检索结果-内蒙古大学图书馆

49th European Conference on Optical Communications, ECOC 2023

作者： Mao, Xiaoxin Fan, Xiaoqi Wang, Longsheng Fu, Songnian Wang, Yuncai Wang, Anbang Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi Province Taiyuan030024 China College of Optoelectronics Taiyuan University of Technology Taiyuan030024 China School of Information Engineering Guangdong University of Technology Guangzhou510006 China Guangdong Provincial Key Laboratory of Information Photonics Technology Guangzhou510006 China

An optical-chaos secure communication of 86-Gb/s 16-Ary QAM signal over 100-km fiber transmission is experimentally demonstrated under the 20%-overhead SD-FEC BER threshold of 2.0×10-2 by using wideband chaos syn... 详细信息

ISBN: (纸本)9781839539954

关键词： Semiconductor lasers

来源：评论

学校读者我要写书评

暂无评论

Quality Prediction of Injection Molding Process Using CNN and Parallel-Cascade LSTMs 43

Quality Prediction of Injection Molding Process Using CNN an...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Yibo Li, Dewei Zhou, Yuanqiang Gao, Furong Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai201100 China Tongji University College of Electronic and Information Engineering Shanghai201804 China Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The Guangzhou Hkust Fok Ying Tung Research Institute Department of Chemical and Biological Engineering Guangzhou511458 China

ISBN: (纸本)9789887581581

Quality prediction of plastic products has always been an important research topic in the injection molding production process. However, existing quality prediction methods struggle to handle both high-frequency data and statistical data generated during the injection molding production process. This paper introduces a novel quality prediction model for injection molding production, utilizing a combination of Convolutional Neural Networks (CNN) and Parallel-Cascade Long Short-Term Memory (PCLSTM) networks. The PCLSTM network is designed to handle the complexities of high-frequency data in injection molding, overcoming the limitations of traditional LSTM methods in processing long sequence data. By segmenting data into stages and utilizing a cascade mechanism, the PCLSTM architecture efficiently captures important temporal dynamics. Additionally, the CNN network is designed to extract statistical data features. The quality prediction results are obtained by fusing two types of data features and then passing them through a fully connected network. Experimental results on real production datasets show that the CNN-PCLSTM model outperforms existing models in prediction accuracy and training convergence speed. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Image Matching Algorithm Based on Structure Feature 1

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Wang, Xing Zhao, Jiajia su, Ang Guan, Banglei Dong, Jing Han, Songlai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China College of Aerospace Science and Engineering National University of Defense Technology Changsha410073 China Research Institution of Aerospace Technology Central South University Changsha410083 China

ISBN: (数字)9789811966132

ISBN: (纸本)9789811966125

Multimodal image matching is a crucial technique for aircraft navigation in GPS denied environment. However, the nonlinear radiometric difference between multimodal images and significant image noise make this task considerably challenging. A multimodal image registration algorithm build on structural features is presented. The method can also accurately extract structural features in the case of severe noise distortion. Besides, A similarity measure method based on parallelism is presented for adapting nonlinear grayscale distortion. The evaluation show that the algorithm has significant superiority over other state-of-the-art algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

End-To-End Autonomous Exploration for Mobile Robots in Unknown Environments through Deep Reinforcement Learning

End-To-End Autonomous Exploration for Mobile Robots in Unkno...

引用

2022 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2022

作者： Li, Zhi Xin, Jinghao Li, Ning Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Autonomous exploration in unknown environments is a significant capability for mobile robots. In this paper, we present an end-To-end autonomous exploration model based on deep reinforcement learning (DRL), which takes the sensor data and a novel exploration map as inputs, and directly outputs the motion control commands of the robot. In contrast to the existing DRL-based exploration methods, the proposed model has no requirements to be combined with the traditional exploration or navigation algorithms, resulting in lower computational complexity. We directly transfer the DRL-based model trained in the training map to four test maps with different sizes and layouts, and the results show that the robot can rapidly adapt to unknown scenes. Besides, a comparison study with RRT-exploration algorithm indicates that the proposed model can reach a higher map exploration rate within less distance and time. Furthermore, we also conduct experiments on the real physical robot to demonstrate the transferability of learned policy from simulation to reality. A video of our experiments in the Gazebo simulator and real world can be found here1 © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

弹流润滑下考虑切片耦合的直齿轮啮合刚度的迭代模型

引用

Journal of Central South University 2023年第10期30卷 3414-3434页

作者：黄文康马辉赵志芳王鹏飞彭志科张晓旭赵松涛 School of Mechanical Engineering and Automation Northeastern UniversityShenyang 110819China Key Laboratory of Vibration and Control of Aero-Propulsion System of Ministry of Education Northeastern UniversityShenyang 110819China Institute of Vibration Shock&Noise State Key Laboratory of Mechanical System and VibrationShanghai Jiao Tong UniversityShanghai 200240China Harbin Marine Boiler and Turbine Research Institute Harbin 150078China School of Mechanical Engineering Tongji UniversityShanghai 201804China

弹流润滑在减少齿轮表面的变形和摩擦方面起着关键作用,可提高齿轮传动的稳定性和可靠性。本文提出了一个模型来研究直齿轮中弹流润滑与时变啮合刚度之间的复杂关系,旨在求解弹流润滑下的直齿轮时变啮合刚度。本模型考虑了弹流润滑、切... 详细信息

弹流润滑在减少齿轮表面的变形和摩擦方面起着关键作用,可提高齿轮传动的稳定性和可靠性。本文提出了一个模型来研究直齿轮中弹流润滑与时变啮合刚度之间的复杂关系,旨在求解弹流润滑下的直齿轮时变啮合刚度。本模型考虑了弹流润滑、切片耦合、延长啮合、齿轮体柔性耦合和修正的轮齿刚度的影响。为提高准确性,通过去除能量的重复计算来修正轮齿刚度。此外,还推导了切片耦合与变形协调方程之间的迭代关系。提出的模型通过MASTA软件和参考文献进行验证。分析了弹流润滑和切片耦合对直齿轮啮合特性的影响。研究结果显示,考虑切片耦合后,带有鼓向修形的直齿轮的时变啮合刚度显著增大,并且导致边缘的集中载荷转移到齿面的中间部位。

关键词：弹流润滑时变啮合刚度切片耦合变形协调方程

来源：评论

学校读者我要写书评

暂无评论

MGL4QGR: Multi-Gait Locomotion of Quadruped Guide Robot via Teacher-Student Learning

MGL4QGR: Multi-Gait Locomotion of Quadruped Guide Robot via ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Baoping Ma Yuanxiang Wang Wenrui Wang Feng Chen Hongwei Kan Qirong Tang Laboratory of Robotics and Multibody System School of Mechanical Engineering Tongji University Shanghai China Shanghai Institute of Aircraft Mechanics and Control Yangpu District Shanghai China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

To address the locomotion control issue of quadruped guide robots across multiple terrains, a teacher-student framework is adopted to learn the multi-gait locomotion policy. Specifically, the interaction forces between the individual and the guide robot are treated as privileged information for the teacher's policy, and the multi-gait stylized unit serves as proprioceptive information for the student's policy. The trained agent policy is then deployed in a zero-shot and no-tuning manner. The experimental results demonstrate that the quadruped guide robot can efficiently climb 25-degree slopes and 20-cm high steps and exhibit excellent omnidirectional tracking capability in trotting, walking, and pacing gaits.

关键词： Legged locomotion Training Imitation learning Biomimetics Supervised learning Propioception Dogs Angular velocity Quadrupedal robots Immune system

来源：评论

学校读者我要写书评

暂无评论

A Joint Longitudinal and Lateral Guidance Scheme for Reentry Gliding Phase of Hypersonic Vehicles

A Joint Longitudinal and Lateral Guidance Scheme for Reentry...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Wang, Ziyu Wu, Yunjie Duan, Jingqi State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing100191 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Science and Technology on Aircraft Control Laboratory Beijing100191 China Large Aircraft Advanced Training Center Beihang University Beijing100191 China

ISBN: (纸本)9789811966125

A joint longitudinal and lateral guidance law design scheme is proposed for the reference trajectory tracking problem of the reentry gliding phase of hypersonic vehicles. With respect to the longitudinal and lateral motion model of the hypersonic vehicle, a longitudinal guidance law based on the Global Fast Terminal Sliding Mode (GFTSM) algorithm and a lateral guidance law based on the Extended State Observer (ESO) is designed respectively, which are combined to get the bank angle for the hypersonic vehicle and obtain the final guidance scheme. From theoretical analysis, it shows that the guidance scheme has the characteristics of global rapidity and finite-time convergence, and both longitudinal and lateral guidance law are robust to system uncertainties which are caused by certain parameter perturbation and external interference. The effectiveness and superiority of this joint guidance scheme compared to traditional guidance method are verified by simulation experiments using the specific gliding reentry model and reference trajectory of a hypersonic vehicle. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Cooperative formation tracking for heterogeneous multi-UAVs with faulty sensors of leader measurement

Cooperative formation tracking for heterogeneous multi-UAVs ...

引用

第43届中国控制会议

作者： Yan Lv Xiao Gong Ruohan Yang Jiayue Fang Shuo Miao Zhichao Feng Yue Yu Key laboratory of information system and technology Beijing institute of control and electronic technology School of Electronics and Information Northwestern Polytechnical University The Rocket Force University of Engineering

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper focuses on cooperative formation tracking problem of heterogeneous leader-following multi-UAVs with faulty sensors where the faulty sensors of the followers can only measure the partial output of the ***,the kinematic models of heterogeneous multi-UAVs based on the individual speed response time constants are ***,by utilizing the output regulation method,a formation controller based on a distributed observer is proposed based on partial outputs obtained by the faulty sensors of the *** should be noted that the proposed controller can achieve formation tracking of UAVs with faulty sensors to the leader ***,a simulation example is performed to check out the validation of the proposed methods.

关键词： Heterogenous UAVs cooperative formation control sensor faults output regulation

来源：评论

学校读者我要写书评

暂无评论

On Fast-Converged Deep Reinforcement Learning for Optimal Dispatch of Large-Scale Power systems Under Transient Security Constraints

SSRN

引用

SSRN 2024年

作者： Xiao, Tannan Chen, Ying Diao, Han Huang, Shaowei Shen, Chen State Key Laboratory of Power System Operation and Control Tsinghua University Beijing10084 China Department of Electrical Engineering Tsinghua University Beijing10084 China

Power system optimal dispatch with transient security constraints is commonly represented as Transient Security-Constrained Optimal Power Flow (TSC-OPF). Deep Reinforcement Learning (DRL)-based TSC-OPF trains efficient decision-making agents that are adaptable to various scenarios and provide solution results quickly. However, due to the high dimensionality of the state space and action spaces, as well as the non-smoothness of dynamic constraints, existing DRL-based TSC-OPF solution methods face a significant challenge of the sparse reward problem, which greatly limits the practical applications of these methods in large-scale power grids. To address this issue, a fast-converged DRL method for TSC-OPF is proposed in this paper. On the one hand, the Markov Decision Process (MDP) modeling of TSC-OPF is improved by reducing the observation space and smoothing the reward design, thus facilitating agent training. On the other hand, an improved Deep Deterministic Policy Gradient algorithm with Curriculum learning, Parallel exploration, and Ensemble decision-making (DDPG-CPEn) is introduced to drastically enhance the efficiency of agent training and the accuracy of decision-making. The effectiveness of the proposed method is demonstrated through experiments on the IEEE 39-bus system and a practical 710-bus regional power grid. In both systems, the training process shows stable and rapid convergence. Furthermore, the efficiency and accuracy of the well-trained agents are confirmed by testing them in new scenarios and comparing their dispatch results with those obtained using the particle swarm optimization algorithm. The source code of the proposed method is made public on GitHub. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring for Railway Point Machines Based on Sound Analysis and Support Vector Machine

引用

Chinese Journal of Electronics 2020年第4期29卷 786-792页

作者： SUN Yongkui CAO Yuan XIE Guo WEN Tao School of Electronic and Information Engineering Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology

Railway point machines(RPMS) are one of the key equipments in the railway system to switch different routes for the *** monitoring for RPMs is a vital measure to keep train operation safe and *** convenience and low cost into consideration, a novel intelligent condition monitoring method for RPMs based on sound analysis is ***-domain and frequency-domain features are obtained,and normalized using z-score standardization method to eliminate the influences of different *** particle swarm optimization(BPSO) is utilized to select the most significant discrimination feature *** effects of the selected optimal features are verified using Support vector machine(SVM), 1-Nearest neighbor(1 NN), Random forest(RF), and Naive Bayes(NB).Experiment results indicate SVM performs best on identification accuracy and computing cost compared with the other three *** identification accuracies on normal switching and reverse switching processes reach100% and 99.67%, respectively, indicating the feasibility of the proposed method.

关键词： Condition monitoring Sound analysis Railway point machines(RPMs) Binary particle swarm optimization(BPSO) Support vector machine(SVM)

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：