检索结果-内蒙古大学图书馆

An Improved Northern Goshawk optimization Algorithm for Feature Selection

Journal of Bionic Engineering 2024年第4期21卷 2034-2072页

作者： Rongxiang Xie Shaobo Li Fengbin Wu State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China

Feature Selection(FS)is an important data management technique that aims to minimize redundant information in a *** work proposes DENGO,an improved version of the Northern Goshawk optimization(NGO),to address the FS *** NGO is an efficient swarm-based algorithm that takes its inspiration from the predatory actions of the northern *** order to overcome the disadvantages that NGO is prone to local optimum trap,slow convergence speed and low convergence accuracy,two strategies are introduced in the original NGO to boost the effectiveness of ***,a learning strategy is proposed where search members learn by learning from the information gaps of other members of the population to enhance the algorithm's global search ability while improving the population ***,a hybrid differential strategy is proposed to improve the capability of the algorithm to escape from the trap of the local optimum by perturbing the individuals to improve convergence accuracy and *** prove the effectiveness of the suggested DENGO,it is measured against eleven advanced algorithms on the CEC2015 and CEC2017 benchmark functions,and the obtained results demonstrate that the DENGO has a stronger global exploration capability with higher convergence performance and ***,the proposed DENGO is used for FS,and the 29 benchmark datasets from the UCL database prove that the DENGO-based FS method equipped with higher classification accuracy and stability compared with eight other popular FS methods,and therefore,DENGO is considered to be one of the most prospective FS ***'s code can be obtained at https://***/matlabcentral/fileexchange/158811-project1.

关键词： Northern goshawk optimization Learning strategy hybrid differential strategy Numerical optimization Feature selection

来源：评论

学校读者我要写书评

暂无评论

Numerical modelling and simulation analysis of wind blades:a critical review

引用

Clean Energy 2024年第1期8卷 261-279页

作者： Ibrahim Alrowwad Xiaojia Wang Ningling Zhou Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing 210096China

Wind energy has emerged as a promising renewable energy source and wind turbine technology has developed rapidly in recent *** wind turbine performance depends heavily on the design and optimization of wind *** work offers a critical evaluation of the state of the art in the field of numerical modelling and simulation analysis,which have become crucial for the design and optimization of wind *** evaluation of the literature includes considerable research on the application of numerical methods for the structural and aerodynamic performance of wind blades under various operating situations,as well as for analysis and optimization of wind *** article illustrates how numerical techniques can be used to analyse wind blade performance and maximize design *** study of blade performance under various wind conditions has also been made possible through the use of simulation analysis,thus enhancing the efficiency and dependability of wind *** in wind turbine efficiency and dependability,and ultimately the move towards a more sustainable energy future,will be greatly helpful for the development of numerical modelling and simulation techniques.

关键词： wind blades simulations optimization numerical analysis mathematical modelling performance

来源：评论

学校读者我要写书评

暂无评论

Aviation armament system-of-systems modeling and identification method of vulnerable nodes based on interdependent network

引用

Chinese Journal of Aeronautics 2024年第12期37卷 358-372页

作者： Yaozu WANG Bolin SHANG Dexiang ZHOU Pengfei LI Renxiang LIN Wenzheng LIU School of Aeronautics Northwestern Polytechnical UniversityXi’an 710072China National Key Laboratory of Aircraft Configuration Design Xi’an 710072China Key Laboratory of Aircraft System of Systems Contribution and Synthetic Design Ministry of Industry and Information TechnologyXi’an 710072China

Aiming at the problem that it is difficult to build model and identify the vulnerable equipment for aviation armament System-of-systems(SoS)due to complex equipment interaction relationships and high confrontation,the interdependent network theory is introduced to solve ***,a two-layer heterogeneous interdependent network model for aviation armament SoS is proposed,which reflects the information interaction,functional dependency and inter-network dependence ***,using the attack cost to describe the confrontation process and taking the comprehensive impact on kill chains as the entry point,the node importance index and the attack cost measurement method are ***,the identification of vulnerable nodes is transformed into the optimization problem of node combinatorial selection,and the vulnerable node identification method based on tabu search is *** on vulnerable nodes,a robustness enhancement strategy for aviation armament SoS network is ***,the above methods are used to an aerial confrontation SoS,and the results verify the rationality and effectiveness of the proposed methods.

关键词： Aviation armament System-of-systems(SoS) Interdependent network Vulnerable node Kill chain Tabu search

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Parking Path Planning Based on Optimal Parking Positions

引用

Automotive Innovation 2023年第2期6卷 220-230页

作者： Yaogang Zhang Guoying Chen Hongyu Hu Zhenhai Gao State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchunJilinChina

Automated valet parking(AVP)has attracted the attention of industry and academia in recent ***,there are still many challenges to be solved,including shortest path search,optimal time efficiency,and applicability of algorithm in complex *** this paper,a hierarchical AVP path planner is proposed,which divides a complete AVP path planning into the guided layer and the planning layer from the perspective of global *** guided layer is mainly used to divide a complex AVP path planning into several simple path plannings,which makes the hybrid A*algorithm more applicable in a complex parking *** planning layer mainly adopts different optimization methods for driving and parking path *** proposed method is verified by a large number of simulations which include the verification of the optimal parking position,the performance of the planner for perpendicular parking,and the scalability of the planner for parallel parking and inclined *** simulation results reveal that the efficiency of the algorithm is increased by more than 20 times,and the average path length is also shortened by more than 20%.Furthermore,the planner overcomes the problem that the hybrid A*algorithm is not applicable in complex parking scenarios.

关键词： Automated valet parking Path planning hybrid A Visibility graph Shortest path

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking Based on Improved Kepler optimization Algorithm and Optimized Perturb&Observe under Partial Shading Conditions

引用

Energy Engineering 2024年第12期121卷 3779-3799页

作者： Zhaoqiang Wang Fuyin Ni School of Electrical and Information Engineering Jiangsu University of TechnologyChangzhou213001China Jiangsu Key Laboratory of Power Transmission&Distribution Equipment Technology JiangsuUniversity of TechnologyChangzhou213001China

Under the partial shading conditions(PSC)of Photovoltaic(PV)modules in a PV hybrid system,the power output curve exhibits multiple *** often causes traditional maximum power point tracking(MPPT)methods to fall into local optima and fail to find the global *** address this issue,a composite MPPT algorithm is *** combines the improved kepler optimization algorithm(IKOA)with the optimized variable-step perturb and observe(OIP&O).The update probabilities,planetary velocity and position step coefficients of IKOA are nonlinearly and adaptively *** adaptation meets the varying needs of the initial and later stages of the iterative process and accelerates *** stochastic exploration,the refined position update formulas enhance diversity and global search *** improvements in the algorithmreduces the likelihood of falling into local *** the later stages,the OIP&O algorithm decreases oscillation and increases *** with cuckoo search(CS)and gray wolf optimization(GWO),simulation tests of the PV hybrid inverter demonstrate that the proposed IKOA-OIP&O algorithm achieves faster convergence and greater stability under static,local and dynamic shading *** results can confirm the feasibility and effectiveness of the proposed PV MPPT algorithm for PV hybrid systems.

关键词： PV hybrid inverter kepler optimization algorithm maximum power point tracking perturb and observe

来源：评论

学校读者我要写书评

暂无评论

Optimizing near-carbon-free nuclear energy systems:advances in reactor operation digital twin through hybrid machine learning algorithms for parameter identification and state estimation

引用

Nuclear Science and Techniques 2024年第8期35卷 177-203页

作者： Li‑Zhan Hong He‑Lin Gong Hong‑Jun Ji Jia‑Liang Lu Han Li Qing Li Paris Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of ChinaChengdu 610041China

Accurate and efficient online parameter identification and state estimation are crucial for leveraging digital twin simulations to optimize the operation of near-carbon-free nuclear energy *** previous studies,we developed a reactor operation digital twin(RODT).However,non-differentiabilities and discontinuities arise when employing machine learning-based surrogate forward models,challenging traditional gradient-based inverse methods and their *** study investigated deterministic and metaheuristic algorithms and developed hybrid algorithms to address these *** efficient modular RODT software framework that incorporates these methods into its post-evaluation module is presented for comprehensive *** methods were rigorously assessed based on convergence profiles,stability with respect to noise,and computational *** numerical results show that the hybrid KNNLHS algorithm excels in real-time online applications,balancing accuracy and efficiency with a prediction error rate of only 1%and processing times of less than 0.1 ***,algorithms such as FSA,DE,and ADE,although slightly slower(approximately 1 s),demonstrated higher accuracy with a 0.3%relative L_2 error,which advances RODT methodologies to harness machine learning and system modeling for improved reactor monitoring,systematic diagnosis of off-normal events,and lifetime management *** developed modular software and novel optimization methods presented offer pathways to realize the full potential of RODT for transforming energy engineering practices.

关键词： Parameter identification State estimation Reactor operation digital twin Reduced order model Inverse problem

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of Forestry Research 2025年第1期36卷 27-59页

作者： Harikesh Singh Li‑Minn Ang Tom Lewis Dipak Paudyal Mauricio Acuna Prashant Kumar Srivastava Sanjeev Kumar Srivastava Geospatial Analytics for Conservation and Management School of Science Technology and EngineeringUniversity of the Sunshine CoastSippy DownsQLDAustralia School of Science Technology and Engineering University of the Sunshine CoastMoreton BayAustralia Queensland Forest Consulting Services GympieQLDAustralia APAC Geospatial BrisbaneAustralia Forest Research Institute University of the Sunshine CoastSippy DownsQLDAustralia SmartSat Cooperative Research Centre North TerraceAdelaideSA 5000Australia Remote Sensing Laboratory Institute of Environment and Sustainable DevelopmentBanaras Hindu UniversityVaranasiUttar Pradesh 221005India

The significant threat of wildfires to forest ecology and biodiversity,particularly in tropical and subtropical regions,underscores the necessity for advanced predictive models amidst shifting climate *** is a need to evaluate and enhance wildfire prediction methods,focusing on their application during extended periods of intense heat and *** study reviews various wildfire modelling approaches,including traditional physical,semi-empirical,numerical,and emerging machine learning(ML)-based *** critically assess these models’capabilities in predicting fire susceptibility and post-ignition spread,highlighting their strengths and *** findings indicate that while traditional models provide foundational insights,they often fall short in dynamically estimating parameters and predicting ignition *** automata models,despite their potential,face challenges in data integration and computational ***,ML models demonstrate superior efficiency and accuracy by leveraging diverse datasets,though they encounter interpretability *** review recommends hybrid modelling approaches that integrate multiple methods to harness their combined *** incorporating data assimilation techniques with dynamic forecasting models,the predictive capabilities of ML-based predictions can be significantly *** review underscores the necessity for continued refinement of these models to ensure their reliability in real-world applications,ultimately contributing to more effective wildfire mitigation and management *** research should focus on improving hybrid models and exploring new data integration methods to advance predictive capabilities.

关键词： Wildfire spread Fire prediction models Cellular automata model WRF-Fire/SFire FIRETEC CAWFE WFDS

来源：评论

学校读者我要写书评

暂无评论

Novel multi-waypoint planning methods based on intermediate state optimization

引用

Science China(Technological Sciences) 2025年第3期68卷 179-191页

作者： Xinyu QIN Guangbao ZHAO Zixuan LIAO Chao LIU Zhenhua XIONG State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai200240China

Multi-waypoint planning is essential for manipulators to execute complex tasks *** requires the manipulator to swiftly traverse designated waypoints while adhering to all the kinematic ***,previous research has not fully exploited the kinematic capabilities of manipulators and has overlooked collision *** address these problems,this paper presents two novel methods called recursive intermediate state optimization(RISO)and overall intermediate state optimization(OISO).RISO decomposes the multi-waypoint planning problem into a sequence of one-waypoint planning tasks,employing a recursive approach to generate feasible solutions *** utilizes an improved whale optimization algorithm(WOA),incorporating multiple iterative processes to perform secondary optimization in high-dimensional space based on the initial value,yielding better *** proposed methods have been validated on a six-degree-of-freedom manipulator platform and compared with several traditional algorithms,as well as the state-of-the-art algorithm,*** results show that RISO outperforms Ruckig in scenarios where computation time is critical,while OISO is better suited for scenarios where trajectory quality is prioritized over ***,the proposed methods can also handle collisions,ensuring the generation of collision-free trajectories.

关键词： multi-waypoint planning intermediate state optimization aerial photography task

来源：评论

学校读者我要写书评

暂无评论

Workspace,stiffness analysis and design optimization of coupled active-passive multilink cable-driven space robots for on-orbit services

引用

Chinese Journal of Aeronautics 2023年第2期36卷 402-416页

作者： Jianqing PENG Haoxuan WU Tianliang LIU Yu HAN School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen UniversityShenzhen 518109China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou 510006China School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China

The use of space robots(SRs)for on-orbit services(OOSs)has been a hot research topic in recent ***,the space unstructured environment(i.e.:confined spaces,multiple obstacles,and strong radiation interference)has greatly restricted the application of *** coupled active-passive multilink cable-driven space robot(CAP-MCDSR)has the characteristics of slim body,flexible movement,and electromechanical separation,which is very suitable for extreme space ***,the dynamic and stiffness modeling of CAP-MCDSRs is challenging,due to the complex coupling among the active cables,passive cables,joints,and the *** deal with these problems,this paper proposes a workspace,stiffness analysis and design optimization method for such type of ***,the multi-coupling kinematics relationships among the joint,cables and the end-effector are *** on hybrid series-parallel characteristics,the improved coupled active–passive(CAP)dynamic equation is ***,the maximum workspace,the maximum stiffness,and the minimum cable tension are resolved,among them,the overall stiffness is the superposition of the stiffness produced by the active and the passive ***,the workspace,the stiffness,and the cable tension are analyzed by using the nonlinear optimization method(NOPM).Finally,an 8-DOF CAP-MCDSR experiment system is built to verify the proposed modeling and trajectory tracking *** proposed modeling and analysis results are very useful for practical space applications,such as designing a new CAP-MCDSR,or utilizing an existing CAP-MCDSR system.

关键词： Coupled active–passive(CAP) hybrid series-parallel Multilink cable-driven space robot(MCDSR) Nonlinear optimization(NOP) On-orbit services(OOSs) Robotics Space

来源：评论

学校读者我要写书评

暂无评论

Detecting physical laws from data of stochastic dynamical systems perturbed by non-Gaussianα-stable Lévy noise

引用

Chinese Physics B 2023年第5期32卷 337-342页

作者：陆凌弘志李扬刘先斌 State Key Laboratory of Mechanics and Control for Mechanical Structures College of Aerospace EngineeringNanjing University of Aeronautics and AstronauticsNanjing 210016China School of Automation Nanjing University of Science and TechnologyNanjing 210094China

Massive data from observations,experiments and simulations of dynamical models in scientific and engineering fields make it desirable for data-driven methods to extract basic laws of these *** present a novel method to identify such high dimensional stochastic dynamical systems that are perturbed by a non-Gaussianα-stable Lévy *** explicitly,firstly a machine learning framework to solve the sparse regression problem is established to grasp the drift terms through one of nonlocal Kramers–Moyal *** the jump measure and intensity of the noise are disposed by the relationship with statistical characteristics of the *** examples are then given to demonstrate the *** approach proposes an effective way to understand the complex phenomena of systems under non-Gaussian fluctuations and illuminates some insights into the exploration for further typical dynamical indicators such as the maximum likelihood transition path or mean exit time of these stochastic systems.

关键词： data-driven modelling noise-induced transitions Lévy noise Kramers–Moyal formuas

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：