检索结果-内蒙古大学图书馆

Online Parameterization of a Milling Force Model using an Intelligent System Architecture and Bayesian Optimization

Procedia CIRP 2022年 107卷 1041-1046页

作者： B. Schmucker F. Trautwein R. Hartl A. Lechler M.F. Zaeh A. Verl Institute for Machine Tools and Industrial Management (iwb Technical University of Munich) Boltzmannstr. 15 85748 Garching Germany Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW University of Stuttgart) Seidenstr 36 70174 Stuttgart Germany

This paper presents an efficient and industry-ready system architecture that enables both the control of machining operations and the high-frequency acquisition of controller data and external sensor signals. Using the recorded data, a dexel-based mechanistic cutting force model, which enables the estimation of cutting forces for complex tool geometries in arbitrary machining operations, is parameterized via an instantaneous cutting force identification method. In the introduced identification method, Bayesian Optimization and Dynamic Time Warping are combined to avoid time-consuming and error-prone synchronization of measurement and simulation. The suitability of this approach was demonstrated by performing cutting experiments at various radial depths of cut and feed rates per tooth. Thereby, a good agreement between simulation and measurement could be observed.

关键词： Industry 4.0 machine tools Data Analytics Process Simulation

来源：评论

学校读者我要写书评

暂无评论

Navigating the Low-Code Landscape: A Comparison of Development Platforms

Navigating the Low-Code Landscape: A Comparison of Developme...

引用

Conference on Model Driven engineering Languages and Systems Companion (MODELS-C)

作者： Jörg Christian Kirchhof Nico Jansen Bernhard Rumpe Andreas Wortmann Software Engineering RWTH Aachen University acronio GmbH Aachen Germany Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Stuttgart Germany

Low-code development is a software-development paradigm that can reduce the conceptual gap between application domain problem expertise and software engineering solution expertise. Hence, it might be a vital means to reduce the impact of the world-wide scarcity of software-developers. Consequently, many different low-code development platforms (LCDPs) have surfaced in the last 5–10 years, which domain experts must understand to chose the best-possible LCDP for their applications. This choice is not made restricting to front-end features of these LCDPs, but also to back-end features, which the domain experts are usually less familiar with. To support domain experts in making this decision, we have investigated popular LCDPs for features relevant to domain experts. Our findings aim to guide these domain experts, but also researchers in better understanding the landscape of LCDPs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An engineering methodology to assess the economic viability of edge-cloud automation systems in manufacturing

引用

Procedia CIRP 2023年 120卷 517-522页

作者： Marco Giani Nelly Frank Patrick Wiener Alexander Verl Robert Bosch GmbH Robert-Bosch-Campus 1 71272 Renningen Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 70174 Stuttgart Germany

The migration of industrial automation systems (IASs) to an edge-cloud hosted on factory premises can reduce the operation costs of a manufacturing line and increase its flexibility thanks to computation scalability and use of cloud-native operation concepts. However, the unclear assessment of costs of an edge-cloud automation system (ECAS) is a significant concern for manufacturing experts, which disincentives its adoption. An ECAS is expected to generate different costs than a traditional IAS, which depends on the requirements of the automation functions hosted in the edge-cloud. Because of this, methods to evaluate various realization concepts of an ECAS concerning their economic viability are required to support its engineering. In this paper, we provide a methodology that helps practitioners to define design specifications for an ECAS and assess their life-cycle costs (LCCs). To provide a robust and transparent LCCs assessment, we leverage the Monte Carlo method, which is a well-affirmed technique to address costs uncertainties. To do so, a cost model has been developed and implemented in a discrete-event simulator to calculate upfront and running costs of an ECAS. The application of the methodology is shown through an exemplar case study and its results are discussed. The presented work helps practitioners to evaluate whether an ECAS is economically viable for a manufacturing scenario, thus increasing the acceptance for this technology and fostering the transition towards flexible and smart manufacturing systems.

关键词： Edge-cloud computing edge-cloud automation engineering methods life-cycle costs

来源：评论

学校读者我要写书评

暂无评论

Analysis and comparison of optimization techniques supporting the engineering planning of reconfigurable robot cells

引用

Procedia CIRP 2023年 120卷 81-86页

作者： Marc Ungen David Kampert Oliver Riedel Robert Bosch Gmbh Robert-Bosch-Campus 1 71272 Renningen Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstr. 36 70174 Stuttgart Germany

The present paper studies the automated optimization of reconfigurable robot cells to support engineering planning activities. The specific type of reconfigurable robot cells under investigation allows an arbitrary arrangement of functional machine modules on a base plane accessible to the robotic manipulators. The research is motivated by the fast-growing configuration space of reconfigurable robot cells which results from the configurability of the cell layout and the performed workflows. Searching for optimized configurations within this configuration space is an iterative procedure which currently requires lots of manual efforts and expert assessment skills for each iteration. Performing many optimization iterations requires much time, which typically results in only a few performable iterations and thus in suboptimal configurations. To compensate for this, automated support for the underlying planning problem is required. The specific planning problem under investigation concerns finding motion-time optimized layout configurations for fixed workflows. This planning problem was chosen because of its strong association with the productivity of robot cells and the fact that it is the basis for further considerations on the influences of performed workflows. The main contribution of the research is a guideline concerning the decomposition of the mentioned optimization problem. This decomposition concerns the specific formulation of the optimization problem as well as its solving principle. The approach of the paper is to compare combinations of single- and multi-objective problem formulations as well as single- and multi-step solving procedures. Respective variants of evolutionary and conventional algorithms are tested for solving the optimization problems. The experiments are conducted using a specifically developed simulation and optimization framework which supports layout reconfiguration, robot path planning, and time parametrization based on state-of-the-art m

关键词： Reconfigurable robot cells Reconfigurable manufacturing systems engineering planning Optimization Adaptability

来源：评论

学校读者我要写书评

暂无评论

Robot machining of thin-walled workpieces with automatically reconfigurable fixturing through feature analysis

引用

Procedia CIRP 2023年 120卷 1065-1070页

作者： Andreas Schütz Armin Lechler Alexander Verl Jürgen Fleischer Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Seidenstrasse 36 70174 Stuttgart Germany Institute of Production Science (wbk) Karlsruhe Institute of Technology Gotthard-Franz-Straße 5 76131 Karlsruhe Gremany

Machining of large scale thin-walled workpieces pose high requirements for fixturing because of large stiffness changes due to material removal. Automatically reconfigurable fixtures that allow in-process reconfiguration are a promising approach. In this paper, an efficient approach based on feature analysis is proposed for fixture reconfiguration planning. For this, material removal is simulated. At discrete points in time, feature analysis is performed and an approximated local stiffness map is calculated with weight functions derived from the features’ parameterizations. Viable fixture configurations are then identified through root finding and validated through simulation in Ansys and experimentally with a fixture jig. In both validations, workpiece deformation for drilling operations could be reduced to an acceptable level enabling the implementation's future use in industrial application.

关键词： industrial robot robot machining fixture reconfigurable filexible

来源：评论

学校读者我要写书评

暂无评论

Assembly procedure generation for reconfigurable robot cells considering operation concurrency and geometrical constraints

Assembly procedure generation for reconfigurable robot cells...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Marc Ungen Elias Huber David Kampert Oliver Riedel Bosch Corporate Research Robert Bosch GmbH Renningen Germany Robert Bosch GmbH Stuttgart Germany the Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

The paper concerns the automated generation of optimized machine assembly procedures for reconfigurable robot cells (RRCs). RRCs are built from individual modules resulting in many possible structural configurations. For the optimization of production performance, assembly procedures must be generated to estimate objectives like productivity or cycle time. However, generating machine procedures is currently subject to manual planning and optimization which requires considerable time and effort. This leads to the investigation of few configuration concepts and thus poor optimization. The main contribution is a simulation-based approach to generate assembly procedures for RRCs. The approach solves the combinatorial problems of robot task assignment and assembly process sequencing jointly. The generation process minimizes the procedure duration by exploiting temporal concurrency while ensuring the geometrical feasibility of the individual robot motions. The paper further presents experimental results from a conducted case study with different RRC configuration concepts, robot synchronization and batch processing modes. The results reveal that significant production speedups can be achieved.

关键词： Concurrent computing Robot motion Productivity Sequential analysis Manuals Planning Synchronization Assembly Robots Optimization

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

arXiv

引用

arXiv 2024年

作者： Weigand, Jonas Beintema, Gerben I. Ulmen, Jonas Görges, Daniel Tóth, Roland Schoukens, Maarten Ruskowski, Martin Chair of Machine Tools and Control Systems RPTU Kaiserslautern The German Research Center for Artificial Intelligence Kaiserslautern Germany Group The Department of Electrical Engineering Eindhoven University of Technology Netherlands The Systems and Control Laboratory 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. © 2024, CC BY-SA.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Identifying machine times with OPC UA for Equipment as a Service (EaaS) – possibilities and limitations

引用

Procedia CIRP 2024年 130卷 578-583页

作者： Dimitri Evcenko Tonja Heinemann Holger Kett Armin Lechler Oliver Riedel Andreas Wortmann Institute of Human Factors and Technology Management (IAT) University of Stuttgart Nobelstraße 12 70569 Stuttgart Germany Institute for Control Engineering of Machine Tools and Manufacturing Units (ISW) University of Stuttgart Seidenstr. 36 70174 Stuttgart Germany Fraunhofer IAO Fraunhofer Institute for Industrial Engineering (IAO) Nobelstraße 12 70569 Stuttgart Germany

With Equipment as a Service (EaaS), subscription-based business models are becoming increasingly popular in mechanical and plant engineering. The main argument in favor for EaaS is a better overall equipment effectiveness (OEE) when a factory supplier operates the equipment. Therefore, the constant determination of the OEE in EaaS operations becomes crucial. This value is usually determined combining data retrieved from the equipment itself in combination with data from higher level systems like the manufacturing execution system (MES) of the customers. The latter are not accessible by the factory supplier. To bridge this information gap, the OEE of a piece of equipment is determined based solely on the available equipment data retrieved through data exchange standards such as the Open Platform Communications Unified Architecture (OPC UA). To achieve this, the time information needed to determine the OEE as defined in the ISO 22400-2 standard is either directly determined from OPC UA data from the machines or approximated through assumptions and exclusions. As an example for the mapping of equipment data to different time information, machine tools are focused and, hence, OPC UA 40501 and OPC UA 40001. In addition, the findings are analyzed regarding limitations in using the available time data via OPC UA. The mapping’s applicability is demonstrated with an exemplary use case and the OEE is compared when calculated only with equipment data retrieved via OPC UA with the OEE calculation having the additional information from a higher level system. This comparison allows to evaluate the uncertainty introduced by making assumptions and exclusions. The results are a valuable input to supplement the OPC UA Companion Specifications in order to cover the OEE determination in EaaS use cases.

关键词： Equipment as a Service (EaaS) OPC UA overall equipment effectiveness (OEE) machine monitoring

来源：评论

学校读者我要写书评

暂无评论

Towards learning digital twin: case study on an anisotropic non-ideal rotor system

arXiv

引用

arXiv 2024年

作者： Zhou, Zhibo Walther, Michael Verl, Alexander Robert Bosch GmbH Robert Bosch Campus 1 Renningen71272 Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Seidenstraße 36 Stuttgart70174 Germany

In the manufacturing industry, the digital twin (DT) is becoming a central topic. It has the potential to enhance the efficiency of manufacturing machines and reduce the frequency of errors. In order to fulfill its purpose, a DT must be an exact enough replica of its corresponding physical object. Nevertheless, the physical object endures a lifelong process of degradation. As a result, the digital twin must be modified accordingly in order to satisfy the accuracy requirement. This article introduces the novel concept of"learning digital twin (LDT)," which concentrates on the temporal behavior of the physical object and highlights the digital twin’s capacity for lifelong learning. The structure of a LDT is first described. Then, in-depth descriptions of various algorithms for implementing each component of a LDT are provided. The proposed LDT is validated on the simulated degradation process of an anisotropic non-ideal rotor system. © 2024, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Real-Time Model Adaption for Online Simulation at machine Level

Towards Efficient Real-Time Model Adaption for Online Simula...

引用

Intelligent Computing and control (IC&C), International Conference on

作者： Darius Deubert Zhibo Zhou Andreas Selig Alexander Verl Bosch Rexroth AG Lohr am Main Germany Corporate Sector Research and Advance Engineering Robert Bosch GmbH Renningen Germany Institute for Control Engineering of Machine Tools and Manufacturing Units University of Stuttgart Stuttgart Germany

ISBN: (数字)9798350351873

ISBN: (纸本)9798350351880

The simulation of components, machines or plants provides many benefits in today's manufacturing. Online simulation, in this context, means that a system is simulated in parallel to its operation. This is beneficial to extract relevant information from the system, which could be used for control, monitoring, service or maintenance of the industrial system. To ensure the reliability of online simulation, especially for dynamically changing behavior, an online adaption of the simulation models is necessary. Real process data and further observations should be used to track the real behavior with the online simulation. This requires metrics to compare simulation with reality, an appropriate triggering mechanism for the adaption, suitable parameter selection and estimation methods to determine optimal model parameters. There are a lot of mathematical tools, which could be considered to solve these problems. However, all of them have individual characteristics regarding their suitability for online simulation. This paper gives an overview of methods that are needed for online model adaption in form of a narrative review and assesses them based on their applicability for real-time online simulation. Furthermore, it addresses realization challenges and adaption of first-principle models. This work therefore provides a theoretical foundation for real-time model adaption for online simulation at machine level.

关键词： Measurement Adaptation models Reviews Estimation Real-time systems Mathematical models Manufacturing Maintenance Data mining Monitoring

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：