期刊文献+
共找到157篇文章
< 1 2 8 >
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
高品质长寿命镀锌铝镁产品研发进展
5
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
机理-数据融合与残差修正的土石坝渗压预测模型研究
6
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
煤矿带式输送机自换电巡检机器人关键技术研究
7
作者 林斌 刘亚军 +1 位作者 吴燕东 董晋国 《煤炭技术》 2025年第3期248-250,共3页
煤矿带式输送机巡检机器人目前亟待解决的关键技术难题:带式输送机巡检机器人的续航能力、故障检测能力以及环境检测能力。为此设计了一款自主快速更换电池机构,提高了巡检机器人的续航能力;提出了基于热红外图像和可见光图像融合的带... 煤矿带式输送机巡检机器人目前亟待解决的关键技术难题:带式输送机巡检机器人的续航能力、故障检测能力以及环境检测能力。为此设计了一款自主快速更换电池机构,提高了巡检机器人的续航能力;提出了基于热红外图像和可见光图像融合的带式输送机异常工况识别的方法,可以有效地在井下恶劣环境中提高带式输送机异常工况的识别精度;提出了基于模型和大数据双驱动的巷道瓦斯浓度预测方法,可实现准确、实时预测巷道瓦斯。 展开更多
关键词 巡检机器人 带式输送机 自主快速换电 图像融合 模型数据双驱动
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
8
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
在线阅读 下载PDF
Ultrahigh Acceleration of Plasma Blocks by Nonlinear Forces for Side-On Laser Ignition of Solid Density Fusion Fuel
9
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
Research on simulation of gun muzzle flow field empowered by artificial intelligence 被引量:1
10
作者 Mengdi Zhou Linfang Qian +3 位作者 Congyong Cao Guangsong Chen Jin Kong Ming-hao Tong 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2024年第2期196-208,共13页
Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow fie... Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal value.Then physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation laws.Through two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and expansion.The proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is divided.It is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous area.Comparison with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation accuracy.The proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions. 展开更多
关键词 Muzzle flow field Artificial intelligence Deep learning data-physical fusion driven Shock wave
在线阅读 下载PDF
基于数据驱动的分布式光伏发电功率预测方法研究进展 被引量:9
11
作者 董明 李晓枫 +4 位作者 杨章 常益 任明 张崇兴 焦在滨 《电网与清洁能源》 CSCD 北大核心 2024年第1期8-17,28,共11页
从综述的角度,以分布式光伏系统为对象,分析了功率预测技术的发展情况、存在的难点以及主要影响因素,梳理了应用数据驱动方法实现功率准确预测的技术路线。再以空间相关性、历史出力功率以及气象等影响因素为切入点,梳理了光伏系统数据... 从综述的角度,以分布式光伏系统为对象,分析了功率预测技术的发展情况、存在的难点以及主要影响因素,梳理了应用数据驱动方法实现功率准确预测的技术路线。再以空间相关性、历史出力功率以及气象等影响因素为切入点,梳理了光伏系统数据驱动的功率预测研究现状,分析其相应的数据增强、时空图信息以及特征融合的手段,讨论了技术的优缺点。最后给出了功率预测数据驱动方法研究方向和发展建议。 展开更多
关键词 分布式光伏出力特性 数据驱动 数据增强 时空图信息 特征融合
在线阅读 下载PDF
Analysis of Fusion Process Model—Case Study
12
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
在线阅读 下载PDF
A New Approach to Software Development Fusion Process Model
13
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
在线阅读 下载PDF
数智时代的信息分析方法:数据驱动、知识驱动及融合驱动 被引量:17
14
作者 卢小宾 霍帆帆 +1 位作者 王壮 霍朝光 《中国图书馆学报》 CSSCI 北大核心 2024年第1期29-44,共16页
数智时代,面对大数据、大知识所带来的挑战,如何创新发展信息分析方法,关乎新时代信息分析工作的开展,关乎数据资源的开发利用。本文在梳理现有信息分析方法的基础上,提出数据驱动、知识驱动,以及数据与知识融合驱动的三种数智型方法思... 数智时代,面对大数据、大知识所带来的挑战,如何创新发展信息分析方法,关乎新时代信息分析工作的开展,关乎数据资源的开发利用。本文在梳理现有信息分析方法的基础上,提出数据驱动、知识驱动,以及数据与知识融合驱动的三种数智型方法思路。首先,提出基于文本、网络、音频、图像等的数据驱动以及与之相应的文本挖掘、图挖掘、音频挖掘、图像挖掘等信息分析模式;其次,提出基于专家知识库、通用知识库、领域知识图谱、通用知识图谱等的知识驱动信息分析模式;最后,提出基于特征、模型、决策三种层面的数据与知识融合驱动的信息分析模式。通过以上三种方法,构建能够系统融合大数据、大知识的信息分析方法,实现数智融合型信息分析,促进图书情报学科方法论发展,赋能国家决策和社会治理。图3。表1。参考文献59。 展开更多
关键词 信息分析 数智时代 数据驱动 知识驱动 融合驱动
在线阅读 下载PDF
支撑新型配电网数字化规划的图形⁃模型⁃数据融合关键技术 被引量:6
15
作者 余涛 王梓耀 +3 位作者 孙立明 曹华珍 吴亚雄 吴毓峰 《电力系统自动化》 EI CSCD 北大核心 2024年第6期139-153,共15页
配电网规划领域期盼实现智能规划,其愿景在于实现无人或少人干预的全自动规划。在数字化转型的背景下,新型配电网规划将面临图形多样化、场景碎片化、数据规模化三大挑战。文中从图形-模型-数据融合的角度提出三大关键技术:基于电气图... 配电网规划领域期盼实现智能规划,其愿景在于实现无人或少人干预的全自动规划。在数字化转型的背景下,新型配电网规划将面临图形多样化、场景碎片化、数据规模化三大挑战。文中从图形-模型-数据融合的角度提出三大关键技术:基于电气图纸识别和拓扑智能分析的图形-模型融合技术、基于知识驱动的负荷/新能源推演分析和智能决策的模型-数据融合技术、基于多模态数据融合和多时空数据联动的图形-数据融合技术,尝试打破理论研究与数字化工程的壁垒。最后,对未来新型配电网数字化规划的发展进行思考和展望,为实现“以机为主,人机协同”的大闭环模式提供借鉴。 展开更多
关键词 图形-模型-数据融合 配电网 数字化规划 知识驱动 图计算
在线阅读 下载PDF
一种Wi-Fi RTT/数据驱动惯性导航行人室内定位方法 被引量:1
16
作者 周宝定 胡超 +3 位作者 孙超 刘旭 吴鹏 杨钧富 《测绘通报》 CSCD 北大核心 2024年第4期76-82,共7页
为了研究基于智能手机的行人室内定位方法,并提高其精度,本文提出了一种基于Wi-Fi往返时间(RTT)、惯性测量单元(IMU)的定位系统。该方法主要包括3部分:(1)使用扩展卡尔曼滤波融合测距信息的Wi-Fi RTT室内定位方法;(2)适用于多手机使用... 为了研究基于智能手机的行人室内定位方法,并提高其精度,本文提出了一种基于Wi-Fi往返时间(RTT)、惯性测量单元(IMU)的定位系统。该方法主要包括3部分:(1)使用扩展卡尔曼滤波融合测距信息的Wi-Fi RTT室内定位方法;(2)适用于多手机使用模式的航位推算方法,该方法基于长短时记忆模型(LSTM)建立神经网络模型,预测行人运动速度及航向;(3)基于误差状态卡尔曼滤波的Wi-Fi RTT/数据驱动惯性导航融合定位方法,进一步提高定位精度。试验结果表明,与单一的基于Wi-Fi RTT方法和数据驱动惯性导航方法相比,本文方法的平均定位精度提升了10%~20%。 展开更多
关键词 智能手机 数据驱动惯性导航 Wi-Fi RTT 行人航迹推算 融合定位
在线阅读 下载PDF
激光间接驱动柱几何内界面减速段的流体力学不稳定性实验研究
17
作者 涂绍勇 蒋炜 +12 位作者 尹传盛 于承新 范征锋 袁永腾 蒲昱东 缪文勇 胡昕 李晋 杨轶濛 车兴森 董云松 杨冬 杨家敏 《强激光与粒子束》 CAS CSCD 北大核心 2024年第12期22-28,共7页
研究收缩几何下的流体力学不稳定性增长对于惯性约束聚变靶丸降低流体力学不稳定性增长和混合的优化设计具有重要的作用。在神光100 kJ激光装置上开展了辐射驱动柱几何内界面减速段的流体力学不稳定性实验,观测到模耦合现象,以及收缩几... 研究收缩几何下的流体力学不稳定性增长对于惯性约束聚变靶丸降低流体力学不稳定性增长和混合的优化设计具有重要的作用。在神光100 kJ激光装置上开展了辐射驱动柱几何内界面减速段的流体力学不稳定性实验,观测到模耦合现象,以及收缩几何独有的Bell-Plesset(BP)效应,理论预估BP效应导致的扰动增长与实验结果基本一致。实验中观察到驱动不对称性引入的2阶模扰动,M2不对称性约为11%,提出了通过增加黑腔长度来优化驱动不对称性的方法。柱几何流体力学不稳定性增长研究将有助于理解收缩几何效应在高能量密度条件下对流体力学不稳定性增长的影响,为优化惯性约束聚变靶丸设计提供帮助。 展开更多
关键词 柱几何 减速段 流体力学不稳定性 间接驱动 惯性约束聚变
在线阅读 下载PDF
物理—数据双驱动的压裂压力实时预测方法
18
作者 胡晓东 刘俊仪 +4 位作者 王天宇 周福建 卢旭涛 易普康 陈超 《石油实验地质》 CAS CSCD 北大核心 2024年第6期1323-1335,共13页
井口压力预测存在压力波动剧烈、干扰因素多以及影响机理复杂等问题。现阶段研究中,由于对复杂的地层条件、裂缝特征及流体动力学过程的过度简化,传统物理模型难以捕捉多重非线性变化和突发波动,导致在真实施工环境下的预测精度和实时... 井口压力预测存在压力波动剧烈、干扰因素多以及影响机理复杂等问题。现阶段研究中,由于对复杂的地层条件、裂缝特征及流体动力学过程的过度简化,传统物理模型难以捕捉多重非线性变化和突发波动,导致在真实施工环境下的预测精度和实时响应能力受到局限。而人工智能模型尽管具有较强的非线性拟合能力,但往往缺乏对压力波动的物理机理的深入理解,对地层和施工参数的敏感性不足,导致在极端或动态变化的条件下稳定性较差、解释性不足。针对这一难题,提出了一种物理—数据双驱动的压力曲线的预测方法对未来压力趋势进行预测。首先,构建了基于长短期记忆(LSTM)神经网络的智能模型,融合缝内支撑剂床平衡高度计算结果与井场实时泵注数据作为模型输入,预测了未来60 s的压力数据;其次,结合传统井口压力反演方法,使用小波变换分解智能模型与传统模型预测结果,利用LSTM模型整体趋势与压力反演计算方法(IPC)模型中突变点特征,重构了兼顾整体趋势和局部波动的井口压力预测曲线。结果表明,相比LSTM模型,IPC和LSTM的小波融合模型未来60 s井口压力预测的均方根误差(RMSE)和均方绝对误差(MAE)分别下降了37.87%和15.29%,预测结果能够精准捕捉现场施工的压裂压力变化,为现场施工提供更为可靠的指导和决策依据。 展开更多
关键词 压裂压力预测 物理—数据双驱 LSTM IPC 小波变换 融合模型
在线阅读 下载PDF
数据驱动的机身对接过程仿真技术研究
19
作者 王仲奇 聂晓乐 +3 位作者 李佳伟 王安洋 赵阳 常正平 《航空制造技术》 CSCD 北大核心 2024年第16期48-58,93,共12页
针对传统机身对接仿真中理论模型偏差较大、有限元模型消耗时间长等问题,开展数据驱动的机身对接过程仿真技术研究。首先通过虚实融合技术,构建六自由度平台运动学模型和机身–调姿平台位姿转换模型,通过数据交互实现仿真数据实时传输... 针对传统机身对接仿真中理论模型偏差较大、有限元模型消耗时间长等问题,开展数据驱动的机身对接过程仿真技术研究。首先通过虚实融合技术,构建六自由度平台运动学模型和机身–调姿平台位姿转换模型,通过数据交互实现仿真数据实时传输从而驱动虚拟模型,利用测量数据和虚拟模型进行了机身对接仿真,确定了对接过程位姿参数,为调姿平台参数修正提供数据基础。之后为提升数据求解效率,根据求解机身变形的有限元模型,计算出变形量并转化成机身位置变化量,将机身姿态角和位置变化量作为输入输出值构建代理模型,并验证方法有效性。最后开发了机身对接过程仿真系统,以机身试验件的对接过程为例,验证了仿真系统的可行性。 展开更多
关键词 机身对接 虚实融合 数据驱动 代理模型 系统开发
在线阅读 下载PDF
融合多源数据的深度学习短时降水预测
20
作者 夏景明 戴如晨 谈玲 《计算机系统应用》 2024年第8期123-131,共9页
针对传统降水预测方法的局限性,提出了一种融合多源数据的深度学习短时降水预测模型MSF-Net.在GPM历史降水数据的基础上融合了ERA5气象数据、雷达数据和DEM数据.利用气象特征提取模块学习多源数据的气象特征,通过注意力融合预测模块进... 针对传统降水预测方法的局限性,提出了一种融合多源数据的深度学习短时降水预测模型MSF-Net.在GPM历史降水数据的基础上融合了ERA5气象数据、雷达数据和DEM数据.利用气象特征提取模块学习多源数据的气象特征,通过注意力融合预测模块进行特征融合并实现短时降水预测.将MSF-Net的降水预测结果与多种人工智能方法进行对比,实验结果表明,MSF-Net模型的风险评分TS和偏差评分Bias最优,表明其可以在6 h的预测时效内提升数据驱动降水预测的效果. 展开更多
关键词 深度学习 短时降水预测 注意力机制 数据融合 数据驱动
在线阅读 下载PDF
上一页 1 2 8 下一页 到第
使用帮助 返回顶部