检索结果-内蒙古大学图书馆

Constitutive modeling of Ta-rich particle reinforced Zr-based bulk metallic composites in the supercooled liquid region by using evolutionary artificial neural network

引用

JOURNAL OF ALLOYS AND COMPOUNDS 2023年第1期938卷

作者： Yu, Guoqing Bao, Xiaoqian Xu, Xiao Wang, Xin Jin, Junsong Gong, Pan Wang, Xinyun Huazhong Univ Sci & Technol Sch Mat Sci & Engn State Key Lab Mat Proc & Die & Mould Technol Wuhan 430074 Peoples R China Univ Sci & Technol Beijing State Key Lab Adv Met & Mat 30 Xue Yuan Rd Beijing 100083 Peoples R China Shanghai Dianji Univ Coll Machine Shanghai 201306 Peoples R China

In this study, a series of in-situ Ta-rich particle reinforced Zr-based bulk metallic glass composites were successfully fabricated by arc-melting copper-mold spray casting. The effects of Ta content on the room temperature plasticity, compressive strength and thermoplastic formability were studied. (Zr55Cu30Al10Ni5)94Ta6 showed good comprehensive performance, and it was selected to systematically study the deformation behavior in the supercooled liquid region. Different from the strain softening after stress overshoot in bulk metallic glass, the composites showed work hardening in the late stage. Some classical constitutive models cannot accurately describe these phenomena. The back-propagation artificial neural network optimized by particle swarm optimization and genetic algorithm was used to establish the constitutive model. The particle-swarm-optimization back-propagation network with the optimal topology showed high accuracy and good generalization ability. The results predicted with this model were con-sistent with the experimental data, providing a powerful approach for describing the hot-deformation behavior of these Zr-based bulk metallic glass composites in the supercooled liquid region.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Bulk metallic glass composites Plasticity Thermoplastic formability Artificial neural network model optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A generality hard channel pruning with adaptive compression rate selection for HRNet

引用

PATTERN RECOGNITION LETTERS 2023年 168卷 107-114页

作者： Liu, Dongjingdian Gao, Shouwan Chen, Pengpeng Cheng, Lei China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Peoples R China Minist Educ Peoples Republ China Engn Res Ctr Mine Digitizat Xuzhou 221116 Peoples R China

Network pruning extends a promising prospect to neural network compression. However, applications of existing methods to various vision tasks, e.g., human pose estimation, are limited by the parameter distribution difference, shortage of general pruning strategies and high pruning cost. As a complex and widely used backbone network, HRNet is an effective benchmark for studying these issues. We propose an adaptive Hard channel pruning method with an Adaptive Compression Rate to replace manual expe-rience in pruned model selection, called HACR. It first designs a hard criterion that takes gamma and fi to measure channel importance with the insight of the consistency relationship between the distribution adjustment of the channel and the final output distribution. Then, a partial pruning strategy is advanced for the complex structural network by only pruning channels without cross-layer integration and keeping the network infrastructure. Next, we adaptively predict an optimal compression rate based on the val-idation metric of unfine-tuned models, providing a reference for compression parameter selection. The processes of HACR are simplified to adaptive pruned model selection and fine-tuning with lower prun-ing cost. Furthermore, the numerical distribution of gamma and fi is used to extend HACR in common pruning task benchmarks, based on the a principle that lower level channels should be preferentially retained. We conduct HRNet pruning experiments on COCO2017 and MPII, and promote extension study on CIFAR-10 to verify the generality of strategy. The results show that HACR is effective on multiple tasks, e.g. HRNet-W48 reduces 58.2% Params and 50.1% FLOPS, and VGG-16 reduces 91.5% Params and 67.5% FLOPS with only 0.3% precision loss. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Human pose estimation Network slimming Convolution networks optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Numerical Computation of Optimal Control Problems with Atangana-Baleanu Fractional Derivatives

引用

JOURNAL OF optimization THEORY AND APPLICATIONS 2023年第2期197卷 798-816页

作者： Liu, Chongyang Yu, Changjun Gong, Zhaohua Cheong, Huey Tyng Teo, Kok Lay Shandong Technol & Business Univ Sch Math & Informat Sci Yantai 264005 Peoples R China Shanghai Univ Dept Math Shanghai 200444 Peoples R China Sunway Univ Sch Math Sci Kuala Lumpur 47500 Malaysia

In this paper, a computational method is proposed for solving a class of fractional optimal control problems subject to canonical constraints of equality and inequality. Fractional derivatives are described in the Atangana-Baleanu-Caputo sense, and their fractional orders can be different. To solve this problem, we present a discretization scheme based on the trapezoidal rule and a novel numerical integration technique. Then, the gradient formulas of the cost and constraint functions with respect to the decision variables are derived. Furthermore, a gradient-based optimization algorithm for solving the discretized optimal control problem is developed. Finally, the applicability and effectiveness of the proposed algorithm are verified through three non-trivial example problems.

关键词： Fractional optimal control Atangana-Baleanu derivative Discretization scheme optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Nonparametric Approach Trained by Metaheuristic algorithm for Voltage Regulation in the Electrical Distribution Network Equipped by PV Farm

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2023年第1期18卷 39-51页

作者： Salah, Samer Z. Ghaeb, Jasim A. Baniyounis, Mohammed Philadelphia Univ Fac Engn Mechatron Engn Dept Amman Jordan

The integration of the Photovoltaic (PV) systems changes the nature of the power flow in the network and causes several problems such as voltage deviation which is considered the most important issue in electrical power systems. In this work, the Augmented Grey Wolf optimization (AGWO) algorithm and advanced nonparametric models are proposed to mitigate the voltage deviation in the distribution network equipped with a PV farm. In the first stage of the work, the AGWO calculates the optimal value of reactive power for Static Synchronous Compensator (STATCOM) to relieve the voltage deviation. This stage is applied only in the offline mode due to the delay in AGWO's dynamic response caused by its iteration process in the computation. Therefore, in the second stage, the data set of AGWO is used to train the nonparametric models;Linear Regression (LR) and Support Vector Machine (SVM) to mitigate the voltage deviation quickly in the online mode. Jordanian Sabha Distribution Network (JSDN) equipped by PV farm is considered and modeled as a real case study to validate the proposed approach. The results showed the superior ability of the proposed integrated approach to handle the voltage deviation quickly and accurately.

关键词： Voltage deviation STATCOM optimization algorithm Load flow calculation Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A model-driven method based on multisource data for reproducing displacement time history

引用

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS 2023年第10期52卷 2910-2927页

作者： He, Zhizhou Wang, Haishen Pan, Peng Tsinghua Univ Dept Civil Engn Beijing Peoples R China Tsinghua Univ Key Lab Civil Engn Safety & Durabil China Educ Minist Beijing Peoples R China Tsinghua Univ Dept Civil Engn Beijing 100084 Peoples R China

The seismic displacement time history of a structure is very important for damage assessment. This paper proposes a displacement estimation method based on multisource measurement data. In this method, the structure is simplified to a mass-spring shear model, where a set of tunable parameters are assigned. The particle swarm optimization algorithm is used to search for the optimal values of the parameters, and the objective of the optimization problem is to minimize the difference between the measured roof response and that calculated by the model. A refined finite element model was established in ABAQUS, and the numerical calculation results were used to verify this proposed method. Results show that the estimation error of the maximum inter-story drift ratio among all floors is 8.9%, and the average error of the maximum displacement of each floor is 7.0%, representing a satisfactory estimation effectiveness. The source of the errors is discussed, and we find that this method is more suitable for low-rise buildings. Shaking table tests of a scaled four-story reinforced concrete (RC) frame were conducted, and the estimation error of the maximum inter-story drift ratio among all floors was 6.1%, indicating the feasibility of this method in practice.

关键词： displacement estimation model-driven multisource data optimization algorithm shaking table test

来源：评论

学校读者我要写书评

暂无评论

Efficient key frame extraction and hybrid wavelet convolutional manta ray foraging for sports video classification

引用

IMAGING SCIENCE JOURNAL 2023年第8期71卷 691-714页

作者： Ramesh, M. Mahesh, K. Alagappa Univ Dept Comp Applicat Karaikkudi India

Sports video classification (SVC) is now considered a challenging topic, therefore, developing an automatic sports scene classification technique has received tremendous interest. This research develops an efficient key frame extraction method and hybrid Wavelet Convolution Neural Network (WCNN) framework with optimization scheme to classify sports videos. Initially, input videos are converted into number of frames, and keyframes are extracted using Enhanced threshold with Discrete Wavelet Transform (ETDWT) method. Then, Cross Guided Bilateral Filter (CGBF) method eliminates the noise from the keyframe. After that, segmentation process is performed by the Fuzzy Equilibrium Optimizer (FEO) algorithm, and then motions are detected using the Farneback optical flow (OF) method. Finally, classification process is performed using Hybrid Wavelet Convolutional Manta Ray Foraging optimization (HWCMRFO) algorithm to categorize different sports videos. The overall work is implemented using Python language. Simulation results proved that the proposed work achieved the highest accuracy (93.17%) compared to existing approaches.

关键词： CNN filtering fuzzy logic keyframe optimization algorithm sports videos wavelet transform segmentation

来源：评论

学校读者我要写书评

暂无评论

Output-Feedback Tube Model Predictive Control for Asteroid Circumnavigation and Descent

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2023年第11期46卷 2235-2244页

作者： Frekhaug, Thomas A. Sanjurjo-Rivo, Manuel Soler, Manuel Carlos III Univ Madrid Madrid 28911 Spain Aerosp Engn Dept Avda Univ 30 Leganes Spain

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of new meta-heuristic-variants for privacy preservation in wireless mobile adhoc networks for IoT applications

引用

COMPUTER COMMUNICATIONS 2023年 198卷 262-281页

作者： Satyanarayana, P. Diwakar, G. Subbayamma, B. V. Kumar, N. V. Phani Sai Arun, M. Gopalakrishnan, S. VR Siddhartha Engn Coll Dept ECE Vijayawada Andhra Pradesh India Koneru Lakshmaiah Educ Fdn Dept Mech Engn Vaddeswaram Andhra Pradesh India Prasad V Potluri Siddhartha Inst Technol Dept ECE Vijayawada Andhra Pradesh India SRKR Engn Coll Dept ECE Bhimavaram Andhra Pradesh India Panimalar Engn Coll Dept ECE Chennai Tamil Nadu India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Elect & Commun Engn Chennai Tamil Nadu India

"Mobile Ad Hoc Network (MANET)"is a self-configurable, self-repairing, self-maintaining, highly mobile, decentralized, and independent wireless network, which has the liberty to move from one to another place. Such networks do not have any pre-existing infrastructure. The adoption of a smart environment in MANET requires new protocols to connect the gadgets to the internet. A smart environment with routing protocols should assure the following properties like connectivity among the nodes, "Quality of Service (QoS)", and fairness, both in access points and ad-hoc networks. Combination with the Internet of Things (IoT) and MANET generates a novel MANET-IoT system, which focuses on reducing the implementing costs of the network and providing better mobility for users. The necessity of these integrated networks is increasing in military operations, rescue operations, personal area networks, emergency rooms, and meeting rooms. Routing in MANETs is a not simple job and has projected a huge range of attention from researchers around the world. Thus, the intention of this task is a development of a security protocol in MANET for the IoT platform. For dealing with encryption and decryption strategies to handle MANET and IoT data, a new approach is suggested through the enhanced chaotic map. Here, three improved algorithms are implemented for proposing the optimized key management scheme under a chaotic map, which is the Modified Updating-based Harris Hawks optimization algorithm (MU-HHO), Mean Solution-based Averaging Sailfish Optimizer (MS-ASFO), Adaptive Basic Reproduction Rate-based Coronavirus Herd Immunity Optimizer (ABRR-CHIO). In the convergence evaluation, while taking the length of plain text as 40, ABRR-CHIO shows superior performance over other techniques at the 60th iteration, which is 96%, 95%, 93%, 96%, and 80% superior to HHO, SFO, CHIO, SA-SFO, and CHHSO. Finally, the performance evaluation is performed regarding "statistical analysis, convergence analysis, a

关键词： Mobile ad hoc network Internet of things Privacy preservation Wireless mobile adhoc networks Modified updating-based Harris Hawks optimization algorithm Mean solution-based averaging sailfish optimizer Adaptive basic reproduction rate-based coronavirus herd immunity optimizer Enhanced chaotic map Optimized key management strategy

来源：评论

学校读者我要写书评

暂无评论

Image steganography technique based on bald eagle search optimal pixel selection with chaotic encryption

引用

ALEXANDRIA ENGINEERING JOURNAL 2023年 75卷 41-54页

作者： Bahaddad, Adel A. Almarhabi, Khalid Ali Abdel-Khalek, Sayed King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Syst Jeddah 21589 Saudi Arabia Umm Al Qura Univ Coll Comp Al Qunfudah Dept Comp Sci Mecca Saudi Arabia Sohag Univ Fac Sci Dept Math Sohag 82524 Egypt

In the digital era, information security becomes a challenging process that can be miti-gated by the utilization of cryptography and steganography techniques. Earlier studies on steganog-raphy have the risk of exposing confidential data by an anonymous user. For resolving, the limitations related to the existing algorithms, one of the efficient solutions in encryption-based steganography. Encryption techniques act as an important part in protect actual data from illegal access. This study focuses on the design of Bald Eagle Search Optimal Pixel Selection with Chaotic Encryption (BESOPS-CE) based image steganography technique. The presented BESOPS-CE tech-nique effectively hides the secret image in its encrypted version to the cover image. For accomplish-ing this, the BESOPS-CE technique employs a BES for optimal pixel selection (OPS) procedure. Besides, chaotic encryption was executed for encrypting the secret image, which is then embedded to choose pixel points of the cover image. Finally, embedding and extraction processes are carried out. The inclusion of the encryption process aids in accomplishing an added layer of security. A comprehensive simulation study was used to report on the BESOPS-CE approach's increased per-formance, and the results are examined from many angles. A thorough comparative analysis revealed that the BESOPS-CE model outperformed more contemporary methods.& COPY;THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University. This is an open access article under the CC BY-NC-ND license (http://***/ licenses/by-nc-nd/4.0/).

关键词： Image Steganography Encryption Bald Eagle Search optimization algorithm Security Pixel Selection

来源：评论

学校读者我要写书评

暂无评论

Sliding mode control based on multi-node transmission hybrid scheduling for Markovian jump systems with constrained bandwidth

引用

NONLINEAR ANALYSIS-HYBRID SYSTEMS 2023年 49卷

作者： Chen, Bei Niu, Yugang Shanghai Univ Engn Sci Shanghai Peoples R China East China Univ Sci & Technol Shanghai 200237 Peoples R China

The sliding mode control (SMC) problem is investigated for Markovian jump systems (MJSs) under constrained communication bandwidth. A multi-node hybrid transmission strategy composed of an event-triggered protocol and the weight try-once-discard (WTOD) protocol is introduced into the sensor-to-controller (S/C) channel. Its key feature is that by using two dynamic thresholds, the number of the transmitted components may be dynamically regulated, not just the one with the largest difference as in the conventional WTOD protocol. That may greatly increase the flexibility of transmission under limited bandwidth, meanwhile, it is also beneficial to balance system performance and network burden. Then, a compensating strategy is proposed via the previous transmitted signals, and a scheduling signal-dependent sliding mode controller is designed. By using mode-dependent Lyapunov function, both the stochastic stability and the reachability are analyzed under different transmission cases, respectively. Moreover, an optimization problem on convergent domain is formulated and the binary-encoded genetic algorithm (GA) is utilized to search a desirable sliding gain. Finally, the proposed multi-node hybrid scheduling-based SMC scheme is illustrated via simulation results.& COPY;2023 Elsevier Ltd. All rights reserved.

关键词： Markovian jump systems Multi-node transmission Hybrid scheduling Sliding mode control 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：