检索结果-内蒙古大学图书馆

Data Driven Control and Learning systems (DDCLS)

作者： Jinquan Lin Bo Zhao Derong Liu School of Automation Guangdong University of Technology Guangzhou China School of Systems Science Beijing Normal University Beijing China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

In this paper, an integral reinforcement learning (IRL)-based approximate optimal control (AOC) method for unknown nonaffine systems is developed by using dynamic feedback. For optimal control problems of nonaffine systems, optimal control policy cannot be expressed explicitly since the input gain matrix is unknown. Therefore, the nonaffine system is transformed into an augmented affine system by introducing a dynamic feedback signal as the virtual control input. Moreover, by designing an appropriate value function for the augmented affine system, the optimal control of augmented affine system is formulated as the AOC for unknown nonaffine systems. Moreover, the IRL method is adopted to derive the approximate solution of Hamilton-Jacobi-Bellman equation via the critic-only structure. Theoretical analysis concludes that the closed-loop system is uniformly ultimately bounded by using the developed IRL-based AOC scheme. An example is utilized to demonstrate the effectiveness of the present approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FSM-Based Volitional Control of Robotic Transfemoral Prosthesis for Walking on Uneven Ground

FSM-Based Volitional Control of Robotic Transfemoral Prosthe...

引用

International Conference on Ubiquitous Robots (UR)

作者： Tae-Geun Park Dong-Joong Kim Jung-Yup Kim Dept. of Mechanical Design and Robot Eng. Seoul Nat'l Univ. of Science and Technology Seoul Korea Dept. of Mechanical and System Design Eng. Seoul Nat'l Univ. of Science and Technology Seoul Korea

To effectively control the robotic transfemoral prosthesis equipped with active actuators, it is necessary to recognize the user's state and intentions and generate an appropriate joint trajectory. In this paper, a walking trajectory generator based on a finite-state machine (FSM) is proposed as a simple algorithm to implement walking, starting, and stopping motions. We define the thigh and knee angles in a one-to-one correspondence by dividing the walking cycle into several states and using FSM controller. Through this, it is possible to linearize the relationships between the thigh and knee, and by setting gait trajectory generation parameters, it is possible to generate the knee angle according to the thigh angle and the FSM state. In addition, a variable impedance control that performs actual ankle movements to enable walking on uneven ground. Finally, the proposed method was successfully verified through walking experiments with the robotic transfemoral prosthesis on treadmill with ground obstacles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Python package for causal discovery based on LiNGAM

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 483-490页

作者： Takashi Ikeuchi Mayumi Ide Yan Zeng Takashi Nicholas Maeda Shohei Shimizu SCREEN Advanced System Solutions Co. Ltd. Japan Department of Computer Science and Technology Tsinghua University China School of System Design and Technology Tokyo Denki University Japan and Center for Advanced Intelligence Project RIKEN Japan Faculty of Data Science Shiga University Japan and Center for Advanced Intelligence Project RIKEN Japan

Causal discovery is a methodology for learning causal graphs from data, and LiNGAM is a well-known model for causal discovery. This paper describes an open-source Python package for causal discovery based on LiNGAM. The package implements various LiNGAM methods under different settings like time series cases, multiple-group cases, mixed data cases, and hidden common cause cases, in addition to evaluation of statistical reliability and model assumptions. The source code is freely available under the MIT license at https://***/cdt15/lingam.

关键词： causal structure learning statistical reliability model evaluation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Network Observer-Based Fault Tolerant Control for Partially Unknown Nonlinear systems via Adaptive Dynamic Programming

Adaptive Neural Network Observer-Based Fault Tolerant Contro...

引用

IEEE International Conference on Cyber technology in Automation, Control, and Intelligent systems

作者： Chujian Zeng Bo Zhao Derong Liu School of Automation Guangdong University of Technology Guangzhou China School of Systems Science Beijing Normal University Beijing China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

This article presents an adaptive neural network (NN) observer-based fault tolerant control (FTC) method for partially unknown nonlinear systems with actuator faults via adaptive dynamic programming. By using an adaptive NN observer, the system states, unknown system dynamics and faults are estimated accurately. An augmented system is constructed to transform the FTC problem into an optimal control problem. Through adopting a critic NN, the Hamilton-Jacobi-Bellman equation is solved for the augmented system. Then, the approximate optimal control policy is obtained, i.e., the FTC policy is acquired. The Lyapunov's direct method is utilized to ensure that the closed-loop nonlinear system is uniformly ultimately bounded. A simulation example shows the FTC performance of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Low Voltage Ride Through (LVRT) Performance of Double-Fed Wind Generator (DFWG) with Grid-Forming (GFM) Capability 8

Enhanced Low Voltage Ride Through (LVRT) Performance of Doub...

引用

8th IEEE International Conference on Energy Internet, ICEI 2024

作者： Fan, Yunquan Hu, Qianjin Tang, Bojin Huai, Xiaochen Liu, Jinlian Tong, Fan Yunnan Mile Shidongshan Power Generation Co. Ltd. Site Management Team Mile China Co. Ltd. China China Three Gorges Corporation Science and Technology Research Institute New Energy & New Power System Engineering Research Center Beijing China Shanghai Investigation Design & Research Institute Co. Ltd. Electric Power Plan Design & Research Department China

ISBN: (纸本)9798331523558

Optimizing the Low Voltage Ride Through (LVRT) performance of Doubly-fed Wind Generation (DFWG) has always been an important task to improve the operational reliability of wind turbines. For this purpose, this paper put forwards a novel DFWG with enhanced LVRT performance, which adopts Grid-forming (GFM) strategy based on virtual synchronous control. First of all, the topology of DFWG and the performance requirements of LVRT are presented respectively. Then, the mathematical modeling and control strategy designs of the grid side converter and rotor-side converter of DFWG, also with the GFM strategy are carried out, respectively. On the basis, a complete GFM-DFWG control structure is formed finally. A typical simulation case and analysis is carried out to by setting several types of disturbance or faults at different occurrence time, corresponding to various voltage drop depths. Simulation results reveal that GFM-DFWG can adapt to greater LVRT depth ranging from 0.2p.u. to 1.0p.u. caused by different disturbance or faults. Even when the grid-connected voltage of DFWG drops by 0.8p.u., it is still able to recover to 0.9p.u. within about 150ms, although the oscillation amplitude and recovery time of the major U-I parameters may have an expansion as the LVRT depth increases, thus verifying the excellent fast response and voltage support effect of GFM. © 2024 IEEE.

关键词： Asynchronous generators

来源：评论

学校读者我要写书评

暂无评论

Integrated Monitoring system for Shrimp Farming: Combining Acoustic and Water Quality Analysis

Integrated Monitoring System for Shrimp Farming: Combining A...

引用

EAI International Conference on Renewable Energy and Sustainable Manufacturing, EAI ICRESM 2023

作者： Bui, Bao Nguyen, Khanh Nguyen, Sy Nguyen, Yen Nguyen, Hoang Nguyen, Huy Nguyen, Le Tran, Binh Nguyen, Hung Cao, Hieu Nguyen, Sang Tran, Hanh VNU-HCM Ho Chi Minh City Viet Nam The University of Tokyo Tokyo Japan Institute of Aquaculture Nha Trang University Nha Trang Viet Nam MnM System Design LLC PalmdaleCA United States Soitec Bernin France Department of Science and Technology Nha Trang University Nha Trang Viet Nam

ISBN: (纸本)9783031601538

The aquaculture industry is a cornerstone of Vietnam’s economy, with the cultivation of white-leg shrimp (Penaeus vannamei) as a significant contributor to its growth. Efficient feeding practices are paramount in optimizing shrimp growth and reducing waste, which accounts for a substantial portion of the production cost. The paper presents an integrated monitoring system that collects acoustic sound of shrimp feeding behavior and water quality characteristics. Acoustic data, recorded manually and streamed to the cloud, provides insights into shrimp feeding patterns, while continuous monitoring of parameters like pH, dissolved oxygen (DO), temperature, and oxidation-reduction potential (ORP) offers a comprehensive view of water conditions. The system was deployed at a commercial shrimp pond at Cam Ranh, Nha Trang to collect data over a shrimp crop cycle. The results reveal that acoustic analysis can accurately detect distinct feeding behaviors, suggesting opportunities for precision feeding strategies. Additionally, water quality parameters, especially DO and temperature, follow consistent daily patterns that correspond to solar activity that can be used to optimally control oxygen aerator. It paves the way for further research into precision feeding using acoustics and understanding the intricate relationship between water quality and shrimp feeding behavior. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

Propagation Characteristics of End-Winding Insulation Fatigue Damage in Variable Frequency Motor Under Multi-Field Coupling

Propagation Characteristics of End-Winding Insulation Fatigu...

引用

IEEE Conference on Electromagnetic Field Computation

作者： Bangwei Zhang Haijun Zhang Jiashun Wang Yuxin Cao Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Hubei university of Arts and Science Xiangyang China School of Electronic Information Engineering Taiyuan University of Science and Technology Taiyuan China

ISBN: (数字)9798350348958

ISBN: (纸本)9798350348965

In this paper, the fatigue propagation mechanism of motor stator insulation damage under variable frequency drive is studied by combining theoretical analysis and finite element numerical simulation. Based on the magneto-thermo-solid coupling and fatigue damage theory, the stress-strain state, crack damage degree and propagation rate of motor stator insulation are analyzed. The crack damage propagation at different positions of the end winding outlet, middle and nose end is simulated and calculated by three-dimensional finite element method. It is found that the stress, strain and stress intensity factor of the end winding insulation at the outlet position change violently, which reflects that the crack damage is easier to expand and the propagation rate is greater. The results of this paper can provide reference for the evolution law, fault diagnosis and optimization design of insulation damage of variable frequency drive motor under complex working conditions.

关键词： Couplings Insulation Windings Stator windings Variable speed drives Motors Fatigue

来源：评论

学校读者我要写书评

暂无评论

Evolution of Heuristics: Towards Efficient Automatic Algorithm design Using Large Language Model

arXiv

引用

arXiv 2024年

作者： Liu, Fei Tong, Xialiang Yuan, Mingxuan Lin, Xi Luo, Fu Wang, Zhenkun Lu, Zhichao Zhang, Qingfu Department of Computer Science City University of Hong Kong Hong Kong Huawei Noah’s Ark Lab China School of System Design and Intelligent Manufacturing Southern University of Science and Technology China

Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Intra Fast Mode Decision Algorithm and Hardware design for AVS2

Intra Fast Mode Decision Algorithm and Hardware Design for A...

引用

2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)

作者： Hao Xie Kaiyang Liu Yang Zhao Xiao Zheng Xianguo Qing Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China School of Software and Microelectronics Peking University

ISBN: (纸本)9781665417358

AVS2 is a kind of video coding standard proposed by China,it adopts 33 intra prediction modes to improve coding performance,while the computational complexity has increased *** order to reduce the complexity of AVS2 intra mode decision and make the AVS2 hardware encoder meet realtime requirements,this paper proposes the AVS2 intra fast mode decision algorithm and hardware *** experimental results show that the intra mode decision algorithm and hardware design proposed in this paper can meet the throughput requirement of 1920 x1080@60 fps at a clock frequency of300 *** using Xilinx FPGA XC7 K325 T 900 on the Vivado HLS platform for synthesis,only 10% of the LUT,5% of FF,5% of BRAM,and 6% of DSP in FPGA resources are consumed to meet the design requirements.

关键词： AVS2 intra coding mode decision

来源：评论

学校读者我要写书评

暂无评论

An Efficient Hybrid PAPR Reduction for 5G NOMA-FBMC Waveforms

引用

Computers, Materials & Continua 2021年第12期69卷 2967-2981页

作者： Arun Kumar Sivabalan Ambigapathy Mehedi Masud Emad Sami Jaha Sumit Chakravarty Kanchan Sengar Department of Electronics and Communication Engineering JECRC UniversityJaipur303905India Center for System Design Chennai Institute of TechnologyIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Electrical and Computer Engineering Kennesaw State UniversityGAUSA

The article introduces Non-Orthogonal Multiple Access(NOMA)and Filter Bank Multicarrier(FBMC),known as hybrid waveform(NOMAFBMC),as two of the most deserving contenders for fifth-generation(5G)*** spectrum access and clampdown of spectrum outflow are unique characteristics of hybrid *** compare the spectral efficiency of Orthogonal Frequency Division Multiplexing(OFDM),FBMC,NOMA,and *** is seen that the hybrid waveform outperforms the existing *** to Average Power Ratio(PAPR)is regarded as a significant issue in multicarrier *** combination of Selective Mapping-Partial Transmit Sequence(SLM-PTS)is an effective way to minimize large peak power *** SLM,PTS,and SLM-PTS procedures are applied to the NOMA-FBMC *** hybrid structure is applied to the existing ***,the correlated factors like Bit Error Rate(BER)and Computational Overhead(CO)are studied and computed for these *** outcome of the work reveals that the NOMA-FBMC waveform coupled with the SLM-PTS algorithm offers superior performance as compared to the prevailing systems.

关键词： 5G NOMA-FBMC SLM-PTS PAPR BER OFDM

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：