检索结果-内蒙古大学图书馆

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Paweł Pawłowski Rafał Długosz Marek Radkowski Mateusz Wątły Adam Dąbrowski Faculty of Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Signal Processing and Electronic Systems Poznań University of Technology Poznań Poland Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

The paper presents project and its verification of a prototype integrated circuit containing an analog, programmable finite impulse response (FIR) filter, implemented in CMOS 350 nm technology. The structure of the filter is based on the switched capacitor technique. In circuits of this type, one of main challenges is an efficient implementation of filter coefficients, which result from several factors described in this work. When implementing such filters as programmable circuits, the values of their coefficients have to be limited to a selected range, i.e. a given resolution in bits. In the implemented prototype filter, the filter coefficients are represented by 6 bits in sign-magnitude notation, so they can take 63 different values only. In such filters, it is not possible to directly implement any frequency response of the filter. Each time, it is necessary to properly round the theoretical values of the coefficients so that they fit into the available range of discrete values resulting from the implementation. The authors of the work designed an algorithm that allows such matching. The paper also presents results of measurements of the prototype chip.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Space Augmentation and Old Class Space Preservation for Class Incremental Learning

Feature Space Augmentation and Old Class Space Preservation ...

引用

第42届中国控制会议

作者： Ming Zeng Siying Li Jiazhe Liu Yuanhao Li Institute of Robotics and Automation Systems Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University

The ability of continuously learning new knowledge without forgetting old ones is crucial to adapt to an ever-changing world. This scenario becomes more challenging when the previous data are not available. Current class incremental learning(CIL) approaches tend to incorporate new classes with backward compatibility, i.e., maintaining discriminability of old ones. By contrast, we focus on the extensibility and compatibility for future new classes in the early stage. Our proposed method achieves this by augmenting feature space. In detail, a large number of pseudo-new classes are generated via real example mixture and then train the initial spatially augmented model using pseudo-new classes and the base classes. Besides, considering the fact that it is impossible to maintain backward compatibility with only one prototype for each old class, the updated model also needs to preserve old class space in incremental stages. We employ a certain perturbation to the old class prototypes to effectively avoid old class space from being over-squeezed by the samples of new classes. The experiments on CIFAR-100 and ImageNet-Subset(100 classes) demonstrate that our method substantially reduces the overlap of old and new classes, outperforming state-of-the-art various baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Soft Sensors for Industrial Applications: Comparison of Variables Selection Methods and Regression Models

Soft Sensors for Industrial Applications: Comparison of Vari...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Joana Leiria Rodrigo Salles Jérôme Mendes Pedro Sousa Department of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Coimbra Portugal Oncontrol Technologies Rua Cidade Poitiers Coimbra Portugal

The digitalization of industrial environments has enabled the development of tools that make the production process more efficient and safer. In this sense, the Soft Sensor (SS) plays a fundamental role. Through historical data and indirect measurements, it is possible to estimate the value of important variables that are difficult to measure. This paper presents the SS development process: data collection and pre-processing, variable selection, model selection for SS implementation, model training and testing, and performance evaluation. The selection of variables was made with the help of Pearson Correlation, Mutual Information, and fastTracker algorithm techniques. For the implementation of SS have been tested several models: Multiple Linear Regression, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Elastic Net, Support Vector Regression and Gaussian Mixture Models. Four datasets were used to test the development of the SS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recyclable thin-film soft electronics for smart packaging and e-skins

arXiv

引用

arXiv 2025年

作者： Carneiro, Manuel Reis de Almeida, Aníbal T. Tavakoli, Mahmoud Majidi, Carmel Soft Machines Lab Department of Mechanical Engineering Carnegie Mellon University PittsburghPA15213 United States Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra3030-290 Portugal

Despite advances in soft, sticker-like electronics, few efforts have dealt with the challenge of electronic waste. Here, we address this by introducing an eco-friendly conductive ink for thin-film circuitry composed of silver flakes (Ag) and a water-based polyurethane (WPU) dispersion. This ink uniquely combines high electrical conductivity (1.6x105 S/m), high resolution digital printability, robust adhesion for microchip integration, mechanical resilience, and recyclability. Recycling is achieved with an ecologically-friendly processing method to decompose the circuits into constituent elements and recover the conductive ink with a decrease of only 2.4% in conductivity. Moreover, adding liquid metal enables stretchability of up to 200% strain, although this introduces the need for more complex recycling steps. Lastly, we demonstrate on-skin electrophysiological monitoring biostickers along with a recyclable smart package with integrated sensors for monitoring safe storage of perishable foods. © 2025, CC BY-NC-ND.

关键词： Electronic Waste

来源：评论

学校读者我要写书评

暂无评论

Emergency Clinical Procedure Detection via Wearable Sensors

引用

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2022年第1期66卷 2239 - 2243页

作者： Prakash Baskaran Jamison Heard Julie A. Adams Collaborative Robotics and Intelligent Systems Institute Oregon State University Corvallis OR Department of Electrical and Microelectronic Engineering Rochester Institute of Technology NY

Communicating a patient’s state accurately during transfer from emergency medical technicians to hospital personnel is crucial for optimal care. Prior work demonstrated automated algorithms that combined wearable sensors with video data from cameras to detect clinical procedures and improve this information transfer. However, incorporating video requires task-or environment-specific installation mechanisms, raises privacy concerns, and is susceptible to occlusion and image noise. The presented approach detects clinical procedures using wearable sensors (i.e., inertial and electrophysiological) only and the procedures’ subtasks to mitigate the sensors’ signal variability to provide clinical procedure detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed operational management of microgrids: a second order dual update approach

引用

IFAC-PapersOnLine 2023年第2期56卷 1540-1545页

作者： Giulio Ferro Michela Robba Federico Delfino Rabab Haider Anuradha M. Annaswamy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA 02141 USA Department of of Electrical Electronic Telecommunications Engineering and Naval Architecture University of Genova

This paper develops a Distributed Energy Management System (EMS) to optimally allocate electric and thermal power production in a polygenerative microgrid. The EMS problem is formulated as a multiperiod convex optimization problem and solved using AL-SODU, a new distributed algorithm based on the augmented Lagrangian method with second order dual updates. The proposed AL-SODU algorithm significantly outperforms state of the art algorithms employing first order dual updates, with 15-times speedup in convergence speed. A case study of the EMS based on AL-SODU is conducted on the Smart Polygeneration Microgrid (SPM) located on the Savona Campus of University of Genova (Italy). The EMS determines the optimal schedules for electric and thermal power plants every 15-minutes. This real time scheduling of the microgrid is enabled by the Al-SODU algorithm, which solves the scheduling problem in 1.86s.

关键词： Microgrids distributed control second order methods

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-Optimized Convolutional Neural Network Controller for Enhanced Performance of Boost DC-DC Converters

引用

Journal of electrical engineering & Technology 2025年 1-17页

作者： Liu, Quancheng Ali, Amjad Alkhayyat, Ahmad Gansu Institute of Architectural Design and Research Co. Ltd Lanzhou City Gansu Province China Interdisciplinary Research Center for Sustainable Energy Systems (IRC-SES) King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Electrical Engineering Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Babylon Babylon Iraq

This paper introduces an innovative control strategy for Boost DC-DC converters utilizing a genetic algorithm-optimized convolutional neural network (GA-CNN) to significantly improve dynamic performance and stability. The proposed method incorporates genetic algorithms to identify optimal hyperparameters and network architectures, allowing the CNN controller to efficiently manage voltage regulation and address the nonlinearities commonly associated with Boost converters. By leveraging real-time data on inductor current, capacitor voltage, and output voltage error, the GA-CNN controller exhibits rapid convergence and enhanced transient response when compared to traditional control methods. Comprehensive experimental evaluations and simulations demonstrate the robustness and efficiency of the proposed approach, showcasing its superiority in achieving reduced settling times and minimal overshoot under varying load and input voltage conditions. The findings underscore the potential of the GA-CNN methodology for high-performance applications in power electronics, paving the way for further advancements in adaptive control strategies within this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Camera View Planning Based on Deep Reinforcement Learning in Indoor Exploration

Active Camera View Planning Based on Deep Reinforcement Lear...

引用

第42届中国控制会议

作者： Hao-Yu Wang Qing-Hao Meng Xu-Yang Dai Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and SystemSchool of Electrical and Information Engineering Tianjin University

In the last decades, significant progress has been made in the field of active vSLAM（visual simultaneous localization and mapping）. However, the majority of active vSLAM methods suffer from the problem of coupling the camera's viewpoint to the robot's motion, which limits the initiative during the exploration of unknown environments. To address this issue, this study proposes a camera view planning method based on deep reinforcement learning（DRL）, which makes the camera rotate independently. First, feature encoding is performed on the reconstructed navigation map using a multi-layer convolutional neural network（CNN）. Second, the DRL-based camera view planning method is trained through the proximal policy optimization（PPO）algorithm. Last, a significant number of tests is performed on a public dataset of indoor environments. The simulation results show that the proposed camera view planning method improves the exploration coverage by an average of 4%（33.86 m for traditional vs. 35.21 m for the suggested method）. Meanwhile, the kind of semantic information newly observed in each step increases by 21%（2.9 for traditional vs. 3.5 for the proposed method） on average, indicating the improvement in the efficiency of information acquisition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Compliant Robot-Assisted Mold Polishing Application Using the Franka Emika Robot

A Compliant Robot-Assisted Mold Polishing Application Using ...

引用

Annual Conference of Industrial Electronics Society

作者： Michael Christopher Xenya Rui Cortesão Electrical and Computer Engineering Department Institute of Systems and Robotics University of Coimbra Coimbra Portugal FOE GCTU PMB100 Accra Ghana

Metal mold casting for many application areas remains imperfect since this involves the control of numerous factors that affect workpiece quality. Surface roughness which remains one of the many issues related to metal mold cast is often mitigated by means of grinding and polishing. As many attempts are being made to address this challenge through robot-assisted techniques, we focus on rapid mold polishing using the Franka Emika (FE) robot and its programming resources, including a built-in impedance control architecture. To accomplish the objective, mold surface segmentation is necessary. For each segment, the polishing approach is based on surface normals, relative motion, and torque sensor data. Results were obtained with open platform communication-unified architecture (opc-ua) client and server that record torque and force data. Results show that tuning internal impedance control parameters for polishing tasks is feasible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compensation Control of PMSMs Based on a High-order Sliding Mode Observer with Inertia Identification

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Li, Ke Ding, Jie Sun, Xiaodong Lei, Gang Dianov, Anton Demidova, Galina Prakht, Vladimir Jiangsu University School of Electrical and Information Engineering Zhenjiang212013 China Jiangsu University Automotive Engineering Research Institute Zhenjiang212013 China University of Technology Sydney School of Electrical and Data Engineering NSW2007 Australia Wenzhou University Pingyang Institute of Intelligent Manufacturing Wenzhou325035 China ITMO University Faculty of Control Systems and Robotics Petersburg197101 Russia Ural Federal University Department of Electrical Engineering Ekaterinburg620062 Russia

This article proposes a new sliding mode control (NSMC) reaching law to improve the speed tracking and anti-interference performance of permanent magnet synchronous motors (PMSMs). The NSMC improves the sliding mode control (SMC) in approaching speed and reducing chattering. Firstly, considering that the external load interference will adversely affect the control system, a high-order sliding mode observer (HOSMO) is designed to observe the load torque, and the observed value is compensated to the output of the speed controller. Then, combined with the Landau algorithm, a variable adaptive gain algorithm is introduced to decrease the impact of inertia mismatch on the system control performance. The algorithm identifies the rotational inertia online, reduces the effect of load disturbance on the identification performance, and updates the identification results to the observation in processors and controllers. Experimental results show that the proposed control method reduces the speed and current fluctuations of the system when load torque and inertia vary and improves the system's robustness. © 2013 IEEE.

关键词： Permanent magnets

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：