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519篇文章
< 1 2 … 26 >
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：
Optimizing force aggregation:SATC-ALO and SOM hybrid clustering model 认领 引用
1
作者 ZHANG Zhenxing YANG Rennong +1 位作者 ZHANG Ying SONG Qi 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2026年第2期604-615,共12页
To overcome the limitations of traditional force aggregation methods,this paper proposes a novel clustering model integrating the self-adaptive tent chaos search ant lion optimizer(SATC-ALO)and the self-organizing map... To overcome the limitations of traditional force aggregation methods,this paper proposes a novel clustering model integrating the self-adaptive tent chaos search ant lion optimizer(SATC-ALO)and the self-organizing map(SOM)network.The model introduces a hybrid distance calculation method to measure inter-target distances and enhances the ant lion optimization algorithm through tent chaos sequences,adaptive tent chaos search,tournament selection,and logistic chaos sequences.Aggregation accuracy is evaluated using minimum quantization error and confidence value for the SOM neural network.The model is resolved using SATC-ALO and SOM independently,with experiments demonstrating that SOM achieves fast and accurate grouping,while SATC-ALO offers higher precision but requires longer computational runtime,making it more suitable for hybrid approaches.Both methods are validated as practical solutions for force aggregation tasks. 展开更多
关键词 force aggregation fuzzy inference hybrid calculating method self-adaptive tent chaos search ant lion optimizer(SATC-ALO)algorithm self organizing maps network(SOM)
暂未订购 下载PDF
A Survey of Distributed Algorithms for Aggregative Games 认领 引用 被引量：1
2
作者 Huaqing Li Jun Li +2 位作者 Liang Ran Lifeng Zheng Tingwen Huang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2025年第5期859-871,共13页
Game theory-based models and design tools have gained substantial prominence for controlling and optimizing behavior within distributed engineering systems due to the inherent distribution of decisions among individua... Game theory-based models and design tools have gained substantial prominence for controlling and optimizing behavior within distributed engineering systems due to the inherent distribution of decisions among individuals.In non-cooperative settings,aggregative games serve as a mathematical framework model for the interdependent optimal decision-making problem among a group of non-cooperative players.In such scenarios,each player's decision is influenced by an aggregation of all players'decisions.Nash equilibrium(NE)seeking in aggregative games has emerged as a vibrant topic driven by applications that harness the aggregation property.This paper presents a comprehensive overview of the current research on aggregative games with a focus on communication topology.A systematic classification is conducted on distributed algorithm research based on communication topologies such as undirected networks,directed networks,and time-varying networks.Furthermore,it sorts out the challenges and compares the algorithms'convergence performance.It also delves into real-world applications of distributed optimization techniques grounded in aggregative games.Finally,it proposes several challenges that can guide future research directions. 展开更多
关键词 Aggregative game distributed algorithm Nash equilibrium(NE) networked control
暂未订购 下载PDF
Distributed Byzantine-Resilient Learning of Multi-UAV Systems via Filter-Based Centerpoint Aggregation Rules 认领 引用 被引量：2
3
作者 Yukang Cui Linzhen Cheng +1 位作者 Michael Basin Zongze Wu 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2025年第5期1056-1058,共3页
Dear Editor,Through distributed machine learning,multi-UAV systems can achieve global optimization goals without a centralized server,such as optimal target tracking,by leveraging local calculation and communication w... Dear Editor,Through distributed machine learning,multi-UAV systems can achieve global optimization goals without a centralized server,such as optimal target tracking,by leveraging local calculation and communication with neighbors.In this work,we implement the stochastic gradient descent algorithm(SGD)distributedly to optimize tracking errors based on local state and aggregation of the neighbors'estimation.However,Byzantine agents can mislead neighbors,causing deviations from optimal tracking.We prove that the swarm achieves resilient convergence if aggregated results lie within the normal neighbors'convex hull,which can be guaranteed by the introduced centerpoint-based aggregation rule.In the given simulated scenarios,distributed learning using average,geometric median(GM),and coordinate-wise median(CM)based aggregation rules fail to track the target.Compared to solely using the centerpoint aggregation method,our approach,which combines a pre-filter with the centroid aggregation rule,significantly enhances resilience against Byzantine attacks,achieving faster convergence and smaller tracking errors. 展开更多
关键词 global optimization goals multi UAV systems filter based centerpoint aggregation distributed learning optimal target trackingby stochastic gradient descent algorithm sgd distributedly optimize tracking distributed machine learningmulti uav
暂未订购 下载PDF
Research on Flexible Load Aggregation and Coordinated Control Methods Considering Dynamic Demand Response 认领 引用
4
作者 Chun Xiao 《Energy Engineering》 EI 2025年第7期2719-2750,共32页
In contemporary power systems,delving into the flexible regulation potential of demand-side resources is of paramount significance for the efficient operation of power grids.This research puts forward an innovative mu... In contemporary power systems,delving into the flexible regulation potential of demand-side resources is of paramount significance for the efficient operation of power grids.This research puts forward an innovative multivariate flexible load aggregation control approach that takes dynamic demand response into full consideration.In the initial stage,using generalized time-domain aggregation modelling for a wide array of heterogeneous flexible loads,including temperature-controlled loads,electric vehicles,and energy storage devices,a novel calculation method for their maximum adjustable capacities is devised.Distinct from conventional methods,this newly developed approach enables more precise and adaptable quantification of the load-adjusting capabilities,thereby enhancing the accuracy and flexibility of demand-side resource management.Subsequently,an SSA-BiLSTM flexible load classification prediction model is established.This model represents an innovative application in the field,effectively combining the advantages of the Sparrow Search Algorithm(SSA)and the Bidirectional Long-Short-Term Memory(BiLSTM)neural network.Furthermore,a parallel Markov chain is introduced to evaluate the switching state transfer probability of flexible loads accurately.This integration allows for a more refined determination of the maximum response capacity range of the flexible load aggregator,significantly improving the precision of capacity assessment compared to existing methods.Finally,in consonance with the intra-day scheduling plan,a newly developed diffuse filling algorithm is implemented to control the activation times of flexible loads precisely,thus achieving real-time dynamic demand response.Through in-depth case analysis and comprehensive comparative studies,the effectiveness of the proposed method is convincingly validated.With its innovative techniques and enhanced performance,it is demonstrated that this method has the potential to substantially enhance the utilization efficiency of demand-side resources in power systems,providing a novel and effective solution for optimizing power grid operation and demand-side management. 展开更多
关键词 Demand response flood fill algorithm load aggregation markov chain SSA-BiLSTM
暂未订购 下载PDF
Modelling the temporal-varied nonlinear velocity profile of debris flow using a stratification aggregation algorithm in 3D-HBP-SPH framework 认领 引用
5
作者 HAN Zheng XIE Wendu +5 位作者 ZENG Chuicheng LI Yange CHEN Guangqi CHEN Ningsheng HU Guisheng WANG Weidong 《Journal of Mountain Science》 SCIE CSCD 2024年第12期3945-3960,共16页
Estimation of velocity profile within mud depth is a long-standing and essential problem in debris flow dynamics.Until now,various velocity profiles have been proposed based on the fitting analysis of experimental mea... Estimation of velocity profile within mud depth is a long-standing and essential problem in debris flow dynamics.Until now,various velocity profiles have been proposed based on the fitting analysis of experimental measurements,but these are often limited by the observation conditions,such as the number of configured sensors.Therefore,the resulting linear velocity profiles usually exhibit limitations in reproducing the temporal-varied and nonlinear behavior during the debris flow process.In this study,we present a novel approach to explore the debris flow velocity profile in detail upon our previous 3D-HBPSPH numerical model,i.e.,the three-dimensional Smoothed Particle Hydrodynamic model incorporating the Herschel-Bulkley-Papanastasiou rheology.Specifically,we propose a stratification aggregation algorithm for interpreting the details of SPH particles,which enables the recording of temporal velocities of debris flow at different mud depths.To analyze the velocity profile,we introduce a logarithmic-based nonlinear model with two key parameters,that a controlling the shape of velocity profile and b concerning its temporal evolution.We verify the proposed velocity profile and explore its sensitivity using 34 sets of velocity data from three individual flume experiments in previous literature.Our results demonstrate that the proposed temporalvaried nonlinear velocity profile outperforms the previous linear profiles. 展开更多
关键词 Debris flow Velocity profile Temporal varied feature Nonlinear Stratification aggregation algorithm
暂未订购 下载PDF
Feature-Based Aggregation and Deep Reinforcement Learning:A Survey and Some New Implementations 认领 引用 被引量：18
6
作者 Dimitri P.Bertsekas 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2019年第1期1-31,共31页
In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinfor... In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement. 展开更多
关键词 Reinforcement learning dynamic programming Markovian decision problems aggregation feature-based architectures policy iteration deep neural networks rollout algorithms
暂未订购 下载PDF
Distributed Event-Triggered Nash Equilibrium Seeking for Aggregative Game With Second-Order Dynamics 认领 引用 被引量：1
7
作者 Yi Huang Jian Sun Qing Fei 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2025年第7期1519-1521,共3页
Dear Editor,This letter studies the distributed Nash equilibrium seeking problem of aggregative game,in which the decision of each player obeys second-order dynamics and is constrained by nonidentical convex sets.To s... Dear Editor,This letter studies the distributed Nash equilibrium seeking problem of aggregative game,in which the decision of each player obeys second-order dynamics and is constrained by nonidentical convex sets.To seek the generalized Nash equilibrium(GNE),a projectionbased distributed algorithm via constant step-sizes is developed with linear convergence.In particular,a variable tracking technique is incorporated to estimate the aggregative function,and an event-triggered mechanism is designed to reduce the communication cost.Finally,a numerical example demonstrates the theoretical results. 展开更多
关键词 generalized nash equilibrium gne estimate aggregative functionand linear convergencein aggregative gamein distributed event triggered control reduce th distributed nash equilibrium seeking projectionbased distributed algorithm
暂未订购 下载PDF
Solving frictional contact problems by two aggregate-function-based algorithms 认领 引用
8
作者 Suyan He Hongwu Zhang Xingsi Li 《Acta Mechanica Sinica》 SCIE EI CAS 2005年第5期467-471,共5页
Three dimensional frictional contact problems are formulated as linear complementarity problems based on the parametric variational principle. Two aggregate-functionbased algorithms for solving complementarity problem... Three dimensional frictional contact problems are formulated as linear complementarity problems based on the parametric variational principle. Two aggregate-functionbased algorithms for solving complementarity problems are proposed. One is called the self-adjusting interior point algorithm, the other is called the aggregate function smoothing algorithm. Numerical experiment shows the efficiency of the proposed two algorithms. 展开更多
关键词 Frictional contact problem. Linear complementarity problem .Aggregate function ~ Interior pointalgorithm ~ Smoothing algorithm
暂未订购 下载PDF
A Tree Based Data Aggregation Scheme for Wireless Sensor Networks Using GA 认领 引用
9
作者 Ali Norouzi Faezeh Sadat Babamir Zeynep Orman 《Wireless Sensor Network》 2012年第8期191-196,共6页
Energy is one of the most important items to determine the network lifetime due to low power energy nodes included in the network. Generally, data aggregation tree concept is used to find an energy efficient solution.... Energy is one of the most important items to determine the network lifetime due to low power energy nodes included in the network. Generally, data aggregation tree concept is used to find an energy efficient solution. However, even the best aggregation tree does not share the load of data packets to the transmitting nodes fairly while it is consuming the lowest possible energy of the network. Therefore, after some rounds, this problem causes to consume the whole energy of some heavily loaded nodes and hence results in with the death of the network. In this paper, by using the Genetic Algorithm (GA), we investigate the energy efficient data collecting spanning trees to find a suitable route which balances the data load throughout the network and thus balances the residual energy in the network in addition to consuming totally low power of the network. Using an algorithm which is able to balance the residual energy among the nodes can help the network to withstand more and consequently extend its own lifetime. In this work, we calculate all possible routes represented by the aggregation trees through the genetic algorithm. GA finds the optimum tree which is able to balance the data load and the energy in the network. Simulation results show that this balancing operation practically increases the network lifetime. 展开更多
关键词 Data Aggregation Genetic Algorithm Wireless Sensor Network Routing Energy Efficiency
暂未订购 下载PDF
激光通信网络星间链路隐私数据汇聚传输方法 认领 引用 被引量：2
10
作者 周显春 焦萍萍 陈鹤鸣 《激光杂志》 CAS 北大核心 2026年第2期191-197,共7页
传统方法对层间链路加密分散数据时,仅依赖单一密钥,会缺乏多层次加密保护,降低了对隐私数据传输的精度。为此,提出激光通信网络星间链路隐私数据汇聚传输方法。采用模糊C均值聚类方法将各卫星链路上的数据汇聚到中心卫星上,引入三维维... 传统方法对层间链路加密分散数据时,仅依赖单一密钥,会缺乏多层次加密保护,降低了对隐私数据传输的精度。为此,提出激光通信网络星间链路隐私数据汇聚传输方法。采用模糊C均值聚类方法将各卫星链路上的数据汇聚到中心卫星上,引入三维维吉尼亚加密算法,通过双重密钥和加密幅值两次加密处理汇聚数据,以增强数据传输的安全性,计算同层星间链路和层间星间链路的距离与夹角,选取权重值最高的星间链路对两次加密后的数据展开安全汇聚传输。实验结果表明,该方法的隐私数据传输到目标卫星中的数据和原始数据之间的相似度超过99.5%,传输精度高于对比方法,而数据传输风险值低于0.25,数据传输风险值一直低于对比方法。 展开更多
关键词 激光通信网络 星间链路 隐私数据汇聚传输 模糊C均值 三维维吉尼亚加密算法
暂未订购 下载PDF
基于集成学习算法的电力负荷聚合方法 认领 引用
11
作者 乔宁 宁波 +3 位作者 张超 陈海东 张吉生 申少辉 《信息技术》 2026年第3期19-24,29,共6页
对于不同类型的负荷(如家庭、商业、工业负荷等),其用电行为和特征差异巨大,同时兼顾电力系统各个组成部分之间的相互影响和耦合关系,增加了负荷聚合的难度。为此,文中提出基于集成学习算法的电力负荷聚合方法。基于局部异常因子检测电... 对于不同类型的负荷(如家庭、商业、工业负荷等),其用电行为和特征差异巨大,同时兼顾电力系统各个组成部分之间的相互影响和耦合关系,增加了负荷聚合的难度。为此,文中提出基于集成学习算法的电力负荷聚合方法。基于局部异常因子检测电力负荷数据中的异常数据并将其剔除;利用加权主成分分析法获得负荷数据的主成分,建立只保留主成分信息的负荷数据序列,将其输入集成学习算法中,完成电力负荷数据聚合。实验结果表明,该方法的异常数据剔除效果较好、数据聚合性能较高。 展开更多
关键词 集成学习算法 电力负荷聚合 异常数据剔除 加权主成分分析 随机森林算法
暂未订购 下载PDF
再生骨料水泥稳定碎石力学性能分析与最优配合比预测 认领 引用
12
作者 申彦利 魏冠超 +5 位作者 王鹏 王嘉炜 徐磊 王辉 王志岭 卫爱魁 《硅酸盐通报》 CAS 北大核心 2026年第7期2561-2572,共12页
为实现废旧道路混凝土再生骨料在道路基层中的资源循环利用,采用试验分析和人工智能相结合的方法,研究不同水泥掺量(3.50%、4.50%、5.50%,质量分数)和再生骨料掺量(4.15%、56.20%、78.10%、100.00%,质量分数)对废旧道路混凝土再生骨料... 为实现废旧道路混凝土再生骨料在道路基层中的资源循环利用,采用试验分析和人工智能相结合的方法,研究不同水泥掺量(3.50%、4.50%、5.50%,质量分数)和再生骨料掺量(4.15%、56.20%、78.10%、100.00%,质量分数)对废旧道路混凝土再生骨料水泥稳定碎石的最大干密度、最佳含水率、无侧限抗压强度、抗压回弹模量和劈裂强度的影响,基于机器学习与遗传算法(GA)构建再生骨料水泥稳定碎石7、90 d无侧限抗压强度预测和级配优化模型。结果表明:水泥掺量越高,再生骨料水泥稳定碎石的力学性能越好;再生骨料掺量提高会降低水泥稳定碎石的最大干密度并提高最佳含水率;适量再生骨料可提升水泥稳定碎石的7、90 d无侧限抗压强度和90 d劈裂强度,而抗压回弹模量随再生骨料掺量的增加逐渐降低,当再生骨料掺量为78.10%、水泥掺量为5.50%时,7、90 d无侧限抗压强度代表值分别为4.24、7.07 MPa,90 d劈裂强度与抗压回弹模量分别为0.64、1925 MPa,均满足相关规范要求。根据再生骨料水泥稳定碎石力学性能的分析结果,选择随机森林模型结合遗传算法的方式进行级配优化,得到最优配合比下7 d无侧限抗压强度预测值为5.82 MPa。 展开更多
关键词 再生骨料 水泥稳定碎石 力学性能 机器学习 随机森林 遗传算法
暂未订购 下载PDF
考虑多时段影响的第四方物流运营策略联合优化 认领 引用
13
作者 蔡近近 宋瑞 +3 位作者 何世伟 何维 丛铭 颜凯 《控制与决策》 EI CSCD 北大核心 2026年第1期44-54,共11页
第四方物流作为供应链资源的集成协调者,能够通过资源整合有效降低供应链成本.首先,从第四方物流作为供应链集成商的视角出发,聚焦其在运营过程中面临的多时段采购、仓储、多式联运以及第三方物流服务商选择等问题,构建以最小化总运营... 第四方物流作为供应链资源的集成协调者,能够通过资源整合有效降低供应链成本.首先,从第四方物流作为供应链集成商的视角出发,聚焦其在运营过程中面临的多时段采购、仓储、多式联运以及第三方物流服务商选择等问题,构建以最小化总运营成本为目标的联合优化模型.然后,为提升求解质量和效率,设计一种结合图采样聚合算法与K最短路径算法的量子微进化算法.接着,基于Chicago-regional数据集,构建小规模和大规模网络进行数值实验.实验结果显示,所提出模型在测试算例中相较于不含仓储的联合优化策略与未联合优化策略,最高可降低11.8%和15%的总运营成本.在大规模网络中,将所提出算法与微进化算法、量子遗传算法、遗传算法以及粒子群算法进行对比,结果表明所提出算法在求解质量和效率方面均表现更优.最后,通过分析参数波动场景下运营成本的变化,验证了所提出模型具备应对多时段变化的能力,最高可降低18.07%的运营成本. 展开更多
关键词 第四方物流 多时段运营策略 联合优化 多服务商多式联运 图采样聚合 量子微进化算法
暂未订购 下载PDF
一种融合降噪算法和CNN-BKA-LSSVM的叶片泵故障诊断方法 认领 引用
14
作者 郭锐 李博闻 +5 位作者 问亚鹏 张佳奇 陈鹏飞 熊陈生 王建伟 蔡伟 《机床与液压》 北大核心 2026年第13期163-169,共7页
针对叶片泵在高压重载荷工况工作易发生故障,且高噪声环境导致信号提取困难、故障诊断精度低,进而影响液压系统安全稳定的问题,提出一种融合三角优化器(TTAO)优化变分模态分解(VMD)的降噪算法和CNN-BKALSSVM模型的故障诊断方法。对叶片... 针对叶片泵在高压重载荷工况工作易发生故障,且高噪声环境导致信号提取困难、故障诊断精度低,进而影响液压系统安全稳定的问题,提出一种融合三角优化器(TTAO)优化变分模态分解(VMD)的降噪算法和CNN-BKALSSVM模型的故障诊断方法。对叶片泵典型磨损故障的振动信号进行预处理,采用TTAO-VMD降噪算法对其进行降噪;采用小波同步提取变换(WSET)实现振动信号的时频域转换,将一维振动信号转换为二维时频分布图并作为输入;利用CNN-BKA-LSSVM模型进行故障诊断;最后,搭建叶片泵故障模拟实验台,获取5种工况的振动信号进行实验验证,并与CNN和CNN-LSSVM模型进行对比。结果表明:CNN模型和CNN-LSSVM模型的识别准确率分别为96.82%和98.16%,而CNN-BKA-LSSVM模型识别准确率达99.16%,表明该模型具有更高的诊断精度。研究为高噪声环境下液压元件智能故障诊断提供了有效方法。 展开更多
关键词 叶片泵 故障诊断 三角优化器 变分模态分解 小波同步提取变换 黑翅鸢优化算法
暂未订购 下载PDF
面向海量灵活性资源的电力系统短期调度方法 认领 引用
15
作者 庄重 孔月萍 陈宇沁 《计算机仿真》 2026年第1期328-332,共5页
随着电力系统灵活性资源种类和数量的增加,资源之间的响应速度、调节范围等物理特性不同,增加了调度复杂性。在短期调度过程中,调度计算量显著增大,降低了调度实时性。为此,提出面向海量灵活性资源的电力系统短期调度方法。提取风光电... 随着电力系统灵活性资源种类和数量的增加,资源之间的响应速度、调节范围等物理特性不同,增加了调度复杂性。在短期调度过程中,调度计算量显著增大,降低了调度实时性。为此,提出面向海量灵活性资源的电力系统短期调度方法。提取风光电、火电、抽水蓄能、电化学储能等灵活性资源特性后,通过电力系统的资源聚合,实现不同种类灵活资源的聚合处理;基于聚合结果,建立不同资源的调度目标函数以及约束条件,并以此建立短期电力系统的灵活性资源调度目标函数;利用分布式共识算法对调度目标函数实施求解计算,根据求解结果完成电力系统灵活性资源的短期调度。仿真结果表明,使用上述方法开展电力系统资源调度时,调度效果好、性能高。 展开更多
关键词 电力系统 灵活性资源 短期调度目标函数 分布式共识算法 资源聚合
暂未订购 下载PDF
基于数据模态分解算法的用户可调节负荷聚合 认领 引用
16
作者 乔宁 陈海东 +2 位作者 张超 张吉生 申少辉 《信息技术》 2026年第4期35-40,共6页
用户的负荷行为具有多样性,每个用户都拥有独特的用电习惯和偏好,这种多样性使得负荷聚合变得复杂且具备多个维度。在多维数据中,存在大量重复或冗余信息,导致数据处理和分析变得困难。因此,文中提出基于数据模态分解算法的用户可调节... 用户的负荷行为具有多样性,每个用户都拥有独特的用电习惯和偏好,这种多样性使得负荷聚合变得复杂且具备多个维度。在多维数据中,存在大量重复或冗余信息,导致数据处理和分析变得困难。因此,文中提出基于数据模态分解算法的用户可调节负荷聚合算法。分别对用户静态负荷和动态负荷展开分析,并建立用户综合负荷模型;将数据模态分解算法与模糊C均值算法相结合,对用户可调节负荷实现分解、重构和特征提取,利用模糊C均值算法对提取到的负荷特征聚合。实验结果表明,所提方法在用户可调节负荷方面具有良好的聚合能力。 展开更多
关键词 数据模态分解算法 用户可调节负荷聚合 综合负荷模型 恒功率模型 模态混叠问题
暂未订购 下载PDF
融合知识元和聚合K近邻算法的客舱火灾案例检索研究 认领 引用
17
作者 吴煜 经理晗 解江 《消防科学与技术》 CAS 北大核心 2026年第8期41-48,共8页
为实现对民航客舱火灾情景的准确描述和快速响应,本文构建了融合知识元和聚合K近邻算法的客舱火灾案例检索模型。通过挖掘客舱火灾的属性特征,作数值转换和预处理,进行相似案例检索和等级预测。结果表明:基于灾害要素解构理论可将客舱... 为实现对民航客舱火灾情景的准确描述和快速响应,本文构建了融合知识元和聚合K近邻算法的客舱火灾案例检索模型。通过挖掘客舱火灾的属性特征,作数值转换和预处理,进行相似案例检索和等级预测。结果表明:基于灾害要素解构理论可将客舱火灾案例解构为含致灾因子、承灾体、孕灾环境和应急处置的四维知识元框架,结合火灾事件特点,将客舱火灾的灾害形成、发展及应对的全过程细分为8类子知识元和12个属性特征;同时,计算随机预测目标案例与全量案例的欧式距离,采用多数投票法和聚合子模型得到最终预测值,构建1500条仿真案例数据集进行训练、验证和调优,选取24条真实案例进行测试,利用留一法交叉验证得出最佳K值为3,模型预测准确率达到0.9167。基于准确率、精确率、召回率和F1分数设置多模型对比评估显示,所提出的聚合K近邻模型显著优于其他模型。因此,提出的客舱火灾案例检索模型,可为民航客舱火灾等级预测及应急决策提供支撑。 展开更多
关键词 客舱火灾 知识元模型 聚合K近邻算法 案例检索 事件等级
暂未订购 下载PDF
基于WD-CPO-VMD和组合聚合的短期净负荷预测研究 认领 引用
18
作者 李伟 吾凯 《现代电力》 CSCD 北大核心 2026年第4期752-760,共9页
随着新能源渗透比例的提高,针对净负荷较传统负荷波动更大、预测难度更高的问题,提出一种基于小波分解(wavelet decomposition,WD)和冠豪猪优化算法(crested porcupine optimizer,CPO)改进的变分模态分解(variational mode decompositio... 随着新能源渗透比例的提高,针对净负荷较传统负荷波动更大、预测难度更高的问题,提出一种基于小波分解(wavelet decomposition,WD)和冠豪猪优化算法(crested porcupine optimizer,CPO)改进的变分模态分解(variational mode decomposition,VMD)的组合聚合预测模型。该模型包括二次分解模块和神经网络预测模块。由于净负荷波动性较强,首先,使用小波分解结合排列熵将原始数据分解成高频分量和低频分量,并利用冠豪猪优化算法改进的变分模态分解对高频分量进行二次分解;其次,将注意力机制融入长短期记忆网络,增强其关注重要信息的能力;最后,将高低频分量分别以矩阵聚合和矢量聚合形式输入改进的神经网络中,整合得到最终预测结果。算例分析表明,所提模型相比常见的预测模型取得了更好的预测效果,并且在趋势转折点提升效果更优,能更好地应对净负荷的突然变动。 展开更多
关键词 净负荷预测 小波分解 变分模态分解 冠豪猪优化算法 组合聚合
暂未订购 下载PDF
基于SM9算法的联邦学习安全聚合框架研究 认领 引用
19
作者 李春燕 刘沅鑫 +1 位作者 汪培 向阳 《通信技术》 2026年第6期713-719,共7页
联邦学习作为一种分布式机器学习范式,能够在不共享原始数据的情况下协同训练模型,但其通信链路中交换的模型参数或梯度仍可能遭受窃听或篡改,并且系统还面临隐私泄露以及投毒攻击的威胁。为保障模型训练过程的安全性与可靠性,提出了一... 联邦学习作为一种分布式机器学习范式,能够在不共享原始数据的情况下协同训练模型,但其通信链路中交换的模型参数或梯度仍可能遭受窃听或篡改,并且系统还面临隐私泄露以及投毒攻击的威胁。为保障模型训练过程的安全性与可靠性,提出了一种基于SM9算法的FL安全聚合框架。该框架的核心是集成SM9密钥交换协议,使得客户端和服务器之间能够根据双方的身份标识协商出共享密钥。该密钥后续用于对称加密算法,可以有效确保梯度在传输过程中的机密性和完整性,且能有效验证数据来源。此外,结合Shamir秘密共享及缩放点积注意力机制设计了隐私保护下的防御投毒协议,提升了系统的隐私性和防御投毒攻击的能力。实验结果表明,所提方案可以有效防范多种投毒攻击,并且在非独立同分布下表现优异,模型准确率普遍优于基线算法。 展开更多
关键词 联邦学习 隐私保护 SM9算法 投毒攻击防御 安全聚合
暂未订购 下载PDF
再生混凝土碳化深度的ANN预测模型 认领 引用
20
作者 唐朝阳 周星妤 +2 位作者 颜海 郑学忠 卓卫东 《福建建设科技》 2026年第2期67-70,共4页
基于452个再生混凝土(RAC)耐久性实验数据样本,采用人工神经网络(ANN)和反向传播(BP)算法,以CO2浓度、相对湿度、水泥含量、骨料吸水率、含水量以及RAC的抗压强度、暴露时间作为输入参数,以碳化深度作为输出参数,构建RAC碳化深度预测... 基于452个再生混凝土(RAC)耐久性实验数据样本,采用人工神经网络(ANN)和反向传播(BP)算法,以CO2浓度、相对湿度、水泥含量、骨料吸水率、含水量以及RAC的抗压强度、暴露时间作为输入参数,以碳化深度作为输出参数,构建RAC碳化深度预测的ANN模型。结果表明,在合理的拓扑结构及网络参数设置下,ANN模型对训练集预测结果的平均误差仅为2.02%,对RAC耐久性实验数据验证集的预测结果平均误差为2.32%,具有良好的泛化能力。因此,ANN模型为快速及准确地预测RCA碳化深度提供了一种可行的智能化方法。 展开更多
关键词 再生混凝土 碳化深度 人工神经网络 加速碳化试验 反向传播算法
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 … 26 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈