检索结果-内蒙古大学图书馆

A computationally Efficient Learning-Based Control of a Three-Phase AC/DC Converter for DC Microgrids

ENERGIES 2025年第9期18卷 2383-2383页

作者： Li, Ran Feng, Wendong Qie, Tianhao Liu, Yulin Fernando, Tyrone Iu, Herbert HoChing Zhang, Xinan Univ Western Australia Dept Elect Elect & Comp Engn Perth WA 6009 Australia

This paper presents a novel learning-based control algorithm for three-phase AC/DC converters, which are key components in DC microgrids, for reliable power conversion. In contrast with conventional model-based nonlinear controllers that rely on detailed system modeling and manual gain tuning, the proposed method is model-free and eliminates such dependencies. By integrating a recurrent equilibrium network (REN), the controller achieves an enhanced dynamic response and robust steady-state performance, while maintaining a low computational complexity. Moreover, its closed-loop stability can be rigorously verified based on contraction theory and incremental quadratic constraints. To facilitate practical implementation, a design guideline is provided. Experimental results confirm that the proposed method outperforms conventional PI and model predictive controllers in terms of response speed, harmonic suppression, and robustness under parameter variations. Additionally, the algorithm is lightweight enough for real-time execution on embedded platforms, such as a TI DSP.

关键词： three-phase AC/DC converter learning-based control low computational complexity stability

来源：评论

学校读者我要写书评

暂无评论

Nonnegative graph embedding induced unsupervised feature selection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 282卷

作者： Mi, Yong Chen, Hongmei Yuan, Zhong Luo, Chuan Horng, Shi-Jinn Li, Tianrui Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Minist Educ Engn Res Ctr Sustainable Urban Intelligent Transpo Chengdu 611756 Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data Appl Chengdu 611756 Peoples R China Southwest Jiaotong Univ Mfg Ind Chains Collaborat & Informat Support Techn Chengdu 611756 Peoples R China Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Asia Univ Dept Comp Sci & Informat Engn Taichung 41354 Taiwan

Recently, many unsupervised feature selection (UFS) methods have been developed due to their effectiveness in selecting valuable features to improve and accelerate the subsequent learning tasks. However, most existing UFS methods suffer from the following three drawbacks: (1) They usually ignore the nonnegative attribute of feature when conducting feature selection, which inevitably loses partial information;(2) Most adopt a separate strategy to rank all features and then select the first k features, which introduces an additional parameter and often obtains suboptimal results;(3) Most generally confront the problem of high time-consuming. To tackle the previously mentioned shortage, we present a novel UFS method, i.e., Nonnegative Graph Embedding Induced Unsupervised Feature Selection, which considers nonnegative feature attributes and selects informative feature subsets in a one-step way. Specifically, the raw data are projected into a low-dimensional subspace, where the learned low-dimensional representation keeps a nonnegative attribute. Then, a novel scheme is designed to preserve the local geometric structure of the original data, and l(2,0) norm is introduced to guide feature selection without ranking and selecting processes. Finally, we design a high-efficiency solution strategy with low computational complexity, and experiments on real-life datasets verify the efficiency and advancement compared with advanced UFS methods.

关键词： Unsupervised feature selection Nonnegative attribute One-step way l(2,0) norm low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Generalised predictive controller (GPC) design on single-phase full-bridge inverter with a novel identification method

引用

IET CONTROL THEORY AND APPLICATIONS 2023年第3期17卷 284-294页

作者： Memeghani, Mehran Jelodari Ghamari, Seyyed Morteza Jouybari, Taha Yousefi Mollaee, Hasan Wheeler, Patrick Semnan Univ Fac Elect & Comp Engn Semnan Iran Shahrood Univ Technol Fac Elect & Comp Engn Shahrud Iran Tabriz Univ Fac Elect & Comp Engn Tabriz Iran Univ Nottingham Fac Elect & Control Engn Nottingham England

The design of an on-line generalised predictive control (GPC) technique with a novel identification method is presented in this paper for a single-phase full-bridge inverter in the presence of different disturbances. The controller uses system discrete-time model to reach the control variables with a prediction over these values, followed by computing a cost function for control aims. However, in this controller, the need for the mathematical model of the system is removed since the black-box identification strategy is used. Moreover, GPC structure has many advantages including low computational complexity, systematic design procedure, and fixed switching frequency that makes it a good alternative for practical applications. Various disturbances can have a negative impact on a DC-AC inverter;thus, considering robust dynamics and ease of implantation, the GPC scheme is used along with an improved exponential regressive least square identification algorithm as an adaptive strategy in the controller. Moreover, the prediction horizons of this controller have been increased, resulting in its low steady-state error and better performance. Furthermore, harmonics in the sinusoidal signal can decrease the total efficiency of the system;thus, an LC filter is used to reduce the level of total harmonic distortion. However, the stability of the filter is the most challenging issue in designing a suitable controller. Finally, the strength of the current controller is verified using experimental and simulations results.

关键词： robust dynamics low computational complexity control variables invertors GPC scheme harmonic distortion different disturbances DC-AC inverter control aims generalised predictive controller design DC-AC power convertors (invertors) mathematical model suitable controller prediction horizons black-box identification strategy Optimal control control system synthesis system discrete-time model computational complexity single-phase full-bridge inverter Control of electric power systems Current control current controller systematic design procedure Power electronics, supply and supervisory circuits Control system analysis and synthesis methods electric current control predictive control least squares approximations GPC structure on-line generalised predictive control technique novel identification method improved exponential regressive least square identification algorithm

来源：评论

学校读者我要写书评

暂无评论

Superposition Signal Input Decoding for Lattice Reduction-Aided MIMO Receivers

引用

IEICE TRANSACTIONS ON COMMUNICATIONS 2023年第2期E106B卷 184-192页

作者： Denno, Satoshi Kashihara, Koki Hou, Yafei Okayama Univ Grad Sch Nat Sci & Technol Okayama 7008530 Japan

This paper proposes a novel approach to low complexity soft input decoding for lattice reduction-aided MIMO receivers. The pro-posed approach feeds a soft input decoder with soft signals made from hard decision signals generated by using a lattice reduction-aided linear detec-tor. The soft signal is a weighted-sum of some candidate vectors that are near by the hard decision signal coming out from the lattice reduction-aided linear detector. This paper proposes a technique to adjust the weight adapt to the channel for the higher transmission performance. Furthermore, we propose to introduce a coefficient that is used for the weights in order to enhance the transmission performance. The transmission performance is evaluated in a 4 x 4 MIMO channel. When a linear MMSE filter or a serial interference canceller is used as the linear detector, the proposed technique achieves about 1.0 dB better transmission performance at the BER of 10-5 than the decoder fed with the hard decision signals. In addition, the low computational complexity of the proposed technique is quantitatively eval-uated.

关键词： soft decision weighted sum lattice reduction linear detectors low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Sparse and robust SVM classifier for large scale classification

引用

APPLIED INTELLIGENCE 2023年第16期53卷 19647-19671页

作者： Wang, Huajun Shao, Yuanhai Changsha Univ Sci & Technol Dept Math & Stat Changsha Peoples R China Hainan Univ Sch Management Haikou Peoples R China

Support vector machine (SVM) has drawn wide attention in various fields, such as image classification, pattern recognition and disease diagnosis and so on. Nevertheless, it requires much memory and runs very slow in large-scale datasets setting. To reduce computational cost and the required storage, we first design a new sparse and robust SVM model according to our construct truncated smoothly clipped absolute deviation (SCAD) loss and then establish its first-order necessary and sufficient optimality conditions though newly defined proximal stationary point. Following the idea of the proximal stationary point, we define the L-ts support vectors of L-ts-SVM and then show that the L-ts support vectors are a small portion of the whole training set, which is convenient for us to introduce a novel working set in each step. We next present a new alternating direction method of multipliers with working set (L-ts-ADMM) to deal with L-ts-SVM, which proves that the proposed algorithm not only converges to a local minimizer of L-ts-SVM but also possesses a relatively low computational complexity. Finally, the extensive numerical experiments demonstrate that the proposed algorithm enjoys better performance than nine leading state-of-the-art methods with regard to best classification accuracy, smallest number of support vectors and super fast computational speed in large-scale datasets setting.

关键词： Truncated SCAD loss Proximal operator Support vectors Working set low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Minimax Design of M-D Interpolated FIR Filters using Convex-Concave Procedure

Minimax Design of M-D Interpolated FIR Filters using Convex-...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Nanthakumar, Pathmapirian Edussooriya, Chamira U. S. Wijenayake, Chamith Madanayake, Arjuna Univ Queensland Sch Elect Engn & Comp Sci Brisbane Qld Australia Univ Moratuwa Dept Elect & Telecommun Engn Moratuwa Sri Lanka Florida Int Univ Dept Elect & Comp Engn Miami FL USA

ISBN: (纸本)9798350330991;9798350331004

We propose a minimax design method for multi-dimensional (M-D) interpolated finite-support impulse response (IFIR) filters. As a result of the cascade structure of an MD IFIR filter, the optimization problem of the minimax design is nonconvex. In order to solve this nonconvex optimization problem, we employ a convex-concave procedure, where each iteration solves a convex constrained optimization problem. We present experimental results to confirm the effectiveness and the superior performance of the proposed method compared to previously proposed minimax designs of M-D IFIR filters. Furthermore, we present an implementation of M-D IFIR filter on the Xilinx Kintex UltraScale KCU105 field-programmable gate array, where a quantization error of 60.59 dB is achieved with the coefficient word length of 24 bits.

关键词： Multi-dimensional filters interpolated FIR filters convex-concave procedure low computational complexity

来源：评论

学校读者我要写书评

暂无评论

low-complexity Grouping Precoding Based on RSMA for Multibeam Satellite System (Invited Paper) 59

Low-Complexity Grouping Precoding Based on RSMA for Multibea...

引用

59th Annual IEEE International Conference on Communications (IEEE ICC)

作者： Li, Zhiqiang Han, Shuai Li, Cheng Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada

ISBN: (纸本)9798350304060;9798350304053

Multibeam satellite system can provide seamless information service with high spectrum efficiency (SE). However, adjacent beams will cause severe inter-beam interference due to the reuse of spectrum resources in each beam. The existing interference management schemes regard multibeam satellite system as terrestrial multi-antenna system, and then apply precoding technology to mitigate inter-beam interference, which neglects the characteristics of beam gain attenuation. Meanwhile, the traditional precoding technology for all users will significantly challenge satellites with limited computational resources. Motivated by this, we design a low-complexity grouping precoding (GP) scheme to simultaneously consider beam gain and complexity. Combined with the promising rate-splitting multiple access (RSMA), we further maximize the weighted sum rate (WSR). Then, an alternating optimization algorithm is proposed. Simulation shows that the proposed GP scheme based on RSMA has higher WSR and lower computational complexity than other baseline access modes.

关键词： Multibeam satellite communication grouping precoding weighted sum rate low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Light-Field Imaging Reconstruction Using Deep Learning Enabling Intelligent Autonomous Transportation System

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第2期23卷 1587-1595页

作者： Silva, Juan Casavilca Saadi, Muhammad Wuttisittikulkij, Lunchakorn Militani, Davi Ribeiro Rosa, Renata Lopes Rodriguez, Demostenes Zegarra Al Otaibi, Sattam Pontificia Univ Catolica Peru Dept Sci Lima 15088 Peru Univ Cent Punjab Dept Elect Engn Fac Engn Lahore 54000 Pakistan Chulalongkorn Univ Dept Elect Engn Wireless Commun Ecosyst Res Unit Bangkok 10330 Thailand Univ Fed Lavras Dept Comp Sci BR-37200000 Lavras Brazil Taif Univ Dept Elect Engn Coll Engn At Taif 21944 Saudi Arabia

Light-field (LF) cameras, also known as plenoptic cameras, permit the recording of the 4D LF distribution of target scenes. However, many times, surface errors of a microlens array (MLA) are responsible for degradation in the images captured by a plenoptic camera. Additionally, the limited pixel count of the sensor can cause missing parallax information. The aforementioned issues are crucial for creating accurate maps for Intelligent Autonomous Transport System (IATS), because they cause loss of LF information, and need to be addressed. To tackle this problem, a learning-based framework by directly simulating the LF distribution is proposed. A high-dimensional convolution layer with densely sampled LFs in 4D space and considering a soft activation function based on ReLU segmentation correction is used to generate a superresolution (SR) LF image, improving the convergence rate in the deep learning network. Experimental results show that our proposed LF image reconstruction framework outperforms the existing state-of-the-art approaches;specifically, it is effective for learning the LF distribution and generating high-quality LF images. Different image quality assessment methods are used to evaluate the performance of the proposed framework, such as PSNR, SSIM, IWSSIM, FSIM, GFM, MDFM, and HDR-VDP. Additionally, the computational efficiency was evaluated in terms of number of parameters and FLOPs, and experimental results demonstrated that our proposed framework reached the highest performance in most of the datasets used.

关键词： Light-field imaging deep learning framework low computational complexity autonomous transportation systems intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Speech Enhancement Using MLP-Based Architecture With Convolutional Token Mixing Module and Squeeze-and-Excitation Network

引用

IEEE ACCESS 2022年 10卷 119283-119289页

作者： Song, Hyungchan Kim, Minseung Shin, Jong Won Gwangju Inst Sci & Technol Sch Elect Engn & Comp Sci Gwangju 61005 South Korea

The Conformer has shown impressive performance for speech enhancement by exploiting the local and global contextual information, although it requires high computational complexity and many parameters. Recently, multi-layer perceptron (MLP)-based models such as MLP-mixer and gMLP have demonstrated comparable performances with much less computational complexity in the computer vision area. These models showed that all-MLP architectures may perform as good as more advanced structures, but the nature of the MLP limits the application of these architectures to the input with a variable length such as speech and audio. In this paper, we propose the cgMLP-SE model, which is a gMLP-based architecture with convolutional token mixing modules and squeeze-and-excitation network to utilize both local and global contextual information as in the Conformer. Specifically, the token-mixing modules in gMLP are replaced by convolutional layers, squeeze-and-excitation network-based gating is applied on top of the convolutional gating module, and additional feed-forward layers are added to make the cgMLP-SE module a macaron-like structure sandwiched by feed-forward layers like a Conformer block. Experimental results on the TIMIT-DNS noise dataset and the Voice Bank-DEMAND dataset showed that the proposed method exhibited similar speech quality and intelligibility to the Conformer with a smaller model size and less computational complexity.

关键词： Speech enhancement local and global information low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Extremum Seeking Control Based LCL Filter Resonant Frequency Online Estimation

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2022年第1期37卷 59-64页

作者： Wu, Yuheng Mahmud, Mohammad Hazzaz Moorthy, Radha Sree Krishna Chinthavali, Madhu Zhao, Yue Univ Arkansas Power Elect Syst Lab Arkansas Fayetteville AR 72701 USA Oak Ridge Natl Lab Elect Energy Syst Integrat Grp Knoxville TN 37932 USA

The LCL filter has been widely used in the grid-tied inverter systems. However, the resonance of the LCL filter can reduce the system stability margin and the control performance. Moreover, the grid impedance variations can lead to the drift of the resonant frequency, which can further worsen the system robustness. Thus, it is important to know the actual resonant frequency of the LCL filter. In this letter, an adaptive extremum seeking control (AESC) based estimation scheme is proposed to estimate the resonant frequency of the LCL filter online. By injecting a high-frequency (HF) signal into the inverter output voltage, the AESC scheme can identify the extremum of the LCL filter amplitude response, i.e., resonant peak. The amplitude of injection signal is adaptive based on the inverter HF response, which can address the tradeoff between the dynamic response and inverter output current quality. Most importantly, compare to other method, the proposed scheme has very low computational complexity, which minimizes the burden to the normal inverter controller operation. Stability analysis is given in this letter, and experimental studies are conducted to validate the effectiveness of the proposed scheme.

关键词： Resonant frequency Inverters Impedance low-pass filters Estimation Delays Frequency estimation Adaptive extremum seeking control (AESC) low computational complexity resonant frequency estimation

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：