检索结果-内蒙古大学图书馆

Wind farm layout optimization based on dynamic Levy sparrow search algorithm: A multi-parameter analysis with active yaw control

引用

ENERGY 2025年 324卷

作者： Shen, Lian Zhou, Pinhan Han, Yan Mi, Lihua Xu, Wenxiang Xu, Jialu Changsha Univ Sch Civil Engn Changsha 410022 Peoples R China Changsha Univ Sci & Technol Hunan Prov Res Ctr Safety Control Technol & Equipm Changsha 410004 Peoples R China Wenzhou Univ Technol Coll Architecture & Energy Engn Wenzhou 325035 Peoples R China

Wind farm layout optimization is essential for improving power generation efficiency and reducing operational costs in wind farms. This study develops a multi-turbine wake superposition model incorporating turbine yaw effects, based on a three-dimensional polynomial wake model. Dynamic weight and Levy flight strategies are employed to enhance the sparrow search algorithm (SSA) for layout optimization. The proposed wake model is validated with experimental data, and the superiority of DLSSA is confirmed through comparisons with traditional algorithms. Parameter analysis of active yaw strategy is conducted using two tandem wind turbines. Integrating DLSSA with the wake model, layout optimization considering height variation and active yawing strategies is investigated using dimensionless annual energy production (DAEP) as the objective function. Simulation data suggests that optimal total power output is attained when two wind turbines are positioned in a tandem configuration, with the upstream turbine set at a yaw angle of 15 degrees. Incorporating height variation and active yaw control significantly enhances the total power output of wind farms. Implementing these strategies in layout optimization can increase total power output by 1.32 %-10.86 % compared to alternative layouts. Notably, joint optimization surpasses sequential optimization, resulting in a 1.70 % higher total power output.

关键词： Three-dimensional wake model Layout optimization Active yawing control optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

optimization of Orthogonal Waveform Using Memetic algorithm with Iterative Greedy Code Search

引用

REMOTE SENSING 2025年第5期17卷 856-856页

作者： Wang, Wanbin Qian, Lu Zhou, Yun Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

The orthogonality of transmitted waveforms is an important factor affecting the performance of MIMO radar systems. The orthogonal coded signal is a commonly adopted waveform in MIMO radar, and its orthogonality depends on the used orthogonal discrete code sequence set (ODCSs). Among existing optimization algorithms for ODCSs, the results designed by the greedy code search-based memetic algorithm (MA-GCS) have exhibited the best autocorrelation and cross-correlation properties observed so far. Based on MA-GCS, we propose a novel hybrid algorithm called the memetic algorithm with iterative greedy code search (MA-IGCS). Extensions involve replacing the greedy code search used in MA-GCS with a more efficient approach, iterative greedy code search. Furthermore, we propose an "individual uniqueness strategy" and incorporate it into our algorithm to preserve population diversity throughout iteration, thereby preventing premature stagnation and ensuring the continued pursuit of feasible solutions. Finally, the design results of our algorithm are compared with the MA-GCS. Experimental results demonstrate that the MA-IGCS exhibits superior search capability and generates more favorable design results than the MA-GCS.

关键词： radar orthogonal waveforms optimization algorithm orthogonal discrete code sequence set (ODCSs) iterative greedy code search (IGCS)

来源：评论

学校读者我要写书评

暂无评论

An LQR-Lagrange algorithm Generated by Interdisciplinary Integration With Optimal Control and optimization

引用

OPTIMAL CONTROL APPLICATIONS & METHODS 2025年第2期46卷 615-633页

作者： An, Molin Han, Xueshan Shandong Univ Sch Elect Engn Jinan Peoples R China

Interdisciplinary integration is a superior method to improve the optimization algorithm. In this paper, control theory and optimization are combined, and the optimization algorithm is regarded as a control process. Based on the premise of optimal control, the state equation corresponding to Lagrange algorithm is established with the Karush-Kuhn-Tucker (KKT) conditions as the objective. As an optimal control method, linear quadratic regulator (LQR) is utilized to control the calculation process, and an innovative LQR-Lagrange algorithm is proposed. The Lyapunov stability criterion is applied to analyze the convergence, and it is proved that the proposed LQR-Lagrange algorithm is bound to converge as long as the parameter matrices Q and R are positive definite. The analysis indicates that the influence of parameters in LQR-Lagrange algorithm on the calculation speed is monotonic, and the elements in Q and R has no effect on the convergence. Therefore, the proposed algorithm has a monotonic and user-friendly parameter tuning strategy. It perfectly tackles the game between parameter tuning strategy and calculation speed, and cracks the difficulties and dilemmas of conventional algorithms in this issue, realizing a win-win situation.

关键词： interdisciplinary integration LQR-Lagrange algorithm monotonic and user-friendly optimal control optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Phase prediction in laser-clad high-entropy alloy coatings through metaheuristic optimization algorithms and interpretable machine learning

引用

MATERIALS CHEMISTRY AND PHYSICS 2025年 332卷

作者： Liu, Hao Ding, Feng Chen, Peijian Hao, Jingbin Geng, Ruwei Liu, Xinhua China Univ Min & Technol Sch Mech & Elect Engn Xuzhou Peoples R China China Univ Min & Technol Jiangsu Collaborat Innovat Ctr Intelligent Min Equ Xuzhou Peoples R China China Univ Min & Technol Sch Mech & Civil Engn Xuzhou Peoples R China

High-entropy alloys (HEAs) have emerged as promising candidates for laser cladding applications, sparking considerable interest in their design. Phase prediction of HEA coatings presents a formidable challenge due to the non-equilibrium solidification characteristics inherent in laser cladding and the intricate influence of substrate variables. This study employs machine learning (ML), leveraging a dataset of 513 HEAs, to explore phase formation and stability in coatings. The dilution rate and carbon equivalent are introduced as input features that encapsulate the processing nuances of laser cladding. Simulated annealing algorithm and over-sampling method are used to optimize the ML model. The predicted outcomes for 10 unexplored HEA phases closely align with experimental results from laser cladding experiments. Utilizing the SHAP (Shapley Additional Explanations) model, the importance of input features is elucidated, identifying valence electron concentration (VEC) as the most influential. Data analysis further probes the solid solution formation capability of HEA coatings, establishing the following criteria: for single BCC phase, VEC is less than 7.4 and delta is less than 7.63;for single FCC phase, VEC is greater than 7.5 and delta is less than 7.46;and for dual-phase BCC + FCC structure, VEC ranges from 7.2 to 7.8 and delta spans 2.5 to 8.24.

关键词： Laser cladding High-entropy alloy Machine learning Phase prediction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Review of Design Schemes and AI optimization algorithms for High-Efficiency Offshore Wind Farm Collection Systems

引用

ENERGIES 2025年第3期18卷 594-594页

作者： Wang, Yuchen Song, Dongran Wang, Li Huang, Chaoneng Huang, Qian Yang, Jian Evgeny, Solomin Cent South Univ Sch Automat Changsha 410083 Peoples R China South Ural State Univ Dept Elect Stn Grids & Power Supply Syst 76 Prospekt Lenina Chelyabinsk 454080 Russia

The offshore wind power sector has witnessed exponential growth over the past decade, with large-scale offshore wind farms grappling with the challenge of elevated construction and maintenance expenses. Given that the collector system constitutes a substantial part of the investment cost in wind farms, the design and optimization of this system are pivotal to enhancing the economic viability of offshore wind farms. A thorough examination of collector system design and optimization methodologies is essential to elucidate the critical aspects of collector system design and to assess the comparative merits and drawbacks of various optimization techniques, thereby facilitating the development of collector systems that offer superior economic performance and heightened reliability. This paper conducts a review of the evolving trends in collector system research, with a particular emphasis on topology optimization models and algorithms. It juxtaposes the economic and reliability aspects of collector systems with varying topologies and voltage levels. Building on this foundation, the paper delves into the optimization objectives and variables within optimization models. Furthermore, it provides a comprehensive overview and synthesis of AI-driven optimization algorithms employed to address the optimization challenges inherent in offshore wind farm collector systems. The paper concludes by summarizing the existing research limitations pertaining to offshore wind farm collector systems and proposes innovative directions for future investigative endeavors. The overarching goal of this paper is to enhance the comprehension of offshore wind farm collector system design and optimization through a systematic analysis, thereby fostering the continued advancement of offshore wind power technology.

关键词： offshore wind collector system topology optimization algorithm reliability

来源：评论

学校读者我要写书评

暂无评论

An optimization-Simulation Method for Low-Impact-Development (LID) Facilities Based on CCMO algorithm Combining an Integrated Finite Volume Coastal Ocean and Drainage Pipe Model

引用

WATER RESOURCES RESEARCH 2025年第5期61卷

作者： Liu, Fei Cheng, Qiming Zeng, Zijian Wei, Shuyi Yuan, Shaochun Liu, Zhen Chen, Yao Chongqing Jiaotong Univ Key Lab Hydraul & Waterway Engn Minist Educ Chongqing Peoples R China Chongqing Jiaotong Univ Engn Lab Environm Hydraul Engn Chongqing Municipal Dev & Reform Commiss Chongqing Peoples R China Chongqing Jiaotong Univ Sch River & Ocean Engn Chongqing Peoples R China

The employment of Low Impact Development (LID) facilities is an effective means to alleviate urban flood in the context of climate change and urbanization. Existing methods for evaluating the hydrological reduction and control effect of LID facilities are mostly based on hydrological models, which have inherent shortages in accurate flood process simulation. In this study, a fully-distributed bidirectional-coupled hydrodynamic model based on the Finite Volume Coastal Ocean Model (FVCOM) and a one-dimensional drainage pipe model is used to evaluate the effectiveness of LID facilities combining the Coevolutionary Constrained Multi-objective optimization (CCMO) algorithm. The proposed method is applied to investigate the responses of LID facilities effectiveness in hydrological reduction and control to rainfall patterns in the Yuelai New City, Chongqing, China. Results show that the overflow volume and peak overflow under unimodal rainfall are larger than those under other rainfall patterns. The time lag between initial and peak overflow under unimodal rainfall is the shortest, and it is shorter under small rainfall return period. The flood reduction and delay effect of LID facilities under unimodal rainfall is lower than that under bimodal rainfall, and it is the best under uniform rainfall. At low costs, the peak flood reduction effect of combined LID facilities may be lower than that of a single LID facility with strong permeability, but as costs continue to increase, combined LID facilities show its superiority. The proposed optimization-simulation method is of great significance for environmental managers to seek best solutions in urban flood control.

关键词： LID facility optimization algorithm FVCOM drainage pipe model hydrological reduction and control rainfall patterns

来源：评论

学校读者我要写书评

暂无评论

SFIMCO: Scalable fair influence maximization based on overlapping communities and optimization algorithms

引用

NEUROCOMPUTING 2025年 629卷

作者： Chen, Lijuan Rezaeipanah, Amin Shandong Univ Polit Sci & Law Jinan 250014 Shandong Peoples R China Univ Rahjuyan Danesh Borazjan Dept Comp Engn Bushehr Iran

Influence Maximization (IM) is a fundamental problem in social networks, aiming to identify a small set of seed nodes that maximize the spread of influence. Fair Influence Maximization (FIM) extends this concept by incorporating fairness criteria, ensuring equitable influence distribution among diverse groups. Welfare fairness, a prominent fairness measure, strives to balance influence spread and fairness levels. However, optimizing welfare fairness objectives is computationally challenging and often limited to small-scale networks. While community structures are widely used to improve FIM performance, the overlapping nature of communities has been largely overlooked in the literature. This oversight can significantly impact the trade-off between computational complexity and fairness. To address these gaps, this study introduces Scalable FIM based on overlapping Communities and optimization algorithms (SFIMCO). SFIMCO considers the influence potential of nodes within communities by distinguishing between overlapping and non-overlapping nodes. It employs an efficient optimization algorithm to select the seed nodes, ensuring a scalable solution. Meanwhile, the objective function for welfare fairness in SFIMCO is formulated as maximizing the weighted exponential welfare across all overlapping communities, ensuring scalable approximation of fair influence. Experimental evaluations on real- world datasets demonstrate that SFIMCO outperforms state-of-the-art methods in both scalability and fairness. Notably, it achieves a 2.54% improvement in average influence spread compared to the best existing approach, highlighting its effectiveness in addressing the trade-offs between influence spread, fairness, and computational efficiency.

关键词： Fair Influence Maximization (FIM) Scalable FIM Overlapping communities Welfare fairness optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Application and effect evaluation of different optimization algorithms in distributed hydrological model

引用

JOURNAL OF HYDROLOGY-REGIONAL STUDIES 2025年 58卷

作者： Wu, Ming Gao, Yuqin Liu, Yunping Xu, Longsheng Gao, Li Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing 210024 Peoples R China

Study Region: The upper reaches of the Shaying River Basin (the USR Basin) in the Huai River Basin, China Study Focus: The calibration of model parameters is one of the key challenges in advancing the application of hydrological models. The study proposes a novel metaheuristic optimization algorithm, the chaotic particle swarm genetic algorithm (CPSGA), and compares its performance with four well-known optimization algorithms in the field of hydrological model calibration: GA, PSO, DE, and SCE-UA. The comparison focuses on effectiveness, stability, time consumption, and convergence characteristics. New Hydrological Insights for the Region: During the parameter calibration process of runoff simulation in the USR Basin, CPSGA demonstrates strong effectiveness and convergence characteristics. It enhances the GA framework by integrating initial population chaotization, perturbation evolution, and sub-adaptation strategies, which improve individual diversity and facilitate targeted evolution, thereby increasing effectiveness and convergence. However, these enhancements compromise stability and increase time consumption compared to other algorithms. While PSO shows the best convergence characteristics, it suffers from reduced swarm diversity in later iterations, leading to local optima and poor effectiveness. The complex concept and competitive complex evolution (CCE) strategy of SCE-UA make it less effective for optimization problems with a considerable number of variables, limiting its suitability for calibrating fully distributed hydrological models. These results can provide reference for parameter calibration and uncertainty analysis in distributed hydrological models.

关键词： optimization algorithm Chaotic particle swarm genetic algorithm Distributed hydrological model Parameter calibration Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Optimizing energy constrained target localization and tracking with radial bias and seeker optimization algorithms in wireless sensor networks

引用

METHODSX 2025年 14卷

作者： Yazhinian, S. Famila, S. Jose, P. Mahendar, A. Sofia, R. Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Chennai India CMR Tech Campus Hyderabad India Manakula Vinayagar Inst Technol Pondicherry India

The standard localization approach is characterized by a fixed position distribution of the anchor nodes, which cannot be dynamically modified based on the deployment environment. This paper proposes a novel approach combining Radial Bias (RB) with the Seeker optimization algorithm (SOA) to address the challenges of energy-constrained target localization and tracking. The RB technique enhances localization accuracy by refining the position estimates of the target, while the SOA optimizes sensor deployment and data transmission paths to minimize energy consumption. By integrating these two methodologies, ensures a balance between precision in tracking and energy efficiency. Extensive simulations shown this technique surpasses existing methods in terms of both accuracy in determining the location and the duration of network operation. This makes it attractive option for applications of energy-constrained WSNs. The investigation examines the outcome of the particle count in the RBSO algorithm, specifically for values of 5, 10, 15, 20, and 25. The simulation results show that the recommended strategy decreases particles, speeds up positioning and tracking, and maintains target localization and tracking accuracy. It is seen that the proposed RadB_SOA achieves 12.4 % of transmission error, 14.6 % of ranging error, 96.3 % of localization coverage, 98.65 % of PDR, and 21.56 % of energy consumption. center dot The Radial Bias-Seeker optimization algorithm (RadB_SOA) suggested enhances the precision in target localization and optimizes energy usage in wireless sensor networks. center dot Simulation outcomes reveal improved tracking accuracy, minimized transmission and ranging errors, as well as increased localization coverage over current techniques. center dot The research presents an extensive evaluation of particle count fluctuations in RBSO, demonstrating enhanced positioning speed and precision with network efficiency.

关键词： Coverage Energy efficiency optimization algorithm Target localization Tracking Received signal strength

来源：评论

学校读者我要写书评

暂无评论

XAI-BO: an architecture using Grad-CAM technique to evaluate Bayesian optimization algorithms on deep learning models

引用

JOURNAL OF INFORMATION AND TELECOMMUNICATION 2025年

作者： Quach, Luyl-Da Khang, Nguyen Quoc Thai-Nghe, Nguyen Nguyen, Chi-Ngon Can Tho Univ Campus 23-2 St Can Tho Vietnam FPT Univ Can Tho Vietnam

The Bayesian optimization algorithm, proposed in the 1980s, is known for its advantages in optimizing parameters and conserving system resources. However, the specific application of this algorithm in various deep-learning models has not been thoroughly evaluated. This study proposes an experimental model to assess the dependency on reducing hyperparameters in Dense layers and dropout layers, as well as the performance and accuracy across 13 deep learning models, implemented on two datasets with different characteristics and sample sizes (Cucumber disease recognition dataset and tomato physiological states dataset). Additionally, the research utilizes Grad-CAM to clarify the positive impact of parameter reduction when using the BO algorithm. Through evaluations based on hyperparameter data, performance by each iteration, accuracy, and model explainability, the study demonstrates that the BO algorithm optimizes hyperparameters through selective processes. However, it significantly impacts the model's accuracy. This is particularly evident in the InceptionResNetV2 and NasNetMobile models. The research results contribute to a clearer understanding of the impact of optimization algorithms on deep learning models, opening up new research directions in optimizing and elucidating models through the use of explainable artificial intelligence.

关键词： optimization algorithm disease classification Bayesian optimization hyperparameter tuning Grad-CAM

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：