期刊文献+
共找到550,583篇文章
< 1 2 250 >
每页显示 20 50 100
Constrained Networked Predictive Control for Nonlinear Systems Using a High-Order Fully Actuated System Approach 被引量:1
1
作者 Yi Huang Guo-Ping Liu +1 位作者 Yi Yu Wenshan Hu 《IEEE/CAA Journal of Automatica Sinica》 2025年第2期478-480,共3页
Dear Editor,In this letter,a constrained networked predictive control strategy is proposed for the optimal control problem of complex nonlinear highorder fully actuated(HOFA)systems with noises.The method can effectiv... Dear Editor,In this letter,a constrained networked predictive control strategy is proposed for the optimal control problem of complex nonlinear highorder fully actuated(HOFA)systems with noises.The method can effectively deal with nonlinearities,constraints,and noises in the system,optimize the performance metric,and present an upper bound on the stable output of the system. 展开更多
关键词 optimal control problem constrained networked predictive control strategy Performance Optimization present upper bound Nonlinear Systems NOISES Constrained networked Predictive Control High Order Fully Actuated Systems
在线阅读 下载PDF
可解释的轻量化无人机网络入侵检测方法
2
作者 王鹏 郭相科 +1 位作者 宋亚飞 王晓丹 《空军工程大学学报》 北大核心 2026年第1期106-116,共11页
针对无人机算力有限、存储空间小和实时性高的特点,提出一种基于Kolmogorov-Arnold Networks(KAN)的可解释的无人机网络入侵检测方法KIDS。受Kolmogorov-Arnold表示定理的启发,KAN利用样条参数化的单变量函数取代了传统的线性权重,从而... 针对无人机算力有限、存储空间小和实时性高的特点,提出一种基于Kolmogorov-Arnold Networks(KAN)的可解释的无人机网络入侵检测方法KIDS。受Kolmogorov-Arnold表示定理的启发,KAN利用样条参数化的单变量函数取代了传统的线性权重,从而动态地学习激活模式,能够有效提取流量序列数据特征并以更轻量化的网络结构实现优异的无人机网络入侵性能。此外,可视化参数化的样条函数能够进一步探索和解释模型在流量特征提取阶段的决策过程,从而增强模型应用的可信度。最后,在真实无人机网络流量数据集UAV-IDS-2020进行广泛实验。结果表明,KIDS以更低的模型复杂度实现了优异的检测性能,且在跨机型入侵检测任务中表现出显著的泛化性能。 展开更多
关键词 无人机网络入侵检测 Kolmogorov-Arnold Networks 可解释性 网络安全
在线阅读 下载PDF
Passenger travel behavior in urban rail transit based on the networked model
3
作者 Haining Sun Keping Li +2 位作者 Zhiao Ma Yuanxi Xu Yan Liang 《Communications in Theoretical Physics》 2025年第12期1-13,共13页
Urban rail transit is an efficient and environmentally friendly mode of transport,which is an important means of transportation for passengers.From a holistic point of view,this paper constructs an urban rail transit ... Urban rail transit is an efficient and environmentally friendly mode of transport,which is an important means of transportation for passengers.From a holistic point of view,this paper constructs an urban rail transit interchange topology(URTIT)network based on the interchange relationships among lines.We investigate a unique influence propagation mechanism to explore the impact of applying new technologies on the passenger travel behavior of urban rail transit.We analyze the influence from three aspects:the influence range,the influence propagation path,and the influence intensity.Based on the Dijkstra algorithm,the influence propagation paths are found according to the shortest transfer time.The improved path-based gravity model is applied to measure the influence intensity.The case study on urban rail transit in Beijing,China is carried out.The influence propagation mechanism of a single line in the Beijing URTIT network is analyzed,considering that Beijing Subway Line S1 is equipped with magnetic levitation technology.We not only quantify the impact of technologies on passenger travel behavior of urban rail transit,but also perform the sensitivity analysis.To avoid randomness,the influence propagation mechanisms of all lines are explored in this paper.The research results correspond to the situation in reality,which can provide certain references for urban rail transit operation and planning. 展开更多
关键词 urban rail transit topology network influence propagation gravity model
原文传递
Optimal Secure Control of Networked Control Systems Under False Data Injection Attacks:A Multi-Stage Attack-Defense Game Approach
4
作者 Dajun Du Yi Zhang +1 位作者 Baoyue Xu Minrui Fei 《IEEE/CAA Journal of Automatica Sinica》 2025年第4期821-823,共3页
Dear Editor,The attacker is always going to intrude covertly networked control systems(NCSs)by dynamically changing false data injection attacks(FDIAs)strategy,while the defender try their best to resist attacks by de... Dear Editor,The attacker is always going to intrude covertly networked control systems(NCSs)by dynamically changing false data injection attacks(FDIAs)strategy,while the defender try their best to resist attacks by designing defense strategy on the basis of identifying attack strategy,maintaining stable operation of NCSs.To solve this attack-defense game problem,this letter investigates optimal secure control of NCSs under FDIAs.First,for the alterations of energy caused by false data,a novel attack-defense game model is constructed,which considers the changes of energy caused by the actions of the defender and attacker in the forward and feedback channels. 展开更多
关键词 designing defense strategy networked control systems ncss alterations energy networked control systems false data injection attacks fdias strategywhile false data injection attacks optimal secure control identifying attack strategymaintaining
在线阅读 下载PDF
Stackelberg game-based optimal secure control against hybrid attacks for networked control systems
5
作者 Wei Xiong Yi Dong Liubin Zhou 《Journal of Automation and Intelligence》 2025年第3期236-241,共6页
This paper investigates the problem of optimal secure control for networked control systems under hybrid attacks.A control strategy based on the Stackelberg game framework is proposed,which differs from conventional m... This paper investigates the problem of optimal secure control for networked control systems under hybrid attacks.A control strategy based on the Stackelberg game framework is proposed,which differs from conventional methods by considering both denial-of-service(DoS)and false data injection(FDI)attacks simultaneously.Additionally,the stability conditions for the system under these hybrid attacks are established.It is technically challenging to design the control strategy by predicting attacker actions based on Stcakelberg game to ensure the system stability under hybrid attacks.Another technical difficulty lies in establishing the conditions for mean-square asymptotic stability due to the complexity of the attack scenarios Finally,simulations on an unstable batch reactor system under hybrid attacks demonstrate the effectiveness of the proposed strategy. 展开更多
关键词 Stackelberg game networked control systems Hybrid attacks DoS attack FDI attack
在线阅读 下载PDF
Networked control with guaranteed performance for IoT rehabilitation robot under nonvanishing uncertainties and input quantization
6
作者 Shilei Tan Xuesong Wang +1 位作者 Haoquan Zhou Wei Gong 《Digital Communications and Networks》 2025年第6期1774-1782,共9页
The Internet of Things(IoT)technology provides data acquisition,transmission,and analysis to control rehabilitation robots,encompassing sensor data from the robots as well as lidar signals for trajectory planning(desi... The Internet of Things(IoT)technology provides data acquisition,transmission,and analysis to control rehabilitation robots,encompassing sensor data from the robots as well as lidar signals for trajectory planning(desired trajectory).In IoT rehabilitation robot systems,managing nonvanishing uncertainties and input quantization is crucial for precise and reliable control performance.These challenges can cause instability and reduced effectiveness,particularly in adaptive networked control.This paper investigates networked control with guaranteed performance for IoT rehabilitation robots under nonvanishing uncertainties and input quantization.First,input quantization is managed via a quantization-aware control design,ensur stability and minimizing tracking errors,even with discrete control inputs,to avoid chattering.Second,the method handles nonvanishing uncertainties by adjusting control parameters via real-time neural network adaptation,maintaining consistent performance despite persistent disturbances.Third,the control scheme guarantees the desired tracking performance within a specified time,with all signals in the closed-loop system remaining uniformly bounded,offering a robust,reliable solution for IoT rehabilitation robot control.The simulation verifies the benefits and efficacy of the proposed control strategy. 展开更多
关键词 networked control IoT rehabilitation robot Guaranteed performance Nonvanishing uncertainties Input quantization
在线阅读 下载PDF
Blockchain for transactive energy management in networked neighborhood microgrids
7
作者 Zhikun Hu Mingyu Yan +2 位作者 Chongyu Wang Ahmed Alabdulwahab Mohammad Shahidehpour 《iEnergy》 2025年第4期235-246,共12页
The proliferation of distributed and renewable energy resources introduces additional operational challenges to power distribution systems.Transactive energy management,which allows networked neighborhood communities ... The proliferation of distributed and renewable energy resources introduces additional operational challenges to power distribution systems.Transactive energy management,which allows networked neighborhood communities and houses to trade energy,is expected to be developed as an effective method for accommodating additional uncertainties and security mandates pertaining to distributed energy resources.This paper proposes and analyzes a two-layer transactive energy market in which houses in networked neighborhood community microgrids will trade energy in respective market layers.This paper studies the blockchain applications to satisfy socioeconomic and technological concerns of secure transactive energy management in a two-level power distribution system.The numerical results for practical networked microgrids located at IllinoisTech−Bronzeville in Chicago illustrate the validity of the proposed blockchain-based transactive energy management for devising a distributed,scalable,efficient,and cybersecured power grid operation.The conclusion of the paper summarizes the prospects for blockchain applications to transactive energy management in power distribution systems. 展开更多
关键词 networked neighborhood microgrids blockchain system transactive energy management power distribution system distributed energy resources
在线阅读 下载PDF
Impact of peer pressure on cooperation evolution in the networked prisoner’s dilemma game with migration mechanisms
8
作者 Xianjia Wang Yanan Li Zhipeng Yang 《Chinese Physics B》 2025年第11期263-274,共12页
In social and ecological systems,individual migration behavior and peer pressure are crucial factors influencing decision-making and cooperative behavior.However,how migration regulates the evolution of cooperation an... In social and ecological systems,individual migration behavior and peer pressure are crucial factors influencing decision-making and cooperative behavior.However,how migration regulates the evolution of cooperation and the specific role of peer pressure in this process remain to be further investigated.To address this,this study develops a model that incorporates migration mechanisms and peer pressure within the framework of the networked prisoner’s dilemma game.Specifically,we modify the population structure and introduce a migration strategy based on payoff maximization,enabling individuals to dynamically adjust their positions according to the local environment.The model also considers the impact of peer pressure on individual decision-making and introduces heterogeneity in individuals’sensitivity to pressure,thereby systematically examining the role of both factors in the evolution of cooperative behavior.Based on this framework,we further compare our model with a scenario in which no migration mechanism is present to evaluate its impact on cooperative dynamics.The results reveal that the migration mechanism significantly promotes the evolution of cooperative behavior.Under this mechanism,higher individual sensitivity leads to an increased level of cooperation,and stronger peer pressure intensity more effectively enhances the promotion of cooperation.Additionally,the influence of population structure on cooperation frequency cannot be overlooked.An increase in vacant nodes provides cooperators with greater buffering space and more migration opportunities,making cooperative behavior more stable and facilitating its propagation within the system.These findings suggest that appropriately regulating individual mobility and reinforcing peer pressure constraints can enhance the stability and propagation of cooperative behavior,providing significant theoretical support for social governance,organizational management,and group collaboration. 展开更多
关键词 prisoner’s dilemma peer pressure migration mechanism COOPERATION two-dimensional grid network
原文传递
基于树形决策卷积神经网络的滚动轴承故障分层诊断
9
作者 杨旭 吴程飞 +1 位作者 黄健 赵鹰昊 《北京工业大学学报》 北大核心 2026年第1期64-74,共11页
针对传统滚动轴承故障诊断中故障层次信息利用不充分、诊断精度不足的问题,提出一种带有树形决策层的卷积神经网络(convolutional neural network,CNN)方法以实现故障位置与严重程度的逐层诊断。该模型同时具备CNN的特征提取能力和决策... 针对传统滚动轴承故障诊断中故障层次信息利用不充分、诊断精度不足的问题,提出一种带有树形决策层的卷积神经网络(convolutional neural network,CNN)方法以实现故障位置与严重程度的逐层诊断。该模型同时具备CNN的特征提取能力和决策树的层次结构及分层决策特性。首先,采用共享网络层和2个任务特定的分支全连接层分别提取与故障位置和故障严重程度有关的特征;然后,将2个全连接层的分类结果输入到树形决策层,并使用加权层次分类损失调整模型权重参数,从而实现模型对故障层次信息的自学习;最后,应用帕德博恩大学轴承数据集进行算法性能测试。实验结果表明,该模型的平均分类准确率可达99.15%,与领域内其他的诊断模型相比,实现了更准确的故障位置和严重性的分类。 展开更多
关键词 故障诊断 分层诊断 滚动轴承 卷积神经网络(convolutional neural network CNN) 决策树 集成模型
在线阅读 下载PDF
基于空洞因果卷积的学生成绩预测及分析方法
10
作者 赖英旭 张亚薇 +1 位作者 庄俊玺 刘静 《北京工业大学学报》 北大核心 2026年第3期252-267,共16页
针对使用循环神经网络对学生长序列行为数据进行特征提取存在梯度消失或爆炸、长期依赖关系提取能力不足、深度学习模型缺乏可解释性等问题,提出一种面向长序列数据的空洞因果卷积(dilated causal convolution,DCC)成绩预测及分析方法... 针对使用循环神经网络对学生长序列行为数据进行特征提取存在梯度消失或爆炸、长期依赖关系提取能力不足、深度学习模型缺乏可解释性等问题,提出一种面向长序列数据的空洞因果卷积(dilated causal convolution,DCC)成绩预测及分析方法。首先,采用生成对抗网络(generative adversarial network,GAN)生成符合少数类学生原始行为数据分布规律的新样本,并将新样本加入学生数据集中以达到均衡数据集的目的;然后,提出一种基于DCC的成绩预测模型,DCC和门控循环单元(gated recurrent unit,GRU)相结合的结构提高了模型对长序列数据依赖关系的提取能力;最后,使用沙普利加性解释(Shapley additive explanations,SHAP)方法并结合三因素理论对影响学生成绩的因素进行重要性分析和解释。在公开数据集上的实验结果表明,在成绩预测任务中提出的方法与基线方法相比,加权F1分数提高了约6个百分点,并进一步验证了所提方法中关键模块的有效性和模型的泛化能力。此外,通过对比优秀学生和风险学生的学习特点发现,良好的学习习惯、课堂学习的主动性以及不同行为环境等因素会对学生成绩产生重要影响。 展开更多
关键词 学生成绩预测 空洞因果卷积(dilated causal convolution DCC) 不均衡数据 生成对抗网络(generative adversarial network GAN) 沙普利加性解释(Shapley additive explanations SHAP)方法 成绩影响因素分析
在线阅读 下载PDF
Event-Based Networked Predictive Control of Cyber-Physical Systems with Delays and DoS Attacks
11
作者 Wencheng Luo Pingli Lu +1 位作者 Changkun Du Haikuo Liu 《IEEE/CAA Journal of Automatica Sinica》 2025年第6期1295-1297,共3页
Dear Editor,This letter studies the stabilization control issue of cyber-physical systems with time-varying delays and aperiodic denial-of-service(DoS)attacks.To address the calculation overload issue caused by networ... Dear Editor,This letter studies the stabilization control issue of cyber-physical systems with time-varying delays and aperiodic denial-of-service(DoS)attacks.To address the calculation overload issue caused by networked predictive control(NPC)approach,an event-based NPC method is proposed.Within the proposed method,the negative effects of time-varying delays and DoS attacks on system performance are compensated.Then,sufficient and necessary conditions are derived to ensure the stability of the closed-loop system.In the end,simulation results are provided to demonstrate the validity of presented method. 展开更多
关键词 cyber physical systems dos attacks necessary conditions derived denial service attacks time varying delays event based networked predictive control stabilization control calculation overload
在线阅读 下载PDF
GPIO-Based Continuous Sliding Mode Control for Networked Control Systems Under Communication Delays With Experiments on Servo Motors
12
作者 Kamal Rsetam Zhenwei Cao +1 位作者 Zhihong Man Xian-Ming Zhang 《IEEE/CAA Journal of Automatica Sinica》 2025年第1期99-113,共15页
To handle input and output time delays that commonly exist in many networked control systems(NCSs), a new robust continuous sliding mode control(CSMC) scheme is proposed for the output tracking in uncertain single inp... To handle input and output time delays that commonly exist in many networked control systems(NCSs), a new robust continuous sliding mode control(CSMC) scheme is proposed for the output tracking in uncertain single input-single-output(SISO) networked control systems. This scheme consists of three consecutive steps. First, although the network-induced delay in those systems can be effectively handled by using Pade approximation(PA), the unmatched disturbance cames out as another difficulty in the control design. Second, to actively estimate this unmatched disturbance, a generalized proportional integral observer(GPIO) technique is utilized based on only one measured state. Third, by constructing a new sliding manifold with the aid of the estimated unmatched disturbance and states, a GPIO-based CSMC is synthesized, which is employed to cope with not only matched and unmatched disturbances, but also networkinduced delays. The stability of the entire closed-loop system under the proposed GPIO-based CSMC is detailedly analyzed.The promising tracking efficiency and feasibility of the proposed control methodology are verified through simulations and experiments on Quanser's servo module for motion control under various test conditions. 展开更多
关键词 Continuous sliding mode control(CSMC) generalized proportional integral observer(GPIO) networked control systems(NCSs) pade approximation(PA) TIME-DELAY unsmatched disturbances
在线阅读 下载PDF
Robust Predefined-Time Control for Optimal Formation of Networked Mobile Vehicle Systems
13
作者 Jing-Zhe Xu Zhi-Wei Liu +2 位作者 Dingxin He Ming-Feng Ge Ming Chi 《IEEE/CAA Journal of Automatica Sinica》 2025年第4期824-826,共3页
Dear Editor,This letter addresses the robust predefined-time control challenge for leaderless optimal formation in networked mobile vehicle(NMV)systems.The aim is to minimize a composite global cost function derived f... Dear Editor,This letter addresses the robust predefined-time control challenge for leaderless optimal formation in networked mobile vehicle(NMV)systems.The aim is to minimize a composite global cost function derived from individual strongly convex functions of each agent,considering both input disturbances and network communication constraints.A novel predefined-time optimal formation control(PTOFC)algorithm is presented,ensuring agent state convergence to optimal formation positions within an adjustable settling time.Through the integration of an integral sliding mode technique,disturbances are effectively countered.A representative numerical example highlights the effectiveness and robustness of the developed approach. 展开更多
关键词 minimize composite global cost function integral sliding mode technique agent state convergence optimal formation networked mobile vehicle systems robust predefined time control strongly convex functions disturbances
在线阅读 下载PDF
一种基于P4的多模态网络控制与安全检测方案
14
作者 李冬 高源 +2 位作者 于俊清 曾木虹 陈俊鑫 《信息网络安全》 北大核心 2026年第1期115-124,共10页
可编程网络技术通过软件定义和编程技术控制网络设备与数据报文,提升网络灵活性、可扩展性和自动化能力,为多模态网络发展奠定基础。文章基于可编程架构设计了身份、内容、地理位置、弹性地址空间、IPv4、IPv6等6种模态的数据报文路由... 可编程网络技术通过软件定义和编程技术控制网络设备与数据报文,提升网络灵活性、可扩展性和自动化能力,为多模态网络发展奠定基础。文章基于可编程架构设计了身份、内容、地理位置、弹性地址空间、IPv4、IPv6等6种模态的数据报文路由转发机制,并在数据平面实现报文解析、路由寻址与转发。同时,构建多模态网络控制系统,支持报文解析、拓扑管理、流表生成与下发、网络测量等功能,并集成资源协调与调度算法,可实时分析网络状态、计算路由规则并下发流表。文章通过流量特征提取实现安全检测,并基于深度学习构建多模态流量时序模型,实现异常检测与识别,引入内生安全特性,保障系统可用性和可靠性。实验结果表明,文章方案可实现多模态网络统一通信与控制,支持多种模态;控制系统功能完善且性能稳定,拓扑规模超过2000节点,平均端到端时延小于100 ms;安全检测功能可实时识别异常流量与网络模态,其中,异常流量检测准确率达到96.49%,模态识别准确率达到99.72%。 展开更多
关键词 多模态网络 软件定义网络 网络测量 异常检测
在线阅读 下载PDF
Distributed Cooperative Regulation for Networked Re-Entrant Manufacturing Systems
15
作者 Chenguang Liu Qing Gao +1 位作者 Wei Wang Jinhu Lü 《IEEE/CAA Journal of Automatica Sinica》 2025年第3期636-638,共3页
Dear Editor,This letter focuses on the distributed cooperative regulation problem for a class of networked re-entrant manufacturing systems(RMSs).The networked system is structured with a three-tier architecture:the p... Dear Editor,This letter focuses on the distributed cooperative regulation problem for a class of networked re-entrant manufacturing systems(RMSs).The networked system is structured with a three-tier architecture:the production line,the manufacturing layer and the workshop layer.The dynamics of re-entrant production lines are governed by hyperbolic partial differential equations(PDEs)based on the law of mass conservation. 展开更多
关键词 production line networked re entrant manufacturing systems three tier architecture production linethe distributed cooperative regulation hyperbolic partial differential equations pdes based distributed cooperative regulation problem manufacturing layer
在线阅读 下载PDF
基于渗流理论的城市交通网络与供水管网级联失效分析
16
作者 胡群芳 张昱 +3 位作者 宋朝阳 赫磊 车德路 苏展 《同济大学学报(自然科学版)》 北大核心 2026年第1期31-39,共9页
为解决交通网络与供水管网之间耦合关系所引发各类突发事件级联失效作用及其建模量化问题,以上海市中心城区为案例,利用出租车GPS数据及道路、供水管网GIS(Geographic Information System)数据,通过空间匹配和时间属性融合建立动态耦合... 为解决交通网络与供水管网之间耦合关系所引发各类突发事件级联失效作用及其建模量化问题,以上海市中心城区为案例,利用出租车GPS数据及道路、供水管网GIS(Geographic Information System)数据,通过空间匹配和时间属性融合建立动态耦合网络,基于渗流理论提出网络影响力指数用于量化级联失效影响。结果表明,交通网络和供水管网之间存在显著的时空耦合效应,尤其在高峰时段供水管网的失效对交通网络的连通性和运行效率产生了直接影响。同时,通过构建解耦策略,提出管网规划和维护优化方案,可减少2个网络之间跨网络级联失效影响,可为提升城市关键基础设施韧性安全与运行可靠性提供参考。 展开更多
关键词 供水管网 交通网络 耦合网络 复杂网络 渗流理论 级联失效
在线阅读 下载PDF
Joint Probabilistic Scheduling and Resource Allocation for Wireless Networked Control Systems
17
作者 Meng Zheng Lei Zhang Wei Liang 《IEEE/CAA Journal of Automatica Sinica》 2025年第1期258-260,共3页
Dear Editor,This letter presents a joint probabilistic scheduling and resource allocation method(PSRA) for 5G-based wireless networked control systems(WNCSs). As a control-aware optimization method, PSRA minimizes the... Dear Editor,This letter presents a joint probabilistic scheduling and resource allocation method(PSRA) for 5G-based wireless networked control systems(WNCSs). As a control-aware optimization method, PSRA minimizes the linear quadratic Gaussian(LQG) control cost of WNCSs by optimizing the activation probability of subsystems, the number of uplink repetitions, and the durations of uplink and downlink phases. Simulation results show that PSRA achieves smaller LQG control costs than existing works. 展开更多
关键词 subsystem activation probability linear quadratic gaussian control cost number uplink repetitions wireless networked control systems joint probabilistic scheduling resource allocation method psra linear quadratic gaussian lqg G based activation probability subsystems
在线阅读 下载PDF
极端天气下高速公路自洽能源系统应急资源优化调度方案
18
作者 李艳波 张云锐 +4 位作者 杨凯 陈楚润 吕浩楠 武奇生 陈俊硕 《西安交通大学学报》 北大核心 2026年第1期190-200,共11页
针对近年来频发的极端天气灾害对高速公路交通及电力网络基础设施造成严重破坏,导致灾后应急资源调度困难的问题,提出了一种考虑交通网(TN)-电力网(PN)耦合网络的高速公路应急资源优化调度方案。分别搭建TN和PN模型以及TN-PN耦合网络模... 针对近年来频发的极端天气灾害对高速公路交通及电力网络基础设施造成严重破坏,导致灾后应急资源调度困难的问题,提出了一种考虑交通网(TN)-电力网(PN)耦合网络的高速公路应急资源优化调度方案。分别搭建TN和PN模型以及TN-PN耦合网络模型;结合历史气象数据构建极端天气模型并利用蒙特卡罗模拟抽样方法模拟故障场景,得到极端天气运行情况以及线路故障率曲线;利用Dijkstra算法分析应急资源移动路径并构建其调度模型,求出灾后最优调度路线;结合河南某高速公路自洽能源系统的相关数据进行灾后应急资源调度仿真。结果表明:所提优化调度方案比目前常用的两种方案能够提前1~2 h完成故障线路维修,故障负荷的平均负荷恢复量提高了5.95%和2.27%,恢复至正常运行状态所需时间缩短了31.38%和16.28%,可进一步提高应急资源调度效率和高速公路自洽能源系统弹性。 展开更多
关键词 自洽能源系统 极端天气 交通网-电力网耦合网络 应急资源调度
在线阅读 下载PDF
基于复杂网络理论的铁路快捷货物运输网络社团特征及脆弱性研究
19
作者 王宇航 周凌云 +1 位作者 梁川 吴昊 《铁道运输与经济》 北大核心 2026年第2期205-216,共12页
探究铁路快捷货物运输网络内部交互特征与服务稳定性,以支撑网络布局优化与抗风险能力提升。基于复杂网络理论,构建“通道设施-运输组织-运行径路”网络模型;结合模块度优化准则,提出一种基于改进粒子群优化算法的社团划分方法;并考虑... 探究铁路快捷货物运输网络内部交互特征与服务稳定性,以支撑网络布局优化与抗风险能力提升。基于复杂网络理论,构建“通道设施-运输组织-运行径路”网络模型;结合模块度优化准则,提出一种基于改进粒子群优化算法的社团划分方法;并考虑货物价值属性,构建以运输时效与成本为核心的网络性能函数,通过多场景仿真评估网络脆弱性。以中国铁路快捷货物运输网络为例进行研究,结果表明:网络可划分为7个社团,社团分布呈现以区域集聚为主导、跨区域衔接为补充的空间特征。网络整体呈现较高的脆弱性,高脆弱性站点主要分布在东部沿海区域,如乔司站、江村站;高脆弱性区段多为连接东部沿海与内陆的主要铁路干线,如京广线江村—舵落口段。研究成果可为推动铁路快捷货物运输网络规模化发展、支撑铁路监测维护工作提供理论依据。 展开更多
关键词 铁路运输网络 铁路快捷货物 复杂网络理论 社团划分 网络脆弱性
在线阅读 下载PDF
基于多道卡尔曼滤波神经网络的无监督微地震去噪方法
20
作者 张岩 张永雪 +4 位作者 魏子心 董宏丽 韩非 张林军 汪靖哲 《地球物理学报》 北大核心 2026年第1期353-365,共13页
微地震数据中有效信号的振幅、频率,及噪声具有显著的时变特征,当前微地震去噪方法中基于卡尔曼滤波方法高度依赖经验调参而影响应用效率,深度学习方法往往需要大量有效样本监督学习.针对以上问题,提出一种结合卡尔曼滤波与循环神经网... 微地震数据中有效信号的振幅、频率,及噪声具有显著的时变特征,当前微地震去噪方法中基于卡尔曼滤波方法高度依赖经验调参而影响应用效率,深度学习方法往往需要大量有效样本监督学习.针对以上问题,提出一种结合卡尔曼滤波与循环神经网络的无监督微地震数据去噪方法.首先,建立多道微地震数据的卡尔曼滤波状态预测与更新方程,充分利用多道相关性提高卡尔曼滤波参数的表征能力;其次,设计多道卡尔曼滤波状态预测与更新的RNN运算算子,通过链式梯度自动求取方式优化卡尔曼滤波的参数,构建基于循环神经网络模式的多道卡尔曼网络去噪;再次,结合无监督的微地震去噪训练方法,实现卡尔曼参数自动优化,避免有效数据标签的过度依赖;最后,通过理论正演与实际微地震数据的实验结果表明,本文方法在微地震去噪准确性与效率上优于传统卡尔曼滤波与变分自编码器等同类方法. 展开更多
关键词 微地震数据处理 卡尔曼滤波 循环神经网络 噪声压制 无监督网络
在线阅读 下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部