检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Matni, Nikolai Ames, Aaron D. Doyle, John C. Dept. of Electrical and Systems Engineering University of Pennsylvania Philadelphia United States Control and Dynamical Systems California Institute of Technology Pasadena United States

This paper focuses on the need for a rigorous theory of layered control architectures (LCAs) for complex engineered and natural systems, such as power systems, communication networks, autonomous robotics, bacteria, and human sensorimotor control. All deliver extraordinary capabilities, but they lack a coherent theory of analysis and design, partly due to the diverse domains across which LCAs can be found. In contrast, there is a core universal set of control concepts and theory that applies very broadly and accommodates necessary domain-specific specializations. However, control methods are typically used only to design algorithms in components within a larger system designed by others, typically with minimal or no theory. This points towards a need for natural but large extensions of robust performance from control to the full decision and control stack. It is encouraging that the successes of extant architectures from bacteria to the Internet are due to strikingly universal mechanisms and design patterns. This is largely due to convergent evolution by natural selection and not intelligent design, particularly when compared with the sophisticated design of components. Our aim here is to describe the universals of architecture and sketch tentative paths towards a useful design theory. Copyright © 2024, The Authors. All rights reserved.

关键词： Bacteria

来源：评论

学校读者我要写书评

暂无评论

Chaotic Behavior of DC-DC Boost Converter by using Voltage Mode control

Chaotic Behavior of DC-DC Boost Converter by using Voltage M...

引用

Emerging Technology (INCET), International Conference for

作者： Sandhu Ganesh Sudarshan K. Valluru Department of Electrical Engineering Control of Dynamical Systems and Computation Laboratory Delhi Technological University (DTU) Delhi India

This paper examines the Boost converter's chaotic behavior. A voltage mode controlled technique is being utilized to analyze the discrete-time mapping to determine the properties of the bifurcation that operate in a closed loop. By varying some parameters while holding others constant, the reference voltage and input voltage are used to examine the bifurcation diagram. It has been noted that the system becomes unstable and splits into two time-periodic systems, four time – periodic systems and then chaos takes over the system. These occurrences have been shown in the bifurcation diagram, therefore the converter's safe operating range can be determined and verified by using the time-domain waveforms and phase plots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design & Validation of ANN based Reinforcement Learning control Algorithm for Coupled Tank System

Design & Validation of ANN based Reinforcement Learning Cont...

引用

International Conference for Convergence of Technology (I2CT)

作者： Digant Rastogi Manika Jain Madan M. Rayguru Sudarshan K. Valluru Dept. of Electrical Engineering Control of Dynamical Systems and Computation Lab Delhi Technological University Delhi India

This paper presents a framework to apply Reinforcement Learning control algorithm on benchmark nonlinear dynamical systems. This work focuses on a novel Artificial Neural Network (ANN) based dynamic programming approach using Value Iteration to obtain optimal control for continuous-time nonlinear system. In particular, Coupled Tank System has been chosen to represent benchmark nonlinear dynamical system. The proposed Artificial Neural Network-Reinforcement Learning (ANN-RL) algorithm, Naive Reinforcement Learning (Naive-RL) algorithm and traditional PID control schemes are investigated on coupled tank system. The ANN-RL algorithm performs better than the Naive-RL and PID controllers in terms of steady state error, stability, oscillations and overshoot.

关键词： PI control Heuristic algorithms Artificial neural networks Reinforcement learning Approximation algorithms Stability analysis Steady-state

来源：评论

学校读者我要写书评

暂无评论

Intelligent control of Mobile Robots with ANN Assisted Improved Q-learning: IQ-CRL Algorithm

Intelligent Control of Mobile Robots with ANN Assisted Impro...

引用

Emerging Technologies (GlobConET), IEEE IAS Global Conference on

作者： Digant Rastogi Manika Jain Madan M. Rayguru Sudarshan K. Valluru Dept. of Electrical Engineering Control of Dynamical Systems and Computation Laboratory Delhi Technological University Delhi India

This paper presents a novel algorithm, IQ-CRL (Improved Q-learning using Classification and Regression with ANN), which is a control architecture that uses the existing Q-learning algorithm and integrates it with Artificial Neural Networks (ANNs). The proposed algorithm addresses the limitations of traditional Q-learning by incorporating an adaptive mechanism that leverages ANN to find an optimal control policy that is more accurate and at lower computational expense. IQ-CRL is designed to be used efficiently with dynamical systems such as mobile robots. The objective of this study is to evaluate the performance of IQ-CRL in comparison to classical Q-learning and PID controller. The results show that the IQ-CRL algorithm outperforms both the classical Q-learning and PID controller in terms of learning efficiency, control accuracy and computing complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computation of Hopf Bifurcation Points in the Magnetic Levitation System 4th

Computation of Hopf Bifurcation Points in the Magnetic Levit...

引用

4th International Conference on Information and Communication Technology for Intelligent systems, ICTIS 2020

作者： Valluru, Sudarshan K. Gupta, Anshul Verma, Aditya Center for Control of Dynamical Systems and Computation Department of Electrical Engineering Delhi Technological University Delhi110042 India

ISBN: (纸本)9789811570773

This research brief aims to study the bifurcation analysis of an electromagnetic levitation (maglev) system. The bifurcation analysis involves first performing the numerical analysis, and then the simulations using MATLAB are analyzed to verify the results. The study requires derivation of a mathematical model for the maglev system, which can be used for the bifurcation analysis. The bifurcation analysis involves a numerical comparison of the system equations with the predefined constraints. The input voltage is being used as the bifurcation parameter, which is by ball’s position, ball’s velocity, and the current flowing through the circuit. The analysis allows us to compute a combination of values of parameters, when simulations are performed to check system characteristics, periodic oscillations at these values are obtained. Hence, it proves the existence of Hopf bifurcation at the computed value of system parameters. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Hopf bifurcation

来源：评论

学校读者我要写书评

暂无评论

A Deep Neural Network Approach to Automatic Multi-Class Classification of Electrocardiogram Signals

A Deep Neural Network Approach to Automatic Multi-Class Clas...

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Rahuja, Nitin Valluru, Sudarshan K. Delhi Technological University Center for Control of Dynamical Systems and Computation Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781728185835

Classification of electrocardiogram (ECG) signals is essential for accurate clinical diagnosis of coronary illness. Deep Neural Network (DNN) has emerged as a promising tool for feature identification in ECG signals with advancements in signal processing techniques and artificial intelligence. Particularly, Convolutional Neural Network (CNN) has enabled intricate feature identification and classification of images. In this scope, an efficient classification methodology utilizing wavelet transform and AlexNet CNN is presented in this paper to classify the ECG signals into three different categories, namely: Arrythmia (ARR), Congestive Heart failure (CHF) and Normal Sinus Rhythm (NSR). Physionet research dataset is utilized in this work. Firstly, all ECG signals are converted to a corresponding scalogram using Continuous Wavelet Transform (CWT). Then, these scalograms are applied as input to AlexNet, which is a pretrained CNN. Finally, transfer learning and fine-tuning are done, and the performance of modified AlexNet is evaluated. The study revealed a good accuracy of 97.3%. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep Neural Network Models using Transfer Learning for Electrocardiogram Signal Classification 6

A Comparative Analysis of Deep Neural Network Models using T...

引用

6th International Conference on Recent Trends on Electronics, Information, Communication and Technology, RTEICT 2021

作者： Rahuja, Nitin Valluru, Sudarshan K. Center for Control of Dynamical Systems and Computation Delhi Technological University Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781665435598

With the development of computational resources in the past decade, the adoption of deep learning methodologies has taken a steep rise. Particularly, the use of various Convolutional Neural Network (CNN) based architectures for various computer vision and image classification problems in healthcare research can be witnessed. In this scope, performance evaluation and comparison of three different CNN architectures for multi-class classification of Electrocardiogram (ECG) signals is presented in this paper. Three distinct classes of ECG signal i.e. Normal Sinus Rhythm (NSR), Arrhythmia (ARR), and Congestive Heart failure (CHF) are utilized in this work, which is representative of an individual's heart conditions. The classification methodology adopted makes use of Continuous Wavelet Transform (CWT) which provides a 2-dimensional time-frequency representation of available samples of ECG signals. ECG dataset was collected from different PhysioBank databases, which provides openly-accessible medical research data. Images with time-frequency representation of ECG signals were applied as input to three CNN architectures namely, AlexNet, GoogLeNet, and SqueezeNet. Using transfer learning approach and modification in certain output layers of three architectures, ECG classification was performed and the performance of three CNN architectures was studied. The results revealed classification accuracy of 97.80%, 97.78% and 97.22% by AlexNet, GoogLeNet and SqueezeNet respectively. AlexNet outperformed GoogLeNet and SqueezeNet models in terms of accuracy as well as training time. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Adaptive-Optimal control for Reconfigurable Robots

Adaptive-Optimal Control for Reconfigurable Robots

引用

Device Intelligence, Computing and Communication Technologies, (DICCT), International Conference on

作者： Adya Maheshwari Aaditya Rautela Madan Mohan Rayguru Sudarshan K. Valluru Department of Electrical Engineering Delhi Technological University New Delhi India Department of Electrical Engineering Control of Dynamical Systems and Computation Laboratory Delhi Technological University New Delhi India

Reconfigurable robots refer to the robotic systems which have the ability to transform their morphological structure to adapt to changes in their surroundings. A specialized control system based upon the dynamic characteristics is required to be modelled so that a vast range of operations can be performed by the reconfigurable robots. Reinforcement learning based technique is therefore considered as a suitable mechanism for carrying out adaptive optimal control for the robotic systems. In this paper, an attempt has been made to model the adaptive optimal control mechanism for a single-link manipulator: a reconfigurable robotic system. The system has been modelled for a dynamic environment. The loss and reward plots are obtained from the simulation of the robotic system by deploying reinforcement learning based techniques with the given controlled input

关键词： Adaptation models Adaptive systems Heuristic algorithms Neural networks Optimal control Reinforcement learning Transforms

来源：评论

学校读者我要写书评

暂无评论

Robust Locomotion on Legged Robots through Planning on Motion Primitive Graphs

arXiv

引用

arXiv 2022年

作者： Ubellacker, Wyatt Ames, Aaron D. The Departments of Control and Dynamical Systems Mechanical and Civil Engineering California Institute of Technology PasadenaCA United States

The functional demands of robotic systems often require completing various tasks or behaviors under the effect of disturbances or uncertain environments. Of increasing interest is the autonomy for dynamic robots, such as multirotors, motor vehicles, and legged platforms. Here, disturbances and environmental conditions can have significant impact on the successful performance of the individual dynamic behaviors, referred to as "motion primitives". Despite this, robustness can be achieved by switching to and transitioning through suitable motion primitives. This paper contributes such a method by presenting an abstraction of the motion primitive dynamics and a corresponding "motion primitive transfer function". From this, a mixed discrete and continuous "motion primitive graph" is constructed, and an algorithm capable of online search of this graph is detailed. The result is a framework capable of realizing holistic robustness on dynamic systems. This is experimentally demonstrated for a set of motion primitives on a quadrupedal robot, subject to various environmental and intentional disturbances. © 2022, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of GOA, WCA and PSO Tuned Fractional Order-PID controller for Cart-Inverted Pendulum

Comparative Analysis of GOA, WCA and PSO Tuned Fractional Or...

引用

Power and Renewable Energy Conference (IPRECON), IEEE International

作者： Neelam Verma Sudarshan K. Valluru Department of Electrical Engineering Center for Control of Dynamical Systems and Computation Delhi Technological University Delhi India

control of cart based inverted pendulum system is a classical problem of control system and is widely used to verify the effectiveness of control algorithms. In this paper, fractional order PID (FOPID) controller has been used to control the cart position and pendulum angle. Three optimization algorithms namely, particle swarm optimization (PSO), water cycle algorithm (WCA) and grasshopper optimization algorithm (GOA) has been used to tune the parameters of the FOPID controller for underline problem. Results shows that, FOPID controller was able to control both cart position and pendulum angle effectively. Further, it has also been shown that GOA tuned FOPID controller performs better as compared to WCA and PSO tuned FOPID controller. The entire system was simulated using MATLAB2018a.

关键词： Renewable energy sources Software packages control systems Particle swarm optimization Optimization Matlab

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：