检索结果-内蒙古大学图书馆

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Wei, Ze-Yu Lin, Qiang-Qiang Xia, Fan-Hao Zhu, Feng-Qing Dong, Peng-Cheng Beijing Institute of Precision Mechatronics and Controls Beijing100076 China Laboratory of Aerospace Servo Actuation and Transmission Beijing100076 China Beijing Institute of Aerospace Automatic Control Beijing100854 China

ISBN: (纸本)9789819733279

Firstly, this paper establishes a multi-agent reinforcement learning parameter tuning framework for PMSM sliding mode controller, and uses TD3 as the algorithm of agent learning. Secondly, the final parameters are obtained by training the model, which reasonably setting the observation value and reward function of reinforcement learning. Finally, the effectiveness of parameter tuning using multi-agent reinforcement learning is verified by simulation and experiment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Robust control Theory Based Stability Certificates for Neural Network Approximated Nonlinear Model Predictive control

引用

IFAC-PapersOnLine 2021年第6期54卷 347-352页

作者： Hoang Hai Nguyen Tim Zieger Richard D. Braatz Rolf Findeisen Laboratory for Systems Theory and Automatic Control Otto-von-Guericke University Magdeburg Germany Department of Powertrain Mechatronics iav GmbH Gifhorn Germany Massachusetts Institute of Technology Cambridge USA

Model predictive control requires the real-time solution of an optimal control problem, which can be challenging on computationally limited systems. Approximating the solution such as by neural networks or series expansions, or deriving an explicit solution, can overcome this challenge. Using neural networks for approximation, a question arises as to how to guarantee closed-loop safety and stability. We use robust control theoretic tools to provide stability guarantees using a neural network trained to approximate a model predictive controller. Notably, the model predictive controller, which might offer desirable closed-loop performance, is not required to provide provable stability properties. To provide stability guarantees for the neural network approximated controller, the closed-loop system is reformulated as a diagonal nonlinear differential form, exploiting that the neural network activation functions are sector bounded and that their slopes are globally bounded. Based on this representation, we establish sufficient closed-loop stability conditions in form of linear matrix inequalities for the nominal and the disturbed system using the neural network approximated model predictive controller.

关键词： Nonlinear model predictive control neural network approximated controller deep learning trustable AI stability analysis NMPC MPC

来源：评论

学校读者我要写书评

暂无评论

Terminal Sliding Modes-Based PLLs for Three-Phase Grid-Connected Inverters

Terminal Sliding Modes-Based PLLs for Three-Phase Grid-Conne...

引用

Annual Conference of Industrial Electronics Society

作者： Pooyan Alinaghi Hosseinabadi Mostefa Kermadi Hemanshu Pota Saad Mekhilef Ali Soltani Sharif Abadi The School of Engineering and Information Technology The University of New South Wales Canberra ACT Australia The Power Electronics and Renewable Energy Research Laboratory (PEARL) University of Malaya Kuala Lumpur Malaysia The School of Science Computing and Engineering Technologies Swinburne University of Technology Hawthorn VIC Australia Faculty of Mechatronics Institute of Automatic Control and Robotics Warsaw University of Technology Warsaw Poland

This paper proposes and experimentally implements new phase-locked loop algorithms using non-adaptive and adaptive terminal sliding modes for the three-phase grid-connected inverters. The proposed algorithms aim to extract the grid voltage phase and frequency and provide them for the inverter controller. The proposed sliding mode-based PLL algorithms provide faster, more robust, and more accurate detection of the grid voltage information compared to the conventional PI-PLL. This leads to better current controller performance and subsequently, improves the quality of the injected currents into the grid. The finite-time stability notion is incorporated with robust sliding modes to ensure a fast convergence rate. An adaptive law is proposed to determine a proper value for the switching gain which leads to a better overall performance of the PLL compared with a non-adaptive one. The Lyapunov stability theory is used to obtain the stability proofs of the closed-loop systems under both designed sliding modes-based PLLs. The proposed PLL algorithms are validated by simulation and experimental results for the three-phase grid-connected inverter under normal and various abnormal grid conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Safe Neural Network Supported Model Predictive control

引用

IFAC-PapersOnLine 2020年第2期53卷 5246-5251页

作者： T. Zieger A. Savchenko T. Oehlschlägel R. Findeisen Laboratory for Systems Theory and Automatic Control Otto-von-Guericke University Magdeburg Germany Department of Powertrain Mechatronics iav GmbH Gifhorn Germany

Model Predictive control has proven to be a universal and flexible method to control complex nonlinear system with guaranteed constraint satisfaction. However, high dependency on model quality often renders it inappropriate for hard to model systems. On the other hand, machine learning methods show great performance when approximating functions based on data. This capability for learning with poor a priori knowledge, however, comes at the cost of low predictability and lack of safety guarantees. To overcome these drawbacks we illustrate how a neural network can be setup as a nonlinear feedforward control that augments the MPC control signal to approximate a desired control behaviour. For instance, it could aim to mimic the control behaviour of a human driver, while the underlying MPC exploits prior knowledge. Moreover, to preserve constraint satisfaction, we suggest to restrict the range of neural network outputs such that it intrinsically satisfies control input constraints. Subsequently, we represent the neural network control signal as a disturbance which enables the application of tube MPC to retain state constraints satisfaction at the cost of introducing some conservatism. We demonstrate these concepts via simulation, test and highlight both the advantages and the drawbacks of the proposed control structure.

关键词： Model predictive control Machine learning Neural networks Constraint satisfaction Tube model predictive control

来源：评论

学校读者我要写书评

暂无评论

Fabrication of UV Photodetectors Based on Photoelectrochemically Etched Nanoporous Silicon: Effect of Etchants Ratio

引用

Journal of Nanomaterials 2023年第1期2023卷

作者： Thahe, Asad A. Qaeed, Motahher A. Abdullah, Suhail Najm Badawy, Ibrahim M. Alqaraghuli, Hasan Alajerami, Yasser Saleh Mustafa Mindil, A. Al-Farga, Ammar Department of Medical Physics College of Applied Science University of Fallujah Baghdad Iraq Faculty of Science University of Jeddah Jeddah Saudi Arabia Department of Medical Equipment Technology Engineering Al-Rasheed University College Baghdad Iraq Energy Materials Laboratory School of Sciences and Engineering The American University in Cairo New Cairo11835 Egypt Faculty of Electrical Engineering Mechatronics and Automatic Control Department University of Technology Malaysia Johor Bahru81310 Malaysia Faculty of Applied Medical Sciences Medical Imaging Department Al-Azhar University-Gaza Gaza Palestine Faculty of Science Department of Biochemistry University of Jeddah Jeddah Saudi Arabia

Despite several attempts to enhance the electrical and charge carrier transport characteristics of porous silicon (PSi), the requisite conditions for optimally synthesizing n-PSi with appealing optoelectronic properties are yet to be achieved. Therefore, this research explores the effect of the chemical ratio of precursor materials (HF:C2H6O:H2O2) on the surface morphology, crystalline structure, and optical and electric properties of PSi. The PSi was produced by photoelectrochemical etching followed by anodization of the n-type Si under light illumination. The properties of the as-prepared PSi were studied by means of microscopic and spectroscopic techniques. The HF:C2H6O:H2O2 chemical ratio was optimized at 2: 1: 1. A metal-semiconductor-metal (MSM) ultraviolet photodetector (Pt/n-PSi/Pt) was fabricated, which exhibited high performances under UV light (365 nm) illumination. The photodetector was shown to be highly stable and reliable with a rapid rise time of 0.56 s at a bias voltage of +5 V. The MSM photodetector displayed responsivity (Rp) of 9.17 A/m at 365 nm, which significantly exceeds the values reported for TiC/porous Si/Si in some contemporary research. The photodetector fabricated from n-PSi, synthesized at an optimum chemical ratio (2: 1: 1) exhibited the best photodetection performance, possibly due to the high porosity and defect-free state of the n-PSi thin films. © 2023 Asad A. Thahe et al.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

Development a cross-loop during adaptive stimulation of hippocampal neural networks by an artificial neural network 4

Development a cross-loop during adaptive stimulation of hipp...

引用

4th International Conference "Neurotechnologies and Neurointerfaces", CNN 2022

作者： Lebedeva, Albina Beltyukova, Anna Fedulina, Anastasiya Gerasimova, Svetlana Mishchenko, Mikhail Matveeva, Mariya Maltseva, Kseniya Belov, Alexey Mikhaylov, Alexey Pisarchik, Alexander Kazantsev, Victor University of Nizhny Novgorod Neurotechnologies Department N.I. Lobachevsky State Nizhny Novgorod Russia University of Nizhny Novgorod Faculty of Radiophysics N.I. Lobachevsky State Department of Theory of Oscillations and Automatic Control Nizhny Novgorod Russia Intitute of Neuroscience N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Innopolis Russia Center for Neuroscience and Mashine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (数字)9781665463294

ISBN: (纸本)9781665463294

The development of promising neuromorphic compact devices (including micro- and nanochips) that reproduce the information and computational functions of the brain is currently one of the breakthrough areas of modern science and technology. Firstly, this is a promising direction in regenerative medicine - the creation of artificial neuromorphic implants that allow the regulation and modulation of electrically excitable cells, as well as replacing damaged areas of the brain. The use of a memristive structure and its ability to change and maintain internal resistance when voltage is applied and turned off. This makes the structure an almost perfect electronic analogue of synapses. Recent discoveries that nanoscale memristors can mimic the basic properties of synaptic plasticity have set the stage for the fusion of nanoelectronics and living neurons to create biohybrid neural networks (bNNs) interconnected by electronics-based plasticity elements. Thus, investigation the interaction of artificial neural networks and memristive connection with living brain neurons is actually problem in neuroscience and technologies. This study is devoted to the development of neuromorphic system for neuroprosthetics problems. © 2022 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Finite control Set MPC for Open-Phase Fault Tolerant control of Synchronous Reluctance Motor

Finite Control Set MPC for Open-Phase Fault Tolerant Control...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Aleksej Kiselev Guillermo R. Catuogno Alexander Kuznietsov Roberto Leidhold Electrical Engineering and Mechatronics Mittelhessen University of Applied Sciences Friedberg Germany Automatic Control Laboratory National University of San Luis Villa Mercedes Argentina Institute of Electrical Energy Systems Otto-von-Guericke University Magdeburg Germany

ISBN: (数字)9781728157542

ISBN: (纸本)9781728157559

In this paper, a model predictive control (MPC) of a synchronous reluctance motor (SynRM) with a fault tolerance against an open-phase fault is proposed. The MPC algorithm is based on the finite control set strategy and takes into account the modified inverter topology which was used to make the fault tolerance possible. The algorithm is intuitive and easy to implement. It provides a fast torque response and smooth transition into fault operation without any torque drop.

关键词： Torque Inverters Switches Topology Voltage control Circuit faults Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic system development based on adaptive neuronal network to modulate synaptic transmission in hippocampus 3

Neuromorphic system development based on adaptive neuronal n...

引用

3rd International Conference "Neurotechnologies and Neurointerfaces", CNN 2021

作者： Lebedeva, Albina Gerasimova, Svetlana Fedulina, Anastasiya Mishchenko, Mikhail Beltyukova, Anna Matveeva, Mariya Mikhaylov, Alexey Pisarchik, Alexander Kazantsev, Victor Neurotechnologies Department N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Department of Theory of Oscillations and Automatic Control Faculty of Radiophysics N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665424745

The project presents fundamental research on the development of concept and basic components of physical circuit based on optoelectronic elements (neuromorphic generators, memristors, optical fibers). This network can replace some functions of brain’s neural networks (such as memory) through adaptive stimulation of neural interfaces at the cellular and cellular networks level. Developing learning system will perform the electrical stimulation of brain areas based on the neural activity recorded and will include electronic devices for recording and processing signals. In addition, this system will include electronic devices for generating electrical stimuli based on hardware models of neurons and memristive devices. The basic idea is to integrate an artificial network with living microcircuits of the brain. The artificial network is capable of adaptively generating electrical output signals and can stimulate a given area of the brain according to the recorded pattern of input signals. We suppose that such a network will be able to reproduce the functions of brain systems, based on the use of learning algorithms. It can be used to expand the functionality of these brain systems and to replace lost functions in pathology or trauma. © 2021 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Integration technology for replacing damaged brain areas with artificial neuronal networks 4

Integration technology for replacing damaged brain areas wit...

引用

4th Scientific School on Dynamics of Complex Networks and their Application in Intellectual Robotics, DCNAIR 2020

作者： Lebedeva, Albina Mishchenko, Mikhail Bardina, Polina Fedulina, Anastasiya Mironov, Andrey Zhuravleva, Zoia Gerasimova, Svetlana Mikhaylo, Alexey Pisarchik, Alexander Kazantsev, Victor Laboratory of Functional Imaging Department of Fundamental and Applied Research N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Department of Theory of Oscillations and Automatic Control Faculty of Radiophysics N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Neurotechnologies Department N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Innopolis Russia

ISBN: (纸本)9781728172866

We present a novel integration technology for replacing damaged microcircuits in the rat brain with electronic neuronal networks. This technology will allow simulating important brain functions, such as memory, through the adaptive stimulating effects of neural interfaces at cellular and neuronal network levels. The proposed system includes electronic devices to register and process neuronal signals and to adaptively stimulate damaged brain areas according to the online algorithm decoding the registered neuronal activity. The stimulation algorithm is implemented in hardware neural network with memristive connections that allows both network learning and adaptive *** basic idea is to develop components of hardware neural network with memristive connections for adaptive generation of electrical signals to stimulate particular brain areas. Moreover, the uniqueness of the system is adaptive closed-loop connection between two hippocampal neuronal networks. Such a system is very promising for restoring functionality of damaged areas in the human brain to replace lost functions in patients with brain pathologies or trauma. © 2020 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Integration technology for replacing damaged brain areas with artificial neuronal networks

Integration technology for replacing damaged brain areas wit...

引用

School on Dynamics of Complex Networks and their Application in Intellectual Robotics (DCNAIR)

作者： Albina Lebedeva Mikhail Mishchenko Polina Bardina Anastasiya Fedulina Andrey Mironov Zoia Zhuravleva Svetlana Gerasimova Alexey Mikhaylo Alexander Pisarchik Victor Kazantsev Neurotechnologies Department Laboratory of Functional Imaging Department of Fundamental and Applied Research N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Department of Theory of Oscillations and Automatic Control Faculty of Radiophysics N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Neurotechnologies Department N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Functional Imaging Department of Fundamental and Applied Research N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Russia

ISBN: (数字)9781728172866

ISBN: (纸本)9781728172873

关键词： Hippocampus Biological neural networks Neurons Neuromorphics Memristors Optical fiber amplifiers Electrodes

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：