检索结果-内蒙古大学图书馆

Neural network sliding mode control of multi-agent systems based on a preview mechanism and whale optimization algorithm

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING 2025年第5期239卷 823-840页

作者： Chen, Yuxin Ren, Junchao Northeastern Univ Coll Sci 3-11 Wenhua Rd Shenyang 110819 Liaoniong Peoples R China

In this work, a neural network sliding mode control (SMC) scheme is proposed to address the tracking issue of discrete-time multi-agent systems (MASs) with unknown nonlinearities by combining the preview mechanism and whale optimization algorithm. An augmented error system (AES) was constructed, which includes previewable reference and disturbance signals. A new sliding mode surface is designed for AES, and the stability criteria are proposed for the sliding mode dynamics. Utilizing the preview mechanism and whale optimization algorithm, the neural network-based SMC law is designed to satisfy the discrete-time reachability condition. Two simulation examples are provided to demonstrate that the proposed control scheme can effectively enhance the tracking performance of MASs.

关键词： Preview mechanism sliding mode control multi-agent systems neural network whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Maximizing the velocity deflection of asteroid Didymos using the whale optimization algorithm

引用

PLANETARY AND SPACE SCIENCE 2025年 258卷

作者： Shafieenejad, Iman Minist Sci Res & Technol Khayyam Res Inst Tehran Iran

This study aims to optimize the velocity change of the Didymos asteroid using the whale optimization algorithm (WOA). The deflection of asteroids that pose significant threats to Earth is a crucial aspect of upcoming space missions. In this research, a spacecraft is attached to the Didymos asteroid, utilizing its gravitational force as a perturbation to modify the asteroid's trajectory. The transfer of kinetic energy from the spacecraft to the asteroid induces a change in velocity (Delta V). The findings indicate that the most substantial impact on velocity occurs in the radial direction, showing divergent oscillatory behavior. The results suggest that the optimal point for significant velocity change is located shortly after the perihelion. At this point, WOA achieves the maximum velocity change. Additionally, the stability of the asteroid's deflection is investigated due to the nonlinear characteristics of the orbital motion equations. The optimal velocity change is identified as Delta Vtotal = 2.5139 x 10-7 km at Delta t = 27.657(h), occurring after the perihelion at t(h)Delta Vmax . This study introduces a novel optimization approach for asteroid deflection, emphasizing the nonlinear dynamics of orbital motion.

关键词： Asteroid Didymos Spacecraft deflection Maximizing velocity change whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A federated learning model with the whale optimization algorithm for renewable energy prediction

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Chifu, Viorica Rozina Cioara, Tudor Anitei, Cristian Daniel Pop, Cristina Bianca Anghel, Ionut Toderean, Liana Tech Univ Cluj Napoca Comp Sci Dept Memorandumului 28 Cluj Napoca 400114 Romania

Federated prediction models for energy prosumers create a global model by combining insights from local machine learning models trained on-site without centralizing the data. For time series energy data, this collaborative approach faces challenges due to the non-IID nature of the data, variations in generation patterns, the high number of model parameters, and convergence issues, leading to poor prediction accuracy. This paper introduces a novel federated learning model, FedWOA, which uses the whale optimization algorithm to determine optimal aggregation coefficients based on the local model weight vectors by pondering the updates considering the model performance and data dimensionality construct the global shared model. To handle the non-IID data the prosumers were clustered based on the similarity of their energy profiles using KMeans. FedWOA improves the prediction quality at the prosumer site, with a 16 % average reduction of the mean absolute error compared to FedAVG while demonstrating good convergence and reduced loss.

关键词： Federated learning whale optimization algorithm Renewable energy prediction Smart grid LSTM neural network K -Means clustering

来源：评论

学校读者我要写书评

暂无评论

An Improved Nonlinear Active Disturbance Rejection Controller via Sine Function and whale optimization algorithm for Permanent Magnet Synchronous Motors Speed Control

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2025年第4期20卷 548-559页

作者： Wang, Longda Liu, Gang Xu, Chuanfang Dalian Jiaotong Univ Sch Elect Engn Dalian 116028 Peoples R China Inner Mongolia Minzu Univ Coll Engn Tongliao 028000 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

Permanent magnet synchronous motors (PMSMs) speed control has gained wide application in various fields. Specifically, there is a disadvantage that nonlinear functions in the conventional active disturbance rejection controller (ADRC) is non-differentiable at the piecewise points. Thus, an improved nonlinear active disturbance rejection controller (NLADRC) for permanent magnet synchronous motor speed control via sine function and whale optimization algorithm (WOA), abbreviated as NLADRC-sin-IWOA, is proposed to overcome this drawback. Considering the unsatisfactory control effect caused by the poor active disturbance resisting ability of the traditional PMSM controllers, this paper proposes an improved NLADRC for PMSM, that reconstructs a novel differentiable and smooth nonlinear function, the novel nonlinear function grounded on primitive function by the function of inverse hyperbolic, sine, square functions, and with difference fitting approach;and designs an improved whale optimization algorithm via convergence factor nonlinear decreasing, Gaussian variation and adaptive cross strategies. The experimental results findings show that the improved NLADRC-sin-IWOA has the advantages of response fast, small steady-state error and tiny overshoot. (c) 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： permanent magnet synchronous motor nonlinear active disturbance rejection controller whale optimization algorithm nonlinear function Gaussian mutation

来源：评论

学校读者我要写书评

暂无评论

Minimum Zone Evaluation of Cylindricity Error Based on the Improved whale optimization algorithm

引用

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING 2025年第4期26卷 859-875页

作者： Zheng, Peng He, Qingze Lyu, Xingchen Li, Jicun Li, Yan Zhengzhou Univ Sch Mech & Power Engn Zhengzhou 450001 Henan Peoples R China

The shape error of shaft-type mechanical components directly influences the quality, fitting precision and lifespan of the components. Among these, cylindricity error is a critical indicator for evaluating the precision of shaft-type components. Based on the new generation geometric product specifications & verification (GPS), this paper researched GPS inspection operation operators, determined extraction and fitting schemes, and constructed a mathematical model for cylindricity error evaluation. Consequently, a method for cylindricity error evaluation based on an improved whale optimization algorithm was proposed. The proposed algorithm introduced chaotic mapping and nonlinear parameters during population initialization to enhance solution quality. Subsequently, adaptive weighting coefficients were incorporated during spiral position updates to improve the algorithm's local search capability. Finally, Levy flight strategies were introduced during random search to enhance the algorithm's global search capability. This study conducted experimental validation and analysis by performing numerous comparative experiments on different extraction point numbers, cross-section numbers, evaluation criteria, and algorithms. The experimental results indicated that the proposed method for cylindricity error evaluation demonstrated significant improvements in both accuracy and efficiency compared to genetic algorithms, least squares methods, and others.

关键词： whale optimization algorithm Cylindricity error Geometric product specifications & verification Inspection operation operator

来源：评论

学校读者我要写书评

暂无评论

Early Quality Prediction of Complex Double-Walled Hollow Turbine Blades Based on Improved whale optimization algorithm

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING 2025年第1期25卷 011003页

作者： Dong, Yiwei Gong, Yuhan Bo, Xu Tan, Zhiyong Xiamen Univ Sch Aerosp Engn 422 Siming Rd Xiamen 361005 Fujian Peoples R China AECC Commercial Aircraft Engine Co Ltd 3998 Lianhua South Rd Shanghai 200241 Peoples R China

The precision in forming complex double-walled hollow turbine blades significantly influences their cooling efficiency, making the selection of appropriate casting process parameters critical for achieving fine-casting blade formation. However, the high cost associated with real blade casting necessitates strategies to enhance product formation rates and mitigate cost losses stemming from the overshoot phenomenon. We propose a machine learning (ML) data-driven framework leveraging an enhanced whale optimization algorithm (WOA) to estimate product formation under diverse process conditions to address this challenge. Complex double-walled hollow turbine blades serve as a representative case within our proposed framework. We constructed a database using simulation data, employed feature engineering to identify crucial features and streamline inputs, and utilized a whale optimization algorithm-back-propagation neural network (WOA-BP) as the foundational ML model. To enhance WOA-BP's performance, we introduce an optimization algorithm, the improved chaos whale optimization-back-propagation (ICWOA-BP), incorporating cubic chaotic mapping adaptation. Experimental evaluation of ICWOA-BP demonstrated an average mean absolute error of 0.001995 mm, reflecting a 36.21% reduction in prediction error compared to conventional models, as well as two well-known optimization algorithms (particle swarm optimization (PSO), quantum-based avian navigation optimizer algorithm (QANA)). Consequently, ICWOA-BP emerges as an effective tool for early prediction of dimensional quality in complex double-walled hollow turbine blades.

关键词： early quality prediction double-walled hollow turbine blade cubic mapping whale optimization algorithm data-driven engineering machine learning for engineering applications physics-based simulations

来源：评论

学校读者我要写书评

暂无评论

Near-Global-Optimal Resource Allocation for Uplink SCMA Systems Based on whale optimization algorithm

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第2期24卷 1089-1103页

作者： Soltanpour, Meysam Zhang, Haixia Shandong Key Lab Intelligent Commun Sensing Comp I Jinan 250061 Shandong Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China

This paper investigates a joint resource allocation (RA) algorithm to maximize the average sum rate (ASR) of the sparse code multiple access (SCMA) random model-based networks. The ASR optimization problem turns out to be non-convex mixed-integer nonlinear programming (MINLP) problem which is challenging to address. The previous works strongly depend on the upper/lower bound of ASR, successive convex approximation (SCA) methods, initial assignment definition, post-processing procedures, and generating/training the data sets, thus cannot be applied. Given the above challenges, considering the ability of the whale optimization algorithm (WOA) in solving the non-convex MINLP NP-hard problems, we first construct the resource element assignment (REA) matrix utilizing the binary WOA (BWOA) through the reshaping the pattern of the arrangement of non-zero elements (PANs) and converting the structural constraints. Then we enhance the continuous WOA (CWOA) to mine the power allocation (PA) coefficients by using an acceleration factor that improves the exploration and exploitation phases. We also develop a Kuhn-Munkres (KM)-based algorithm as an REA benchmark which needs no for post-processing requirements. Finally, our proposed algorithms are compared with the state-of-the-art works in the literature. Results show that SCMA CWOA-BWOA algorithm (CBWOA) provides more robust optimality in massive connectivity situations with a larger number of users. Besides, the CBWOA method guarantees the structural constraints by increasing the number of search agents (NSAs) through the exploitation phase.

关键词： Resource management Uplink Interference whale optimization algorithms Vectors Clustering algorithms Training Measurement Industrial Internet of Things Wireless networks SCMA whale optimization algorithm non-convex MINLP resource allocation metaheuristic

来源：评论

学校读者我要写书评

暂无评论

whale optimization algorithm coupled with machine learning models for quantitative prediction of soil Ni content

引用

MICROCHEMICAL JOURNAL 2025年 209卷

作者： Fu, Chengbiao Feng, Xiqin Tian, Anhong Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China Kunming Univ Sci & Technol Fac Land Resource Engn Kunming 650093 Peoples R China

Under the background of environmental protection and sustainable agricultural development, it is crucial to monitor soil heavy metals, especially potentially harmful substances such as nickel. Spectroscopy technology is characterized by non-destructiveness and high efficiency, it can rapidly monitor the nickel content in the soil and provide guidance for safe agricultural production, thus promoting the green development of agriculture. There are few reports on the quantitative prediction of soil heavy metal nickel (Ni) content based on visible and nearinfrared (Vis-NIR) spectroscopy. In this study, 60 soil samples were collected from the Mojiang Hani Autonomous County, Yunnan Province, to explore a high-precision quantitative prediction model. A feature band extraction method based on whale optimization algorithm (WOA) was proposed and analyzed in comparison with the traditional feature selection methods based on genetic algorithm (GA) and particle swarm optimization (PSO). Three machine learning models (support vector regression (SVR), random forest (RF), and back propagation (BP)) were employed to study the prediction accuracy of the quantitative prediction model, and the performance of the constructed model was evaluated based on the coefficient of determination (R2), the root mean square error (RMSE), the residual prediction bias (RPD), and the performance ratio of the quartile distance (RPIQ). The results of the study indicated that: The swarm intelligent optimization algorithm based on WOA can extract fewer feature bands. The soil feature bands extracted by WOA are reduced by 15.67 % and 14.93 % compared to the GA and PSO algorithms, respectively. For quantitative prediction of soil Ni content, machine learning models based on BP had the best accuracy, GA-BP, PSO-BP and WAO-BP performance for quantitative prediction of soil Ni content was very good, extremely good, and extremely good with RPD values of 2.523, 2.644, and 3.098, respectively. Compared to the GA-

关键词： whale optimization algorithm Machine learning Soil heavy metals Vis-NIR spectroscopy Feature variable selection

来源：评论

学校读者我要写书评

暂无评论

An Enhanced whale optimization algorithm for Task Scheduling in Cloud Computing

An Enhanced Whale Optimization Algorithm for Task Scheduling...

引用

International Conference on 6G Communications Networking and Signal Processing, SGCNSP 2023

作者： Srilatha, P. Ramadan, Ghazi Mohamad Kumar, T. M. Kiran Alekhya, Y. Pani, Alok Kumar Department of AI & DS Chaitanya Bharathi Institute of Technology Telangana Hyderabad India College of MLT Ahl Al Bayt University Karbala Iraq Department of CSE Siddaganga Institute of Technology Tumakuru India Maisammaguda Hyderabad India Bangalore India

ISBN: (纸本)9789819778751

Task Scheduling is the significant challenge in the environment of Cloud Computing (CC) and has attention in numerous researchers in recent years with respect to attain cost effective computation and improve resource utilization. The existing algorithms has limitations of role and selection criteria of inertia weight was not considered. In this research, Enhanced whale optimization algorithm (EWOA) is proposed for maximize effectiveness of task scheduling in CC. An inertia weight is implemented in WOA algorithm that enhances the convergence and accuracy of algorithm that helps in task scheduling effectiveness. The performance of proposed technique is estimated with performance measure of Makespan (ms), execution time (s) and resource utilization (%). The proposed method attained less execution time of 2304, 2537, 2765, 2983 and 3016 s for 200, 400, 600, 800 and 1000 number of tasks. The proposed method attained the superior results when compared with other existing algorithms like Ant Colony optimization (ACO), Grey Wolf optimization (GWO), Particle Swarm optimization (PSO) and whale optimization algorithm (WOA). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud computing Inertia weight Resource utilization Task scheduling whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-swarm whale optimization algorithm based on elite tuning for high-dimensional feature selection classification problems

引用

APPLIED SOFT COMPUTING 2025年 169卷

作者： Miao, Fahui Wu, Yong Yan, Guanjie Si, Xiaomeng Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Univ Macau Zhuhai UM Sci & Technol Res Inst Zhuhai 519000 Peoples R China Shanghai Urban Construct Vocat Coll Dept Basic Educ Shanghai 201415 Peoples R China Shanghai Polytech Univ Inst Artificial Intelligence Sch Comp & Informat Engn Shanghai 201209 Peoples R China

Feature selection algorithms are crucial technologies for reducing the dimensionality of high-dimensional data. However, the exponential expansion of the decision space due to high-dimensional data makes most feature selection algorithms highly susceptible to local optima. To increase the quality of feature selection, we propose a dynamic multi-swarm whale optimization algorithm based on elite tuning (EMSWOA). First, we propose a dynamic multiple swarm construction mechanism based on the centroid distance metric, which enhances the exploitation and exploration abilities of the algorithm by improving the connectivity between sub-population topologies and preventing the algorithm from falling into precocious convergence. Secondly, to address the issue of invalid probability flips caused by random thresholds during feature space transformation, we design a novel elite tuning mechanism. This mechanism uses the high-quality information in the elite solution to assess and correct the probability of feature flipping;it effectively improves the algorithm's recognition of important features and reduces the interference of invalid probability flips in the optimization search. Finally, we validated the EMSWOA against six comparison algorithms on 19 datasets. The experimental results demonstrate that, compared with the most effective benchmark algorithms, the EMSWOA yields an average accuracy increase of 2.91 % and an average reduction in the number of features by a factor of 3.58.

关键词： whale optimization algorithm Feature selection Swarm intelligence Centroid distance metric Elite tuning strategy

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：