检索结果-内蒙古大学图书馆

50th International Symposium on Robotics, ISR 2018

作者： Boanta, Catalin Margaritescu, Mihai Verl, Alexander Brisan, Cornel Department of Mechatronics and Machine Dynamics Technical University of Cluj-Napoca Romania National Institute of Research and Development in Mechatronics and Measurement Technique Bucharest Romania Institute for Control Engineering of Machine Tools and Manufacturing Units Stuttgart Germany

ISBN: (纸本)9781510870314

The selective disposal of the solid waste represents one of the modern problems of the middle and low income cities around the globe, a problem that generates environmental hazards if it is not properly managed. Since the selective collection of the waste is still far to be achieved on a large scale, an automated selection of the waste could overcome the environmental problems generated by landfill sites. This paper presents the concept of an automated solid waste selection system composed by several sub-systems: a transportation network (a set of conveyors), an image recognition system to identify the type of transported solid waste and a waste robot disposal system that selectively grabs the unsorted waste items. Besides this, a waste disposal algorithm is developed as task planning for the robot disposal system. © VDE VERLAG GMBH · Berlin · Offenbach

关键词： Solid wastes

来源：评论

学校读者我要写书评

暂无评论

Comparison of 3D shape reconstruction methods for fiber-optic sensors 50

Comparison of 3D shape reconstruction methods for fiber-opti...

引用

50th International Symposium on Robotics, ISR 2018

作者： Riehs, Christopher Kleiner, Bernhard Schneider, Urs Verl, Alexander Graduate School of Excellence advanced Manufacturing Engineering Stuttgart Germany Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Germany

ISBN: (纸本)9781510870314

A comparison of two methods for the 3D shape reconstruction of a new kind of fiber-optic sensor using Fiber Bragg Gratings (FBG) is presented. The sensors, developed at the Fraunhofer Heinrich-Hertz-institute, consists of FBGs written in the cladding of a standard 125 µm fiber. In this way, simple and cost efficient bending sensors can be produced. Shape reconstruction strategies using a single fiber, that was actively moved along an path, which shape was reconstructed, and with a fiber, that was resting, were investigated. The achievable accuracy of both methods was compared with an experimental setup. © VDE VERLAG GMBH · Berlin · Offenbach

关键词： Fiber optic sensors

来源：评论

学校读者我要写书评

暂无评论

Configuration of Application Layer Protocols within Real-time I4.0 Components

Configuration of Application Layer Protocols within Real-tim...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Frederick Prinz Michael Schoeffler Andreas Eckhardt Armin Lechler Alexander Verl Corporate Sector Research and Advance Engineering Robert Bosch GmbH Renningen Germany Engineering Automation Systems Bosch Rexroth AG Erbach Germany Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Stuttgart Germany

Within the context of Industry 4.0, future production systems are expected to support mass customization up to lot size one. In order to realize the individual production processes, a changeable and consistent integration of assets from different manufacturers is required. Therefore, the concept of I4.0 components was developed. Every I4.0 component provides a so-called asset administration shell, i.e. a standardized virtual representation of its capabilities. This paper focuses on real-time I4.0 components that require a deterministic communication with bounded low-latency in-between. In contrast to non-real-time I4.0 components, Ethernet (IEEE 802.3) is enhanced by the new real-time communication technology Time-Sensitive Networking (TSN, IEEE 802.1). The basic configuration of TSN connections within the asset administration shell was already addressed by previous work. In this work, we present the configuration of application layer protocols using the example of OPC UA Publish/Subscribe (PubSub). More precisely, we outline the underlying concept and define additional submodels for the asset administration shell of real-time I4.0 components. Finally, we discuss the advantages of the presented approach in terms of changeability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-based method for condition monitoring and diagnosis of compressors

引用

Procedia CIRP 2018年 72卷 1321-1326页

作者： Tim Engelberth Daniel Krawczyk Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units Seidenstr. 36 70174 Stuttgart Germany

In process industries, compressor plants provide process mediums with certain flows and pressures. Due to corrosion, wear and fouling, the plant behavior may change throughout the entire life cycle of several decades. This paper presents a new model-based method for condition monitoring and diagnosis of turbo compressors, in which the characteristic operating behavior is mainly influenced by fouling. The real-time capable method is implemented on a plant control unit and validated by Hardware-in-the-Loop simulation. Furthermore, the diagnostic result is used to automatically adapt the controller behavior. The presented approach increases the original system’s resource efficiency without reducing its robustness.

关键词： Diagnosis Condition monitoring Modelling Compressor Fouling

来源：评论

学校读者我要写书评

暂无评论

Reduction of Support Structures and Building Time by Optimized Path Planning Algorithms in Multi-axis Additive Manufacturing

引用

Procedia CIRP 2018年 67卷 221-226页

作者： Daniel Coupek Jens Friedrich David Battran Oliver Riedel Institute for Control Engineering of Machine Tools and Manufacturing Units Seidenstr. 36 Stuttgart 70174 Germany

Additive manufacturing is an emerging technology that enables new product design. However, major inhibitors are long building times and a fixed build direction of the workpieces. In this article, new optimization and path planning methods for multi-axis additive manufacturing are presented going beyond conventional three-axis systems. This includes an adaptation of the building direction and an algorithm for the special case of cylindrical axes. These methods can reduce the production time drastically by avoiding support structures and by using the integration of predefined building blocks to substitute the infill. We present both, the new manufacturing process and the necessary computation methods for optimal process and path planning. Decreasing the building time and the amount of support structures paves the way for new application domains of additive manufacturing in the future.

关键词： Additive manufacturing Multi-axis Path planning Trajectory Support structures

来源：评论

学校读者我要写书评

暂无评论

Persistent data backend for OPC UA namespaces in IT infrastructures

引用

Procedia CIRP 2018年 72卷 174-178页

作者： Felix Kretschmer Christian von Arnim Armin Lechler Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units Seidenstr. 36 70174 Stuttgart Germany

This paper presents an approach for persistent data backends for OPC UA namespaces. OPC UA as M2M protocol is used in various manufacturing machines and provides data access to e.g. sensors and setpoints. The central and persistent data storage for e.g. data-mining and condition-monitoring services in information technology infrastructures is challenging. Therefore, a holistic approach for storing OPC UA information in lightweight directory access protocol server is presented including a model for storing namespaces, information models and values in LDAP trees of scalable enterprise infrastructures to fulfil manufacturing and IT requirements in the context of Industry 4.0.

关键词： opc ua ldap it architectures data backend

来源：评论

学校读者我要写书评

暂无评论

Online Learning of Stability Lobe Diagrams in Milling

引用

Procedia CIRP 2018年 67卷 278-283页

作者： Jens Friedrich Jonas Torzewski Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Seidenstrae 36 70174 Stuttgart Germany

The productivity of milling machines is limited by chatter vibrations. Stability lobe diagrams (SLD) allow the selection of suitable process parameters to maximize the productivity. However, the calculation of SLDs is very time-consuming and requires complex experiments. In this article a new online learning method is presented, which allows the calculation of SLDs during the production process. The algorithm is a combination of reinforcement learning and nearest-neighbor-classification and allows the estimation of the stability border based on measured vibration signals during machining. The proposed algorithm is capable of being continuously trained with sorted input data. A trust criterion is introduced, which allows judging the prediction quality of the algorithm. The algorithm is validated with analytical benchmark functions and with a 2-DOF milling stability simulation.

关键词： Milling Stability Chatter Learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning of Material Flow control Logic Using Hardware-in-the-Loop Simulation

Reinforcement Learning of Material Flow Control Logic Using ...

引用

Artificial Intelligence for Industries (AI4I)

作者： Florian Jaensch Akos Csiszar Annika Kienzlen Alexander Verl Institute of control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany

ISBN: (纸本)9781538694633;9781538692097

In this paper the concept of reinforcement learning agent is presented, which can deduce the correct control policy of a plant by acting in its digital twin (the HiL simulation). This way the agent substitutes a real control system. By using reinforcement learning methods, a proof of concept application is presented for a simplistic material flow system, with the same type of access to the digital twin which a PLC controller-hardware would have. With the presented approach the agent is able to find the correct control policy.

关键词： Reinforcement learning Belts Hardware-in-the loop simulation control systems Process control Software Training

来源：评论

学校读者我要写书评

暂无评论

A Symbolic-Numeric Method to Capture the Impact of Varied Geometrical Parameters on the Translational Workspace of a Planar Cable-Driven Parallel Robot

A Symbolic-Numeric Method to Capture the Impact of Varied Ge...

引用

ASME/IFToMM International Conference on Reconfigurable Mechanisms and Robots, ReMAR

作者： Felix Trautwein Philipp Tempel Andreas Pott Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany

In this paper, an approach to capture and visualize the impact of a geometrical adjustments of a cable-driven parallel robot is presented. This method combines the precision of an analytic description with the efficiency of numeric methods. The translational workspace of the robot, corresponding to a set of geometrical parameters, is determined by a piecewise assembly of boundary segments. The intersections of the curves, defining the workspace border, are computed by utilizing their shape as conic sections. Calculation examples are also given, comparing the impact of different parameter sets on the workspace.

关键词： Transmission line matrix methods Robot kinematics Mathematical model Shape Kinematics Redundancy

来源：评论

学校读者我要写书评

暂无评论

Kernel Selection for Support Vector machines for System Identification of a CNC Machining Center

引用

IFAC-PapersOnLine 2019年第29期52卷 192-198页

作者： Muzaffer Ay David Stenger Max Schwenzer Dirk Abel Thomas Bergs Institute of Automatic Control RWTH Aachen University Campus-Boulevard 30 Aachen Germany David Stenger is an associated member of the research training group GRK 1856 of the german research foundation Laboratory for Machine Tools and Production Engineering (WZL) RWTH Aachen University Campus-Boulevard 30 Aachen Germany

Advanced learning methods enable the model-based control of systems with complex unknown dependencies. Within the German cluster of excellence “Internet of Production”, a configuration for an interconnected data-base is proposed, where data-driven model-based control strategies can be applied using the collective knowledge and adapted online according to data. For the exchanged data it is imperative to establish a generalizing learning technique for the controller design. A machine learning technique with inherent generalization ability is the Support Vector machines (SVM) algorithm, where the choice of kernel is crucial for the resulting model quality. In the related literature, usually a radial basis function (RBF) is chosen as kernel, although many studies show the necessity of a more sophisticated kernel selection. This work tackles the point of a kernel selection based on composite kernel search in context of data-driven model-based control of a CNC machining center. The results support the capability of the presented approach to further automate and improve the identification of the controller model for the machining center.

关键词： kernel selection support vector machines machine learning system identification data driven control internet of production

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：