检索结果-内蒙古大学图书馆

2023 China automation Congress, CAC 2023

作者： Zou, Mengmeng Lu, Yiwen Liu, Hanxiao Mo, Yilin Ren, Xiaoqiang The School of Computer Engineering and Science Shanghai University Shanghai China The School of Institute of Artificial Intelligence Shanghai University Shanghai China The School of Mechatronic Engineering and Automation Shanghai University Shanghai China Department of Automation BNRist Tsinghua University Beijing China

ISBN: (纸本)9798350303759

Deep reinforcement learning (DRL) has shown promise in solving the autonomous racing problem without requiring an accurate dynamics model, but random sampling of actions can lead to inefficient exploration. This paper proposes an efficient racing method, Constrained Residual Race (CRR), which combines a geometry-based reactive obstacle avoidance algorithm, Follow-The-Gap Method (FTG), with DRL. CRR generates safe guided actions with FTG and complementary actions with DRL, which are then fused into a final control action through a constraint equation. Using FTG as a prior controller enhances exploration efficiency and produces safe driving actions. Constraining the DRL policy output ensures that it does not overwrite the prior policy during early stages of exploration. Additionally, the DRL policy improves over the performance of the prior controller during training, reducing the lap time of the car. Validation on the F1TENTH simulator shows that CRR achieves lower lap times in most cases and exhibits excellent generalization capability. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Experimental study of hardness and corrosion properties of AZ91 magnesium alloy after electroless nano composite coating

引用

Materials Today: Proceedings 2022年 62卷 2926-2929页

作者： Sayyad, Dr Farook Sayyad, Dr Shabnam Ansari, Dr. Md. Imran Mechanical Engineering Department. Dr. D. Y. Patil School of Engineering Pune India Associate Professor Computer Engineering Department. AISSMS College of Engineering Pune India Robotics & Automation Department. Bharati Vidyappeth Pune India

Magnesium and its numerous alloys have excellent rigidity, low density, and electromagnetic protection properties, making them ideal for usage in numerous industrial components. Magnesium alloys have a significant disadvantage in terms of corrosion and hardness, which restricts their practical uses. One of the most recent ways for improving the corrosion and hardness of Mg alloys is electro-less nano-coating. The experimental research of corrosion and hardness of AZ91 Mg Alloy due to nano composite coating procedures of ENi-B-TiO2is examined in this study. It would be useful to conduct a thorough examination, including experimental analysis, into the possibilities of increasing the deposit efficiency and characteristics of composite deposits by designing a suitable bath composition and operating circumstances. It has been discovered that as the concentration of titania particles increases, so does the surface hardness of coatings. The optimal concentration of second-phase (titania) particles and bath agitation are also examined in order to get superior surface properties following nano coating. Following this nano coating, the materials may be employed for a variety of materials engineering applications. © 2022

关键词： Surface properties

来源：评论

学校读者我要写书评

暂无评论

Physics-informed neural networks for modeling water flows in a river channel

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1001-1015页

作者： Nazari, Luis Fernando Camponogara, Eduardo Seman, Laio Oriel Department of Mathematics Federal Institute of Education Science and Technology Catarinense Rio do Sul89160-202 Brazil Department of Automation and Systems Engineering Federal University of Santa Catarina Florianopolis88040-900 Brazil Program in Applied Computer Science Universidade Do Vale Do Itajai Itajai88302-901 Brazil

The impacts incurred by floods regularly affect the planets population, inflicting social and economic problems. Optimal control strategies based on reservoir management may aid in controlling floods and mitigating the resulting damage. To this end, an accurate dynamic representation of water systems is needed. In practice, flood control strategies rely on hydrological forecasting models obtained fromconceptual or data-drivenmethods. Encouraged by recent works, this research proposes a novel surrogate model for water flow in a river channel based on physics-informed neural networks (PINNs). This approach achieved promising results regarding the assimilation of real-data measurements and the parameter identification of differential equations that govern the underlying dynamics. This article investigates PINN performance in a simulated environment built directly from a configuration of the Saint-Venant equations. The objective is to create a suitable model with high prediction accuracy and scientifically consistent behavior for use in real-Time applications. The experiments revealed promising results for hydrological modeling and presented alternatives to solve the main challenges found in conventional methods while assisting in synthesizing real-world representations. Impact Statement-The research seeks to contribute to the hydrological modeling area with a surrogate model based on physicsinformed neural networks (PINNs) to water flow in a watershed. In practice, thesemodels use conceptual or *** models to reach the precision provided by themethodology use large numbers of physical parameters. These parameters can demand deep knowledge about the environment and are possibly hard to identify in a complex basin. On the other hand, while data-driven methods do not require such knowledge about the dynamic system, they depend on a reliable and useful database to guarantee the accuracy of system *** introduce PINNs as a viable solution for

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Core Losses Calculation and Thermal Evaluation Using the VBR-Based Finite Element Model of Induction Motors

Computationally Efficient Core Losses Calculation and Therma...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Valipoor, Zahra Koti, Hossein Nejadi Demerdash, Nabeel A. O. Marquette University Electrical and Computer Engineering Department Milwaukee United States Rockwell Automation Inc. Motion Control Team Mequon United States

ISBN: (纸本)9798350316445

Accuracy of the simulation results obtained from the FEA analysis of electric motors is highly dependent on the quality of the motor performance metrics such as motor steady state temperatures and losses. In addition such FEA analysis is typically computationally burdensome and demanding. Improving the computational burden and accuracy of core losses calculation and thermal evaluation in Time-Stepping Finite Element (TS-FE) models of induction motors is addressed in this paper. The Virtual Blocked Rotor (VBR)-based Time-Stepping Finite Element (TS-FE) technique is utilized to mitigate the numerical transient response of the induction motor FE model. The motor core losses have been calculated through the harmonic based core loss calculation that assumes variable loss coefficients as a function of magnetic flux density. In addition, the motor estimated losses, including the calculated core losses are fed to a thermal network model to estimate the temperature of different motor components. © 2023 IEEE.

关键词： Core Losses Induction Motor Temperature Thermal Calibration VBR-based FEA

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Output-Feedback Control of Discrete-Time Systems based on Hybrid Iteration 63

Adaptive Optimal Output-Feedback Control of Discrete-Time Sy...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Liu, Sitong Gao, Weinan Jiang, Zhong-Ping Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Lianning Shenyang110819 China Tandon School of Engineering New York University Department of Electrical and Computer Engineering BrooklynNY11201 United States

ISBN: (纸本)9798350316339

In this paper, a novel adaptive dynamic programming (ADP) algorithm, named output-feedback hybrid iteration (HI),is proposed to address the adaptive optimal control problem of discrete-time linear systems. The proposed output-feedback HI strategy learns the optimal control policy through two phases. First, a novel data-driven value-iteration (VI) scheme is employed to learn an admissible output-feedback control policy using the input/output data without relying on the knowledge of system matrices. Then, with the obtained admissible control policy, the optimal output feedback-control policy is approximated with an accelerated convergence rate through output-feedback policy iteration (PI). Online input/output data are utilized to reconstruct the full state of the system and integrated into the new output-feedback HI algorithm. Simulation results are presented and demonstrate the efficacy and practicality of the proposed output-feedback HI approach in comparison with traditional PI and VI techniques. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Advanced Analysis of Electro-Oculographic Signal using Deep Neural Networks for Safety Purposes in automation and Production Systems 15

Advanced Analysis of Electro-Oculographic Signal using Deep ...

引用

15th International Conference on computer and automation engineering, ICCAE 2023

作者： Kuric, Ivan Stenchlak, Vladimir Zajacko, Ivan Bohusik, Martin Wiecek, Dorota University of Žilina Department of Automation and Production Systems Žilina Slovakia University of Bielsko-Biala Faculty of Mechanical Engineering and Computer Science Bielsko-Biala Poland

ISBN: (纸本)9798350396225

This article deals with the problematics of obtaining and processing the EOG signals. This research describes the ways in which it is possible to measure and evaluate the measured bio-electrical signals of brain and muscle activity in more detail. The work also describes the analysis of the current state of this problematics and individual models of artificial intelligence are also described in the work - artificial neural networks that can be used for such advanced analysis. The experimental part of this work is performed in the MATLAB environment using the Deep Neural Network Toolbox. The experimental part of the work is focused on the analysis and processing of bio-electrical activity eye-motor muscles in the area of eye-tracking with the help of the OLIMEX EEG-SMT device. The information provided in this research can be used for improving safety and reliability and elimination of potential risks connected to an epilepsy disease and epilepsy seizures in automated production systems. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Pareto Analysis of PI Tuning in Direct Digital Control of Multi-phase Drives ⁎

引用

IFAC-PapersOnLine 2024年第7期58卷 144-149页

作者： Manuel G. Satué J.D. Álvarez Manuel A. Perales Systems Engineering and Automation Department University of Seville 41092 Seville Spain Department of Computer Engineering Automation and Robotics CIESOL—ceiA3 University of Almería 04120 Almería Spain Electronic Engineering Department University of Seville 41092 Seville Spain

PI tuning for variable-speed multi-phase drives is a complex task. In this paper, a Pareto analysis is introduced to reveal not previously reported links between figures of merit. The drive used for the study includes a 5-phase induction motor supplied by a voltage source inverter. A finite state predictive method is used for the inner loop (current control). The outer loop (speed control) is governed by a PI. The analysis is done experimentally thus including all sorts of non-idealities not appearing in commonly found models. The experimental results show how the pursuit for better performance is hindered by the existence of links between figures of merit. The importance of the result lies in showing that arbitrary performance enhancements are not possible in a general case.

关键词： Application of power electronics Digital implementation Modeling simulation of power systems PI control Tuning

来源：评论

学校读者我要写书评

暂无评论

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient VBR-Based Sensitivity Analysis of Induction Motors

Computationally Efficient VBR-Based Sensitivity Analysis of ...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Koti, Hossein Nejadi Valipoor, Zahra Demerdash, Nabeel A. O. Rockwell Automation Inc. Motion Control Team Mequon United States Marquette University Electrical and Computer Engineering Department Milwaukee United States

ISBN: (纸本)9798350316445

Sensitivity analysis is a powerful tool that can be utilized for reducing the size of the design space at hand to explore and significantly reduce the computational burden of the optimization process. This is achieved by 'smart' design variable selection. The term 'smart' indicates fixing the un-conflicting design variables that do not require exploration to their maximum or minimum values, depending on their enhancing or degrading effect on the objective functions and allowing the conflicting design variables to be explored within their allowable dynamic range. Intelligent optimization is a critical part of induction motor design process. In this paper, computationally efficient sensitivity analysis is performed to effectively reduce the number of the design variables that will be actively explored in the optimization process of the induction motors. This goal is achieved through the VBR-based TS-FEA together with Design of Experiment and Response Surface Methodology. In addition, the motor estimated losses, including the calculated core losses are fed to a thermal network model to estimate the temperature of different motor components. © 2023 IEEE.

关键词： Core Losses Induction Motor Temperature Thermal Calibration VBR-based FEA

来源：评论

学校读者我要写书评

暂无评论

A NOVEL REAL-TIME DEVS SIMULATION ARCHITECTURE WITH HARDWARE-IN-THE-LOOP CAPABILITIES

A NOVEL REAL-TIME DEVS SIMULATION ARCHITECTURE WITH HARDWARE...

引用

2024 Annual Modeling and Simulation Conference, ANNSIM 2024

作者： Fernández-Sebastián, Óscar Cárdenas, Román Arroba, Patricia Risco-Martín, José L. Department of Computer Architecture and Automation Universidad Complutense de Madrid Spain Department of Electronic Engineering Universidad Politécnica de Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Spain

ISBN: (纸本)9781713899310

Advanced Modelling and Simulation (M&S) techniques, including Digital Twins (DTs) and Hardware-In-the-Loop (HIL) simulation, are essential for the design and operation of today’s complex systems. Despite these advances, there remains a gap between the simulation methods used in design and those used in implementation. This paper introduces a Real-Time (RT) simulation framework that connects models using the Discrete-Event System Specification (DEVS) with external systems, improving implementation and operation. The Python xDEVS tool has been enhanced to introduce a new suite of real-time simulation components and a DEVS-based communication interface, facilitating adaptable communication protocols. The framework demonstrates its capability to integrate both DEVS and non-DEVS systems and establish effective communication through various experiments, ranging from RT simulation of DEVS models to complex multi-component systems. This tool has significant potential in supporting real and incremental system implementations through HIL techniques, making a valuable contribution to complex system design and operation. © 2024 Society for Modeling & Simulation International (SCS).

关键词： Hardware-in-the-loop simulation

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：