检索结果-内蒙古大学图书馆

Model-based automatic generation of digital twin models for the simulation of reconfigurable manufacturing systems for timber construction

引用

Procedia CIRP 2022年 107卷 387-392页

作者： Benjamin Kaiser Alexander Reichle Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 D-70174 Stuttgart Germany

Reconfigurable manufacturing systems adapt to changing requirements and therefore offer a solution to the challenges associated with increasing product variety and shorter product life cycles. This is especially helpful in the prefabrication in timber construction, as components and requirements vary widely between projects. However, reconfigurations must be quick to keep downtimes short. The planning of reconfigurations is a complex problem where digital twins and simulation models of the manufacturing systems are necessary for simulation and validation. In our timber prefabrication use case, building components and requirements change from project to project, and the manufacturing system needs to reconfigure frequently. The building components and the configuration of the manufacturing system are designed simultaneously during a co-design process to ensure the integrity of the manufacturing process in a changing manufacturing environment. Hence, this may require many iterations of the planning process. Each iteration needs validation through a simulation. However, the manual generation of simulation models is time-consuming and error-prone and thus poses an obstacle for the digital planning phase. This paper addresses this issue and presents a model-based approach to generate simulation models for reconfigurable manufacturing systems. Our system and its components are modeled in automation markup language as this domain-specific language allows us to model not only kinematics and geometry but also behavior, skills, and interfaces to check the compatibility of components. We apply the method to our use case with the IntCDC wood prefabrication system. The proposed method builds a component graph for a configuration of the manufacturing system and generates the required packages for the simulation in Gazebo and ROS. To build simulation models automatically, we apply model-to-model and model-to-text transformation techniques. The proposed method is suitable for integr

关键词： AutomationML ROS URDF Software Defined Manufacturing Reconfigurable Manufacturing System Simulation Timber Prefabrication IntCDC

来源：评论

学校读者我要写书评

暂无评论

On data, information, and knowledge in the context of online simulation in industrial automation

引用

Procedia CIRP 2024年 130卷 1188-1193页

作者： Darius Deubert Andreas Selig Alexander Verl Bosch Rexroth AG Bgm.-Dr.-Nebel-Straße 2 97816 Lohr am Main Germany Institute for Control Engineering of Machine Tools and Manufacturing Units - University of Stuttgart 70049 Stuttgart Germany

In the course of digitalization and Industry 4.0, data-based optimization strategies and AI technologies are increasingly applied in industrial automation. To achieve benefits from this, it is necessary to contextualize and interpret the widely available data and process them to value adding information and knowledge. This paper deals with the processing of data, information, and knowledge in the context of online simulation in industrial automation. It forms a basis by defining the terms within an industrial perspective and examining the data landscape regarding properties that get important in cyber-physical systems including online simulation. Subsequently the generation of resulting information and knowledge with online simulation is discussed. Within this work, by changing the point of view from a technical perspective to an abstraction it is shown that known principles from intelligent systems and knowledge engineering also hold for manufacturing systems that are supported by an online simulation system. Additionally, this contemplation points out that online simulation systems exceed the level of information by gaining and processing knowledge, which enables to infer new information. By this, the influence of online simulation in industrial automation on data, information, and knowledge handling is expounded comprehensively.

关键词： simulation digital twins manufacturing robotics automation semantics

来源：评论

学校读者我要写书评

暂无评论

A simulation model extension to enable continuous control tests during the Virtual Commissioning

引用

Procedia CIRP 2022年 112卷 97-102页

作者： Erik-Felix Tinsel Prof. Dr.-Ing Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Seidenstr. 36 70174 Stuttgart Germany

Model-, Software-, and Hardware-in-the-Loop simulations are used in the Virtual Commissioning of machines and plants to reduce costly control errors early in the engineering process. Each simulation type represents a different grade of detail. As a result, the underlying models change on every transition between the three types. Regarding the model structure there is no solution to enable a continuous and effortless transition. This work proposes a model extension concept which allows cycling all X-in-the-Loop configurations during Virtual Commissioning. The extension includes abundant submodules describing every component transformation required to switch to a specific simulation configuration.

关键词： X-in-the-Loop Simulation model Virtual Commissioning

来源：评论

学校读者我要写书评

暂无评论

Adaptive CAM planning to support co-design in the building industry

引用

Procedia CIRP 2022年 109卷 78-83页

作者： Alexander Reichle Carsten Ellwein Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 D-70174 Stuttgart Germany

Co-design describes a collaborative design process between different stakeholders. These stakeholders usually come from various domains. To enable co-design, data has to be exchanged between the stakeholders. Current approaches to data management in the building industry are usually oriented along the process chain and therefore only allow a unidirectional flow of information. This is an obstacle in the implementation of co-design within the building industry. As more and more buildings are built by utilizing prefabricated modules to accelerate the on-site building process and to reduce the cost, a major effort in terms of implementing co-design is to link the design information of the building industry with the production information of the manufacturing industry. The problem occurs as the building industry mainly uses the fndustry Foundation Classes and the manufacturing industry uses the Standard for the Exchange of Product Model Data as a data format to exchange information. This leads to a break in the flow of information. Furthermore, information about the manufacturability of products, that is generated during the computer-aided manufacturing process, cannot be easily returned to the architect who can utilize the information to adapt the design in the computer-aided design process. This paper addresses these problems by defining a data processing pipeline that enables the conversion of the geometric design information stored in IFC into the STEP data format. From there, the CAM strategy can be defined and results in an executable G-Code. The information of the CAM planning is returned to the architect, who can adapt the design by interpreting the results of the CAM processing. To close the co-design loop, the G-Code for the design adaptions can be generated automatically by reusing the predefined CAM strategy.

关键词： Co-Design IFC STEP CAD CAM Data Processing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Instance Segmentation for Feature Extraction of Branched Deformable Linear Objects for Robotic Manipulation

Deep Learning-Based Instance Segmentation for Feature Extrac...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Manuel Zürn Annika Kienzlen Lars Klingel Armin Lechler Alexander Verl Shiyi Ren Weiliang Xu Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany Department of Mechanical and Mechatronics Engineering The University of Auckland Auckland New Zealand

Branched deformable linear objects, like wire harnesses, are vastly used in the electrical industry to interconnect multiple electronic components while allowing small relative motions. Their deformable nature gives them an infinite-dimensional configuration space, which is challenging for robotic manipulation and requires sensor feedback about the actual configuration. Cameras have been used before in automation attempts as sensor feedback of branched deformable linear objects. However, image processing is sensible to occlusions and unstructured environments. This paper presents a method of using deep learning-based instance segmentation networks to extract topological features like connectors, clips, branch points and overlapping points on the branched deformable linear object. The topological features originate from features that can be used for matching a stretched representation of the branched deformable linear object to its sensor representation. Our results show that the network is capable of extracting the features for different datasets with high accuracy. Furthermore, this paper evaluates the use of preliminary results in the training process to facilitate annotation by predicting the labels. For now, this paper only uses 2D images of the branched deformable linear objects. Future work will also use depth images, such that individual deformable linear object features, such as length or radius, can be extracted from the images. We anticipate the usage of wire harness automation with robotic manipulation, augmented reality support of the worker or quality control of wire harnesses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifting ROS to Model-Driven Development: Lessons Learned from a bottom-up approach

Lifting ROS to Model-Driven Development: Lessons Learned fro...

引用

Workshop on Robotics Software engineering (RoSE)

作者： Nadia Hammoudeh Garcia Harshavardhan Deshpande Ruichao Wu Björn Kahl Andreas Wortmann Fraunhofer Institute for Manufacturing Engineering and Automation (IPA) 70569 Stuttgart Germany Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart 70174 Stuttgart Germany

The benefits of using model-based technologies are well proven in different sectors. However, in robotics, where the dominant framework is one whose nature is to create the code by hand, MDD approaches are struggling to gain a foothold. Our approach is distinctly different from traditional MDD solutions, we have created models and tools with a bottom-up perspective, i.e. analyzing “ everyday” code and encapsulating this existing code in models. In this paper we present the lessons learned from (1) designing the models to encapsulate ROS hand-written code, (2) creating tools to ease the production and debugging of complex systems using the models, and (3) applying them to real use cases. Through this work we have identified in which situations it is worth using model-based technologies and in which situations the traditional approach is more meaningful. Our aim is to give a broad view of our conclusions and inspire the design of new model-based tools for the assistance of roboticists.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Direct Trajectory Generation on Parametric Compound Surfaces in a Numerical control to Improve Surface Homogeneity for Material Extrusion

SSRN

引用

SSRN 2023年

作者： Elser, Anja Lechler, Armin Verl, Alexander Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 Stuttgart Baden-Württemberg70174 Germany

HighlightsSurface quality in the sense of homogeneity and exactness of Material Extrusion processes depends on material extrusion control as well as trajectory generation. In this paper, the authors improve the trajectory generation process, that can then be combined with existing material extrusion control to maximize surface quality while at the same time ensuring high process velocity. In the currently established Slicer-CNC interface, the tool path description is transferred by the use of discrete points. There are four main deficits that result from this discretization: (i) The path error is unknown in the CNC. (ii) The computed tool path tends to oscillate. (iii) Parallel paths are processed differently in the CNC. (iv) Transitions between two surface patches of a compound surface are blurred. To overcome these drawbacks, in this paper, the surface description of curved compound surfaces is transferred to the CNC. A CNC architecture dealing with this description is presented, including the information flow, the definition of manufacturing paths, and different smoothing methods. Smoothing methods on a single surface as well as across surface boundaries are defined. In particular, a corner smoothing method is developed, that results in $G^2$-continuous transitions for arbitrary boundary conditions, such as non-zero curvatures. The smoothing methods are validated experimentally and discussed. The produced parts show remarkable increase in surface quality. © 2023, The Authors. All rights reserved.

关键词： Surface properties

来源：评论

学校读者我要写书评

暂无评论

Software Architecture For Deformable Linear Object Manipulation: A Shape Manipulation Case Study

Software Architecture For Deformable Linear Object Manipulat...

引用

Workshop on Robotics Software engineering (RoSE)

作者： Manuel Zü rn Markus Wnuk Armin Lechler Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units Stuttgart Baden-Württemberg Germany

Deformable linear object manipulation is challenging due to their high dimensional configuration space and their underactuated nature when manipulated by a robotic gripper. Due to the complexity of the task, robotic manipulation relies on sensors and computationally demanding models, which end up in multiple different software components interacting with each other. Research in deformable object manipulation usually focuses on modeling, planning or control, without focusing on a software architecture. This paper presents a novel software architecture for deformable linear object manipulation. The software architecture includes components for deformable linear object manipulation, namely perception-, observation-, robot control-, planning-, communication- and decision component. On top of these components, a layered software architecture consisting of a decision layer, a skill layer and a functional layer is presented The proposed concept aims to be a blueprint for a unified software architecture satisfying the requirements of robotic systems to achieve deformable linear object manipulation. The validation of the software architecture is done in a case study of an autonomous shape manipulation task, where one robot and a stereo camera shape a deformable linear object to a predefined desired shape. This use case is inspired by an automated cable routing process, which today in the industry is still mainly handled manually and therefore offers a vast potential for automation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Literature Review and Model Proposal on the machine Life Cycle in Industrial Automation from Different Perspectives 56

Literature Review and Model Proposal on the Machine Life Cyc...

引用

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Stegmaier, Valentin Eberhardt, Tobias Schaaf, Walter Jazdi, Nasser Weyrich, Michael Verl, Alexander University of Stuttgart Nobelstraße 12 Stuttgart70569 Germany Institute of Industrial Automation and Software Engineering University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstraße 36 Stuttgart70174 Germany J. Schmalz GmbH Johannes-Schmalz-Straße 1 Glatten72293 Germany

The life cycle model of machines as idealistic subsequent phases is often used to analyze industrial automation systems. Depending on their focus, literature holds a number of different state of the art approaches for the machine life cycle with various phases. However, the consideration is mainly from the perspective of machine manufacturers. Often, the life cycle of the product, that is manufactured with the corresponding machine or the life cycle of the components installed in the machine are thoroughly considered. The development, production and operation of these assets can also be divided into corresponding phases. The aim of this paper is to provide an overview of existing approaches of machine life cycles based on a structured literature review. This will also address the differences in the life cycle phases for the typical stakeholders of the industrial value chain. Since the life cycles of the individual stakeholders of the industrial value chain are coupled, a chronological classification of the individual life cycle models based on the product creation process is presented one above the other. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference on Manufacturing Systems 2023.

关键词： Industrial value chain Life cycle Literature review machine life cycle

来源：评论

学校读者我要写书评

暂无评论

State Derivative Normalization for Continuous-Time Deep Neural Networks

引用

IFAC-PapersOnLine 2024年第15期58卷 253-258页

作者： Jonas Weigand Gerben I. Beintema Jonas Ulmen Daniel Görges Roland Tóth Maarten Schoukens Martin Ruskowski Chair of Machine Tools and Control Systems RPTU Kaiserslautern and the German Research Center for Artificial Intelligence Kaiserslautern Germany Control Systems (CS) Group at the Department of Electrical Engineering Eindhoven University of Technology Netherlands. R. Tóth is also affiliated to the Systems and Control Laboratory at the Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.

关键词： System Identification Continuous-Time Neural Ordinary Differential Equations Nonlinear State-Space

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：