检索结果-内蒙古大学图书馆

Analysis of the acoustoelectric response of SAW gas sensors using a COM model

Microsystems & Nanoengineering 2024年第3期10卷 87-96页

作者： Yang Yuan Tao Yang Xi Chen Linglang Yu Xiaoxiao Hou Guangzu Zhang Wen Dong Zixiao Lu Honglang Li Leonhard Reindl Wei Luo School of Integrated Circuits Huazhong University of Science and Technology430074 WuhanPeople’s Republic of China CAS Center for Excellence in Nanoscience National Center for Nanoscience and Technology100190 BeijingPeople’s Republic of China Department of Microsystems Engineering Laboratory for Electrical Instrumentation and Embedded SystemsUniversity of Freiburg79110 FreiburgGermany Research Institute of Huazhong University of Science and Technology in Shenzhen 518057 ShenzhenPeople’s Republic of China

Surface acoustic wave(SAW)gas sensors based on the acoustoelectric effect exhibit wide application prospects for in situ gas ***,establishing accurate models for calculating the scattering parameters of SAW gas sensors remains a ***,we present a coupling of modes(COM)model that includes the acoustoelectric effect and specifically explains the nonmonotonic variation in the center frequency with respect to the sensing film’s sheet *** sensing parameters of the gas sensors,including the center frequency,insertion loss,and phase,were experimentally compared for accuracy and ***,the frequency of the phase extremum(FPE)shift was determined to vary monotonically,and the range of selectable test points was wide,making the FPE an appropriate response parameter for leveraging in SAW gas *** simulation results of the COM model were highly consistent with the experimental *** study is proposed to provide theoretical guidance for the future development of gas SAW sensors.

关键词： COM SAW establishing

来源：评论

学校读者我要写书评

暂无评论

ReACT: Reinforcement Learning for Controller Parametrization Using B-Spline Geometries

ReACT: Reinforcement Learning for Controller Parametrization...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Rudolf, Thomas Flögel, Daniel Schürmann, Tobias Süß, Simon Schwab, Stefan Hohmann, Sören FZI Research Center for Information Technology Embedded Systems and Sensors Engineering Department Karlsruhe76131 Germany Institute of Control Systems The Karlsruhe Institute of Technology Karlsruhe76131 Germany

ISBN: (纸本)9798350337020

Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. Furthermore, this work contributes actor regularizations that are relevant to real-world environments which differ from training. Accordingly, we apply dropout layer normalization to the actor and critic networks of the truncated quantile critic (TQC) algorithm. To show our approach's working principle and effectiveness, we train and evaluate the DRL agent on the parametrization task of an industrial control structure with parameter lookup tables. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Sustainable Energy Communities: Local Optimization of Battery Usage in P2P Energy Trading

Towards Sustainable Energy Communities: Local Optimization o...

引用

2023 IEEE International Conference on Omni-Layer Intelligent systems, COINS 2023

作者： Grob, Christoph Gehring, Florian Bringmann, Oliver FZI Research Center for Information Technology Karlsruhe Germany University of Tübingen Faculty of Science Embedded Systems Group Department of Computer Science Germany

ISBN: (纸本)9798350346473

As renewable energy resources are integrated into the power grid to address the global energy and climate crisis, local energy markets have emerged as a possible solution. In such markets, peers in a smart grid trade locally generated energy. To reduce the stress on the grid caused by the volatility of renewable energy sources, households use electric batteries to maximize their self-consumption of generated energy. In this paper, we propose a peer-To-peer trading platform that integrates batteries into the distributed energy management trading system. We show that local optimization of single households not only benefits the individual households in terms of increased self-consumption and financial gains but also has an overall positive impact on the energy community compared to a simple battery implementation. © 2023 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Robust Parameter Estimation and Tracking through Lyapunov-based Actor-Critic Reinforcement Learning 48

Robust Parameter Estimation and Tracking through Lyapunov-ba...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Rudolf, Thomas Ransiek, Joshua Schwab, Stefan Hohmann, Soren Fzi Research Center for Information Technology Embedded Systems and Sensors Engineering Karlsruhe Germany Karlsruhe Institute of Technology Institute of Control Systems Karlsruhe Germany

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

This work presents an approach for parameter estimation of nonlinear systems by means of robust maximum entropy offline reinforcement learning (RL). The identification of parameter variant systems is a challenging problem in industrial applications. We address the parameter estimation on disturbed measurements with an actor-critic RL agent that is extended by a Lyapunov neural network. Accordingly, a robust soft actor-critic algorithm (RSAC) is applied to the parametrization problem. The policy is learned on test trajectories and can be applied to identify nonlinear system parameter maps for comparable system dynamics across an operating range. In a simulative study, the performance of the proposed concept is shown for a permanent magnet synchronous machine model in the d/q-frame formulation with current dependent and nonlinear flux linkages. The trained RL agent is evaluated on a different nonlinear machine parameter set under noisy measurements. The results indicate applicability to real-world tasks such as system parameter tracking. © 2022 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

systems Engineering Approach for Compliant Over-the-Air Update Development

Systems Engineering Approach for Compliant Over-the-Air Upda...

引用

Recent Advances in systems Science and Engineering (RASSE), IEEE International Conference on

作者： Jacqueline Henle Stefan Otten Eric Sax Embedded Systems and Sensors Engineering (ESS) FZI Research Center for Information Technology Berlin Germany Embedded Systems and Sensors Engineering (ESS) FZI Research Center for Information Technology Karlsruhe Germany Institute for Information Processing Technologies (ITIV) Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (数字)9798331528263

ISBN: (纸本)9798331528270

A broad spectrum of technical innovations in-fluences the automotive industry. Vehicles are increasingly governed by software, enabling continuous development over the entire product life cycle. In this context, software updates, especially those conducted Over The Air (OTA), represent a significant technological advancement. Regularly implementing OTA updates enhances the sustainability of vehicles as they lead to the possibility of keeping cars continuously functional, safe, secure, and performant. Requirements for OTA updates, their development, and implementation are formulated in industry standards and regulations. With the entry into force of UN Regulation 156, manufacturers operating in the member countries must establish processes for the development and overall management of OTA updates. At the same time, there are numerous other standards that apply in the industry. Furthermore, development process models and standardized approaches, such as the V-model for systems and software engineering, are widely adopted. Following the aim to develop a framework that focuses on secure and efficient OTA updates while adhering to legal and industry-specific requirements, a unified process model is presented in this paper. Requirements from the ISO 24089 standard and the UN Regulation 156 are extracted for that purpose. Interrelationships and overlaps between them, and further applicable standards for vehicle design, system, and software development are identified. Processes and work products not yet covered by other norms and legal guidelines are extracted. These activities are then linked content-wise and organizationally to the established V-model. The resulting integrated concept provides a basis for compliant and efficient software update management.

关键词： Industries Technological innovation Law Wireless networks Software Regulation Modeling Sustainable development Standards Software engineering

来源：评论

学校读者我要写书评

暂无评论

Flexible Automotive Power Management: Formalization of an Auction-based Approach

Flexible Automotive Power Management: Formalization of an Au...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Tobias Schürmann Max Grobbel Sören Hohmann Embedded Systems and Sensors Engineering FZI Research Center for Information Technology Karlsruhe Germany Institute of Control Systems Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (数字)9798331541606

ISBN: (纸本)9798331541613

The electrification of former mechanical components and the expansion of infotainment systems lead to an increasing automotive power network (APN) in terms of components and power consumption. Additionally, customers desire a flexible hardware composition. As a consequence, automotive power management has to ensure power balancing for volatile generation and demand and to support the integration of new hardware during development, vehicle configuration, and even after production. In this paper, we propose an adapted management architecture, formalize an auction framework for automotive power management of APNs with multiple voltage levels, and show respective simulation results.

关键词： HVAC Power demand Power system management Simulation Voltage Propulsion Hardware Temperature control Resource management Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning in Lifestyle: Weight-In Image Classification using Convolutional Neural Networks

Application of Machine Learning in Lifestyle: Weight-In Imag...

引用

2022 IEEE International Conference on Agents, ICA 2022

作者： Asawaponwiput, Warisara Sriiesaranusorn, Panyawut Mohchit, Thawat Thatphithakkul, Nattanun Surangsrirat, Decho Information and Communication Technology for Embedded Systems Kasetsart University Bangkok Thailand Assistive Technology and Medical Devices Research Center National Science and Technology Development Agency Pathum Thani Thailand

ISBN: (数字)9781665469364

ISBN: (纸本)9781665469364

Nowadays, people are increasingly concerned for their health as being healthy is regarded as a profitable investment. Obesity is one of the most common health problems that leads to multiple diseases. We work with the team that developed a mobile application to encourage users to change their eating and activity behaviors to improve their health based on a virtual competition platform. Participants are required to upload a weight-in photo to verify their weight before the challenge. Manually verifying these images can be time-consuming and error-prone due to the large number of images in each competition. In this study, we proposed an image classification approach to help screen incorrect images of the weight-in photo for the virtual competition. The image augmentation techniques were applied to the training images before being input into the classification model. Since the goal is to deploy the model in a mobile application, the suitable model must be small and efficient enough for use in a limited resources environment. Therefore, VGGNet-16 and MobileNet-V2 were selected as the classification models. The experimental results show that the model could learn from the preprocessed images and obtain satisfactory classification results from pre-trained VGGNet-16 with the highest accuracy and F1-score of 95.00% and 95.23%, respectively. MobileNet-V2 inference time was approximately 10 times faster but the performance was lower with the highest accuracy and F1-score of 93.00% and 93.32%, respectively. © 2022 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries

arXiv

引用

arXiv 2024年

作者： Rudolf, Thomas Flögel, Daniel Schürmann, Tobias Süß, Simon Schwab, Stefan Hohmann, Sören Embedded Systems and Sensors Engineering department The FZI Research Center for Information Technology Karlsruhe76131 Germany The Institute of Control Systems The Karlsruhe Institute of Technology Karlsruhe76131 Germany

Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. Furthermore, this work contributes actor regularizations that are relevant to real-world environments which differ from training. Accordingly, we apply dropout layer normalization to the actor and critic networks of the truncated quantile critic (TQC) algorithm. To show our approach’s working principle and effectiveness, we train and evaluate the DRL agent on the parametrization task of an industrial control structure with parameter lookup tables. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Designing an embedded Human Activity Recognition System for a Kitchen Use Case Based on Machine Learning

A Method for Designing an Embedded Human Activity Recognitio...

引用

2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications technology, IAICT 2022

作者： Schroth, Marc Ilg, Andreas Kohout, Lukas Stork, Wilhelm FZI Research Center for Information Technology Dept. of Embedded Systems and Sensors Engineering Karlsruhe Germany Institute of Information Processing Technologies Karlsruhe Institute of Technology KIT Karlsruhe Germany

ISBN: (数字)9781665451260

ISBN: (纸本)9781665451260

Human activity recognition enables technical systems to analyse human behaviour in various settings. For example, it can be directly used to support the user in elder care, healthcare or training environments. Nevertheless, human activities are often times highly variable and therefore pose a challenge for any technical system to correctly classify and, even more importantly, generate a feedback that is valuable to the user. In this paper the process for designing a system that uses machine learning on the sensor node itself is presented in order to improve human activity recognition within a sensor network. Each sensor node of the network consists of a Bluetooth capable system on module and an accelerometer. The acceleration data is used to distinguish between several slicing techniques of different vegetables with the aim to help the network to distinguish the different dishes cooked with those vegetables. Various steps were taken to find the best possible machine learning model and sensor configuration to infer the cut vegetable on the sensor hardware, which is based on a standard microcontroller and therefore poses a challenge with its limited memory. Overall, the system is able to correctly infer the correct class most of the times while enabling a sufficient battery run time. Within this paper these steps and tests for the design and implementation of the embedded machine learning algorithm is described and its capability for activity recognition evaluated © 2022 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Threat Modeling to Design a Decentralized Health Data Management Application

Threat Modeling to Design a Decentralized Health Data Mana...

引用

International Conference on Information technology and systems, ICITS 2023

作者： Erler, Christina Hu, Shanshan Danelski, Alexa Stork, Wilhelm Sunyaev, Ali Gersch, Martin Embedded Systems and Sensors Engineering FZI Research Center for Information Technology Karlsruhe76131 Germany Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Karlsruhe76131 Germany Department of Information Systems Free University of Berlin Berlin14195 Germany Institute for Information Processing Technologies Karlsruhe Institute of Technology Karlsruhe76131 Germany

ISBN: (纸本)9783031332609

Decentralized applications are increasingly recognized as efficient tools to overcome security challenges in the management of highly sensitive health information. However, research still lacks the understanding of how to address the complex security challenges in the design of health data management applications (HDMAs). In this study, we structurally analyzed security requirements of health data management systems to improve the efficiency of their design. We leveraged threat modeling to inform the design of HDMAs and proposed the system architecture accordingly to facilitate the security of interorganizational health data exchange. Our results contribute to the exaptation of threat modeling to the innovative design of decentralized applications for health data management and to the exploration of benefits of decentralization for healthcare. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information management

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：