检索结果-内蒙古大学图书馆

5th International Conference on Transdisciplinary AI, TransAI 2023

作者： Gulde, Ralf Nguyen, Khanh Tuscher, Marc Riedel, Oliver Verl, Alexander Institute of Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart70174 Germany

ISBN: (纸本)9798350358018

Reinforcement Learning (RL) has gained popularity for developing intelligent robots, but challenges such as sample inefficiency and lack of generalization persist. The choice of observation space significantly influences RL algorithms' sample efficiency in robotics. While end-to-end learning has been emphasized, it increases complexity and inefficiency as the agent must re-learn forward and inverse kinematics. To address these issues, we propose a straightforward approach that utilizes readily available control techniques, such as forward and inverse kinematics, to capitalize on domain knowledge. Our approach involves enhancing the observation space with task-space features and utilizing task-space inverse kinematics. Our contributions include a proposal for mathematical formulation and a framework for RL algorithms in robotics. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control for Force control in Milling

引用

IFAC-PapersOnLine 2017年第1期50卷 15871-15876页

作者： Stemmler, S. Abel, D. Schwenzer, M. Adams, O. Klocke, F. Institute of Automatic Control RWTH Aachen University Aachen52056 Germany Laboratory for Machine Tools and Production Engineering RWTH Aachen University Aachen52056 Germany

Milling is one of the most flexible and productive manufacturing processes for machining metals. In the case of rough milling as much material as possible should be removed in as little time as possible. Therefore, a high cutting force is desirable. The maximum force is thus a suitable control variable to reduce the manufacturing time. The cutting force is related to the feed velocity. The relationship can be described by force models. They in turn can be used to determine the maximum feed velocity for a given force. This maximum feed velocity can be used as a reference, which shall not be exceeded. Hence, a Model-based Predictive controller (MPC) manipulates the desired feed velocity of the machine with respect to the machine behavior. This MPC shows good performance in the case of feed velocity references in time-domain. Though, the feed velocity reference depends on the position of the cutting tool through the workpiece. Hence, an approach shall be described which enables force control in position-domain. Therefore, the existing MPC is extended to a 2-Layer-MPC. An additional MPC works as a reference generator transforming the reference in position-domain into time-domain. Furthermore, an approach is described which allows position dependent feed velocity control without an additional MPC. Finally, the presented approaches are implemented and validated on a real machining center. © 2017

关键词： Model predictive control Cutting Cutting tools Force control Manufacture Milling (machining) Predictive control systems Velocity 2 Layer MPC Manufacturing process Model based controls Model based predictive controller Position dependents Predictive control Production system Reference generator

来源：评论

学校读者我要写书评

暂无评论

A planning system for generating manipulation sequences for the automation of maintenance tasks

A planning system for generating manipulation sequences for ...

引用

2016 IEEE International Conference on Automation Science and engineering, CASE 2016

作者： Friedrich, Christian Lechler, Armin Verl, Alexander Institute of Control Engineering Machine Tools and Manufacturing Units University of Stuttgart Stuttgart70174 Germany

ISBN: (纸本)9781509024094

The adaption of autonomous robots to complex assignments like automating maintenance tasks, requires the study of novel planning systems for task generation which use a priori and sensor-based data. This paper presents an approach to disassembly and assembly planning for automating maintenance tasks in production systems. The planning system combines CAD data with visual data from an RGB-D sensor. This allows the creation of a consistent environmental model, which can be used to plan a (dis)assembly task for an autonomous robot. The proposed method allows to compute manipulations directly in the task space of the robot. The algorithm uses a geometric and semantic reasoning concept to compute a relational graph which describes the individual degrees of freedom in-between the components. The proposed algorithm is highly time efficient, thus being particularly suited for the automation of maintenance tasks. With the additional integration of visual data, it is possible to compensate environmental uncertainty from the CAD data as well. This paper describes the planning architecture and algorithms in detail and concludes with an experimental validation. © 2016 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Analysis of CNC software modules regarding parallelization capability 24

Analysis of CNC software modules regarding parallelization c...

引用

24th International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2014

作者： Keinert, Matthias Kaiser, Benjamin Lechler, Armin Verl, Alexander Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart70174 Germany

ISBN: (纸本)9781605951737

The software design of current CNC systems is of limited suitability for real parallel execution on multicore systems. Even though CNC systems are rudimentarily designed in a modular way, a good load balancing and therefore an efficient use of multiple processor cores is not satisfactorily to be accomplished, as the modularization is not sophisticated enough. A parallelization of CNC functions and algorithms would remedy this deficit. This paper presents an analysis on which parts of a CNC system show the capability for parallelization. Furthermore an approach is presented on how the parallelization of a specific function, namely the look-ahead function, can be accomplished. © Copyright 2014 by DEStech Publications, Inc. All rights reserved.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

A control model for downstream compensation strategy in multi-stage manufacturing systems of complex parts

引用

IFAC-PapersOnLine 2019年第13期52卷 1473-1478页

作者： Magnanini, Maria Chiara Eger, Florian Reiff, Colin Colledani, Marcello Verl, Alexander Dipartimento di Meccanica Politecnico di Milano Milano Italy Institute for Control Engineering of Machine Tools and Manufacturing Units ISW University of Stuttgart Stuttgart Germany

The capability of delivering high-quality products with the required service level is a key factor for competitiveness in manufacturing companies. Zero-Defect Manufacturing control strategies aim at ensuring these targets grounding on the combination of knowledge extraction from the process and advanced statistical tools. This work presents the approach proposed within the EU-funded project ForZDM for selected use-cases in different industrial sectors characterized by multi-stage manufacturing systems and high-value complex parts. The control model is proposed and the overall control strategy is presented with respect to the state-of-the-art solutions, in order to show a comprehensive methodology integrating the joint product-system quality-oriented approach. © 2019, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Adaptive control systems Defects Statistical mechanics Statistical process control Adaptive control Compensation strategy High quality products Manufacturing companies Manufacturing control strategies Multi stage manufacturing systems Variation models Zero defects

来源：评论

学校读者我要写书评

暂无评论

Automation of the casting process using a model-based NC architecture 4

Automation of the casting process using a model-based NC arc...

引用

4th IFAC Workshop on Mining, Mineral and Metal Processing, MMM 2015

作者： Birkhold, M. Friedrich, C. Lechler, A. Institute for Control Engineering of Machine Tools and Manufacturing Units Seidenstrasse 36 Stuttgart70174 Germany

Automation of the casting process in foundries is most commonly limited to foundry lines for series manufacturing. The employed teach-in method for programming the process is time-consuming and, therefore, only suited for large lot sizes. Thus, manufacturing of small lot sizes or single parts still necessitates the handwork and expertise of workers pouring the molten metal into the mould. This creates a dangerous environment for the worker. In recent years researchers have developed a model-based process control, which allows precise casting control without having to previously teach the process. Usage of these process models has been limited to special process control systems, specifically designed for a certain machine. In this paper, a novel approach is presented, in which a NC (Numerical control) system is enhanced by process models. Instead of programming the NC in kinematic coordinates, it will be shown that programming in process coordinates allows robust and flexible casting, even for small lot sizes. The paper will prove the feasibility of the approach by evaluation of the processing time of the model. © 2015, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Foundries

来源：评论

学校读者我要写书评

暂无评论

A data model for data gathering from heterogeneous IoT and Industry 4.0 applications

A data model for data gathering from heterogeneous IoT and I...

引用

18th International Stuttgart Symposium on Automotive and Engine Technology, 2018

作者： Strljic, Matthias Milan Tasci, Timur Schmidt, Alexander Korb, Tobias Riedel, Oliver Institute of Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Germany

ISBN: (纸本)9783658211936

Industry 4.0 (I4.0) offers the opportunity to gain a detailed insight into the current production process by means of an increased networking of production plants. This crosslinking makes it possible to record the entire state of a production plant and to trace it within a later analysis. The aim of this analysis is to optimize the monitored production process resulting from analyses of I4.0 value-adding services [1, 2]. Figure 1 schematically visualizes the information flow for such a scenario. Data from the various levels of production are collected, stored in a data storage facility and evaluated by a valueadding service pipeline. The results are integrated back into the production process as optimizations. In this work, first the requirements for such a value-adding service pipeline are determined, which results in a total of five requirements and is abbreviated with R1 to R5. Subsequently, a suitable system architecture from the Big Data area is selected in order to meet the previously established requirements and thus implement a value-adding service pipeline. The requirements R1 - R5 and the system architecture will then flow into a data model for data acquisition and transmission within the shop floor of the production. © Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2018.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Parameter Estimation for Model-Based Force control in Milling Processes

引用

IFAC-PapersOnLine 2016年第12期49卷 634-639页

作者： Petruck, Henning Schlick, Christopher M. Stemmler, Sebastian Abel, Dirk Adams, Oliver Klocke, Fritz Institute of Industrial Engineering and Ergonomics RWTH Aachen University Germany Institute of Automatic Control RWTH Aachen University Aachen Germany Laboratory for Machine Tools and Production Engineering RWTH Aachen University Aachen Germany

In order to adapt to a milling machine's changing behavior while operating due to changing tool-workpiece contact conditions adaptive controllers are an advantageous approach to control the machine's feed rate. Otherwise inaccuracies can occur leading to poor quality. In this paper Model Predictive control (MPC) is used to control the feed rate of the machine. By applying a parameterized model to the current state of the milling process its future trend can be predicted. An n-th order system with delay time is used to model the behavior of the milling machine's velocity control loop. By continually re-estimating the model parameters at run time, the controller adapts to the current machine behavior. We developed solutions of the maximum likelihood estimators of the model's independent parameters for a state-space representation that can be numerically efficiently calculated. These estimators can be used to estimate the parameters of the n-th order system and the delay time iteratively based on the collected process data. Two validation studies, one emulating an online estimation based on real data from the five-axis machining center Mazak Variaxis 630II-T, and one simulation study with a simulated machine, were carried out to validate the iterative parameter estimation algorithm. In these studies, the time variant model, whose parameters are re-estimated on the basis of the developed estimators, is compared to a time invariant model, for which the controller does not adapt to changing machine behavior. © 2016

关键词： Parameter estimation Adaptive control systems controllers Identification (control systems) Iterative methods Least squares approximations Machining centers Maximum likelihood estimation Milling (machining) Milling machines Model predictive control Numerical methods Predictive control systems State space methods Adaptive control Least squares methods Model based controls Numerical algorithms State space models

来源：评论

学校读者我要写书评

暂无评论

Introducing an automated reconfiguration mechanism for flexible metal forming systems using a web service-based architecture approach 22

Introducing an automated reconfiguration mechanism for flexi...

引用

22nd International Conference on Production Research, ICPR 2013

作者： Birkhold, M. Abel, M. Verl, A. Institute for Control Engineering of Machine Tools and Manufacturing Units Seidenstraße 36 Stuttgart70174 Germany

Classic mechanical presses limit the flexibility of metal forming systems due to their fixed sinusoidal motion. Servo presses are no longer limited to a fixed sinusoidal motion, combining the free motion capability of hydraulic presses with the speed of classic mechanical presses. This new freedom of the press motion allows the integration of peripheral processes into the forming tool, reducing the necessity of follow-up processes. However, this new capability comes at the cost of increased complexity of the tool, which needs its own control system. Current techniques for the integration of peripheral systems lack granularity and need tedious hand tweaking. Therefore, many tool manufacturers have yet to embrace the new capabilities of servo presses. In this paper we introduce a novel approach, in which a press tool uses a middleware to automatically set-up the fieldbus configuration, during reconfiguration of the press. The considered peripheral system consists of three transfer modules which combine two forming parts in the tool for welding. The access to additional system data is necessary for the sophisticated transfer motions in this tool. Additionally, the necessity of manually tweaking the synchronization of the transfer is eliminated by this new approach. The capabilities of the new approach are demonstrated using state of the art controllers of a production system.

关键词： Presses (machine tools)

来源：评论

学校读者我要写书评

暂无评论

A PLANNING APPROACH FOR ROBOT-ASSISTED MULTIPLE-BENT PROFILE HANDLING

引用

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 1994年第1期11卷 35-40页

作者： ZUSSMAN, E HORSCH, T Institute of Machine Tools and Manufacturing Technology Technical University of Berlin 1000 Berlin 10 Pascalstr. 8-9 Germany Control System Theory and Robotics Group Institute of Control Engineering Darmstadt Institute of Technology 6100 Darmstadt Landgraf-Georgstr. 4 Germany

This paper describes a solution for the general problem of handling a multiple-bent profile of sheet metal in the constrained environment of a bending machine. The handling device is a robot feeding the machine and handling the sheet metal in between the bending operations. A new planning approach for a multiple-bent profile handling which is based on the configuration space and a potential function is presented. Special heuristics for the multiple-bent profile are applied and accelerate the motion planning process by recognition of the critical part of the profile and its orientation and position relative to the bending machine. This approach assists the sheet metal part planner to plan in advance the handling operations and to confirm if the robot can perform the handling or not. Two examples of handling multiple-bent profiles inside a bending machine are described and demonstrate the overall approach by a simulation.

关键词： Industrial robots

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：