期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到187,084篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Numerical simulation and analysis of risk factors leading to pancreaticobiliary reflux:Insights from a computational fluid dynamics study to idealized models 认领 引用 被引量：1
1
作者 Nian-Zong Hou Zhao-Guang Wang +5 位作者 Guan-Qing Xiong Ming-Zhe Li Yan Hou Hai Hu Kai Wang Yu-Long Yang 《Hepatobiliary & Pancreatic Diseases International》 SCIE CAS CSCD 2026年第2期198-211,共14页
Background:The analysis and prediction of pancreaticobiliary reflux(PBR)play a crucial role in planning surgical interventions for hepato-biliary-pancreatic diseases,considering the uncertain mechanism behind it.Howev... Background:The analysis and prediction of pancreaticobiliary reflux(PBR)play a crucial role in planning surgical interventions for hepato-biliary-pancreatic diseases,considering the uncertain mechanism behind it.However,current practices are limited by fragmented clinical observations,making it challenging to visualize the complex phenomenon in the pancreaticobiliary junction(PBJ)through imaging and radiography experiments.This study aimed to comprehensively describe the retrograde flow characteristics in various PBR scenarios and assess the factors leading to PBR using simulations based on idealized geometry and boundary conditions.Methods:By Cadence Pointwise,we developed a computational fluid dynamics(CFD)model using an idealized PBJ system.Standard parameters such as pressure and viscosity were applied,along with typical assumptions relevant to fluid dynamic modeling.Subsequently,based on the aforementioned basic idealized model,we analyzed 8 hypothetical PBR conditions,covering a range of high(shorter)and low(longer)values or different positions for each specific parameter,at a representative stage of a peristaltic propagation cycle of the Oddi's sphincter.Results:We modeled a two-dimensional PBJ with the propagation of a peristaltic wave.These findings demonstrated that the shortened septum,the extended ampulla,the increased wavelength and enhanced amplitude of the Oddi's sphincterial peristalsis,the widened diameter difference and the increased pressure difference between the common bile duct(CBD)and the main pancreatic duct(MPD),as well as the gravitational effect(position),strongly impacted PBR,while the viscosity of bile and pancreatic juice had a weaker influence.Additionally,an inequality incorporating these risk factors was developed for the evaluation of whether reflux occurs.Conclusions:Numerical simulation can be used to describe the reflux flow field,offering the possibility to visualize and analyze PBR,which has the potential to significantly revolutionize the understanding of PBR and improve clinical decision-making.Future work should focus on bridging the gap between CFD and clinical practice. 展开更多
关键词 Pancreaticobiliary reflux Computational fluid dynamics
暂未订购 下载PDF
基于MPC集成自适应PID的菠萝田间无人驾驶农机路径跟踪控制方法 认领 引用
2
作者 刘天湖 孙伟龙 +2 位作者 陈嘉鹏 梁兆正 刘舒阳 《农业机械学报》 EI CAS CSCD 北大核心 2026年第7期373-382,395,共10页
路径跟踪是实现菠萝田间管理无人驾驶农机自主行走的基础。为了提高导航精度与安全,提出一种模型预测控制(Model predictive control,MPC)集成自适应PID的路径跟踪控制方法。首先,开发了无人驾驶实验平台,并建立了其运动学模型。其次,... 路径跟踪是实现菠萝田间管理无人驾驶农机自主行走的基础。为了提高导航精度与安全,提出一种模型预测控制(Model predictive control,MPC)集成自适应PID的路径跟踪控制方法。首先,开发了无人驾驶实验平台,并建立了其运动学模型。其次,基于该运动学模型构建了MPC算法。然后,为实现高精度的路径跟踪,提出了一种MPC和自适应PID相结合的控制方法。通过仿真和田间实验对MPC集成自适应PID控制方法、MPC控制方法和自适应PID控制方法进行了比较。仿真和田间实验均表明,MPC集成自适应PID控制方法具有更高的路径跟踪精度、更小的横向误差和平滑的航向角变化,并且在田间曲线路径,该控制方法在速度1 m/s和2 m/s时的横向误差和航向角误差仍然保持在-0.162~0.162 m和-6°~6°。该研究为菠萝田间管理无人驾驶农机的路径跟踪提供了可行的解决方案和理论支撑,为其他无人驾驶农机的路径跟踪控制提供了参考思路。 展开更多
关键词 菠萝田 无人驾驶农机 路径跟踪 MPC 自适应PID
暂未订购 下载PDF
基于强化学习的轻型货车自适应MPC路径跟踪控制 认领 引用
3
作者 王志红 杨东浩 +3 位作者 胡杰 曾嘉荣 廖啼航 陈家骥 《汽车工程》 EI CSCD 北大核心 2026年第7期1552-1564,共13页
针对固定权重MPC在复杂工况下路径跟踪精度不足的问题,本文提出一种基于强化学习的自适应MPC方法。首先,基于车辆动力学模型构建转角增量式MPC控制器,在代价函数中引入可动态调节的全局权重系数,并设置分步长权重系数以实现预测时域内... 针对固定权重MPC在复杂工况下路径跟踪精度不足的问题,本文提出一种基于强化学习的自适应MPC方法。首先,基于车辆动力学模型构建转角增量式MPC控制器,在代价函数中引入可动态调节的全局权重系数,并设置分步长权重系数以实现预测时域内的差异化权重分配,从而增强控制器权重设计的灵活性。随后,构建基于双延迟深度确定性策略梯度(TD3)的强化学习模型,训练目标兼顾跟踪精度与行驶稳定性,使权重参数能够随车辆状态和道路条件自适应协同调整。最后,进行TruckSim/Simulink联合仿真与实车试验。实车试验结果表明,横向误差方差、航向误差方差及转向盘转角方差分别为0.041 m、0.106 rad和234.226°,均优于对照算法,验证了该方法在控制性能与自适应调节能力方面的优越性。 展开更多
关键词 自动驾驶控制 路径跟踪 MPC 强化学习
暂未订购 下载PDF
基于LSTM-NGO-MPC控制器的农机横向跟踪控制方法 认领 引用 被引量：2
4
作者 王瞧 魏世博 +2 位作者 吴翔 牛群峰 王莉 《农机化研究》 北大核心 2026年第7期117-125,共9页
针对智能农机路径跟踪控制中车辆动力学模型不准确和所用控制器权重难以自适应调节问题,提出了一种基于融合长短期记忆(LSTM)神经网络和北方苍鹰优化(NGO)算法的农机横向跟踪模型预测控制(MPC)方法,以提高农机横向跟踪控制精度。首先,... 针对智能农机路径跟踪控制中车辆动力学模型不准确和所用控制器权重难以自适应调节问题,提出了一种基于融合长短期记忆(LSTM)神经网络和北方苍鹰优化(NGO)算法的农机横向跟踪模型预测控制(MPC)方法,以提高农机横向跟踪控制精度。首先,在传统MPC路径跟踪控制的基础上,利用LSTM网络对车辆动力学模型进行补偿,从而更准确地反映农机的真实动力学特性。其次,设定横向误差阈值,一旦超过该误差阈值,利用NGO对MPC控制器固定权重参数进行在线自动更新,使二次规划输出的控制量有更好的控制效果。最后,通过MATLAB/Simulink和CarSim软件搭建农机跟踪控制联合仿真系统,通过不同曲率的2个单弯道路径和1个多弯道路径对跟踪效果进行验证实验,结果表明,LSTM-NGO-MPC控制器在车速15 km/h和20 km/h下的跟踪精度远优于传统控制器,在车速为15 km/h的3种路径跟踪中比NGO-MPC控制器提高40.71%、27.86%、11.80%,在车速为20 km/h的3种路径跟踪中比NGO-MPC控制器提高21.28%、22.22%、44.66%。 展开更多
关键词 智能农机 横向跟踪 模型预测控制 长短期记忆神经网络 北方苍鹰优化算法
暂未订购 下载PDF
Data-driven computing ligament loading mechanisms:integration of the computational ligament mechanics models with deep learning 认领 引用 被引量：1
5
作者 Datao Xu Huiyu Zhou +7 位作者 Yi Yuan Zanni Zhang Tianle Jie Zhifeng Zhou Zixiang Gao Liangliang Xiang Meizi Wang Yaodong Gu 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第5期628-672,共45页
Ankle injuries account for more than 25%of sports-related injuries.However,there is a lack of computational mechanics modeling and assessment tools for the ligament loading mechanism(LLM)caused by ankle injury.This st... Ankle injuries account for more than 25%of sports-related injuries.However,there is a lack of computational mechanics modeling and assessment tools for the ligament loading mechanism(LLM)caused by ankle injury.This study combines medical imaging data to construct the subject-specific ankle musculoskeletal model,which considers the subject's individualized characteristics and ligamentous attributes.Furthermore,we developed the structural constitutive model to restore the nonlinear short-term viscoelastic properties of the ligament-dense connective tissue,which can more realistically revert the LLM and reveal the mechanical properties of ankle injury.Based on the computational ligament mechanics(CLM)model,we developed a deep learning-based prediction model to predict LLM by CLM data-driven modeling.The modeling simulation results are highly consistent with the calculation results from the dual fluoroscopic imaging system,which demonstrated that the CLM model has high accuracy.The data-driven modeling performs exceptionally well in predicting ligament loading forces.The findings indicate that the constructed CLM data-driven model has the potential to enhance the accuracy and safety of ankle rehabilitation robots,while also providing personalized,dynamically adjusted rehabilitation training programs.The proposed comprehensive solutions would bring benefits to more patients with sports injuries and the general rehabilitation population,and promote the development and advancement of the research field of CLM and biomechanical variable prediction. 展开更多
关键词 Computational ligament mechanics Subject-specific musculoskeletal model Structural constitutive model Ankle ligament injury mechanisms Biomechanical variable prediction
暂未订购 下载PDF
基于多参考点线性MPC的类车机器人路径跟踪 认领 引用
6
作者 白国星 刘飞 +3 位作者 孟宇 顾青 宋治玮 刘绍冲 《浙江大学学报（工学版）》 EI CAS CSCD 北大核心 2026年第4期679-689,共11页
针对传统类车机器人路径跟踪控制方法在精确性和实时性之间的矛盾,提出基于多参考点线性模型预测控制的方法(MRP-LMPC).该方法通过重新设定线性化展开点并修正差分模型,结合非线性与线性迭代预测获得非线性补偿量,再提取多个参考路径点... 针对传统类车机器人路径跟踪控制方法在精确性和实时性之间的矛盾,提出基于多参考点线性模型预测控制的方法(MRP-LMPC).该方法通过重新设定线性化展开点并修正差分模型,结合非线性与线性迭代预测获得非线性补偿量,再提取多个参考路径点,构建能够适应曲率突变的MRP-LMPC控制器.联合仿真验证表明,所提出的MRP-LMPC在U形路径上的最大横向位移误差为0.0971 m,在单车道变换路径上的最大横向位移误差为0.1185 m.在硬件在环实验中,在无定位误差的情况下,最大位移误差为0.1897 m;在有定位误差的情况下,最大位移误差为0.2486 m.与相同条件下的非线性预测控制(NMPC)相比,MRP-LMPC的精度损失较小,最大误差增加小于0.0949 m.与单参考点线性模型预测控制(SRP-LMPC)和比例积分微分(PID)控制器相比,MRP-LMPC精度优势显著.在实时性方面,所提方法在联合仿真中的最差工况下,平均求解时间为3.53 ms,在硬件在环测试中的最差工况下,平均求解时间为5.59 ms.在所有测试中,最大计算时间占控制周期的比例为44.15%.在相同工况下,相比NMPC,所提方法可将平均求解时间减少39.14%.综上,联合仿真和硬件在环测试的结果表明,MRPLMPC有效地平衡了精度和实时性能,计算速度比NMPC快,精度比PID和SRP-LMPC更高. 展开更多
关键词 路径跟踪控制 类车机器人 模型预测控制(MPC) 线性控制 多参考点
暂未订购 下载PDF
基于MPC算法的水稻培育智能水温控制系统设计及应用 认领 引用
7
作者 王伍梅 倪大虎 +2 位作者 刘银燕 王玉 杜士云 《杂交水稻》 CSCD 北大核心 2026年第3期47-55,共9页
针对两系光温敏核不育系水稻育性不稳定制约杂交水稻推广的核心问题,旨在开发一套低功耗智能控温系统,通过精准维持处理池水温的恒定且在适宜的范围内,为水稻育性稳定性鉴定提供标准化环境。设计了基于低功耗远距离无线电(LoRa)的水稻... 针对两系光温敏核不育系水稻育性不稳定制约杂交水稻推广的核心问题,旨在开发一套低功耗智能控温系统,通过精准维持处理池水温的恒定且在适宜的范围内,为水稻育性稳定性鉴定提供标准化环境。设计了基于低功耗远距离无线电(LoRa)的水稻培育智能水池控温系统,采用“单主控节点+多受控节点”架构,以实现对水稻光温敏核不育系培育水池广域温度的监控。系统集成高精度温度传感器实时采集水温数据,并利用模型预测控制(MPC)方法动态优化控温策略,以克服水池控温系统中制热机存在的惯性与延迟问题,从而实现快速精准的温度调节。通过控制冷热水混合阀门实现水池精准温控,并依托LoRa扩频调制技术与节点间歇休眠机制,在实现1000 m范围内低功耗数据传输的同时,进一步降低了系统能耗。试验结果表明,该系统能将处理池水温波动控制在目标值±0.2℃范围内,控温上升时间缩短至17.6 s,与传统比例积分微分(PID)算法相比,调节速度提高了145.6%。水稻不育系1892S在该控温系统中,设置长日照恒温22.5℃的环境下培育6 d,套袋自交结实率最高为23.61%,而在对照高温自然环境下,1892S套袋自交结实率为0.00%。该系统的应用可有效降低功耗,实现水池的精准温控,提高水稻光温敏核不育系的选育效率,为两系杂交水稻的大面积推广应用提供支撑。 展开更多
关键词 杂交水稻 低功耗 LoRa MPC 控温系统
暂未订购 下载PDF
准PIλR与MPC协同优化的MMC混合控制策略 认领 引用
8
作者 徐鹏 曹方 +5 位作者 李德智 马浩楠 李会娟 彭鑫鑫 王小俊 万世斌 《电子测量与仪器学报》 EI CSCD 北大核心 2026年第3期208-219,共12页
模块化多电平换流器(modular multilevel converter,MMC)因其模块化设计、扩展性和容错能力,在高压直流输电系统中得到广泛应用。传统模型预测控制(model predictive control,MPC)虽具有动态响应快、实现简便的优势,但其高计算负担及环... 模块化多电平换流器(modular multilevel converter,MMC)因其模块化设计、扩展性和容错能力,在高压直流输电系统中得到广泛应用。传统模型预测控制(model predictive control,MPC)虽具有动态响应快、实现简便的优势,但其高计算负担及环流抑制不足的问题限制了其应用。针对这些问题,提出一种改进型间接MPC与分数阶准PIλR(FO-QPIλR)控制器相结合的混合型MPC策略(hybrid model predictive control,H-MPC)。改进型间接MPC优化控制目标并简化滚动优化过程,显著降低了计算负担,同时避免了传统MPC加权因子设置的复杂性,实现快速的电流跟踪与子模块电容均压。与此同时,分数阶准PIλR控制器比传统PI控制器具有更好的动态性能和鲁棒性,无需解耦即可有效抑制环流。为验证所提策略的有效性,与传统间接MPC策略对比,在仿真结果中,环流幅值降低了80%,子模块电容电压波动减少9%;在实验结果中,环流幅值降低了53%,子模块电容电压波动减少10%。仿真与实验结果表明,所提的混合控制策略在保证MPC快速动态响应和输出电流质量的同时,显著抑制了环流谐波,增强了子模块电容电压均衡能力,验证了该策略的有效性与优越性。 展开更多
关键词 模块化多电平换流器 模型预测控制 分数阶 混合型MPC 环流抑制 子模块电容均压
暂未订购 下载PDF
基于路面识别的NSGA-Ⅱ权值优化主动悬架MPC控制 认领 引用
9
作者 寇发荣 姜小娜 +1 位作者 张润朋 邢龙龙 《汽车工程》 EI CSCD 北大核心 2026年第5期1076-1090,共15页
针对车辆悬架系统中路面局部脉冲激励检测不足与模型预测控制权重依赖经验化设定导致性能受限的问题,本文提出一种轻量化语义分割与多目标动态优化的主动悬架分层控制架构。通过构建路面图像数据集,采用以MobileNetV2为骨干网络的轻量化... 针对车辆悬架系统中路面局部脉冲激励检测不足与模型预测控制权重依赖经验化设定导致性能受限的问题,本文提出一种轻量化语义分割与多目标动态优化的主动悬架分层控制架构。通过构建路面图像数据集,采用以MobileNetV2为骨干网络的轻量化DeepLabV3+网络进行实时语义分割;基于1/4车辆模型设计MPC控制器,利用NSGA-Ⅱ算法离线优化生成6类典型路面的Pareto最优权值集。在实际行驶中,通过训练好的神经网络实时识别路面,动态匹配最优控制参数,实现悬架系统在线自适应控制。结果表明:基于DeepLabV3+的语义分割路面识别算法可高效准确地识别多种路面状态;相较于ResNeSt-MPC与定权重MPC控制策略,本文设计的变权重MPC控制策略可根据路面状态调整控制参数,在随机路面下有效改善悬架性能。在脉冲路面工况下,系统调节时间缩短25%以上,提升了悬架的平顺性。 展开更多
关键词 路面识别 NSGA-Ⅱ 模型预测控制(MPC) 主动悬架系统 多目标优化 权值优化
暂未订购 下载PDF
基于模糊MPC的四轮爬壁机器人轨迹跟踪控制 认领 引用
10
作者 高春艳 解衡 +1 位作者 吕晓玲 李满宏 《科学技术与工程》 EI 北大核心 2026年第19期7998-8004,共7页
针对大型储罐除锈机器人在立面作业过程中易受到风力扰动、曲率突变导致轨迹跟踪精度下降的问题,提出一种基于模糊模型预测控制(fuzzy model predictive control,Fuzzy-MPC)策略。首先,构建四轮机器人运动学模型并离散化,得出一个采样... 针对大型储罐除锈机器人在立面作业过程中易受到风力扰动、曲率突变导致轨迹跟踪精度下降的问题,提出一种基于模糊模型预测控制(fuzzy model predictive control,Fuzzy-MPC)策略。首先,构建四轮机器人运动学模型并离散化,得出一个采样周期内的线性离散方程。建立预测模型与多目标优化函数,采用二次优化求最优解。通过对位置误差与航向角误差进行模糊归一化处理,并将其作为模糊控制器的输入变量。采用改进型加权中心平均法进行解模糊计算,输出自适应调整的预测步长、控制步长及权重矩阵参数,实现对MPC控制器参数的实时优化。采用MATLAB/Simulink进行仿真验证,结果表明所提出的模糊MPC方法相较于传统MPC能使位移误差减少49%、误差峰值减少14.65%,航向角误差减少46.7%、误差峰值减少17.4%,验证了所提出的Fuzzy-MPC算法的有效性,为爬壁机器人高精度轨迹跟踪控制提供有效可行的优化策略。 展开更多
关键词 移动机器人 轨迹跟踪控制 模型预测控制(MPC)
暂未订购 下载PDF
Secformer:Privacy-preserving atomic-level componentized transformer-like model with MPC 认领 引用
11
作者 Chi Zhang Tao Shen +3 位作者 Fenhua Bai Kai Zeng Xiaohui Zhang Bin Cao 《Digital Communications and Networks》 SCIE EI CSCD 2026年第1期86-100,共15页
The global surge in Artificial Intelligence(AI)has been triggered by the impressive performance of deep-learning models based on the Transformer architecture.However,the efficacy of such models is increasingly depende... The global surge in Artificial Intelligence(AI)has been triggered by the impressive performance of deep-learning models based on the Transformer architecture.However,the efficacy of such models is increasingly dependent on the volume and quality of data.Data are often distributed across institutions and companies,making cross-organizational data transfer vulnerable to privacy breaches and subject to privacy laws and trade secret regulations.These privacy and security concerns continue to pose major challenges to collaborative training and inference in multi-source data environments.These challenges are particularly significant for Transformer models,where the complex internal encryption computations drastically reduce computational efficiency,ultimately threatening the model's practical applicability.We hence introduce Secformer,an innovative architecture specifically designed to protect the privacy of Transformer-like models.Secformer separates the encoder and decoder modules,enabling the decomposition of computation flows in Transformer-like models and their efficient mapping to Multi-Party Computation(MPC)protocols.This design effectively addresses privacy leakage issues during the collaborative computation process of Transformer models.To prevent performance degradation caused by encrypted attention modules,we propose a modular design strategy that optimizes high-level components by reconstructing low-level operators.We further analyze the security of Secformer's core components,presenting security definitions and formal proofs.We construct a library of fundamental operators and core modules using atomic-level component designs as the basic building blocks for encoders and decoders.Moreover,these components can serve as foundational operators for other Transformer-like models.Extensive experimental evaluations demonstrate Secformer's excellent performance while preserving privacy and offering universal adaptability for Transformer-like models. 展开更多
关键词 Privacy-preserving computation Deep learning Multi-party computation Data sharing
暂未订购 下载PDF
A Computational Modeling Framework for Verifiable Computation Offloading in Resource-Constrained IoT Smart Contract Systems Using Zero-Knowledge and Fuzzy Logic 认领 引用
12
作者 Hong Min Yousef Ibrahim Daradkeh +2 位作者 Jung Taek Seo Mohd Anjum Sana Shahab 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第6期1488-1520,共33页
This study presents a computational modeling framework for efficient and secure computation offloading in Internet of Things(IoT)-enabled smart contract systems.The integration of IoT,edge computing,and blockchain int... This study presents a computational modeling framework for efficient and secure computation offloading in Internet of Things(IoT)-enabled smart contract systems.The integration of IoT,edge computing,and blockchain introduces significant challenges,including limited device capacity,high verification cost,and scalability constraints.Existing blockchain verification approaches depend on computationally intensive cryptographic operations that are inefficient for resource-constrained IoT devices,resulting in increased latency,energy consumption,and transaction costs.To address these issues,this study proposes the Zero-Knowledge Fuzzy Logic Offloading and Rollup(Z-FLOR)framework,an adaptive and energy-efficient model designed to enable secure and verifiable computation in IoT-based smart contract systems.The proposed framework integrates three key components.First,a zero-knowledge proof-based verification model using the Grothl6 zkSNARK module generates compact and privacy-preserving proofs that enable fast and reliable verification.Second,a Fuzzy Logic-Driven Energy-Aware Offloading module dynamically allocates computational tasks between IoT devices,edge servers,and cloud platforms based on energy availability,network delay,and device reliability.Third,an Optimistic Rollup Verification module aggregates proofs off-chain and submits them in batches to reduce gas costs and enhance scalability.Extensive simulation and experimental evaluation across diverse IoT scenarios demonstrate the effectiveness of the proposed computational framework.Results indicate that Z-FLOR achieves 99.7%verification accuracy and 98.9%proof compression efficiency,while gas cost analysis indicates gas cost reductions in the range of 80%-98%.Z-FLOR additionally achieves a 44.0%reduction in latency,5l.0%savings in gas costs,and 38.0%energy consumption compared to baseline approaches.These findings highlight the capability of the proposed approach to serve as a scalable and energy-efficient modeling solution for secure IoT smart contract execution in decentralized environments. 展开更多
关键词 Zero-knowledge proofs zkSNARK IoT smart contracts verifiable computation blockchain scalability edge computing rollup architecture
暂未订购 下载PDF
基于模型蒸馏和MPC的源荷储电力系统调度优化方法 认领 引用
13
作者 周志烽 朱文 +2 位作者 方文崇 马光 李文朝 《自动化与仪器仪表》 2026年第3期336-339,344,共4页
为了提高源荷储电力系统调度的精度与实时性,研究提出了一个基于数据驱动模型、模型预测控制与知识蒸馏的一个源荷储电力系统调度优化模型。该模型通过数据驱动模型挖掘源荷储数据的时序特征与不确定性规律,并利用模型预测控制动态适配... 为了提高源荷储电力系统调度的精度与实时性,研究提出了一个基于数据驱动模型、模型预测控制与知识蒸馏的一个源荷储电力系统调度优化模型。该模型通过数据驱动模型挖掘源荷储数据的时序特征与不确定性规律,并利用模型预测控制动态适配系统的实时波动同时借助知识蒸馏简化模型结构以保留核心优化逻辑,进而提高模型的实时性。结果表明,研究模型预测时序数据的准确率为96.6%、平均绝对误差的平均值为0.73%,刻画系统不确定性的平均覆盖度为0.897。同时该模型调度优化的平均总成本为9.67万元/天,生成决策调度方案的消耗时间与日负荷峰谷差率分别为10.1 min、25.8%。以上数据均优于对比模型,充分证明了研究模型的可行性与优越性,为相关研究提供了新方法。 展开更多
关键词 数据驱动模型 源荷储电力系统 MPC 模型蒸馏 调度优化模型
暂未订购 下载PDF
DRL-Based Cross-Regional Computation Offloading Algorithm 认领 引用
14
作者 Lincong Zhang Yuqing Liu +2 位作者 Kefeng Wei Weinan Zhao Bo Qian 《Computers, Materials & Continua》 SCIE EI 2026年第1期901-918,共18页
In the field of edge computing,achieving low-latency computational task offloading with limited resources is a critical research challenge,particularly in resource-constrained and latency-sensitive vehicular network e... In the field of edge computing,achieving low-latency computational task offloading with limited resources is a critical research challenge,particularly in resource-constrained and latency-sensitive vehicular network environments where rapid response is mandatory for safety-critical applications.In scenarios where edge servers are sparsely deployed,the lack of coordination and information sharing often leads to load imbalance,thereby increasing system latency.Furthermore,in regions without edge server coverage,tasks must be processed locally,which further exacerbates latency issues.To address these challenges,we propose a novel and efficient Deep Reinforcement Learning(DRL)-based approach aimed at minimizing average task latency.The proposed method incorporates three offloading strategies:local computation,direct offloading to the edge server in local region,and device-to-device(D2D)-assisted offloading to edge servers in other regions.We formulate the task offloading process as a complex latency minimization optimization problem.To solve it,we propose an advanced algorithm based on the Dueling Double Deep Q-Network(D3QN)architecture and incorporating the Prioritized Experience Replay(PER)mechanism.Experimental results demonstrate that,compared with existing offloading algorithms,the proposed method significantly reduces average task latency,enhances user experience,and offers an effective strategy for latency optimization in future edge computing systems under dynamic workloads. 展开更多
关键词 Edge computing computational task offloading deep reinforcement learning D3QN device-to-device communication system latency optimization
暂未订购 下载PDF
基于GRU-MPC的双全回转推进拖轮轨迹跟踪控制 认领 引用 被引量：1
15
作者 李诗杰 刘泰序 +2 位作者 刘佳仑 董智霖 徐诚祺 《上海交通大学学报》 EI CAS CSCD 北大核心 2026年第3期418-426,共9页
针对双全回转尾推进拖轮轨迹跟踪控制问题,提出通过门控循环单元(GRU)神经网络构建拖轮三自由度运动数据驱动模型,并基于GRU模型构建模型预测控制(MPC)轨迹跟踪控制器,克服传统控制方法对精确系统机理模型限制.在不改变拖轮推进器转速... 针对双全回转尾推进拖轮轨迹跟踪控制问题,提出通过门控循环单元(GRU)神经网络构建拖轮三自由度运动数据驱动模型,并基于GRU模型构建模型预测控制(MPC)轨迹跟踪控制器,克服传统控制方法对精确系统机理模型限制.在不改变拖轮推进器转速前提下,通过调节左右舵角对拖轮速度与航向进行调控,并通过仿真实验验证所提出方案的有效性.在噪声干扰下,模型精度良好.通过对比不同预测步长下的控制性能,探讨预测步长对控制效果及求解时间的影响.当预测步长增加时,控制精度得到提升,但由于优化求解复杂度提升,求解时间增加.本研究为拖轮的精确轨迹跟踪控制提供新思路,也为类似非线性系统控制研究提供有价值的参考. 展开更多
关键词 全回转尾推进型拖轮控制 模型预测控制 门控循环单元神经网络 轨迹跟踪控制 数据驱动模型
暂未订购 下载PDF
A Multi-Objective Deep Reinforcement Learning Algorithm for Computation Offloading in Internet of Vehicles 认领 引用
16
作者 Junjun Ren Guoqiang Chen +1 位作者 Zheng-Yi Chai Dong Yuan 《Computers, Materials & Continua》 SCIE EI 2026年第1期2111-2136,共26页
Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrain... Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively. 展开更多
关键词 Deep reinforcement learning internet of vehicles multi-objective optimization cloud-edge computing computation offloading service caching
暂未订购 下载PDF
弱电网下基于改进APCL-MPC的构网型变流器快速频率支撑策略 认领 引用
17
作者 顾振宇 孙丹 +2 位作者 陆凯东 胡彬 年珩 《电力自动化设备》 EI CSCD 北大核心 2026年第7期208-216,共9页
针对构网型变流器在低短路比弱电网中有功功率响应速度下降导致频率支撑能力不足的问题,提出一种基于改进有功功率控制环路(APCL)的模型预测控制构网型变流器方案。通过分析APCL动态响应机理,设计含自适应微分补偿与频率偏差调节的改进A... 针对构网型变流器在低短路比弱电网中有功功率响应速度下降导致频率支撑能力不足的问题,提出一种基于改进有功功率控制环路(APCL)的模型预测控制构网型变流器方案。通过分析APCL动态响应机理,设计含自适应微分补偿与频率偏差调节的改进APCL,在保持稳态特性的同时提升频率支撑能力。结合有限控制集模型预测控制的多目标优化能力,将电压电流控制、有功功率响应速度及频率变化率抑制纳入统一约束,优化系统的动态响应。实验结果表明,所提方案在弱电网下可有效提升系统的动态响应速度,增强频率主动支撑性能。 展开更多
关键词 构网型变流器 弱电网 模型预测控制 频率支撑 动态响应能力
暂未订购 下载PDF
Joint computation offloading and service downloading in satellite edge computing networks 认领 引用
18
作者 Wu Qi Zhu Lidong 《China Communications》 SCIE EI CSCD 2026年第4期238-258,共21页
The limited onboard cache and computing resources significantly constrain the computational service capabilities of individual edge satellites in hotspot regions.To address this challenge,we propose a twotier cloud-ed... The limited onboard cache and computing resources significantly constrain the computational service capabilities of individual edge satellites in hotspot regions.To address this challenge,we propose a twotier cloud-edge computing architecture that organizes edge satellites and their associated ground clouds into multiple collaborative domains.Within each domain,we formulate a joint optimization problem for computation offloading and service downloading under the constraints of edge satellites’service deployment and caching space,aiming to minimize the sum of weighted energy consumption and latency.The originally non-convex problem is transformed into a more tractable convex optimization formulation through variable relaxation.Subsequently,we develop an alternating direction method of multipliers(ADMM)-based distributed optimization framework that enables cooperative decision-making among domain satellites for the optimization of computational offloading,service downloading,and service deleting variables.Additionally,we propose an innovative binary variable recovery algorithm that ensures feasible conversion from continuous solutions to discrete decision variables while preserving constraint satisfaction.Extensive simulations demonstrate that our approach achieves lower task execution cost and packet loss rate compared with benchmarks. 展开更多
关键词 alternating direction method of multipliers(ADMMs) cloud-edge computing architecture computation offloading edge satellites service downloading
暂未订购 下载PDF
An Adaptive Hybrid Edge-Cloud Collaborative Offloading Method for Large-Scale Computational Tasks of Intelligent Machine Tool:Low-Latency,Energy-Efficient,and Secure 认领 引用
19
作者 Zhiwen Lin Kaien Wei +4 位作者 Yiqiao Wang Chuanhai Chen Jinyan Guo Qiang Cheng Zhifeng Liu 《Engineering》 SCIE EI CSCD 2026年第1期201-218,共18页
Intelligent machine tools operating in continuous machining environments are commonly influenced by the coupled effects of multi-component degradation and updates in machining tasks.These factors result in the generat... Intelligent machine tools operating in continuous machining environments are commonly influenced by the coupled effects of multi-component degradation and updates in machining tasks.These factors result in the generation of vast multi-source sensor data streams and numerous computational tasks with interdependent data relationships.The stringent real-time constraints and intricate dependency structures present considerable challenges to traditional single-mode computational frameworks.Furthermore,there is a growing demand for computational offloading solutions in intelligent machine tools that extend beyond merely optimizing latency.These solutions must also address energy management for sustainable manufacturing and ensure security to protect sensitive industrial data.This paper introduces an adaptive hybrid edge-cloud collaborative offloading mechanism that combines single-edge-cloud collaboration with multi-edge-cloud collaboration.This mechanism is capable of dynamically switching between collaborative modes based on the status of computational nodes,task characteristics,dependency complexity,and resource availability,ultimately facilitating low-latency,energy-efficient,and secure task processing.A novel hybrid hyper-heuristic algorithm has been developed to address largescale task allocation challenges in heterogeneous edge-cloud environments,enabling the flexible allocation of computational resources and performance optimization.Extensive experiments indicate that the proposed approach achieves average enhancements of 27.36%in task processing time and 7.89%in energy efficiency when compared to state-of-the-art techniques,all while maintaining superior security performance.Validation through case studies on a digital twin gantry five-axis machining center illustrates that the mechanism effectively coordinates task execution across multi-source concurrent data processing,complex dependency task collaboration,high-computational machine learning workloads,and continuous batch task deployment scenarios,achieving a 37.03%reduction in latency and a 25.93%optimization in energy use relative to previous generation collaboration methods.These results provide both theoretical and technical backing for sustainable and secure computational offloading in intelligent machine tools,thereby contributing to the evolution of next-generation smart manufacturing systems. 展开更多
关键词 Intelligent machine tools Edge-cloud collaboration Task offloading Resilient resources Sustainable computing
暂未订购 下载PDF
飞机-牵引车系统MPC高精度轨迹跟踪算法研究 认领 引用
20
作者 魏志民 张威 +1 位作者 马佳琪 崔矗 《机械设计与制造》 北大核心 2026年第5期269-275,281,共7页
为实现飞机地面自动滑行牵引新模式系统的高精度轨迹追踪,在分析滑行牵引模式下飞机-牵引车系统的运动特性基础上,提出并验证一种基于模型预测控制(MPC)的算法。采用“理论建模-算法设计-仿真优化”的技术路线和方法,考虑滑行牵引模式... 为实现飞机地面自动滑行牵引新模式系统的高精度轨迹追踪,在分析滑行牵引模式下飞机-牵引车系统的运动特性基础上,提出并验证一种基于模型预测控制(MPC)的算法。采用“理论建模-算法设计-仿真优化”的技术路线和方法,考虑滑行牵引模式下各种速度,设置牵引环境为对象,构建牵引车的运动学模型,分析不同工况下牵引系统运动学特性。建立MPC预测模型,设计轨迹跟踪最优控制的目标函数,搭建TruckSim/Simulink联合仿真系统,规划典型牵引车运动工况,并开展轨迹跟踪仿真实验,并与传统的线性二次调节器(LQR)算法的轨迹跟踪效果进行对比。结果表明,相较于LQR算法,提出的MPC算法在路径跟踪中具有较高的精度和稳定度,其跟踪横向误差和横摆角误差均在合理范围内,为新型离港模式下牵引系统的自动控制提供理论基础和技术参考。 展开更多
关键词 自动牵引滑行 飞机牵引车 轨迹跟踪 模型预测控制(MPC) 运动学模型
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈