检索结果-内蒙古大学图书馆

2024 Panhellenic Conference on Electronics and Telecommunications, PACET 2024

作者： Mach, Jan Kohutka, Lukas Cicak, Pavel Slovak University of Technology Institute of Computer Engineering and Applied Informatics Slovakia Information Systems and Software Engineering Slovak University of Technology Institute of Informatics Slovakia

ISBN: (纸本)9798350318845

Fulfilling increasing performance demands of space and automotive applications can be problematic as high dependability is required. Memory is one of the most radiationsensitive parts, so it is often protected with information redundancy. This paper describes an integration of error correction and detection techniques into the interface of RISC-V processor to protect the data stored in the memory. We also provide a hardware-software interface for reporting errors and software routines for correcting data in memory. Our solution has a negligible impact (-3.9%) on the overall performance of the core with a small area and power consumption overhead. © 2024 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Lockstep Vs Microarchitecture: A Comparison 37

Lockstep Vs Microarchitecture: A Comparison

引用

37th IEEE International System-on-Chip Conference, SOCC 2024

作者： Mach, Jan Kohutka, Lukas Cicak, Pavel Slovak University of Technology Institute of Computer Engineering and Applied Informatics Bratislava842 16 Slovakia Slovak University of Technology Institute of Informatics Information Systems and Software Engineering Bratislava842 16 Slovakia

ISBN: (纸本)9798350377569

Safety/mission-critical applications require high dependability of the control systems. Their state-of-the-art protection approach is a system-level lockstep. This paper compares the system-level dual and triple lockstep technique to the microarchitecture-level protection of the Hardisc RISC-V core. For a fair comparison, each system is based on the same core(s) and integrates protection against bit-flips in memory and transient faults in the bus. We propose a fault injection methodology, combining pre-synthesis simulation with synthesis data to analyse the vulnerability of a system to faults. The fault injection campaigns show that the Hardisc can withstand fault rates orders of magnitude higher than the dual-core lockstep system while preserving the same area and power consumption. It comes with a 5% frequency penalty. We have shown that system failures are more frequent once the fault rate reaches an application-specific threshold (one fault in 100 clock cycles). © 2024 IEEE.

关键词： Failure rate

来源：评论

学校读者我要写书评

暂无评论

Automated Configuration of Behavior Models in Digital Twins based on a Knowledge-Graph 57

Automated Configuration of Behavior Models in Digital Twins ...

引用

18th IFAC Workshop on Time Delay systems, TDS 2024

作者： Dittler, Daniel Bodenstein, Frederike Hildebrandt, Gary Jazdi, Nasser Weyrich, Michael Institute of Industrial Automation and Software Engineering University of Stuttgart Pfaffenwaldring 47 Stuttgart70569 Germany Institute of Smart Systems and Services Pforzheim University of Applied Sciences Pforzheim Germany

A modular production plant can be simulated with different behavior models with varying modeling depths, thus enabling a wide variety of applications. However, the plant operator faces the challenge of linking the right models for his application. This contribution describes the need to adapt model configurations and associated challenges. Related approaches from the literature and standards are discussed. Subsequently, a novel modeling approach is presented that combines and extends the information from the analyzed approaches to enable automatic linking of model configurations. The approach is realized with the help of a knowledge-graph and evaluated using a material flow simulation scenario. © 2024 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Enhancing multiscale simulations with constitutive relations-aware deep operator networks

Enhancing multiscale simulations with constitutive relations...

引用

94th Annual Meeting of the International Association of applied Mathematics and Mechanics, GAMM 2024

作者： Eivazi, Hamidreza Alikhani, Mahyar Tröger, Jendrik-Alexander Wittek, Stefan Hartmann, Stefan Rausch, Andreas Institute for Software and Systems Engineering Clausthal University of Technology Clausthal-Zellerfeld Germany Institute of Applied Mechanics Clausthal University of Technology Clausthal-Zellerfeld Germany

Multiscale problems are widely observed across diverse domains in physics and engineering. Translating these problems into numerical simulations and solving them using numerical schemes, for example, the finite element method, is costly due to the demand of solving initial boundary-value problems at multiple scales. On the other hand, multiscale finite element computations are commended for their ability to integrate micro-structural properties into macroscopic computational analyses using homogenization techniques. Recently, neural operator-based surrogate models have shown trustworthy performance for solving a wide range of partial differential equations. In this work, we propose a hybrid method in which we utilize deep operator networks for surrogate modeling of the microscale physics. This allows us to embed the constitutive relations of the microscale into the model architecture and to predict microscale strains and stresses based on the prescribed macroscale strain inputs. Furthermore, numerical homogenization is carried out to obtain the macroscale quantities of interest. We apply the proposed approach to quasi-static problems of solid mechanics. The results demonstrate that our constitutive relations-aware DeepONet can yield accurate solutions even when being confronted with a restricted dataset during model development. © 2024 The Author(s). Proceedings in applied Mathematics & Mechanics published by Wiley-VCH GmbH.

关键词： Constitutive models

来源：评论

学校读者我要写书评

暂无评论

Control of Composite Manufacturing Processes Through Deep Reinforcement Learning 22

Control of Composite Manufacturing Processes Through Deep Re...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Stieber, Simon Heber, Leonard Obertscheider, Christof Reif, Wolfgang Institute for Software & Systems Engineering University of Augsburg Augsburg Germany University of Applied Sciences Wiener Neustadt Wiener Neustadt Austria

ISBN: (纸本)9798350345346

Resin transfer molding (RTM) is a composite manufacturing process that uses a liquid polymer matrix to create complex-shaped parts. There are several challenges associated with RTM. One of the main challenges is ensuring that the liquid polymer matrix is properly distributed throughout the composite material during the molding process. If the matrix is not evenly distributed, the resulting part may have weak or inconsistent properties. This is the challenge we tackle with the approach presented in this work. We implement an online control using deep reinforcement learning (RL) to ensure a complete impregnation of the reinforcing fibers during the injection phase, by controlling the input pressure on different inlets. This work uses this self-learning paradigm to actively control the injection of an RTM process, which has the advantage of depending on a reward function instead of a mathematical model, which would be the case for model predictive control. A reward function is more straightforward to model and can be applied and adapted to more complex problems. RL algorithms have to be trained through many iterations, for which we developed a simulation environment with a distributed and parallel architecture. We show that the presented approach decreases the failure rate from 54 % to 27 %, by 50 % compared to the same setup with steady parameters. © 2023 IEEE.

关键词： Control Reinforcement Learning Resin Transfer Molding

来源：评论

学校读者我要写书评

暂无评论

Automated Integration of External Data into Digital Twins for Manufacturing Processes 28

Automated Integration of External Data into Digital Twins fo...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Hildebrandt, Gary Habiger, Pascal Dittler, Daniel Drath, Rainer Weyrich, Michael Pforzheim University of Applied Sciences Institute of Smart Systems and Services Pforzheim Germany Stuttgart University Institute of Industrial Automation and Software Engineering Stuttgart Germany

ISBN: (纸本)9798350339918

In the era of Industry 4.0, data is becoming increasingly vital for future manufacturing and digital twin applications. Currently, primarily asset-created data is utilized, while the potential benefits of incorporating external data from connected production systems remain untapped. This underutilization is largely due to the complex and time-consuming nature of integrating external data. Automating this process could significantly improve efficiency and unlock valuable insights for more effective decision-making. In this paper, we present the requirements for a system aimed at automating the integration of external data, considering factors such as data heterogeneity and the need to support diverse communication protocols. We further introduce an assistant system that facilitates this automated integration, enhancing manufacturing processes and digital twin applications. Furthermore, we provide a prototypical implementation of the assistant system in the context of a collaborative robot utilizing information from its surroundings obtained through external camera and LiDAR imaging. By addressing the challenges of external data integration, this research contributes to the advancement of data-driven manufacturing and the optimization of digital twin technologies. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Dynamic Production Scheduling with Intelligent Products in a Modular Production System 28

Dynamic Production Scheduling with Intelligent Products in a...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Artelt, Maurice Dittler, Daniel Hildebrandt, Gary Braun, Dominik Jazdi, Nasser Weyrich, Michael University of Stuttgart Institute of Industrial Automation and Software Engineering Stuttgart Germany Pforzheim University for Applied Sciences Institute of Smart Systems and Services Pforzheim Germany

ISBN: (纸本)9798350339918

Industrial automation is driven by trends such as autonomy, intelligence and networking. Increasing energy demands, scarce resources and shorter product lifecycles pose challenges to production systems such as interoperability, flexibility and extensibility. The concept of the Digital Twin, acting as a virtual representation of a production system, can address these challenges. This paper presents a concept that realizes a dynamic production scheduling as partial function of the Digital Twin using the Asset Administration Shell and a service-oriented architecture. The authors specifically address automated asset production scheduling and propose an MQTT broker with a Functionality Dictionary server. Through the Asset Administration Shell interface, the proposed production scheduler communicates with the proposed product calendar to generate a specialized production schedule for each product. The evaluation scenario in a cyber-physical laboratory shows the advantages of this concept. © 2023 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Categorizing methods for integrating machine learning with executable specifications

引用

Science China(Information Sciences) 2024年第1期67卷 5-19页

作者： David HAREL Raz YERUSHALMI Assaf MARRON Achiya ELYASAF Department of Computer Science and Applied Mathematics Weizmann Institute of Science Department of Software and Information Systems Engineering Ben-Gurion University of the Negev

Deep learning(DL),which includes deep reinforcement learning(DRL),holds great promise for carrying out real-world tasks that human minds seem to cope with quite *** promise is already delivering extremely impressive results in a variety of ***,while DL-enabled systems achieve excellent performance,they are far from *** has been demonstrated,in several domains,that DL systems can err when they encounter cases they had not hitherto ***,the opacity of the produced agents makes it difficult to explain their behavior and ensure that they adhere to various requirements posed by human *** the other end of the software development spectrum of methods,behavioral programming(BP) facilitates orderly system development using self-standing executable modules aligned with how humans intuitively describe desired system *** this paper,we elaborate on different approaches for combining DRL with BP and,more generally,machine learning(ML) with executable specifications(ES).We begin by defining a framework for studying the various approaches,which can also be used to study new emerging approaches not covered *** then briefly review state-of-the-art approaches to integrating ML with ES,continue with a focus on DRL,and then present the merits of integrating ML with *** conclude with guidelines on how this categorization can be used in decision making in system development,and outline future research challenges.

关键词： machine learning artificial intelligence grey box learning domain knowledge rules behavioral programming deep reinforcement learning survey

来源：评论

学校读者我要写书评

暂无评论

A New RISC-V CPU for Safety-Critical systems 12

A New RISC-V CPU for Safety-Critical Systems

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Mach, Jan Kohutka, Lukas Cicak, Pavel Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava842 16 Slovakia Institute of Informatics Information Systems and Software Engineering Slovak University of Technology Bratislava842 16 Slovakia

ISBN: (纸本)9798350322910

In this paper, we propose a novel hardening technique against Single Event Effects, which enables high-frequency operation and does not cause large power consumption and area overhead. The protection is based on redundancy, separation of the pipeline into two main sections, and is fully applicable at Register Transfer Level. It provides fast detection of faults, simple recovery by a flush of the pipeline, and allows a large prediction unit to be unprotected. We present the protection scheme at the core with the RISC-V instruction set. Simulations confirm that the protection can handle the injected faults. Synthesis shows that protection lowers the maximum frequency by only 3.9%. The area increase is only 108% and can be even lower. Total power consumption increased by 119%. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Efficient integration of deep neural networks in sequential multiscale simulations

Efficient integration of deep neural networks in sequential ...

引用

93rd Annual Meeting of the International Association of applied Mathematics and Mechanics, GAMM 2023

作者： Tröger, Jendrik-Alexander Eivazi, Hamidreza Hartmann, Stefan Wittek, Stefan Rausch, Andreas Institute of Applied Mechanics Clausthal University of Technology Clausthal-Zellerfeld Germany Institute for Software and Systems Engineering Clausthal University of Technology Clausthal-Zellerfeld Germany

Multiscale computations involving finite elements are often unfeasible due to their substantial computational costs arising from numerous microstructure evaluations. This necessitates the utilization of suitable surrogate models, which can be rapidly evaluated. In this work, we apply a purely data-based deep neural network as a surrogate model for the microstructure evaluation. More precisely, the surrogate model predicts the homogenized stresses, which are typically obtained by the solution of (initial) boundary-value problems of a microstructure and subsequent homogenization. Furthermore, the required consistent tangent matrix is computed by leveraging reverse mode automatic differentiation. To improve data efficiency and ensure high prediction quality, the well-known Sobolev training is chosen for creating the surrogate model. This surrogate model is seamlessly integrated into a Fortran-based finite element code using an open-source library. As a result, this integration, combined with just-in-time compilation, leads to a speed-up of more than 6000×, as demonstrated in the example of a plate with a hole examined in this work. Furthermore, the surrogate model proves to be applicable even in load-step size controlled simulations, where it overcomes certain load-step size limitations associated with the microstructure computations. © 2023 The Authors. Proceedings in applied Mathematics & Mechanics published by Wiley-VCH GmbH.

关键词： Deep neural networks

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：