检索结果-内蒙古大学图书馆

18th IFAC Workshop on Time Delay systems, TDS 2024

作者： Deubert, Darius Selig, Andreas Verl, Alexander Bosch Rexroth AG Bgm.-Dr.-Nebel-Straße 2 Lohr am Main97816 Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart70049 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. © 2024 The Authors.

关键词： Smart manufacturing

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 32

Adaptive CAM planning to support co-design in the building i...

引用

32nd CIRP Design Conference, CIRP Design 2022

作者： Reichle, Alexander Ellwein, Carsten Verl, Alexander Institute For Control Engineering Of Machine Tools And Manufacturing Units University Of Stuttgart Seidenstr. 36 StuttgartD-70174 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. © 2022 The Authors.

关键词： Computer aided manufacturing

来源：评论

学校读者我要写书评

暂无评论

Test-Driven Reward Function for Reinforcement Learning: A Contribution towards Applicable machine Learning Algorithms for Production systems 15

Test-Driven Reward Function for Reinforcement Learning: A Co...

引用

15th CIRP Conference on Intelligent Computation in manufacturing engineering, ICME 2021

作者： Jaensch, Florian Kübler, Karl Schwarz, Elmar Verl, Alexander Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidentraße 36 StuttgartD-70174 Germany

Reinforcement Learning algorithms find more and more application in fields where complex tasks need to be solved. The automation of production systems is one of those fields. Normally, programming a control system defines the automation strategy. Previous contributions by the authors have shown that a so-called agent can learn automation strategies for production systems using a Reinforcement Learning setup. However, the development of the reward function for the agent can be challenging and needs Reinforcement Learning domain knowledge. This paper introduces a novel approach in combining Test-Driven Development with Reinforcement Learning in order to solve the problem of a suitable reward function. In the presented approach predefined test cases are used to derive rewards for the agent. The use of an automated test framework allows for continuous learning sequences until all test cases are passed. An application example of a robot cell is used to demonstrate the novel approach and verify its suitability and usability. The first application shows promising results for further examination towards more application scenarios. © 2022 The Author(s).

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Ambiguity Tolerant Commissioning Ontology: From an upper ontology to a domain specific implementation 15

Ambiguity Tolerant Commissioning Ontology: From an upper ont...

引用

15th CIRP Conference on Intelligent Computation in manufacturing engineering, ICME 2021

作者： Ellwein, Carsten Hekeler, Marc Riedel, Oliver Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 StuttgartD-70174 Germany

There are no standardized interfaces or descriptions for the outsourcing of production orders, e.g. through cloud manufacturing. For this reason, an upper ontology was developed in a preliminary work;associated models describe the entire process and parameters from the request for quotation over its return to the conclusion of the contract. Products can either be described by their final state or by the initial product in conjunction with the applied processes. In this paper, the process from this upper ontology to a concrete implementation is further elaborated and a middleware is introduced which offers a machine-readable interface to edit the ontology as well as various validation options are addressed. © 2022 Elsevier B.V.. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Offline and Online Energy Simulation using Virtual Commissioning Models with Extended Dynamical Behavior

Offline and Online Energy Simulation using Virtual Commissio...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Deubert, Darius Pfeifer, Denis Scheifele, Christian Fehr, Jorg Verl, Alexander Bosch Rexroth AG Lohr am Main97816 Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart70174 Germany ISG Industrielle Steuerungstechnik GmbH Stuttgart70563 Germany Institute of Engineering and Computational Mechanics University of Stuttgart Stuttgart70174 Germany

ISBN: (纸本)9798331531614

Considering energy consumption and dynamical behavior within the simulation of manufacturing systems emerges as an important objective for their development, commissioning, and operation. Currently, these aspects are often neglected in many fields including virtual commissioning. This work presents an approach to extend highly detailed virtual commissioning models of components from industrial automation by dynamics models for the calculation of energy consumption in an offline simulation and for reuse in an online simulation. To validate the presented approach, an exemplary offline virtual commissioning simulation of a pick-and-place robot application is implemented and subsequently transferred to an online simulation. The validation shows a good accuracy of the simulated energy consumption, enabling virtual commissioning engineers to analyze and optimize energy consumption already in the design phase of manufacturing systems. Additionally, the dynamical behavior was well reflected in the online simulation, contributing to the capability of simulation in the operation phase. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Introduction of an industrial transfer learning use case systematization for machine tools 56

Introduction of an industrial transfer learning use case sys...

引用

56th CIRP International Conference on manufacturing systems, CIRP CMS 2023

作者： Netzer, Markus Michelberger, Jonas Puchta, Alexander Verl, Alexander Fleischer, Jürgen wbk Institute of Production Science Karlsruhe Institute of Technology Kaiserstraße 12 Karlsruhe76131 Germany ISW Institute for Control Engineering of Machine Tools and Manufacturing Units Keplerstraße 7 Stuttgart70174 Germany

Traditional intelligent systems such as fault detection are mainly developed for isolated use on single machines and are mostly trained individually. A cross-machine knowledge transfer of intelligent systems holds an immense potential and can reduce implementation effort of intelligent systems. To enable a structured analysis of real-world transfer problems, an industry-relevant, far-reaching systematization of typical machine tool use cases is developed. This provides the overview over different typical use case classes from the industrial use case perspective. Based on the derived transfer criteria of each use case class, a conceptual approach of concrete transfer methods is proposed. © 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 transfer learning knowledge transfer machine tools Transfer learning transfer learning systemization

来源：评论

学校读者我要写书评

暂无评论

Semantic Integration and Interdisciplinary Collaboration in Production Planning: A Graph-Based Approach for Enhanced Data Consistency 57

Semantic Integration and Interdisciplinary Collaboration in ...

引用

18th IFAC Workshop on Time Delay systems, TDS 2024

作者： Dausch, Valesko Lentes, Joachim Riedel, Oliver Kreimeyer, Matthias Institute for Engineering Design and Industrial Design University of Stuttgart Pfaffenwaldring 9 StuttgartDE-70569 Germany Fraunhofer Institute for Industrial Engineering Nobelstrasse 12 StuttgartDE-70569 Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstrasse 36 StuttgartDE-70174 Germany

Based on increasing individualization, shorter innovation cycles and integrating services into products complexity in the development of products and production processes increases. In combination with digitalization, this results in an increased need for interdisciplinary work. A high level of data consistency is required to cope with the resulting diverse and complex data structures, leading to the need for a consistent data model that orchestrates information flows. PLM-systems fall short in their ambition of reaching an overarching data management across the product lifecycle. This results in a lot of administrative work in planning instead of value-adding as well as in inconsistencies and incomplete change processes. To improve interdisciplinary collaboration in production planning, goal of this work is to develop a method leading to a comprehensive data model and to show it's applicability by means of a case study. The steps of the research performed follow the typical circle of action research: diagnosis, planning, action, evaluation, and reflection. The data model resulting of the application of the method uses semantics to make relationships understandable for both humans and machines. This is necessary for downstream automation and the use of artificial intelligence. The three essential steps of the method are, firstly, an as-is modeling of the processes of interest. Then, the process models are used to evaluate the consistency and efficiency of the planning processes. The method is completed by a guideline for setting up the data model. The proposed approach aims to improve efficiency and quality in assembly planning processes, resulting in its importance for industrial companies. © 2024 The Authors.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

Towards an Implementation of Simulation Based Digital Twins in Cyber-Physical Production systems Environments

Towards an Implementation of Simulation Based Digital Twins ...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Shan Fur Samed Ajdinović Armin Lechler Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Germany

The increasing digitization of the manufacturing industry offers a wide range of opportunities for the effective use of production data, which can lead to significant time and cost savings. One promising approach is the use of synchronous simulations during the actual operation of cyber-physical production systems (CPPS) to provide valuable insights into possible performance improvements and at the same time reduce the risk of costly downtime. This paper presents a novel concept that enables structured storage of CPPS production data as part of a digital twin that serves as a virtual replica of the physical production environment. In particular, this approach is based on the Asset Administration Shell (AAS), which provides a comprehensive framework for the management of production data and allows for a seamless integration with simulation models. Storing production data in a structured and standardized format can make data queries efficient, facilitate data processing, and provide a solid foundation for simulation model development, calibration, and validation. These simulation models can then be used to identify potential process improvements and test different scenarios, minimizing the risk of disruption to actual production.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of a Lumped-Parameter-Model for a Dual-Motor Robotic Drive Train with Backlash and Electrical Preload

Identification of a Lumped-Parameter-Model for a Dual-Motor ...

引用

International Symposium on Power Electronics, Electrical Drives, Automation and Motion, SPEEDAM

作者： Benedikt Kaiser Adrian Schäfer Andreas Schütz Nejila Parspour Armin Lechler Alexander Verl Institute of Electrical Energy Conversion Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany

ISBN: (数字)9798350387599

ISBN: (纸本)9798350387605

The mechanical interface of rotating robot joints require torque to speed ratios that are not suitable for an elec-tromagnetic direct drive. Typically, gearboxes are used to convert torque and speed, although these introduce non-linear backlash into the system. By using a dual-motor drive train, it is possible to electrically preload the gearbox and compensate for the backlash. In order to describe the system dynamics, a lumped-parameter-model is presented for which the parameters are determined to represent an experimental setup. Measurements are carried out in various coupling scenarios and the associated parameters of the subsystems of the models are identified. The measurement and the model are further adapted through optimization. Based on the evaluated transfer functions, the model is able to describe the basic behavior of the system. The measurements with coupled motors and activated preload indicate persistent differences from the actual system. However, the presented model may be applied in simulation and control to improve the dynamics of a dual-motor robot drive train with backlash-prone gearing and the possibility of electrical preload.

关键词： Couplings Adaptation models Transient response Torque System dynamics Transfer functions Electric variables measurement

来源：评论

学校读者我要写书评

暂无评论

Software-defined manufacturing: Data Representation

引用

Procedia CIRP 2023年 118卷 360-365页

作者： Carsten Ellwein Rebekka Neumann Alexander Verl Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstraße 36 70174 Stuttgart Germany

Due to constantly decreasing product cycles, a fast adaptability of manufacturing plants is a prerequisite for profitable operation. The paradigm of Software-defined manufacturing (SDM) pursues this overriding goal by decoupling software from mechanical and electrical components. In this way, SDM allows the free definition of functionality, purely through software, limited only by the physical limitations of the machines and systems. This paper analyzes existing approaches that pursue the goal of digitally representing manufacturing to enable flexible adaptation. Based on this analysis, a model for the data representation is proposed that allows consistent use across the entire supply chain.

关键词： Software defined manufacturing Data representation manufacturing ontology

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：