据及裂纹扩展信息作为模型的训练和验证数据,通过腐蚀疲劳寿命PINN预测模型,实现模型试验与数值仿真多维、多源信息的有效融合。研究结果表明:所建立的理论模型能够融合试验数据与物理先验知识,显著提高疲劳寿命预测精度;多源疲劳信息融合能够显著增强模型在应对复杂腐蚀疲劳行为时的鲁棒性和泛化能力;所提出的“模型试验-数字仿真”融合驱动方法为解决钢结构疲劳问题提供了新途径和新范式。 展开更多
关键词 钢结构 疲劳 “模-数”融合驱动理论模型 信息融合 模型试验 数字仿真
原文传递
高品质长寿命镀锌铝镁产品研发进展
11
作者 于浩 程子嫣 邵慧敏 《鞍钢技术》 2025年第1期1-9,共9页
在“双碳”战略目标的推动下,高品质、长寿命镀层的研究与开发日益受到重视,热浸镀锌铝镁以良好的耐腐蚀、耐磨损等性能而广泛应用于汽车、光伏及建筑等多个领域。从成分设计及优化、组织调控、工艺改进等方面总结了热浸镀锌铝镁板的耐... 在“双碳”战略目标的推动下,高品质、长寿命镀层的研究与开发日益受到重视,热浸镀锌铝镁以良好的耐腐蚀、耐磨损等性能而广泛应用于汽车、光伏及建筑等多个领域。从成分设计及优化、组织调控、工艺改进等方面总结了热浸镀锌铝镁板的耐蚀性能提升策略,探讨了先进技术在锌铝镁产品开发中的创新应用。针对锌铝镁镀层工艺的长流程、复杂性,提出了融合驱动技术,以期能够推进热浸镀锌铝镁产品的研发与应用,进一步提升产品质量、稳定性和一致性。 展开更多
关键词 热浸镀 锌铝镁镀层 耐蚀性 融合驱动技术
在线阅读 下载PDF
基于气象监测数据融合和XGBoost算法的雷电智能预警方法
12
作者 张磊 李璨 +1 位作者 田然 章鸣 《微型电脑应用》 2025年第10期187-191,共5页
雷电预警对于防雷减灾、确保航空活动至关重要。为此,研究基于气象监测数据融合和XGBoost算法的雷电智能预警方法,以提升雷电智能预警的临界成功指数。布置多个气象传感器节点,形成气象传感网,采集气象监测数据;利用异常数据驱动的数据... 雷电预警对于防雷减灾、确保航空活动至关重要。为此,研究基于气象监测数据融合和XGBoost算法的雷电智能预警方法,以提升雷电智能预警的临界成功指数。布置多个气象传感器节点,形成气象传感网,采集气象监测数据;利用异常数据驱动的数据融合算法,融合处理采集的数据。利用长短期记忆神经网络,在融合的数据内,提取气象监测数据特征。XGBoost算法依据气象监测数据特征,建立雷电智能预警模型,求解雷电智能预警结果。实验证明所提方法可有效采集并融合处理气象监测数据,可有效实现雷电智能预警。对于各种气象站,所提方法雷电智能预警的临界成功指数高于94.5,雷电智能预警精度较高。 展开更多
关键词 气象监测 数据融合 XGBoost算法 雷电智能预警 异常数据驱动
在线阅读 下载PDF
融合与建构:媒体助力陕西创新发展良好舆论氛围的策略
13
作者 李明德 杜瑶 李龙飞 《新闻知识》 2025年第3期3-12,92,共11页
实施创新驱动,推动高质量发展,是陕西贯彻落实习近平新时代中国特色社会主义思想的重要举措。在这一进程中,媒体需要充分发挥融合与建构功能,助力陕西创新发展良好舆论氛围的营造。本研究以媒介融合理论与媒介建构理论为框架,基于Pytho... 实施创新驱动,推动高质量发展,是陕西贯彻落实习近平新时代中国特色社会主义思想的重要举措。在这一进程中,媒体需要充分发挥融合与建构功能,助力陕西创新发展良好舆论氛围的营造。本研究以媒介融合理论与媒介建构理论为框架,基于Python文本挖掘、关键词聚类、语义网络与案例分析,研究媒体助力陕西创新发展良好舆论氛围的基本策略:推进创新驱动高质量发展提速、提升主流媒体服务大局水平、带动发挥全媒体平台新动能。根据实证数据指出策略的效果及不足,并提出建议:积极实践创新思维、将报道向“四个面向”倾斜、充分运用新媒体和自媒体、有效发挥市级媒体作用、利用新兴技术为宣传赋能,向“生态型”传播网络转化,为陕西经济社会高质量发展做好舆论支持。 展开更多
关键词 媒体赋能 创新驱动 舆论氛围 融合建构 策略优化
在线阅读 下载PDF
理论数据协同分析的路面性能预测 被引量:2
14
作者 刘文博 杨旭 +2 位作者 汪海年 徐坤 范泰博 《长安大学学报(自然科学版)》 北大核心 2025年第1期38-49,共12页
道路变形及结构强度是路面性能评价的重要内容,实现上述两者的精确预测对于道路科学养护决策具有重要意义,但当前研究对于其发展预测精度仍有待提升。为提升路面性能预测效果,提出一种理论-数据双驱动的路面性能预测方法。首先基于影响... 道路变形及结构强度是路面性能评价的重要内容,实现上述两者的精确预测对于道路科学养护决策具有重要意义,但当前研究对于其发展预测精度仍有待提升。为提升路面性能预测效果,提出一种理论-数据双驱动的路面性能预测方法。首先基于影响机理理论分析确定路面性能发展的关键影响因子,随后基于分析结果及北京环道足尺试验场数据确定模型输入、输出变量,最终提出一种时间卷积网络-门控制循环融合预测模型(TCN-GRU)实现车辙、承载力的发展预测,并与基础单模型及时间卷积网络-长短时记忆网络融合模型(TCN-STM)进行对比。研究结果表明:对于车辙深度预测,TCN-GRU取得了最好的预测性能,其M_(SE)、R_(MSE)、M_(AE)及R^(2)分别为22.635、4.758、3.319及0.940,其中R^(2)相比单模型(TCN、GRU)分别提升0.53%与0.86%;对于弯沉值发展预测,TCN-GRU同样取得了最好的预测性能,其M_(SE)、R_(MSE)、M_(AE)及R^(2)分别为8.009、2.830、1.819及0.850,R^(2)相比单模型(TCN、GRU)分别提升5.85%与2.04%;提出的TCN-GRU对道路车辙及承载力发展预测效果最好,其充分结合了TCN的长时依赖建模能力和GRU的高效状态更新优势,提升了序列数据的预测准确性与效率,可以基于历史数据实现对特定道路的车辙及承载力发展的精确预测,为公路养护管理部门科学养护决策提供数据支撑。 展开更多
关键词 道路工程 路面性能预测 双驱动 理论-数据 融合模型 TCN-GRU
原文传递
机理-数据融合与残差修正的土石坝渗压预测模型研究 被引量:3
15
作者 黄昊冉 谷艳昌 +2 位作者 陈斯煜 王士军 黄海兵 《水利学报》 北大核心 2025年第3期398-410,共13页
机理模型预测评估土石坝渗流安全性态,物理意义明确、可解释性好,但是预测精度波动性较大。通过麻雀搜索算法(SSA)与径向基函数(RBF)对渗透系数进行反演并构建SSA-RBF渗压预测代理模型,得到模型预测值与残差序列;通过变分模态分解(VMD)... 机理模型预测评估土石坝渗流安全性态,物理意义明确、可解释性好,但是预测精度波动性较大。通过麻雀搜索算法(SSA)与径向基函数(RBF)对渗透系数进行反演并构建SSA-RBF渗压预测代理模型,得到模型预测值与残差序列;通过变分模态分解(VMD)将残差序列进行分解,并通过长短时记忆网络(LSTM)进行训练得到残差序列修正模型;将机理模型与数据驱动模型叠加构建得到SSA-RBF-VMD-LSTM融合模型,并实现对渗压水位准确预测。工程实例表明:本文提出的模型具有较高预测精度,相比于统计模型、LSTM模型和SSA-RBF-LSTM模型,其预测精度提高了89.64%、69.59%、60.45%,且在过程线出现较大幅度变动时,该模型仍能够及时给出准确的预测值,模型稳定性与外推能力较好,具有推广使用价值。 展开更多
关键词 土石坝 代理模型 麻雀搜索算法 变分模态分解 LSTM神经网络 机理-数据驱动融合
在线阅读 下载PDF
基于深度特征融合模型的电动汽车不同模式充电时长自适应预测
16
作者 韦介洋 申江卫 +3 位作者 陈峥 魏福星 夏雪磊 刘永刚 《储能科学与技术》 北大核心 2025年第11期4330-4345,共16页
精准预测锂电池充电时长能够提升充电效率、优化资源分配,对电动汽车的发展具有重要意义。本工作提出了一种基于深度特征融合模型的电动汽车不同模式下充电时长自适应预测方法。首先,对新能源汽车监控平台采集的车辆运行数据进行清洗和... 精准预测锂电池充电时长能够提升充电效率、优化资源分配,对电动汽车的发展具有重要意义。本工作提出了一种基于深度特征融合模型的电动汽车不同模式下充电时长自适应预测方法。首先,对新能源汽车监控平台采集的车辆运行数据进行清洗和分割,结合充电电压、电流及平均功率划分充电模式,形成快慢充数据集;接着,基于充电数据集采用主成分分析(PCA)提取模型输入特征;其次,融合Attention注意力机制构建多层感知器(MLP)模型,对输入特征进行非线性映射获取中间特征;考虑到从原始数据中直接提取的特征无法全面反映与充电时长间的复杂关系,故引入随机森林(RF)模型,根据RF内部分裂原理构造叶节点规则特征,发掘隐含的特征信息;然后,在MLP建立“规则层”处理融合的中间特征与规则特征,实现两模型的结构性融合。最后,对Attention MLP-RF融合模型预测结果进行验证,结果显示,融合模型在快、慢充模式下预测平均绝对误差分别为4.25分钟和6.68分钟,平均绝对百分比误差分别仅有4.33%和3.86%,实现了不同电动汽车充电时长的精准预测。同时,该方法对于电池老化和短时充电情况下的充电时长预测仍具有很高的精度,平均预测误差不超过2分钟,融合模型整体具有很强的预测性能及泛化能力。 展开更多
关键词 锂离子电池 数据驱动 充电模式 充电时长 特征融合
在线阅读 下载PDF
基于语义驱动的红外与可见光图像交互融合
17
作者 王瑾春 马萍 +2 位作者 张宏立 王聪 苑茹 《哈尔滨工业大学学报》 北大核心 2025年第9期56-64,共9页
为解决现有的红外与可见光图像融合算法存在像素信息保留和语义特征提取不足的问题,提出一种基于语义驱动的红外与可见光图像交互融合算法。首先,通过联合操作图像融合网络和图像分割网络,形成语义驱动效果,更好地保留图像在像素域和语... 为解决现有的红外与可见光图像融合算法存在像素信息保留和语义特征提取不足的问题,提出一种基于语义驱动的红外与可见光图像交互融合算法。首先,通过联合操作图像融合网络和图像分割网络,形成语义驱动效果,更好地保留图像在像素域和语义域的信息特征;然后,构建跨域交互整合模块,捕捉红外与可见光图像特征,允许特征在不同空间和独立通道之间交互传递,实现特征从局部到全局的映射,增强两类图像的互补特性;最后,引入语义损失函数约束网络训练以保留源图像的内在语义特征。在多波段图像数据集和多光谱道路场景数据集上进行图像融合和分割实验,并与其他6种先进的融合算法进行比较。融合实验结果表明,本文算法在基于梯度的相似性度量、信息熵、峰值信噪比、空间频率、标准差、视觉保真度6个客观评价指标上分别平均提高了47.92%、6.15%、0.87%、44.31%、35.99%、36.88%;分割实验结果表明,本文算法在所有评价指标中,结果均为最优。所提算法在主观视觉效果的定性分析与客观质量评价的定量指标方面整体效果优于现有融合算法,融合图像可以兼顾视觉质量和高级语义任务,能更好地服务于人类视觉观察和机器视觉感知。 展开更多
关键词 交互融合 红外与可见光图像 语义驱动 语义分割
在线阅读 下载PDF
基于Transformer-GAT并行特征融合的数据驱动的电力系统暂态稳定评估
18
作者 侯一帆 徐天奇 +1 位作者 李琰 李晓兰 《科学技术与工程》 北大核心 2025年第21期8945-8954,共10页
随着电力系统的快速发展,大规模新能源并网及源网荷储协同优化增加了电力电子设备的比重,使得电网稳定性,特别是暂态稳定性评估,变得尤为重要。针对传统方法在拓扑结构考虑不足的问题,提出了一种基于Transformer-图注意力网络(graph att... 随着电力系统的快速发展,大规模新能源并网及源网荷储协同优化增加了电力电子设备的比重,使得电网稳定性,特别是暂态稳定性评估,变得尤为重要。针对传统方法在拓扑结构考虑不足的问题,提出了一种基于Transformer-图注意力网络(graph attention network,GAT)并行特征融合的深度学习方法,用于电力系统暂态稳定性评估。以母线电压幅值、相角及拓扑邻接矩阵作为输入特征,利用西门子仿真软件PSS/E生成批量数据,并通过Transformer和GAT并行提取特征,采用注意力机制进行加权融合。与其他方法的对比结果表明,该方法在IEEE 39节点系统中模拟了不同负荷条件和故障工况,结果表明评估精度和鲁棒性较高,能够有效提升电力系统的安全稳定性。 展开更多
关键词 暂态稳定性 数据驱动 注意力机制 TRANSFORMER 图注意力网络 特征融合
在线阅读 下载PDF
基于D3QN的目标驱动移动机器人自主导航方法
19
作者 卢赵清 王宏伟 +2 位作者 何丽 司盼召 陈耀华 《电子测量技术》 北大核心 2025年第9期9-18,共10页
在未知或危险环境中(如应急救灾、抢险救援),传统导航方法因无法预先获得先验地图和位置信息,难以实现特定目标的导航。本文提出了一种基于竞争双深度Q网络(D3QN)的目标驱动移动机器人自主导航方法。该方法的跨模态融合模块对不同模态... 在未知或危险环境中(如应急救灾、抢险救援),传统导航方法因无法预先获得先验地图和位置信息,难以实现特定目标的导航。本文提出了一种基于竞争双深度Q网络(D3QN)的目标驱动移动机器人自主导航方法。该方法的跨模态融合模块对不同模态特征动态加权融合,在整合观测数据的同时充分捕捉环境信息,增强了对环境的感知能力。在此基础上,设计了一种通用的目标驱动导航方法,使用YOLOv5识别特定目标(如火焰、烟雾)并获取其位置,用识别出的目标位置替代深度强化学习导航中的预设位置点,实现自主导航至特定目标。仿真实验结果表明,本文方法在导航成功率等指标上具有显著优势,在简单、复杂和动态场景中,成功率分别提高了9%、27%和38%。此外,在简单仿真环境中训练的模型,能够直接部署在复杂的仿真环境和真实场景中,表现出良好的泛化能力。 展开更多
关键词 深度强化学习 D3QN算法 多模态融合 识别与定位 目标驱动导航
原文传递
烧结优化配矿研究现状 被引量:2
20
作者 章新宇 潘从元 +6 位作者 袁溢 申远 谢蒙 余正伟 龙红明 唐银华 陈良军 《中国冶金》 北大核心 2025年第7期96-108,共13页
烧结优化配矿作为钢铁冶金生产的关键环节,旨在通过多矿种协同配比实现资源高效利用、成本控制与冶炼性能优化,对提高资源利用率、改善烧结矿质量、降低生产成本与能耗有重要意义。然而,随着优质铁矿资源日益紧缺和原料结构复杂化,传统... 烧结优化配矿作为钢铁冶金生产的关键环节,旨在通过多矿种协同配比实现资源高效利用、成本控制与冶炼性能优化,对提高资源利用率、改善烧结矿质量、降低生产成本与能耗有重要意义。然而,随着优质铁矿资源日益紧缺和原料结构复杂化,传统配矿方法因依赖静态线性模型与经验决策,难以应对矿石成分波动、多目标优化、多工序动态耦合及非线性指标约束等挑战,尤其在处理化学成分、成本、冶金性能的协同优化时存在显著局限。以遗传算法、粒子群优化为代表的智能算法通过融合数据驱动与机理模型,可显著提升多目标优化能力,为突破多目标动态优化瓶颈提供了新路径。系统梳理了烧结优化配矿的研究进展,对比传统方法与智能算法的适用边界,并针对动态响应、跨工序协同及数据-机理融合等核心问题,提出构建智能低碳配矿体系的技术方向,为钢铁行业实现资源集约化利用与智能化转型提供理论支撑与实践参考。 展开更多
关键词 烧结优化 智能配矿 数据驱动 机理融合 多目标优化
在线阅读 下载PDF
上一页 1 2 10 下一页 到第
使用帮助 返回顶部