检索结果-内蒙古大学图书馆

Whale optimisation algorithm with role labour division for multimodal optimisation

International Journal of Innovative Computing and Applications 2024年第1期15卷 26-37页

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education of China Huazhong University of Science and Technology Hubei Wuhan430074 China

The multimodal optimisation problem challenges the balance between diversity and convergence, which poses a great degree of challenge to traditional population-based intelligence optimisers. The whale optimisation algorithm has the limitation of easily falling into local optimum when facing multimodal optimisation. To address this problem, this paper proposes a whale optimisation algorithm with role labour division (WOA-RDL). In WOA-RDL, a multi-stage role division of labour mechanism is designed to divide the optimisation process into two stages of group hunting. In the first stage, the task allocation in the hunting process is considered as two types of search tasks: exploration and exploitation. The external environmental stimulus of the task and the internal response threshold of the individual were designed to allow individuals to switch between exploration and exploitation tasks flexibly. In the second stage, the distribution mechanism of different roles was designed to simulate the 'strong to weak' distribution rule for the distribution of results after the hunt. The elite roles are selected to further strengthen their capabilities or remain robust, while the inferior roles are predicted and eliminated to improve the overall optimisation of the population and reduce the risk of falling into a local optimum. The results of the optimisation experiments using multimodal, unimodal, CEC2017 combined functions and CEC2009 dynamic functions to validate the effectiveness of the algorithm. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A New Approach Based on Crater Detection and Matching for Self-Localization During Lunar Landings

A New Approach Based on Crater Detection and Matching for Se...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Qian, Zhouyuan Cheng, Hao Hu, Tao Cao, Tao Han, Yu He, Liang Shanghai Aerospace Control Technology Institute Shanghai201109 China Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai201109 China

ISBN: (纸本)9789811669620

This paper provides an approach of visual localization based on crater detection and matching in lunar landing missions. Firstly, considering that the lunar image intensity is not uniform, and the contrast between the bright and dark areas is not obvious, a multi-threshold segmentation method based on gray features and geometric constraints is introduced to realize automatic extraction of multi-scale craters. Secondly, by constructing a rigid transformation model, the craters in descent images are roughly matched with the corresponding craters in database. Meanwhile, an efficient method using re-projection errors is proposed for reducing false matches so as to improve the localization accuracy. Images taken by Chang’e-3 landing camera and Lunar Reconnaissance Orbiter (LRO) are utilized to test the performance of the proposed approach, simulation results show that the proposed approach is able to detect the small-scale craters in low contrast areas with a high detection rate, and it can also match the correct craters to the database even when the resolution ratio between descent image and database is up to 10:1, which confirms that the proposed approach has strong robustness and high reliability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-stream fusion network for continuous gesture recognition based on sEMG

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 374-383页

作者： Li, Jun Zou, Chunlong Tang, Dalai Sun, Ying Fan, Hanwen Li, Boao Tang, Xinjie Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Inner Mongolia University of Finance and Economics Hohhot China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China

Dynamic gesture recognition is an essential step in human-computer interaction. However, dynamic gesture recognition based on Surface Electromyography (sEMG) signals faces issues such as incomplete feature extraction and incomplete recognition of temporal information between continuous gestures. Therefore, this paper proposes a multi-stream fusion network (MSK-LCNN) for dynamic gesture recognition to improve accuracy. We combine CNN and LSTM models into a unified framework which extracts spatio-temporal information both globally and in depth, and combines feature fusion to retain essential information. This framework uses an attention mechanism (SKNet) to learn more intricate feature information. The gesture recognition accuracy of this method on our data set is 95.23%, and on the NinaPro DB1 data set, it is 91.45%, which outperforms other similar networks in recent years. Applying this algorithm to prosthetic hand control has achieved flexible and stable control of the prosthetic hand. © 2024 Inderscience Enterprises Ltd.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Two performance indicators of reaction wheel underactuated configuration 1

引用

19th Chinese intelligent Systems Conference, CISC 2023

作者： Xie, Jun Feng, Jia-Jia Zhang, Yu-Jie Chen, Qiang Beijing Institute of Control Engineering Beijing100190 China Science and Technology on Space Intelligent Control Laboratory Beijing100190 China

ISBN: (数字)9789819968824

ISBN: (纸本)9789819968817

It is of great engineering significance to study the underactuated configuration of reaction wheels. Aiming at the problem of how to effectively improve the control performance of the control system, this paper proposes two performance optimization indicators in the reaction wheel underactuated configuration from the control mechanism of the underactuated control, which provides a reference for the optimization design of the reaction wheel underactuated configuration. The two performance indicators are the area of the actuated Euler axis and the error angle of the underactuated axis. The simulation analysis of the performance indicators is carried out for an engineering example. The results show that the optimization of the two performance indicators proposed in this paper can effectively improve the control performance of the system under underactuated control. It is proved that the two performance optimization indicators proposed in this paper are feasible and effective, and have certain engineering application value. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Fully Actuated System Approach for Free-Flying Space Manipulator

Neural Network-Based Fully Actuated System Approach for Free...

引用

2023 China Automation Congress, CAC 2023

作者： Zhao, Qin Duan, Guang-Ren Tian, Guangtai Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen China

ISBN: (纸本)9798350303759

This study explores the trajectory tracking control problem of a free-flying space manipulator subject to parametric uncertainties, external disturbance, and actuator saturation. An adaptive control strategy, employing the fully actuated system (FAS) approach, is designed, wherein the radial basis function neural network (RBFNN) is incorporated to offset lumped uncertainties. As a result, a constant linear closed-loop system is obtained with an arbitrarily assigned eigenstructure. Then the parametric method is utilized for controller parameter selection. In the context of Lyapunov theory, the presented controller ensures robust convergence of position and velocity tracking errors to a small neighborhood of the origin. A numerical simulation is finally performed to validate the efficacy of the presented controllers. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Mars Terrain Segmentation Algorithm Based on Improved PSPNet

Mars Terrain Segmentation Algorithm Based on Improved PSPNet

引用

2023 International Conference on Optics and Machine Vision, ICOMV 2023

作者： Zhou, Peng Xiong, Kai Beijing Institute of Control Engineering Beijing100090 China Science and Technology on Space Intelligent Control Laboratory Beijing100094 China

ISBN: (纸本)9781510664777

Planet rovers are becoming more and more crucial as deep space exploration missions develop. Accurate terrain segmentation can increase the rovers' capacity for independent detection. At present, the task of Mars terrain segmentation is difficult and the computational resources on rover are limited. This paper proposes an improved PSPNet algorithm for Mars terrain segmentation. MobileNetV2 is a lightweight network that replaces ResNet as the feature extraction backbone network. The channel attention mechanism SEnet is integrated into the network structure to improve the network's feature extraction capability. The experimental results show that the number of parameters and calculation amount of M-PSPNet are greatly reduced when compared to traditional PSPNet, but the recall rate of M-PSPNet on soil, bedrock, sand, and big rock can reach 92%, 91%, 86%, and 72%, respectively. Engineering-wise, the M-PSPNet is competitive. © 2023 SPIE. All rights reserved.

关键词： Rovers

来源：评论

学校读者我要写书评

暂无评论

Combine deep learning and Bayesian analysis to separate overlapping gravitational wave signals

引用

science China(Physics,Mechanics & Astronomy) 2025年第5期68卷 205-219页

作者： Cunliang Ma Weiguang Zhou Zhoujian Cao Mingzhen Jia Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and TechnologyGanzhou 341000China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

Future gravitational wave(GW)observatories,such as the Einstein Telescope,are anticipated to encounter overlapping GW signals,presenting considerable obstacles to GW data processing techniques,including signal identification and parameter *** this letter,we propose a scheme of combining deep learning and Bayesian analysis to disentangle overlapping GW *** deep learning part takes a data-driven approach that employs an encoder-separation-decoder framework which is powerful enough to extract the shape of the signal even when the GW signals completely *** Bayesian analysis part takes the matched filtering technique to extract the amplitude of the GW *** scheme can facilitate the utilization of existing GW detection and parameter estimation methods for future instances of overlapping *** methodology effectively reduces biases in parameter estimation when handling multiple intertwined ***,this marks the first known instance where deep learning has been successfully utilized to disentangle overlapping GW signals.

关键词： gravitational wave separation machine learning Einstein Telescope parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Robust H∞ Attitude Stabilization for the Cluster Takeover of Non-cooperative Flexible Spacecraft 1

引用

29th International Conference on Computational and Experimental Engineering and sciences, ICCES 2023

作者： Yue, Xiaokui Yang, Ziyu Yu, Hongyu Huang, Panxing Liu, Yuan National Key Laboratory of Aerospace Flight Dynamics School of Astronautics Northwestern Polytechnical University Xi’an710072 China Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100094 China Beijing Institute of Remote Sensing Information Beijing100011 China

ISBN: (数字)9783031449475

ISBN: (纸本)9783031449468

In this paper, a cooperative control scheme based on the small spacecraft cluster is proposed for the takeover control of the failed flexible spacecraft in space. In order to overcome external disturbance, inertia uncertainty and controller gain perturbation, the controller spacecraft calculates the control torque which can stabilize the combined spacecraft in theory, and generates the desired control signal according to the robust H∞ non-fragile control law set in advance. Based on the communication topology, the actuator spacecraft restores the control signal according to the distributed control torque allocation scheme considering the saturation state of all reaction wheels, and implements it to achieve the attitude stabilization and vibration suppression of the combined spacecraft. Simulation results show that the distributed control torque allocation scheme can implement the desired control signal with relatively small error. Under the condition that the external disturbance, controller gain perturbation and inertia uncertainty coexist, the angle and angular velocity of the combined spacecraft can be stabilized quickly. Moreover, the vibration of the flexible appendages can also be suppressed effectively. During the whole takeover control process, the dynamic allocation scheme can always ensure that all reaction wheels of each actuator spacecraft never reach saturation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Flexible spacecraft

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of Magnetic control of Ultra Quiet control System in Gravity Satellite 10th

The Design and Implementation of Magnetic Control of Ultra Q...

引用

10th International Conference on Signal and Information Processing, Network and Computers, ICSINC 2022

作者： Guan, Bin Liu, Yiwu Liu, Qirui Li, Yan Fan, Jiakun Beijing Institute of Control Engineering Beijing100190 China Science and Technology on Space Intelligent Control Laboratory Beijing100190 China

ISBN: (纸本)9789811999673

In order to obtain gravity field data with high-precision, ultra quiet control should be applied in the attitude control system to reduce the influence of micro vibration caused by attitude control, since the measurement accuracy of the high-precision acceleration of the key load of the gravity measurement satellite has reached the level of 10 - 10m / s 2. A set of ultra quiet control system of magnetic control with high-precision is proposed in the paper, which makes the magnetic control accuracy reach the high-precision level of 0.01mNm and establishes an "extremely quiet" working environment for high-precision acceleration load by improving the geomagnetic field acquisition accuracy and high-precision magnetic torquer control. According to the data analysis of orbit, the result shows that the micro vibration environment of the magnetic control system has reached the ug level. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： control systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Satellite Mission Planning Method for Dynamic Targets Based on Reinforcement Learning

Multi-Satellite Mission Planning Method for Dynamic Targets ...

引用

2023 China Automation Congress, CAC 2023

作者： Liu, Yilong Zhang, Cong Zhang, Sihang Li, Jiaxing Beijing Institute of Control Engineering Beijing China Beijing Institute of Control Engineering Science and Technology on Space Intelligent Control Laboratory Beijing China

ISBN: (纸本)9798350303759

The autonomous mission planning problem of space targets tracking with multi-satellite is studied in this paper. For effective evaluation of different candidate tracking resource combinations, a tracking performance evaluation model based on GDOP is proposed firstly, then a tracking priorities evaluation model for maneuverable dynamic targets is designed to autonomous evaluate and update the planning priorities during the tracking. To solve the problem of conflict resolution of tracking resources scheduling, the reinforcement learning algorithm is applied, considering of restricted computation resources onboard. A pointer network is utilized as the strategy model, with the tracking targets and corresponding priorities, the tracking performance evaluation of each potential candidate tracking resources combinations as input tensors, and the tracking tasks allocation of multi-satellites will be inferenced by the network accordingly. The actor-critic reinforcement learning algorithm is selected for training. It is shown that the algorithm proposed can formulate better planning strategies than the heuristic method, which reduces the mean tracking error by 21% during the whole tracking process. © 2023 IEEE.

关键词： Reinforcement learning

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：