检索结果-内蒙古大学图书馆

3rd International Conference on Electrical Engineering and Control Science, IC2ECS 2023

作者： Liang, Lingyu Zhang, Huanming Zhao, Xiangyu Cao, Shang Huang, Wenqi China Southern Power Grid Digital Grid Research Institute Co. Ltd Guangdong Guangzhou510000 China

ISBN: (纸本)9798350382426

This paper proposes an action space preprocessing method adapted to the distribution network self-healing decision-making problem for the action space of the distribution network power load adaptive decision-making problem. On this basis, the traditional hybrid action space solving methods are analyzed, their limitations are pointed out, and reinforcement learning hybrid action space algorithms based on the state action value function, based on the state value function and based on the representation learning are proposed respectively. Based on the hybrid action characterization method, a high-quality implicit action space is constructed by mapping the discrete and continuous variables of the self-healing decision-making problem of the distribution network to the hidden variable space through embedded tables and conditional variational self-encoders. Finally, the action representations are decoded back to the original action space by the decoder of the action representations, and a hybrid encoding-decoding power load adaptive optimization algorithm for distributed distribution networks with discrete and continuous variables is established. © 2023 IEEE.

关键词： adaptive optimization algorithm Distributed distribution network Equipment capacity Power load

来源：评论

学校读者我要写书评

暂无评论

Intelligent controllable ultrafast fiber laser via deep learning and adaptive optimization algorithm

引用

INFRARED PHYSICS & TECHNOLOGY 2024年 142卷

作者： Zhang, Chuhui Xiang, Pengfei Zhu, Wei Chen, Chen Liu, Xueming Nanjing Univ Informat Sci & Technol Sch Automat Nanjing 210044 Peoples R China Southeast Univ Sch Elect Sci & Engn Nanjing 210096 Peoples R China Changchun Univ Sci & Technol Sch Photoelect Engn Changchun 230022 Peoples R China

Ultrafast fiber lasers based on nonlinear polarization rotation can generate femtosecond pulses with different pulse durations and high peak powers, which are powerful tools for engineering applications and scientific research. However, achieving a precise and repeatable polarization state for generating the ultrashort pulses with the shortest pulse duration remains a significant challenge. In this paper, we extend the use of recurrent neural networks and adaptive optimization algorithms, specifically designed to optimize repetitive processes in optical systems, to facilitate intelligent search and control aimed at achieving the minimum pulse duration within a mode-locked fiber laser cavity. Our multi-algorithm-based intelligent system can fully simulate and optimize the processes involved in hands-on experiments. Our intelligent system identified a mode-locked fiber laser with the shortest pulse duration of 465 fs, which was experimentally verified. The proposed intelligent algorithm not only identifies the shortest pulse but also holds significant potential for selecting related laser characteristic parameters. We believe this work opens up a novel avenue for exploration and optimization in mode-locked lasers and the intelligent laser can find practical applications in engineering and scientific research.

关键词： Ultrafast fiber laser Recurrent neural network adaptive optimization algorithm Minimum pulse width

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Data Transmission and Sharing Based on Optimal Gradient adaptive optimization algorithm

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第11期24卷 13330-13340页

作者： Li, Xing Zhang, Haotian Shen, Yajing Hao, Lina Shang, Wanfeng Dongguan Univ Technol Sch Elect Engn & Intelligentizat Dongguan 523808 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Liaoning Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China City Univ Hong Kong Dept Biomed Engn Hong Kong Peoples R China Northeastern Univ Sch Mech & Engn Shenyang Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen Peoples R China

This work aims to improve the transmission and sharing efficiency of intelligent transportation data and promote the further development of intelligent transportation and smart city. In this work, an EEMR (Energy Efficient Multi-hop Routing) is designed for the intelligent transportation wireless sensor network. In the EEMR algorithm, the base station runs the IAP clustering algorithm for network clustering after receiving the information of all surviving nodes. A method called ACRR (adaptive Cluster-head Round Robin) is proposed for local dynamic election of cluster heads. In addition, the deep learning-based stochastic gradient descent algorithm and its evolution algorithm are sorted out, and its application in practical scenarios is analyzed. Due to the disadvantages of the adaptive algorithm in the current data processing process, the gradient optimization algorithm based on deep learning is adopted and the concept of adaptive friction coefficient is applied to the Adam algorithm to obtain a new adaptive algorithm (TAdam). The simulation experiment reveals that the proportion of network surviving nodes of the EEMR algorithm is still as high as 90% in 1,500 rounds of data collection. This shows that the EEMR algorithm achieves the energy balance of the network nodes as much as possible while minimizing the system energy consumption. In application scenario 1, when the network surviving nodes of the four data collection algorithms compares dropped below 40%, the number of surviving nodes in the EEMR algorithm is still as high as 97.6%. On the PTB (Penn Tree Bank) test data set, the TAdam algorithm shows the fastest convergence speed and the best generalization performance. The TAdam algorithm based on deep learning discussed in this work was of great significance for improving the transmission and sharing efficiency of intelligent transportation data.

关键词： Intelligent transportation optimal gradient adaptive optimization algorithm data transmission data sharing Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-View Human Action Recognition using adaptive optimization algorithm with Skeleton Based Graph Neural Networks 2

Multi-View Human Action Recognition using Adaptive Optimizat...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Srilakshmi, N. Radha, N. Psgr Krishnammal College for Women Department of Computer Science Tamilnadu Coimbatore India

ISBN: (纸本)9798350306415

Recognizing human actions from multi-viewpoint video data is a complex task with applications in various fields, including surveillance, robotics, and human-computer interaction. An innovative approach is presented in this study to Multi-View Human Action Recognition (MV-HAR) using an adaptive optimization algorithm (AOA) combined with a Skeleton-based Graph Neural Network (SGNN). The proposed architecture aims to leverage the complementary information from multiple viewpoints while effectively capturing the temporal and spatial dependencies inherent in human actions. The pre-processing pipeline aligns and fuses skeleton data extracted from different viewpoints, producing a coherent representation of the action across cameras. Each skeleton sequence is transformed into a graph structure, where joints represent nodes and edges encapsulate the relationships between joints over time. This sequence of graphs is then processed by the SGNN, which learns to capture the evolving dynamics of the action through multiple graph convolutional layers. On benchmark datasets, the proposed approach proves effective with an accuracy of 96.8%. © 2024 IEEE.

关键词： adaptive optimization algorithm Deep Learning Multi-View Human Action Recognition Skeleton-based Graph Neural Network Temporal and Spatial Dependencies

来源：评论

学校读者我要写书评

暂无评论

An adaptive optimization algorithm based on clustering analysis for return multi-flight-phase of VTVL reusable launch vehicle

引用

ACTA ASTRONAUTICA 2021年 183卷 112-125页

作者： Zhao, Jian He, Xiangyue Li, Haiyang Lu, Lin Natl Univ Def Technol Coll Aerosp Sci & Engn Changsha 410073 Hunan Peoples R China Hunan Key Lab Intelligent Planning & Simulat Aero Changsha 410073 Hunan Peoples R China

The return multi-flight-phase trajectory optimization of reusable launch vehicle is the key problem of vertical takeoff and vertical landing (VTVL) technologies. In order to solve the problem of ac-curate pinpoint soft landing in the high-dimensional parameter space composed of complex multi-variables and multi-constraints, this paper proposes a strategy of automatic parameter identification and classification and adaptive allocation of optimization algorithms based on clustering analysis. Firstly, state transition matrix of the terminal constraint variables relative to the design variables in the high-dimensional parameter space is obtained, which describes the sensitivity of the terminal constraint variables to the perturbation of the design variables. Then, K-means clustering algorithm is used to classify the sensitivity of the data elements in the state transition matrix, and the linear and nonlinear constraint variables and design variables together with linear state transition matrix are obtained according to the given linearity criterion. Finally, different optimization algorithms are allocated adaptively according to the linear and nonlinear characteristics of different parameter variables. Numerical simulation shows that the proposed algorithm can effectively deal with complex landing constraints, which has well accuracy, convergence and computational efficiency, and reduces the dimension and complexity of parameter space for the return trajectory optimization problem. Besides, the proposed algorithm is suitable for different return missions and has good adaptability and high expansibility.

关键词： Vertical takeoff and vertical landing reusable launch vehicle Return multi-flight-phase High-dimensional parameter space State transition matrix Clustering analysis adaptive optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel adaptive optimization method for deep learning with application to froth floatation monitoring

引用

APPLIED INTELLIGENCE 2023年第10期53卷 11820-11832页

作者： Ma, Boyan Du, Yangyi Zhou, Xiaojun Yang, Chunhua Cent South Univ Sch Automat Changsha 410083 Peoples R China Beihang Univ Sch Instrumentat & Optoelect Engn Beijing 100191 Peoples R China

Although Adam and its variants are widely used optimization methods, they have issues such as non-convergence and slow optimization speed. Researches have shown that weighting more of the past information in the the second moment estimation could be beneficial to the optimization process. But the design of update formulas and the standard of ideal switching time need to be considered. In this paper, a novel optimization method called adaptive learning Rate switCH (ARCH) is proposed. According to a well-designed update formula, ARCH can increase the weight of historical information in the second moment estimation continuously. Besides, the switching time can be selected adaptively and automatically through experimental performance. A theoretical proof of the convergence of the proposed algorithm is also presented. To verify the performance of ARCH, a series of comparative experiments, which compare ARCH with other optimization methods in several classical convolution neural networks, are carried out. Experimental results have shown that ARCH has fast convergence speed as well as good generalization performance. Moreover, the algorithm proposed in this paper is also applied in practical froth flotation monitoring and results show that ARCH can perform excellently in practical application as well.

关键词： adaptive optimization algorithm Neural network Deep learning Froth flotation Gradient-weighted method

来源：评论

学校读者我要写书评

暂无评论

A cascaded piecewise unsaturated asymmetric under-damped tri-stable stochastic resonance system and its application in bearing fault diagnosis

引用

NONLINEAR DYNAMICS 2024年第2期112卷 925-943页

作者： He, Lifang Bi, Lujie Xiong, Qing Chongqing Univ Posts & Telecommun CQUPT Sch Commun & Informat Engn Chongqing 400065 Peoples R China

In this paper, a cascaded piecewise unsaturated asymmetric under-damped tri-stable stochastic resonance (CPUAUTSR) system is proposed to improve the detection capability of the classical tri-stable system and addresses the output saturation problem. Firstly, it demonstrates the good unsaturated characteristics of the piecewise unsaturated asymmetric under-damped tri-stable stochastic resonance (PUAUTSR) system. Then, the steady-state probability density (SPD), mean first passage time (MFPT) of PUAUTSR system are derived, respectively. Based on the adiabatic approximation theory, the spectral amplification (SA) coefficient of CPUAUTSR system is derived for the first time. The effects of different system parameters on the performance indexes are also investigated. The parameters are optimized using the adaptive genetic algorithm (AGA) and used to measure the stochastic resonance performance using signal-to-noise ratio (SNR). Finally, the piecewise unsaturated asymmetric over-damped tri-stable stochastic resonance (PUAOTSR) and CPUAUTSR system are applied to diagnose the fault signal of bearing. The results show that CPUAUTSR system provides better enhancement and detection of bearing fault signals. In particular, in the detection of bearing inner and outer ring faults, the SNR of the second stage CPUAUTSR system is higher than that of PUAOTSR and first stage CPUAUTSR systems by 8.107 dB, 2.733 dB, 1.879 dB, and 0.185 dB, respectively. These findings provide valuable theoretical support and application prospects for practical engineering.

关键词： Bearing fault diagnosis Stochastic resonance Cascaded piecewise tri-stable system Unsaturated characteristics adaptive optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Stochastic adaptive optimization With Dithers

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2022年第1期67卷 189-202页

作者： Xie, Siyu Liang, Shu Wang, Le Yi Yin, George Chen, Wen Wayne State Univ Dept Elect & Comp Engn Detroit MI 48202 USA Tongji Univ Dept Control Sci & Engn Shanghai 201804 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 201210 Peoples R China Univ Connecticut Dept Math Storrs CT 06269 USA Wayne State Univ Div Engn Technol Detroit MI 48202 USA

optimization methods are essential and have been used extensively in a broad spectrum of applications. Most existing literature on optimization algorithms does not consider systems that involve unknown system parameters. This article studies a class of stochastic adaptive optimization problems in which identification of unknown parameters and search for the optimal solutions must be performed simultaneously. Due to a fundamental conflict between parameter identifiability and optimality in such problems, we introduce a method of adding stochastic dither signals into the system, which provide sufficient excitation for estimating the unknown parameters, leading to convergent adaptive optimization algorithms. Joint identification and optimization algorithms are developed and their simultaneous convergence properties of parameter estimation and optimization variable updates are proved. Under both noise-free and noisy observations, the corresponding convergence rates are established. The main results of this article reveal certain fundamental relationships and tradeoff among updating step sizes, dither magnitudes, parameter estimation errors, optimization accuracy, and convergence rates. Simulation case studies are used to illustrate the adaptive optimization algorithms and their main properties.

关键词： optimization Convergence Signal processing algorithms Stochastic processes Parameter estimation Noise measurement Estimation adaptive optimization algorithm convexity identification optimization stochastic dither

来源：评论

学校读者我要写书评

暂无评论

Numerical investigation and performance enhancement of an ammonia-water radial-outflow turbine through the flow-oriented optimization

引用

APPLIED THERMAL ENGINEERING 2023年第1期222卷

作者： Song, Peng Sun, Jinju Wang, Xuesong Xi An Jiao Tong Univ Sch Energy & Power Engn 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China

The radial-outflow turbine has advantages due to its liquid-rich gas adaptability when applied in a Kalina ammonia-water cycle system for the utilization of geothermal energy and waste heat. However, the existing radial-outflow turbine shows relatively lower efficiency than the conventional radial-inflow turbines due to its distinct stage configuration and the lack of efficient design method. In the present study, numerical investigation has been conducted on a radial-outflow turbine adopted in Kalina cycle system, by which the turbine flow losses are analyzed. To enhance the turbine performance, a design optimization method has been developed, which includes the following features: the flexible geometry variations are realized to explore the optimization po-tentials, where the stator and rotor blades are optimized simultaneously;the flow-oriented objective function is established to drive the optimizer to suppress the flow losses in blade passages while adjust the flow matching. To solve the complex geometry optimization problem, adaptive optimization algorithm is imported to accelerate global searching and reduce the costly Computational Fluid Dynamics evaluations. The developed optimization method has been applied in the geometry optimization of a radial-outflow ammonia-water turbine. Benefitting from the fine-tuned blade geometries, the flow matching between stator and rotor is adjusted and the flow losses are mitigated. Thus, the turbine efficiency and shaft power are improved by 6.46% and 5.85%, respectively.

关键词： Kalina cycle Radial -outflow turbine Geometry optimization Flow -oriented objective function adaptive optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Credal identification of damage patterns in ultra-thin-ply composite bonded/bolted interference-fit joints

引用

ENGINEERING FAILURE ANALYSIS 2024年 162卷

作者： Kang, Yonggang Kou, Shuaijia Meng, Kejuan Zhang, Zuowei Wang, Anyang Northwestern Polytech Univ Sch Mech Engn Xian 710072 Shaanxi Peoples R China City Univ Hong Kong Dept Mech Engn Hong Kong 999077 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710072 Shaanxi Peoples R China

Investigating the mechanical behavior and damage patterns of ultra-thin-ply composite joints is essential for ensuring their widespread application in the aerospace field. It is currently an advanced method of exploring the damage patterns of composite joint structures via a combination of acoustic emission and machine learning algorithms. However, the existing research lacks the evaluation indexes for the determination of the number of damage categories, and on the other hand, the overlapping area and noise of the monitored damage data cannot be accurately identified. In this paper, load-bearing performance of ultra-thin-ply composite hybrid bonded/bolted interference-fit joints is studied, then the SDI(Structural Damage Index) evaluation index is proposed to quantitatively analyze the number of damage categories of the complex joints, and finally the adaptive optimization algorithm based on the credal partition for the complex joints of composite is studied. The experimental results demonstrate the accuracy and generalization of the SDI formulae, and the introduction of the credal partition that submits data where overlapping regions cannot be accurately identified to ensembles of special single classes (meta-clusters) obtains deeper insights into the damage data and improves identification and isolation of noise.

关键词： Aerospace engineering Bonded/bolted interference-fit joints Ultra-thin-ply composites Adhesives Mechanical testing Installation/assembly error adaptive optimization algorithm

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：