检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Ki Deng Yanjie Li Songshuo Lu Yongjin Mu Xizheng Pang Qi Liu Department of Control Science and Engineering Harbin Institute of Technology Shenzhen Shenzhen China

ISBN: (纸本)9781665481106

With the booming development of artificial in-telligence, the autonomous decision-making of robots on the battlefield has become a future trend. In the field of en-tertainment games, some institutions have already attained outstanding results in multi-agent decision-making tasks by using reinforcement learning algorithms. But in the field of robot confrontation game, the robot confrontation strategies are still based on the simple logic of artificial design in most cases, which hinders the further improvement of robot strategies. In this paper, a reinforcement-learning-based multi-robot control method is proposed to improve the strategy performance. We enhanced the reinforcement learning algorithm PPO with the self-play method by easy-to-implement tricks for multi-agent training and improve training efficiency. In simulated experiments based on the rules of the RoboMaster University AI Challenge, we show our method has a much higher winning percentage than traditional approaches like behavior tree.

关键词： Training Recurrent neural networks Decision making Reinforcement learning Games Market research Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of Angle-Based Network Localization

Performance Optimization of Angle-Based Network Localization

引用

IEEE Conference on Decision and control

作者： Chenyang Liang Liangming Chen Yibei Li Jie Mei Lihua Xie Center for Control Science and Technology and Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China

Recent advances in sensor network localization have enabled sensor nodes to localize themselves by using the measurements of inter-node angles. According to our earlier work, the proposed angle-based localization algorithms' performance, particularly, the convergence rate, is relatively poor, which, however, has not been adequately addressed in the existing literature. Motivated by this, this paper aims to improve the performance of angle-based localization algorithms, specifically, the stability margin, convergence rate and robustness against measurement noises. Firstly, we show that the stability margin, convergence rate and robustness of angle-based localization algorithms are commonly determined by one parameter, namely, the minimum eigenvalue of the network's localization matrix. Secondly, we formulate the performance optimization problem as an eigenvalue optimization problem, and show the non-differentiability of the eigenvalue optimization problem. By carefully choosing the decision variable, we utilize interior-point methods to obtain an optimal solution to the eigenvalue optimization problem. Finally, simulation examples validate the improvement of the algorithms' performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Method for Analog Circuits Based on the Wavelet Features and One-class KNN 2

A Fault Detection Method for Analog Circuits Based on the Wa...

引用

2nd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2021

作者： Zhang, Fuyong Hong, Zhiwei Gao, Tianyu Yin, Shuangyan Consulting CO. LTD. ZhongKeXin Engineering Beijing China Harbin Institute of Technology Department of Automatic Test and Control Harbin China

ISBN: (纸本)9781665427470

The fault detection method for analog circuits based on multi-classification learning can not only determine the circuit state, but also locate the faulty components and identify the fault classes. However, in the absence of fault samples, only the fault detection method based on one-class learning can accurately identify the circuit states. To ensure the reliability of electronic equipment, a fault detection method based on the wavelet features and one-class KNN is proposed in this paper. This method can obtain the detection threshold by using only the normal samples of the analog circuits to identify the circuit states effectively. Firstly, the wavelet features are calculated to mine the key information of the signals. Then, to enhance the efficiency of fault detection, principal component analysis (PCA) is used to reduce the dimension of wavelet features. Finally, the normal samples are adopted to train the fault detection model named one-class K-nearest neighbor (KNN), and the detection threshold is empirically determined from the training samples, therefore monitoring the circuit states. Furthermore, the four-op-amp biquad high-pass filter circuit is chosen as the experimental circuit to implement the simulation experiments of fault detection. Experimental results demonstrate that the proposed fault detection method presents better performance on identifying circuit states compared with other typical methods. © 2021 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Day-Ahead Market Clearing Model Under System Inertia Constraints

A Day-Ahead Market Clearing Model Under System Inertia Const...

引用

IEEE PES Asia-Pacific Power and Energy engineering Conference (APPEEC)

作者： Yuting Ma Jiangliang Jin Liangliang Hao Qisheng Huang Liye Shen College of Information Scienc and Technology Donghua University Shanghai China Department of Control Science and Engineering Shandong University Shandong China School of Mechanical Engineering and Automation Harbin Institute of Technology Shanghai China

ISBN: (数字)9798350386127

ISBN: (纸本)9798350386134

We study the market clearing model for electric energy, inertia, and reserve in the day-ahead market, with a particular focus on the virtual inertia provided by wind units. In this paper, we consider synchronous inertia and virtual inertia as sources of system inertia. We incorporate system inertia constraints into the unit commitment (UC) and the economic dispatch (ED) models, and assign economic value to virtual inertia, so as to incentivize wind power to provide virtual inertia. Numerical results demonstrate that the proposed model enhances the participation of wind power units, increases the wind utilization rate and reduces the total costs.

关键词： Renewable energy sources Costs Wind power generation Stability analysis Numerical models Frequency synchronization Thermal stability Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Fast Terminal Quasi-Sliding Mode control for Spacecraft Formation Flying Systems via RBFNN

Fast Terminal Quasi-Sliding Mode Control for Spacecraft Form...

引用

Chinese Automation Congress (CAC)

作者： Zhihua Xiang Yufei Li Xiaoqing Zhong Wenxiao Lei Feilong Tang Yinhao Ju Department of Control Science and Engineering Harbin Institute of Technology Harbin China Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing China Institute of Telecommunication Satellite China Academy of Space Technology Beijing China

This paper investigates the problem of relative control for spacecraft formation flying systems. With elliptical orbit, the model is built by relative position vector. To improve the tracking performance, a controller is designed and proven stable as a fast terminal quasi-sliding mode controller with feedback control based on radial basis function neural network (RBFNN). The performance of the proposed method is validated with numerical simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IT2FNN-Based Mode-Asynchrony Variable-Structure control Under Event-Triggered Communication

IT2FNN-Based Mode-Asynchrony Variable-Structure Control Unde...

引用

第34届中国控制与决策会议

作者： Jiahui Wang Wen Zuo Yabin Gao Jianxing Liu Ligang Wu College of Intelligent Systems Science and Engineering Harbin Engineering University Department of Control Science and Engineering Harbin Institute of Technology

This paper deals with the problem of mode-asynchrony sliding-mode variable-structure control(VSC) under event-triggered communication for continuous-time Markov jump systems with hidden *** hidden-mode Markov jump systems with both the matched and mismatched uncertainties are *** terms of the event-triggered communication from the sensor to the controller,static and dynamic mechanisms based on periodic/aperiodic sampling are designed for mitigating the burden of *** this case of mode-asynchrony and aperiodic sampling state measurements,new sliding-mode VSC laws integrated with an interval type-2 fuzzy neural network are *** interval type-2 fuzzy neural network is used to approximate matched ***,the analysis of the finitetime practical stability of the control system is presented based on the Lyapunov function ***,a set of simulation results are given to show the validity and practicability of the present results.

关键词： Markoy jump systems asynchronous control variable-structure control dynamic event-triggered communication fuzzy neural network

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning and Disturbance Observer Based Optimal control for Uncertain Systems

Reinforcement Learning and Disturbance Observer Based Optima...

引用

Chinese Automation Congress (CAC)

作者： Yucheng Chen Yupeng Zhu Shaohai Wang Liyuan Yin Hongming Zhu Xingjian Sun Chengwei Wu Department of Control Science and Engineering Harbin Institute of Technology Harbin China Tianjin Zero-One Intelligent Technology Co. Ltd Tianjin China Department of Electrical Engineering Nantong University Nantong China

This paper investigates the robust adaptive optimal control problem for linear systems in the presence of matching uncertainties. A nominal controller utilizing Q-Iearning algorithm is designed for the nominal linear system without uncertainties. Introducing a disturbance observer serves the purpose of actively estimating uncertainties, enabling proactive compensation for matching uncertainties. The analysis of the closed-loop system's stability under the robust adaptive optimal controller is conducted, presenting sufficient conditions to ensure its stability. Finally, the control algorithm is validated using a two-wheeled mobile robot as the experimental platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-covalent interaction of atomically dispersed dual-site catalysts featuring Co and Ni nascent pair sites for efficient electrocatalytic overall water splitting

引用

Journal of Materials Science & technology 2024年第11期178卷 210-225页

作者： Imran Khan Yaogang Chen Zhiyang Li Wenjie Liu Salman Khan Sami Ullah Linlin Liu Amir Zada Sharafat Ali Shabana Shaheen Lei Yang State Key Laboratory of Urban Water Resource and Environment Shenzhen Key Laboratory of Organic Pollution Prevention and ControlSchool of Civil and Environmental EngineeringHarbin Institute of Technology ShenzhenShenzhen 518055China School of Physics and Electronics Central South UniversityChangsha 410083China CNAS Accredited Test Center Guangdong Engineering Technology Research Center of Air PurificationHealthlead Co.Ltd.Shenzhen 518055China Key laboratory of Functional Inorganic Material Chemistry Ministry of Education of the People's Republic of ChinaHeilongjiang UniversityHarbin 150080China K.A.CARE Energy Research&Innovation Center(ERIC) King Fahd University of Petroleum&Minerals(KFUPM)Dhahran 31261Saudi Arabia Department of Chemistry Abdul Wali Khan UniversityMardanKhyber Pakhtunkhwa 23200Pakistan School of Physics University of Electronic Science and Technology of ChinaChengdu 610054China

The scarcity of highly effective and economical catalysts is a major impediment to the widespread adop-tion of electrochemical water splitting for the generation of ***_(2),a low-cost candidate,suffers from inefficient catalytic ***,a captivating strategy has emerged,which involves the en-gineering of heteroatom doping to enhance electrochemical *** investigation demonstrates a successful implementation of the strategy by combining ultrathin MoS_(2) nanosheets with Co and Ni dual single multi-atoms(DSMAs)grown directly on 2D N-doped carbon nanosheets(CoNi-MoS_(2)/NCNs)for the purpose of improving hydrogen evolution reaction(HER)and oxygen evolution reaction(OER).With the aid of a dual-atom doped bifunctional electrocatalyst,effective water splitting has been achieved across a broad pH range in *** double doping of Co and Ni strengthens their interactions,thereby altering the electromagnetic composition of the host MoS_(2) and ultimately leading to improved electrocat-alytic ***,the synergistic effect between NCNs and MoS_(2) nanosheets provided efficient electron transport channels for ions and an ample surface area with open voids for ion ***-sequently,the CoNi-MoS_(2)/NCNs catalysts demonstrated exceptional stability and activity,producing low degree overpotentials of 180.5,124.9,and 196.4 mV for HER and 200,203,and 207 mV for OER in neu-tral,alkaline,and acidic mediums,respectively,while also exhibiting outstanding overall water-splitting performance,durability,and stability when used as an electrolyzer at universal pH.

关键词： Multifunctional catalyst Water splitting Functionalized carbon nanosheets Interface engineering pH-universal electrocatalysis

来源：评论

学校读者我要写书评

暂无评论

Classifier-guided neural blind deconvolution: a physics-informed denoising module for bearing fault diagnosis under heavy noise

arXiv

引用

arXiv 2024年

作者： Liao, Jing-Xiao He, Chao Li, Jipu Sun, Jinwei Zhang, Shiping Zhang, Xiaoge Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong School of Instrumentation Science and Engineering Harbin Institute of Technology Harbin China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing China

Blind deconvolution (BD) has been demonstrated as an efficacious approach for extracting bearing fault-specific features from vibration signals under strong background noise. Despite BD's desirable feature in adaptability and mathematical interpretability, a significant challenge persists: How to effectively integrate BD with fault-diagnosing classifiers? This issue arises because the traditional BD method is solely designed for feature extraction with its own optimizer and objective function. When BD is combined with downstream deep learning classifiers, the different learning objectives will be in conflict. To address this problem, this paper introduces classifier-guided BD (ClassBD) for joint learning of BD-based feature extraction and deep learning-based fault classification. Firstly, we present a time and frequency neural BD that employs neural networks to implement conventional BD, thereby facilitating the seamless integration of BD and the deep learning classifier for co-optimization of model parameters. Specifically, the neural BD incorporates two filters: i) a time domain quadratic filter to utilize quadratic convolutional networks for extracting periodic impulses;ii) a frequency domain linear filter composed of a fully-connected neural network to amplify discrete frequency components. Subsequently, we develop a unified framework to use a deep learning classifier to guide the learning of BD filters. In addition, we devise a physics-informed loss function composed of kurtosis, l2∕l4 norm, and a cross-entropy loss to jointly optimize the BD filters and deep learning classifier. Consequently, the fault labels provide useful information to direct BD to extract features that distinguish classes amidst strong noise. To the best of our knowledge, this is the first of its kind that BD is successfully applied to bearing fault diagnosis. Experimental results from three datasets demonstrate that ClassBD outperforms other state-of-the-art methods under noisy conditions

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Event-Based Distributed Estimation of Stochastic Systems over Sensor Networks with Deception Attacks∗

Event-Based Distributed Estimation of Stochastic Systems ove...

引用

2021 IEEE International Conference on Power Electronics, Computer Applications, ICPECA 2021

作者： Wang, Zifan Liu, Yifan Fan, Yougao Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China Institute of Spacecraft System Engineering Beijing100094 China Beijing Institute of Spacecraft Environment Engineering Beijing100094 China

ISBN: (纸本)9781728190037

This paper addresses H∞ state estimation problem for a class of discrete-time stochastic delayed systems subject to deception attacks over sensor networks. We consider the scenario where the sensor output and estimator output are transmitted to its corresponding estimator and other estimators, respectively, over two different digital channels. To cope with the problem of constrained bandwidth, the event-triggering ideas are implemented on both sensor-to-estimator and estimator-to-estimator channels. Meanwhile, we consider there is an attacker that possibly corrupts the measurement output. Under these circumstances, we aim to design the state estimator such that the exponential mean-square stability with H∞ performance is satisfied. By virtue of Lyapunov-Krasovskii functional, we can derive the explicit estimator parameters by solving a set of linear matrix inequalities (LMIs). Finally, a numerical example is established to verify our theoretical results. © 2021 IEEE.

关键词： Sensor networks

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：