检索结果-内蒙古大学图书馆

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Fabian Reiling Christian Henke Matthias Hunstig Stefan Gröger Ansgar Trächtler department Scientific Automation Fraunhofer Institute for Mechatronic Systems Design Paderborn Germany Deputy Head of Research at Hesse GmbH Paderborn Germany Head of Chair of Control Engineering and Mechatronics Paderborn Germany

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Setting optimum process parameters for complex manufacturing processes such as ultrasonic wire bonding is already challenging for one target variable. Due to numerous influencing physical factors, such processes often lack the necessary detailed physical models. Due to the lack of these models, such processes cannot be adjusted to an optimum using classic optimization methods. In manufacturing processes in particular, the process must be optimized with regard to several objectives such as process time or quality. A popular method for optimizing such processes without models is multi-objective Bayesian optimization. For this purpose, surrogate models in the form of Gaussian processes are used in combination with a multi-objective acquisition function. In real processes, parallel function evaluation offers advantages in terms of trial efficiency and scalability. In this paper, we present a new algorithm for batch-constrained Bayesian multi-objective optimization. With this algorithm, an arbitrary number of function evaluations per iteration can be specified, whereby a more efficient determination of the Pareto front approximation can be achieved in real applications. For this purpose, the Expected Hypervolume Improvement is extended by a term to consider a quality criterion. Using the ultrasonic wire bonding process as an example, we experimentally prove that the proposed framework is able to approximate the Pareto front of the system with only a few function evaluations. For this purpose, the process capability index should be maximized and the process time minimized.

关键词： Manufacturing processes Mechatronics Scalability Optimization methods Predictive models Approximation algorithms Acoustics

来源：评论

学校读者我要写书评

暂无评论

Nonlinear System Identification Based on B-Spline Neural Network and Modified Particle Swarm Optimization

Nonlinear System Identification Based on B-Spline Neural Net...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： L. dos Santos Coelho R.A. Krohling Production and Systems Engineering Graduate Program Automation and Systems Laboratory PPGEPS/CCET/PUCPR Pontifical Catholic University of Paraná Parana Brazil Chair for Control Systems Engineering RST Faculty of Electrical Engineering and Information Technology University of Dortmund Dortmund Germany

Artificial neural networks, in particular, feedforward multilayer networks and basis function networks, have gradually established themselves as a usual tool in approximating complex nonlinear systems. B-spline networks, a type of basis function neural network, are normally trained by gradient-based methods, which may fall into local minima during the learning phase. In order to overcome the drawbacks encountered by conventional learning methods, particle swarm optimization - a swarm intelligence methodology - can provide a stochastic global search of B-spline networks for nonlinear system identification. In this paper, a modified particle swarm optimization algorithm using Gaussian and Cauchy probability distributions are applied to adjust the control points of B-spline neural networks. Simulation results for the identification of Rossler systems are provided and demonstrate the effectiveness and robustness of the proposed identification scheme.

关键词： Nonlinear systems Spline Neural networks Particle swarm optimization Artificial neural networks Multi-layer neural network Learning systems Stochastic systems Probability distribution Robustness

来源：评论

学校读者我要写书评

暂无评论

Asset management solution based on PROFIBUS-PA profiles

Asset management solution based on PROFIBUS-PA profiles

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： M. Wollschlaeger C. Diedrich J. Muller U. Epple Ifak Institut f. Automation U Kommunikation e. V. Magdeburg Barleben Germany Chair of Process Control Engineering PLT RWTH Aachen University of Technology Aachen Germany

ISBN: (纸本)0780372417

Effective solutions for asset management become increasingly important in modern automation and control systems. They are especially required in the area of process control. The control systems used here usually consist of PLC-based networks, which are optimised concerning the special temporal and topological requirements of the process. Asset management functions have to be introduced to those systems, without any influence on the existing equipment. The paper shows an object-oriented solution based on PROFIBUS-PA device. By automatically evaluating a system structure and mapping the profile-relevant parameters of devices to proxy objects, different application modules for asset management functions can be implemented acting on these objects.

关键词： Asset management Automatic control automation control systems Process control Data mining Data engineering Field buses Actuators Programmable control

来源：评论

学校读者我要写书评

暂无评论

Learning References with Gaussian Processes in Model Predictive control applied to Robot Assisted Surgery

Learning References with Gaussian Processes in Model Predict...

引用

European control Conference (ECC)

作者： Janine Matschek Tim Gonschorek Magnus Hanses Norbert Elkmann Frank Ortmeier Rolf Findeisen Laboratory for Systems Theory and Automatic Control Otto-von-Guericke Univ. Magdeburg Chair of Software Engineering Otto-von-Guericke Univ. Magdeburg Fraunhofer-Institute for Factory Operation and Automation Magdeburg

ISBN: (数字)9783907144022

ISBN: (纸本)9781728188133

One of the key benefits of model predictive control is the capability of controlling a system proactively in the sense of taking the future system evolution into account. However, often external disturbances or references are not a priori known, which renders the predictive controllers shortsighted or uninformed. Adaptive and learning based prediction models can provide suitable predictions to the controller and therefor can be applied to overcome this issue. We propose to learn references for model predictive controllers via Gaussian processes. To illustrate the approach, we consider robot assisted surgery, where a robotic manipulator must follow a learned reference position based on optical tracking measurements.

关键词： Predictive models Gaussian processes Robots Predictive control Task analysis control systems Tracking

来源：评论

学校读者我要写书评

暂无评论

Execution Time Oriented Design of an Adaptive controller for Mobile Machines

Execution Time Oriented Design of an Adaptive Controller for...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Marius Krüger Birgit Vogel-Heuser Dominik Hujo Christoph Huber Johannes Schwarz Boris Lohmann Fabian Kreutmayr Markus Imlauer Technical University of Munich TUM School of Engineering and Design Institute of Automation and Information Systems Garching near Munich Technical University of Munich TUM School of Engineering and Design Chair of Automatic Control Garching near Munich HAWE Hydraulik SE Aschheim near Munich

Mobile and stationary mechatronic systems are often driven by hydraulic actuators which are controlled using valves. Hydraulic systems have a high power density, are robust and cost-effective in the application and can work reliably under rough environmental conditions. For many years, PID controllers build the state-of-the-technology for valve control. Although PID controllers are easy to synthesize and can be executed on low-performing devices, the demand for more adaptive control approaches to deal with non-linearities in hydraulic circuits is increasing. Adaptive controllers tend to be more computationally expensive than PID controllers, so the capability of common hardware devices to execute the algorithms in real-time must also be considered. This paper contributes a feasibility study examining whether adaptive control approaches can be used for valve control in hydraulic-driven mobile machines. Thus, a literature review on adaptive valve control approaches is conducted and a model-based linear adaptive control approach consisting of system identification and control logic execution is extracted. The adaptive controller is applied to a hydraulic testbed and the controller performance is measured in dependence on the cycle time of the controllers to estimate the worst-case execution time. It is investigated whether common control units in mobile machines can reach the execution times and how many valves can be controlled by one control unit in terms of the execution time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motion planning and feedback control of a planar robotic unicycle model

引用

IFAC Proceedings Volumes 2009年第13期42卷 501-506页

作者： Matthias Franke Joachim Rudolph Frank Woittennek Fraunhofer Institut Integrierte Schaltungen Design Automation Division Zeunerstraße 38 01069 Dresden Germany Chair of systems theory and control engineering Saarland University 66123 Saarbrücken Germany Institut für Regelungs- und Steuerungstheorie Technische Universität Dresden 01062 Dresden Germany

Abstract Open and closed loop control design for the planar motion of a unicycle model consisting of a double pendulum mounted on a rolling wheel is considered. The motion planning problem is solved by prescribing trajectories to the two pendulum angles, the wheel angle is then obtained by integrating twice. A feedforward control trajectory directly follows from this parametrization. A feedback stabilizing the planned motion is designed after linearization of the relevant subsystem about the planned trajectories. Simulation results show the usefulness of the result.

关键词： Underactuated system motion planning feedback control trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

Testing Intelligence: Accelerating the Verification and Validation of Intelligent Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年 1-14页

作者： Wang, Fei-Yue Hu, Jia Lai, Jintao State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China ZhongTe Distinguished Chair in Cooperative Automation Professor Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China

来源：评论

学校读者我要写书评

暂无评论

A Sectorized FCS-MPC Transformerless SST For Power Transmission Application

A Sectorized FCS-MPC Transformerless SST For Power Transmiss...

引用

European Conference on Power Electronics and Applications

作者： Gabriel Gaburro Bacheti Renner Sartório Camargo Emilio José Bueno Marco Liserre Lucas Frizera Encarnação Department of Electrical Engineering Federal University of Espirito Santo (UFES) Vitoria Brazil Department of Control and Automation Engineering Federal Institute of Espirito Santo (IFES) Serra Brazil Department of Electronics Alcalá University (UAH) Madrid Spain Chair of Power Electronics Christian-Albrechts-Universitat Kiel Germany

ISBN: (数字)9789075815399

ISBN: (纸本)9781665487009

This work proposes a sectorized optimization with Graph Theory applied in cascaded multilevel trans-formerless SST. The sectorized optimization can reduce the FCS-MPC combinational explosion due to the multiple cascaded H-bridges cells, while the proposed control is capable to avoid the prohibitive states maintaining the converter controllability and power quality.

关键词： Reactive power Windings Power quality Power transmission Transformers Prediction algorithms IEEE Standards

来源：评论

学校读者我要写书评

暂无评论

Modeling and Iterative Learning control of a Circular Deformable Mirror

引用

IFAC-PapersOnLine 2017年第1期50卷 3117-3122页

作者： Cichy B. Augusta P. Gałkowski K. Rauh A. Aschemann H. Rogers E. Rehák B. Institute of Control and Computation Engineering University of Zielona Góra ul. Szafrana 2 Zielona Góra 65-516 Poland Institute of Information Theory and Automation The Czech Academy of Sciences Pod Vod´arenskou věží 4 Prague CZ-182 08 Czech Republic Chair of Mechatronics University of Rostock Justus-von-Liebig-Weg 6 Rostock D-18059 Germany Department of Electronics and Computer Science University of Southampton Southampton SO17 1BJ United Kingdom

An unconditionally stable finite difference scheme for systems whose dynamics are described by a fourth-order partial differential equation is developed using a regular hexagonal grid. The scheme is motivated by the well-known Crank-Nicolson discretization that was originally developed for second-order systems and it is used in this paper to develop a discrete in time and space model of a deformable mirror as a basis for control law design. As one example, the resulting model is used for iterative learning control law design and supporting numerical simulations are given. © 2017

关键词： control of partial differential equations Iterative learning control Linear systems N-dimensional systems Stability of distributed parameter systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach

arXiv

引用

arXiv 2022年

作者： Gong, Hailong Li, Zirui Lu, Chao Du, Guodong Gong, Jianwei School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Chair of Traffic Process Automation "Friedrich List" Faculty of Transport and Traffic Sciences TU Dresden Germany Institute of Dynamic System and Control ETH Zurich Sonneggstrasse 3 Zurich8092 Switzerland

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which fail in dealing with low-light conditions. This paper proposes a novel approach for trajectory prediction in low-illumination scenarios by leveraging multi-stream information fusion, which flexibly integrates image, optical flow, and object trajectory information. The image channel employs Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) networks to extract temporal information from the camera. The optical flow channel is applied to capture the pattern of relative motion between adjacent camera frames and modelled by Spatial-Temporal Graph Convolutional Network (ST-GCN). The trajectory channel is used to recognize high-level interactions between vehicles. Finally, information from all the three channels is effectively fused in the prediction module to generate future trajectories of surrounding vehicles in low-illumination conditions. The proposed multi-channel graph convolutional approach is validated on HEV-I and newly generated Dark-HEV-I, egocentric vision datasets that primarily focus on urban intersection scenarios. The results demonstrate that our method outperforms the baselines, in standard and low-illumination scenarios. Additionally, our approach is generic and applicable to scenarios with different types of perception data. The source code of the proposed approach is available at https://***/TommyGong08/MSIF. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

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：