检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Pingli Lu Ying Yang Ministry of Education Key Laboratory of Complex System Intelligent Control and Decision (Beijing Institute of Technology) Beijing P. R. China Department of Mechanics and Engineering Science Peking University Beijing P. R. China

Chaotic synchronization criteria for a class of dynamical networks with each node being RCL-shunted Josephson junction is proposed in this paper. The proposed algorithms, which are established in terms of linear matrix inequalities (LMIs), guarantee the synchronized states to be global asymptotically stable. In addition, an interesting conclusion is reached that the chaotic synchronization in the coupled whole 3N-dimensional networks can be converted into that of 3-dimensional space.

关键词： Junctions Synchronization Integrated circuits Linear matrix inequalities Josephson junctions Eigenvalues and eigenfunctions Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Biomimetic inspiration for PKM torso design in humanoid robots

Biomimetic inspiration for PKM torso design in humanoid robo...

引用

IEEE International Conference on Mechatronics and Automation

作者： Hulin Huang Ceccarelli Marco Weimin Zhang Qiang Huang Zhangguo Yu Xuechao Chen Ministry of Education Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Beijing China Laboratory of Robotics and Mechatronics University of Cassino and South Latium Cassino Italy Ministry of Education International Joint Research Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing China

ISBN: (纸本)9781479970995

A new torso design of humanoid robot is proposed as a 3-DOF PKM (Parallel Kinematic Manipulator) structure by using results of a biomimetic analysis of torso in humans and animals. Main characteristics of torso in nature are presented from which design requirements are outlined for a solution in humanoid robot. The PKM torso is consist of two platforms and four UPU mechanisms. The usefulness of such a biomimetic inspiration is proved by a numerical simulation of the proposed PKM torso in its basic movements.

关键词： Torso Humanoid robots Joints Thorax Horses Payloads

来源：评论

学校读者我要写书评

暂无评论

Multi-player pursuit–evasion games with one superior evader

引用

Automatica 2016年 71卷 24-32页

作者： Jie Chen Wenzhong Zha Zhihong Peng Dongbing Gu School of Automation Beijing Institute of Technology Beijing 100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081 China School of Computer Science and Electronic Engineering University of Essex Colchester CO4 3SQ UK

Inspired by the hunting and foraging behaviors of group predators, this paper addresses a class of multi-player pursuit–evasion games with one superior evader, who moves faster than the pursuers. We are concerned with the conditions under which the pursuers can capture the evader, involving the minimum number and initial spatial distribution required as well as the cooperative strategies of the pursuers. We present some necessary or sufficient conditions to regularize the encirclement formed by the pursuers to the evader. Then we provide a cooperative scheme for the pursuers to maintain and shrink the encirclement until the evader is captured. Finally, we give some examples to illustrate the theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Vision Decoder: A Robust Automatic Target Recognition Model for Sar Images

SSRN

引用

SSRN 2022年

作者： Ayodeji, Abiodun Wang, Wenhai Su, Jianzhong Yuan, Jianquan Liu, Xinggao State Key Laboratory of Industrial Control Technology Control Department Zhejiang University Hangzhou310027 China Tianjin Jinhang Technical Physics Institute Tianjin300192 China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

The synthetic aperture radar (SAR) is the recent all-weather technology used to monitor areas with low to moderate penetration. However, the scarcity of SAR imagery, and the high-level noise in the images makes it difficult for real-time image interpretation. This work presents a novel fast vision decoder (FViD), a target recognition model with a frozen backbone and stack dilated autoencoder. The autoencoder architecture is introduced to learn the compressed latent representation. Moreover, a robust backbone selection method is introduced to select a task-specific optimal backbone. The proposed FViD is extensively evaluated using the Chinese TerraSAR-X ship images, and the US MSTAR datasets. Evaluation results show that the proposed method has significant improvement over the conventional models. The speed and accuracy of the proposed FViD are further compared with five state of the art models previously used for SAR target recognition tasks, and the comparison result shows that the FViD performs better. Moreover, an ablation study is performed to provide insights into the contribution of FViD architecture. The results of the ablation study as well as the performance improvement of FViD are discussed in this paper. © 2022, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

An empirical evaluation of attention-based multi-head models for improved turbofan engine remaining useful life prediction

arXiv

引用

arXiv 2021年

A single unit (head) is the conventional input feature extractor in deep learning architectures trained on multivariate time series signals. The importance of the fixed-dimensional vector representation generated by the single-head network has been demonstrated for industrial machinery condition monitoring and predictive maintenance. However, processing heterogeneous sensor signals with a single-head may result in a model that cannot explicitly account for the diversity in time-varying multivariate inputs. This work extends the conventional single-head deep learning models to a more robust form by developing context-specific heads to independently capture the inherent pattern of each sensor reading in multivariate time series signals. Using the turbofan aircraft engine benchmark dataset (CMAPSS), an extensive experiment is performed to verify the effectiveness and benefits of multi-head fully connected neurons, recurrent networks, convolution network, the transformer-style stand-alone attention network, and their variants for remaining useful life estimation. Moreover, the effect of different attention mechanisms on the multi-head models is also evaluated. In addition, each architecture's relative advantage and computational overhead are analyzed. Results show that utilizing the attention layer is task-sensitive and model dependent, as it does not provide consistent improvement across the models investigated. The result is further compared with five state-of-the-art models, and the comparison shows that a relatively simple multi-head architecture performs better than the state-of-the-art models. The results presented in this study demonstrate the importance of multi-head models and attention mechanisms to improved understanding of the remaining useful life of industrial assets. © 2021, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Network control for a Lower-Limb Exoskeleton using Variable Stiffness Transferring

Adaptive Neural Network Control for a Lower-Limb Exoskeleton...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Longbin Zhang Yingbai Hu Hang Su Jiehao Li Salih Ertug Ovur KTH MoveAbility Lab and KTH BioMEx Center KTH Royal Institute of Technology Stockholm Sweden Technical University of Munich Munich Germany Politecnico di Milano Milano Italy State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

Lower-limb exoskeletons are increasingly used in gait assistance applications to assist patients with locomotive disorders in rehabilitation and daily life. To provide assistance based on the user's variable joint stiffness with human-like characteristics is a growing and challenging field. This paper proposed an adaptive controller for a lower-limb exoskeleton with time-varying delay using variable stiffness transferring strategy. Neural network compensation was applied to estimate the nonlinearity caused by the time-varying delay and the model uncertainties in the lower-limb exoskeleton systems. To compensate for the delay, an integral Lyapunov function was introduced and an adaptive Lyapunov-based control structure was constructed. In the controller design, a variable stiffness transferring strategy was integrated and the stiffness was transferred from an able-bodied individual estimated with muscle forces and musclotendinous stiffness. By utilizing the proposed adaptive neural network control strategy and adaptive Lyapunov-based control structure, the global stability of lower-limb exoskeleton system was guaranteed and the tracking errors converged to the zero. The proposed control strategy was validated on 2-DOFs knee and ankle lower limb exoskeleton in simulation, demonstrating effective results in trajectories tracking, and thus is crucial for determining strategies for exoskeleton control.

关键词： Exoskeletons Robots Muscles Adaptive systems Force Mathematical model Mechatronics

来源：评论

学校读者我要写书评

暂无评论

Evaluation of continuity effectiveness for networked space based information system

Evaluation of continuity effectiveness for networked space b...

引用

作者： Chen, Chen Chen, Jie Zhang, Juan Department of Automation Tsinghua University Beijing 100084 China School of Automation Beijing Institute of Technology Beijing 100081 China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing 100081 China

ISBN: (纸本)9787894631046

As the trend of future space based information system, networked space based information system can acquire and process all sorts of information more quickly and continuously under the user task scheduling. In the background of earthquake relief for applications, working flow and main tasks of the system are analyzed, and continuity effectiveness evaluation index system is constructed in multi-task level. The continuity effectiveness is a measurement of intensive degree of information returned. Evaluation model based on grey evaluation method is constructed and different reference indexes are used for different tasks. Examples are given by using statistical data in simulation, and the integrative evaluation results are obtained. Detailed evaluation results in every specific task level are offered, which are helpful to find out the effectiveness bottleneck factors meanwhile provide guidance in system design and development.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network Based Maximum Power Point Tracking for PV system

Artificial Neural Network Based Maximum Power Point Tracking...

引用

第三十八届中国控制会议

作者： Al-wesabi Ibrahim Min Ding Xiaoling Jin Xianzhong Dai Mohammad Abu Sarhan Muhammed Badeaa Shafik Hao Zhou School of Automation China University of Geoscience Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System State Grid Energy Research Institute School of electrical engineering and automation Wuhan university

Nowadays PV systems is suffering from two main problems: high production cost and low efficiency especially under variable weather conditions. Therefore, to reduce such associated problems, PV systems are being connected with various optimization controllers such as maximum power point tracking. In this paper, an artificial neural network maximum power point method has been designed to be linked between a PV system and DC-DC buck converter, and each part of the system is fully explained. The whole system was modeled under MATLAB/Simulink environment, simulation results demonstrated the efficiency of the proposed method. The proposed method has been examined to track the maximum power point under different weather conditions which shows a rapid and accurate tracking of the maximum power point(MPP) of PV system. The whole system which consists of PV arrays, Buck converter, ANN tracker, and load has been modeled using MATLAB/Simulink environment. This Simulink model has been examined using different levels of temperature and irradiation and the output results of both P-V and I-V characteristics, output power, and the system efficiency clearly demonstrate the validation of the modeled system. This demonstration has been done by comparing between the result of experimental platform and the results of simulated model which approves that ANN is highly recommended to be used in the field of maximum power point tracking of PV system.

关键词： Artificial neural network(ANN) Photovoltaic(PV) Maximum power point tracking(MPPT) Buck converter

来源：评论

学校读者我要写书评

暂无评论

Deep Domain Adaptation Regression for Force Calibration of Optical Tactile Sensors

Deep Domain Adaptation Regression for Force Calibration of O...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Zhuo Chen Ni Ou Jiaqi Jiang Shan Luo Department of Engineering Robot Perception Lab Centre for Robotics Research King’s College London London United Kingdom State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4% in full force range) for normal force, and 0.095N (6.3%) and 0.062N (4.1%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors.

关键词： Accuracy Force Tactile sensors Lighting Elastomers Data collection Optical imaging Adaptive optics Calibration Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Learning Hidden Markov Models for Linear Gaussian systems with Applications to Event-based state Estimation

arXiv

引用

arXiv 2020年

作者： Zheng, Kaikai Shi, Dawei Shi, Ling State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

This work attempts to approximate a linear Gaussian system with a finite-state hidden Markov model (HMM), which is found useful in solving sophisticated event-based state estimation problems. An indirect modeling approach is developed, wherein a state space model (SSM) is firstly identified for a Gaussian system and the SSM is then used as an emulator for learning an HMM. In the proposed method, the training data for the HMM are obtained from the data generated by the SSM through building a quantization mapping. Parameter learning algorithms are designed to learn the parameters of the HMM, through exploiting the periodical structural characteristics of the HMM. The convergence and asymptotic properties of the proposed algorithms are analyzed. The HMM learned using the proposed algorithms is applied to event-triggered state estimation, and numerical results on model learning and state estimation demonstrate the validity of the proposed algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Hidden Markov models

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：