检索结果-内蒙古大学图书馆

27th International Conference on Automation and Computing, ICAC 2022

作者： Nikentari, Nerfita Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Tide level forecasting is one of major components in oceanography and marine research. The future prediction of tides is an important issue for human and environment. This study proposes new tide level prediction methods with multiple input multiple output (MIMO) approach based on nonlinear autoregressive with exogenous inputs (NARX) model and three types of recurrent neural networks (RNNs), namely, long short-term memory (LSTM), bi-directional long short-term memory (biLSTM) and gated recurrent unit (GRU) networks. We develop three types of NARX models: NARX-LSTM, NARX-biLSTM and NARX-GRU. We evaluate the three models and compare their performances with LSTM, biLSTM and GRU network models. It turns out that the proposed MIMO NARX based RNN models, especially NARX-LSTM and NARX-GRU have better performance in comparison with their RNN counterparts (i.e., LSTM, biLSTM, and GRU). The NARX-GRU model shows the best performance for one step and three step ahead prediction in terms of RMSE in each location and average RMSE, while NARX-LSTM performs better for two steps ahead prediction in terms average RMSE. The results also show that the mixture of RNN and NARX improves the performance of RNN model for all the four tasks at four locations in the UK (Wick, Workington, Ullapol and New Heaven) and for the three time horizons (i.e., 1, 2 and 3 steps ahead). © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Output Stabilization control for Nonlinear systems With Generalized Disturbances 25

Reinforcement Learning-Based Output Stabilization Control fo...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Tang, Zezhi Rossiter, J Anthony Dong, Yi Panoutsos, George University Of Sheffield Department Of Automatic Control And Systems Engineering SheffieldS13JD United Kingdom University Of Southampton Department Of Electronics And Computer Science Southampton United Kingdom

ISBN: (纸本)9798350340266

This paper proposes a new disturbance observer (DO)-based reinforcement learning (RL) control approach for nonlinear systems with unmatched (generalized) disturbances. While a nonlinear disturbance observer (NDO) is utilized to measure the plant uncertainties, disturbances can exist in the plant via distinct channels from those of the control signals;so-called mismatched disturbances are theoretically difficult to attenuate within the channel of the system's states. A generalized disturbance observer-based compensator is implemented to address the uncertainty cancellation problem by removing the influence of uncertainties from the output channels. Con-currently, a composite actor-critic RL scheme is utilized for approximating the optimal control policy as well as the ideal value function pertaining to the compensated system by solving a Hamilton-Jacobi-Bellman (HJB) equation for both online and offline iterations simultaneously. Stability analysis verifies the convergence of the proposed framework. Simulation results are included to illustrate the effectiveness of the proposed scheme. © 2024 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Behavioural Swarm Optimisation for Stable Slung-Load Aerial Transportation

Behavioural Swarm Optimisation for Stable Slung-Load Aerial ...

引用

2023 IEEE Congress on Evolutionary Computation, CEC 2023

作者： Chen, Jingyu Oyekan, John The University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom University of York Department of Computer Science York United Kingdom

ISBN: (纸本)9798350314588

Collaboration of agents in a natural swarm enables the accomplishment of tasks that would be difficult or impossible for a single agent to complete alone. For example, a swarm of autonomous Unmanned Aerial Vehicles (UAVs) enables the collaborative sensing of bulky loads for transportation over impassable terrains when the load weighs several times more than each UAV. In this work, we propose a hierarchical algorithmic architecture that supports the search and coverage of various unknown payload profiles for subsequent transportation. The grasping formation of UAVs over the payload emerges from the synthetic behaviours in the architecture without any path planning. Experiments show that our proposed design can be successfully applied in searching and coverage of various loads and has been validated in the real world through the use of Crazyflie micro-UAVs. Furthermore, the proposed grasping formation satisfies static equilibrium thereby reducing orientation changes in the load-swarm system during transportation. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Method for control of Mixed Autonomy Traffic systems

Deep Reinforcement Learning Method for Control of Mixed Auto...

引用

2024 IEEE International Conference on Multisensor Fusion and Integration for Intelligent systems, MFI 2024

作者： Liu, Xingyu Apriaskar, Esa Mihaylova, Lyudmila University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Semarang50229 Indonesia

ISBN: (纸本)9798350368031

The introduction of autonomous vehicles (AVs) presents a novel approach to regulating and optimising traffic flow through the automated control of AVs. In this context, the AV is defined as the actuator and an optimal control policy is desired to make control decisions. Deep Reinforcement Learning (DRL) is a novel method which aims to maximize the cumulative rewards given by the predefined reward function by making sequential decisions in a stochastic environment. In light of the above, we propose a DRL-based vehicular control method to train an optimal policy for the control of AV in a model-free fashion, and consequently improve the traffic efficiency with the obtained control policy. A single-lane circular road environment with both AV and human-driven vehicles is selected to serve as the mixed autonomy traffic system in the Simulation of Urban MObility (SUMO) [1] traffic simulator, and the Proximal Policy Optimization (PPO) algorithm is applied for the policy improvement. Simulation results demonstrate that our strategy is effective in mitigating the unstable stop-and-go waves, increasing 67.7% of the average driving speed and reducing 19.3% of the average energy consumption in a closed-ring road environment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Tool Condition Monitoring Based on Nonlinear Output Frequency Response Functions and Multivariate control Chart

引用

Journal of Dynamics, Monitoring and Diagnostics 2023年第4期2卷 243-251页

作者： Yufei Gui Ziqiang Lang Zepeng Liu Hatim Laalej Department of Automatic Control and Systems Engineering University of SheffieldSheffield S102TNUK Advanced Manufacturing Research Centre University of SheffieldSheffield S102TNUK

Tool condition monitoring(TCM)is a key technology for intelligent *** objective is to monitor the tool operation status and detect tool breakage so that the tool can be changed in time to avoid significant damage to workpieces and reduce manufacturing ***,an innovative TCM approach based on sensor data modelling and model frequency analysis has been *** from traditional signal feature-based monitoring,the data from sensors are utilized to build a dynamic process ***,the nonlinear output frequency response functions,a concept which extends the linear system frequency response function to the nonlinear case,over the frequency range of the tooth passing frequency of the machining process are extracted to reveal tool health *** order to extend the novel sensor data modelling and model frequency analysis to unsupervised condition monitoring of cutting tools,in the present study,a multivariate control chart is proposed for TCM based on the frequency domain properties of machining processes derived from the innovative sensor data modelling and model frequency *** feature dimension is reduced by principal component analysis *** the moving average strategy is exploited to generate monitoring variables and overcome the effects of *** milling experiments of titanium alloys are conducted to verify the effectiveness of the proposed approach in detecting excessive flank wear of solid carbide end *** results demonstrate the advantages of the new approach over conventional TCM techniques and its potential in industrial applications.

关键词： intelligent manufacturing multivariate control chart Nonlinear Autoregressive with eXogenous Input modelling Nonlinear Output Frequency Response Functions tool condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Generating Continuous Paths On Learned Constraint Manifolds Using Policy Search

Generating Continuous Paths On Learned Constraint Manifolds ...

引用

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

作者： Ethan Canzini Simon Pope Ashutosh Tiwari Department of Automatic Control & Systems Engineering University of Sheffield UK Airbus Robotics Airbus UK

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Many robotic manipulation tasks are constrained due to kinematic limitations placed on the object being manipulated. This increases the complexity of manipulation tasks that operate in high dimensions, leading to increased risk that sampling based planners are unable to find optimal solutions. Whilst trajectory optimisation methods provide guaranteed optimal solutions when implementing constraints, they only provide locally optimal solutions in sequential decision-making and struggle to provide globally optimal paths. These constraints can be incorporated into the probabilistic latent spaces by using demonstrations that satisfy the constraint function. However whenever constraints change or a manipulator must perform different tasks the network must be retrained to accommodate the new constraints. In this paper, we provide an approach that allows the training of a single learned manifold that can be augmented to determine the constraint manifold for the manipulation task. Using this manifold, the geodesic between two points can be computed using policy search to solve the cost function associated with the geodesic curve length ${\mathcal{L}_\gamma }$. We provide comparisons in terms of path length against popular path planning algorithms with different kinematic constraints, demonstrating our method’s ability to find optimal shortest paths on constraint manifolds.

关键词： Manifolds Training Runtime Optimization methods Kinematics Reinforcement learning Probabilistic logic Real-time systems Trajectory Splines (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Holistic Self-Distillation with the Squeeze and Excitation Network for Fine-grained Plant Pathology Classification 26

Holistic Self-Distillation with the Squeeze and Excitation N...

引用

26th International Conference on Information Fusion, FUSION 2023

作者： Su, Jingxuan Anderson, Sean Mihaylova, Lyudmila University of Sheffield Department of Automatic Control & Systems Engineering S1 3JD United Kingdom

ISBN: (纸本)9798890344854

Fine-grained plant pathology classification is an important task for precision agriculture, but at the same time, it is challenging due to the subtle difference in plant categories. Variances in the lighting conditions, position, and stages of disease symptoms usually lead to degradation of classification accuracy. Knowledge distillation is a popular method to improve the model performance to deal with the indistinguishable image classification problem. It aims to have a well-optimised small student network guided by a large teacher network. Existing knowledge distillation methods mainly consider training a teacher network that needs a high storage space and considerable computing resources. Self-knowledge distillation methods have been proposed to distil knowledge from the same network. Although self-knowledge distillation saves time and space compared with knowledge distillation, it only learns label knowledge. In this paper, we propose a novel self-distillation method to recognize the fine-grained plant category, which considers holistic knowledge based on the Squeeze and Excitation Network. We label this new method as holistic self-distillation because it captures knowledge through spatial features and labels. The performance validation of the proposed approach is performed on two public fine-grained plant datasets: Plant Pathology 2021 and Plant Pathology 2020 with the accuracy of 98.22% and 90.72% respectively. We also present experiments on the state-of-the-art algorithm (ResNet-50). The classification results demonstrate the effectiveness of the proposed approach with respect to accuracy. © 2023 International Society of Information Fusion.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

On Sparse Nonlinear System Identification Using Orthogonal Matching Pursuit, Orthogonal Least Squares and LASSO

On Sparse Nonlinear System Identification Using Orthogonal M...

引用

Mediterranean Conference on control and Automation (MED)

作者： Hua-Liang Wei The Department of Automatic Control and Systems Engineering The University of Sheffield Sheffield

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

System identification, as a rich and vital discipline, provides a practical and general methodology and tool for quantitatively modelling the input-output relationships of dynamical systems. Sparse nonlinear system identification (SNSI), especially parametric sparse nonlinear system identification (PSNSI), is an important and vital field of research with a wide range of applications. This work is concerned with PSNSI and particular attention is paid to the assessment of three well-known mainstream sparse learning methods, namely, orthogonal least squares (OLS), orthogonal matching pursuit (OMP) and least absolute shrinkage and selection operator (LASSO). The performances of these methods are tested and evaluated through three case studies relating to PSNSI problems. The research results and findings of this work provide practical useful information and guidance for researchers to better choose or adapt methods when solving PSNSI problems.

关键词： Learning systems Automation Matching pursuit algorithms System identification Nonlinear systems Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

A simulation research method for data injection attacks on DC microgrids

A simulation research method for data injection attacks on D...

引用

2024 China Automation Congress, CAC 2024

作者： Hou, Yunhui Liu, Mengxiang Shen, Na National Key Laboratory of Transient Physics Nanjing University of Science and Technology Nanjing China Department of Automatic Control and Systems Engineering University of Sheffield Western Bank Sheffield United Kingdom

ISBN: (纸本)9798350368604

By using Typhoon HIL simulator, a simulation research method of data injection attack against secondary control DC microgrid is established, which reveals the important influence of the attack function on the effectiveness and covertness of the attack. Firstly, a decentralized four-node DC microgrid system using TCP/IP Modbus protocol for communication is built in Typhoon HIL simulator, then, a microgrid security testing experimental platform based on the man-in-the-middle attack as a network attack method is built in Kali Linux system, which can carry out timed single- and multilinks data injection attacks and replay attack on the above four-node DC microgrid. The paper designs a variety of data injection attack schemes to study the impact of data injection attacks on voltage and current control in this DC microgrid, including single-link attack, multi-link composite attack, and replay attack using different attack functions. By controlling the main parameters of the attack function, the amplitude of the fluctuation of the output voltage generated by the attack can be controlled, which can produce a more covert and effective attack effect. © 2024 IEEE.

关键词： DC microgrids False data injection attack Man-in-the-middle attack Power grid cyber security Replay attack

来源：评论

学校读者我要写书评

暂无评论

Combined Filters Design, Using the Principle of Internal Models

Combined Filters Design, Using the Principle of Internal Mod...

引用

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Gaiduk, Anatoly Denisenko, Darya Prokopenko, Nikolay Southern Federal University Scientific Design Office Robotics and Control Systems Department of Automatic Control Systems Rostov-on-Don Taganrog Russia Department of scientific research Don State Technical University Rostov-on-Don Russia Department of Automatic Control Systems Southern Federal University Rostov-on-Don Russia Don State Technical University Department of Information Systems and Radio Engineering Rostov-on-Don Russia

To design active analog, discrete-analog and digital filters a new method is suggested, taking into account the conditions of selective invariance and using the internal models principle of the dynamic systems. For this purpose, the structure of each basic filter ensures the presence of an explicit spectral model of the filtered signal. Such a filter is selectively invariant, and this property depend only on the spectrum-setting parameters and do not depend on other parameters. It is suggest-ed to carry out the design of the combined selective filters by integration of the suggested basic second-order filters, focusing on the log magnitude plot of the latter. This makes possible to minimize the order of the combined both analog and digital filters. The combined selective filters are distinguished by high stability of selective properties and can be used in the systems for measurement, signal processing, data transmission, as well as automatic and automated control of various social, production and special facilities. © 2024 IEEE.

关键词： Wiener filtering

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：