检索结果-内蒙古大学图书馆

A CFD model for analyzing multiphysics coupling and efficiency optimization in a PEMEC

JOURNAL OF POWER SOURCES 2025年 625卷

作者： Hu, Chenyang Wang, Jingjing Xu, Yuanwu Fu, Xiaowei Deng, Zhonghua Kim, Jung-Sik Li, Xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518055 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Wuhan Huamao Automat Co Ltd Wuhan 430205 Hubei Peoples R China Beihang Univ Sch Gen Engn Beijing 100191 Peoples R China

Proton exchange membrane electrolysis cell (PEMEC) is a promising hydrogen energy storage technology, which is very suitable for energy scheduling in microgrids. The multiple physical fields inside it are affected by many factors and form complex coupling states. In electrolysis, this complexity manifests as uneven distribution of temperature, current density, and liquid water volume fraction, which can lead to local hot spots, reactant starvation, and performance degradation. These challenges pose a threat to PEMEC's service life and operational safety in microgrid systems. Although several studies have explored their Computational Fluid Dynamics (CFD) modeling, the effects of certain operating parameters on their performance are unclear, and few studies have effectively evaluated energy efficiency, which is key to optimizing the operating conditions of the PEMEC system. Therefore, this study is employing a 2D (two dimensional) multiphysics model to investigate the electrochemical processes within PEMEC. The model's validity is being confirmed through comparison with electrochemical experimental data. Subsequently, the effects of applied voltage, anode inlet flow rate, and cathode inlet flow rate on the multiphysics are being examined, and trends in efficiency changes are being analyzed. Moreover, by optimizing operational conditions, maximum energy efficiency (79.0 %) can be achieved. This study is laying the groundwork for future investigations into control strategies and multi-objective optimization, and promoting the application of PEMEC in energy scheduling.

关键词： Multiphysical modeling Proton exchange membrane electrolyzer optimization Energy efficiency optimization PEM electrolyzer performance

来源：评论

学校读者我要写书评

暂无评论

Evolution of Cooperation in Snowdrift Game with Multi-Memory Mechanism 42

Evolution of Cooperation in Snowdrift Game with Multi-Memory...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Yaojun Liu, Xingwen Tashi, Nyima College of Electrical Engineering Southwest Minzu University Lab. of Complex Systems & Intelligent Control Key Lab. of Electronic Information of State Ethnic Affairs Commission Sichuan Chengdu610225 China Engineering Research Center for Tibetan Information Processing School of Information Science and Technology Tibet University Lhasa850000 China

ISBN: (纸本)9789887581543

Cooperative behavior has been of great concern in evolutionary game researches because of its important role in social life and natural evolution. Since memory can greatly influence the emergence of cooperative behavior, memory-based research on evolutionary games has proliferated in recent years. In the present paper, inspired by the well-known 'Stanford marshmallow experiment' (SME), we proposed a multi-memory mechanism in Snowdrift game (SDG) on spatial lattice networks whose core lies in what follows: Players are divided into two groups according to individual self-control;different memory lengths are set by group and by time in a single realization. The simulation results show that our proposed mechanism promotes cooperation level of the considered evolutionary game. More specifically, as memory length increases to an intermediate length, the cooperation level increases as well. For mechanism with short memory length, the effect of population structure is obvious and small values of adjusting factor can intensively facilitate high-frequency cooperative behavior. These findings may be helpful to understand the connection between population heterogeneity and the emergence of high cooperation. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Second Harmonic Seamless Splicing Technique Based on Maximum Active-Voltage Vector for Online MTPA Tracking control of SynRM

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2022年第11期69卷 10958-10968页

作者： Tang, Qipeng Yu, Baiqiang Luo, Pan Luo, Xin Shen, Anwen Xia, Yanghong Xu, Jinbang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Sci & Technol Reactor Syst Design Technol Lab Chengdu 610213 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China

Maximum-torque-per-ampere (MTPA) control strategy is widely employed to achieve the optimal efficiency control of synchronous reluctance machines (SynRMs). However, the control efficiency of the conventional method that the optimal current distribution angle is directly calculated based on the knowledge of the machine parameters is seriously affected by the highly nonlinear and time-varying characteristics of SynRMs. Therefore, in order to effectively resolve this problem, a novel MTPA control scheme based on the second harmonic splicing technique is proposed in this article. Differing from the conventional method, the proposed solution utilizes the transient response current slopes of fundamental maximum active-voltage vector to splice a specific second harmonic signal that contains the optimal current distribution angle. After selecting two available and different splicing coefficients in each sector to guarantee the continuity of the spliced second harmonic signal, the optimal current distribution angle can be obtained accurately without any machine parameters through a simple signal demodulation, which significantly enhances the robustness to machine parameter variations. Furthermore, the influence of rotor position acquisition errors caused by the position sensor's limited accuracy and installation misalignment is analyzed in detail. Finally, the experimental results demonstrate the effectiveness and feasibility of the proposed MTPA control scheme.

关键词： Harmonic analysis Stators Rotors Torque Splicing Current distribution Voltage control Maximum active-voltage vector (MAVV) maximum-torque-per-ampere (MTPA) second harmonic splicing technique synchronous reluctance machines (SynRM)

来源：评论

学校读者我要写书评

暂无评论

BoostTree and BoostForest for Ensemble Learning

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第7期45卷 8110-8126页

作者： Zhao, Changming Wu, Dongrui Huang, Jian Yuan, Ye Zhang, Hai-Tao Peng, Ruimin Shi, Zhenhua Huazhong Univ Sci & Technol Key Lab Minist Educ Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518029 Guangdong Peoples R China Minist Educ China Autonomous Intelligence Unmanned Syst Engn Res Ct Beijing 100089 Peoples R China State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Hubei Peoples R China Second Ship Design & Res Inst Wuhan 430205 Hubei Peoples R China

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This article proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners.

关键词： Boosting Bagging Regression tree analysis Biological system modeling Predictive models Ensemble learning Training Bagging BoostForest BoostTree boosting ensemble learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-DoF Prosthetic Hand Finger Joint controller for Wearable sEMG Sensors by Nonlinear Autoregressive Exogenous Model

引用

SENSORS 2021年第8期21卷 2576页

作者： Gao, Zhaolong Tang, Rongyu Huang, Qiang He, Jiping Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China Beijing Inst Technol Beijing Adv Innovat Ctr Intelligent Robots & Syst Beijing 100081 Peoples R China

The loss of mobility function and sensory information from the arm, hand, and fingertips hampers the activities of daily living (ADL) of patients. A modern bionic prosthetic hand can compensate for the lost functions and realize multiple degree of freedom (DoF) movements. However, the commercially available prosthetic hands usually have limited DoFs due to limited sensors and lack of stable classification algorithms. This study aimed to propose a controller for finger joint angle estimation by surface electromyography (sEMG). The sEMG data used for training were gathered with the Myo armband, which is a commercial EMG sensor. Two features in the time domain were extracted and fed into a nonlinear autoregressive model with exogenous inputs (NARX). The NARX model was trained with pre-selected parameters using the Levenberg-Marquardt algorithm. Comparing with the targets, the regression correlation coefficient (R) of the model outputs was more than 0.982 over all test subjects, and the mean square error was less than 10.02 for a signal range in arbitrary units equal to [0, 255]. The study also demonstrated that the proposed model could be used in daily life movements with good accuracy and generalization abilities.

关键词： EMG NARX neural network prosthesis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Sparse Bayesian Learning Algorithm Based on Gaussian-Scale Mixtures

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第7期33卷 3065-3078页

作者： Zhou, Wei Zhang, Hai-Tao Wang, Jun Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China City Univ Hong Kong Sch Data Sci Dept Comp Sci Hong Kong Peoples R China

Sparse Bayesian learning (SBL) is a popular machine learning approach with a superior generalization capability due to the sparsity of its adopted model. However, it entails a matrix inversion at each iteration, hindering its practical applications with large-scale data sets. To overcome this bottleneck, we propose an efficient SBL algorithm with O(n(2)) computational complexity per iteration based on a Gaussian-scale mixture prior model. By specifying two different hyperpriors, the proposed efficient SBL algorithm can meet two different requirements, such as high efficiency and high sparsity. A surrogate function is introduced herein to approximate the posterior density of model parameters and thereby to avoid matrix inversions. Using a data-dependent term, a joint cost function with separate penalty terms is reformulated in a joint space of model parameters and hyperparameters. The resulting nonconvex optimization problem is solved using a block coordinate descent method in a majorization-minimization framework. Finally, the results of extensive experiments for sparse signal recovery and sparse image reconstruction on benchmark problems are elaborated to substantiate the effectiveness and superiority of the proposed approach in terms of computational time and estimation error.

关键词： Bayes methods Computational modeling GSM Kernel Gamma distribution Covariance matrices Approximation algorithms Gaussian scale mixture iterative algorithms optimization methods regression sparse Bayesian learning (SBL)

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Discovery of Block-Oriented Nonlinear Models Using Sparse Null-Subspace Methods

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第5期52卷 3794-3804页

作者： Li, Junlin Li, Xiuting Zhang, Hai-Tao Chen, Guanrong Yuan, Ye Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol MOE Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

This article develops an identification algorithm for nonlinear systems. Specifically, the nonlinear system identification problem is formulated as a sparse recovery problem of a homogeneous variant searching for the sparsest vector in the null subspace. An augmented Lagrangian function is utilized to relax the nonconvex optimization. Thereafter, an algorithm based on the alternating direction method and a regularization technique is proposed to solve the sparse recovery problem. The convergence of the proposed algorithm can be guaranteed through theoretical analysis. Moreover, by the proposed sparse identification method, redundant terms in nonlinear functional forms are removed and the computational efficiency is thus substantially enhanced. Numerical simulations are presented to verify the effectiveness and superiority of the present algorithm.

关键词： Nonlinear systems Brain modeling Optimization Ear Dictionaries Cybernetics Numerical simulation Alternating direction method (ADM) machine learning sparse null-subspace learning system identification

来源：评论

学校读者我要写书评

暂无评论

Distributed Surrounding control of Multiple Unmanned Surface Vessels With Varying Interconnection Topologies

引用

IEEE TRANSACTIONS ON control SYSTEMS TECHNOLOGY 2022年第1期30卷 400-407页

作者： Hu, Bin-Bin Zhang, Hai-Tao Liu, Bin Meng, Haofei Chen, Guanrong Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mgf Equipment & Technol Wuhan 430074 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

In this brief, a distributed surrounding control problem is investigated for multiple unmanned surface vessels (USVs) with varying interconnection topologies. A distributed estimation-and-control hierarchical framework is developed, where an individual estimator is designed for a USV to predict the state of the target in an interconnection network with jointly dwellingly connected topologies. Thereby, the vessels could be governed to encircle the target in a convex hull, which evenly rotate around the target at the center. Moreover, asymptotical stability conditions are derived to guarantee the feasibility of the proposed surrounding controller. Finally, experiments are conducted for a real multi-USV system consisting of three 1.6 meters-long vessels and a differential GPS station, to verify the effectiveness of the proposed controller.

关键词： Protocols Task analysis Topology Urban areas Space vehicles Maintenance engineering Global Positioning System Distributed control multiagent systems unmanned surface vessels

来源：评论

学校读者我要写书评

暂无评论

Deep Network Quantization via Error Compensation

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4960-4970页

作者： Peng, Hanyu Wu, Jiaxiang Zhang, Zhiwei Chen, Shifeng Zhang, Hai-Tao Chinese Acad Sci Shenzhen Inst Adv Technol Multimedia Lab Shenzhen 518055 Peoples R China Tencent AI Lab Beijing 100080 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

For portable devices with limited resources, it is often difficult to deploy deep networks due to the prohibitive computational overhead. Numerous approaches have been proposed to quantize weights and/or activations to speed up the inference. Loss-aware quantization has been proposed to directly formulate the impact of weight quantization on the model's final loss. However, we discover that, under certain circumstances, such a method may not converge and end up oscillating. To tackle this issue, we introduce a novel loss-aware quantization algorithm to efficiently compress deep networks with low bit-width model weights. We provide a more accurate estimation of gradients by leveraging the Taylor expansion to compensate for the quantization error, which leads to better convergence behavior. Our theoretical analysis indicates that the gradient mismatch issue can be fixed by the newly introduced quantization error compensation term. Experimental results for both linear models and convolutional networks verify the effectiveness of our proposed method.

关键词： Quantization (signal) Taylor series Optimization Neural networks Training Computational modeling Approximation algorithms Deep learning network compression

来源：评论

学校读者我要写书评

暂无评论

Interval Observer-Based Robust Coordination control of Multi-Agent Systems Over Directed Networks

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2021年第12期68卷 5145-5155页

作者： Wang, Xiaoling Su, Housheng Jiang, Guo-Ping Nanjing Univ Posts & Telecommun Coll Automat & AI Nanjing 210023 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan 430074 Peoples R China Jiangsu Engn Lab IOT Intelligent Robots IOTRobot Nanjing 210023 Peoples R China

In this paper, the robust coordination control of multi-agent systems (MASs) with uncertainties is considered, where the uncertainties include the external disturbances and the measurement noises as well as the unknown initial states. Motivated by the interval observer of single-agent systems, a distributed interval observer is designed for MASs communicating through a directed network which contains a directed spanning tree by using only the bounding information on the uncertainties and the output information, to implement the interval-valued state estimation on the absolute state of each agent. It also finds that the robust coordination control is a by-part of the distributed interval observer design of this kind of MASs. Moreover, a time-invariant transformation is used to perfect the distributed interval observer design. Finally, numerical simulations are proposed to verify the theoretical results.

关键词： Observers Uncertainty Output feedback Noise measurement Multi-agent systems Directed graphs control systems Multi-agent system coordination interval observer uncertainty

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：