检索结果-内蒙古大学图书馆

Clamping Error Calibration algorithm of Aero-Engine Blade Surface Polishing

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING 2023年第7期24卷 1147-1159页

作者： Wu, Dongbo Wang, Zesheng Liang, Jiawei Wang, Hui Zhang, Kung Yu, Jie Tsinghua Univ Dept Mech Engn Beijing 100084 Peoples R China Tsinghua Univ Inst Aero Engine Beijing 100084 Peoples R China Beihang Univ Beijing 100191 Peoples R China Xinjiang Univ Urumqi 830000 Xinjiang Peoples R China AECC Xian Aeroengine LTD Xian 710021 Shaanxi Peoples R China

Polishing is an effective process method to improve the surface quality of aero-engine blade. The clamping error between fixture and blade leads to position error of blade surface and reduces processing quality. In this paper, a laser calibration system and a calibration algorithm are proposed to compensate clamping error. Firstly, theoretical point data of blade surface is obtained from CAD model, and the measurement point data of blade surface is obtained through laser sensor. A modified ICP algorithm is designed to calculate the coordinate transformation between the theoretical points and the measurement points. Secondly, Bezier surface is introduced to evaluate the calibration accuracy based on the distance between fitting surfaces rather than points. Finally, the point cloud registration is optimized by particle swarm optimization (PSO) algorithm based on the Bezier surface evaluation. The calibration algorithm combined ICP algorithm, Bezier surface evaluation and PSO algorithm to realize clamping error compensation. The quality of polished blade surface is consequently improved.

关键词： Blade polishing process Clamping error calibration Error evaluation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第11期82卷 16591-16633页

作者： Hassan, Esraa Shams, Mahmoud Y. Hikal, Noha A. Elmougy, Samir Kafrelsheikh Univ Fac Artificial Intelligence Kafrelsheikh 33516 Egypt Mansoura Univ Fac Comp & Informat Dept Informat Technol Mansoura 35516 Egypt Mansoura Univ Fac Comp & Informat Dept Comp Sci Mansoura 35516 Egypt

optimization algorithms are used to improve model accuracy. The optimization process undergoes multiple cycles until convergence. A variety of optimization strategies have been developed to overcome the obstacles involved in the learning process. Some of these strategies have been considered in this study to learn more about their complexities. It is crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint since this can provide direction for future work in both machine learning and optimization. The approaches under consideration include the Stochastic Gradient Descent (SGD), Stochastic optimization Descent with Momentum, Rung Kutta, Adaptive Learning Rate, Root Mean Square Propagation, Adaptive Moment Estimation, Deep Ensembles, Feedback Alignment, Direct Feedback Alignment, Adfactor, AMSGrad, and Gravity. prove the ability of each optimizer applied to machine learning models. Firstly, tests on a skin cancer using the ISIC standard dataset for skin cancer detection were applied using three common optimizers (Adaptive Moment, SGD, and Root Mean Square Propagation) to explore the effect of the algorithms on the skin images. The optimal training results from the analysis indicate that the performance values are enhanced using the Adam optimizer, which achieved 97.30% accuracy. The second dataset is COVIDx CT images, and the results achieved are 99.07% accuracy based on the Adam optimizer. The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages.

关键词： optimization algorithm Stochastic gradient decent Rung Kutta optimization Deep ensembles Medical images

来源：评论

学校读者我要写书评

暂无评论

FastAdaBelief: Improving Convergence Rate for Belief-Based Adaptive Optimizers by Exploiting Strong Convexity

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6515-6529页

作者： Zhou, Yangfan Huang, Kaizhu Cheng, Cheng Wang, Xuguang Hussain, Amir Liu, Xin Univ Sci & Technol China Sch Nano Tech & Nano Bio Hefei 230026 Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanobio SINANO Suzhou 215123 Peoples R China Duke Kunshan Univ Data Sci Res Ctr Kunshan 215316 Peoples R China Gusu Lab Mat Suzhou 215123 Peoples R China Edinburgh Napier Univ Sch Comp Edinburgh EH11 4BN Midlothian Scotland Univ Sci & Technol China Sch Nanotech & Nanobio Hefei 230026 Peoples R China

AdaBelief, one of the current best optimizers, demonstrates superior generalization ability over the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in which it has a data-dependent O(root T) regret bound when objective functions are convex, where T is a time horizon. It remains, however, an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. To this end, we make the first attempt in this work and design a novel optimization algorithm called FastAdaBelief that aims to exploit its strong convexity in order to achieve an even faster convergence rate. In particular, by adjusting the step size that better considers strong convexity and prevents fluctuation, our proposed FastAdaBelief demonstrates excellent generalization ability and superior convergence. As an important theoretical contribution, we prove that FastAdaBelief attains a data-dependent O(log T) regret bound, which is substantially lower than AdaBelief in strongly convex cases. On the empirical side, we validate our theoretical analysis with extensive experiments in scenarios of strong convexity and nonconvexity using three popular baseline models. Experimental results are very encouraging: FastAdaBelief converges the quickest in comparison to all mainstream algorithms while maintaining an excellent generalization ability, in cases of both strong convexity or nonconvexity. FastAdaBelief is, thus, posited as a new benchmark model for the research community.

关键词： Convergence optimization Training Task analysis Learning systems Deep learning Benchmark testing Adaptive learning rate image classification online learning optimization algorithm stochastic gradient descent strong convexity

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Joint Spectrum Resource and Power Allocation for Ultra Dense Networks

引用

China Communications 2023年第5期20卷 104-118页

作者： Qiang Wang Yanhu Huang Qingxiu Ma Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal UniversityYulin 537000China

In this paper,we propose a low complexity spectrum resource allocation scheme cross the access points(APs)for the ultra dense networks(UDNs),in which all the APs are divided into several AP groups(APGs)and the total bandwidth is divided into several narrow band spectrum resources and each spectrum resource is allocated to APGs independently to decrease the interference among the ***,we investigate the joint spectrum and power allocation problem in UDNs to maximize the overall *** problem is formulated as a mixed-integer nonconvex optimization(MINCP)problem which is difficult to solve in *** joint optimization problem is decomposed into two subproblems in terms of the spectrum allocation and power allocation *** the spectrum allocation,we model it as a auction problem and a combinatorial auction approach is proposed to tackle *** addition,the DC programming method is adopted to optimize the power allocation *** decrease the signaling and computational overhead,we propose a distributed algorithm based on the Lagrangian dual *** results illustrate that the proposed algorithm can effectively improve the system throughput.

关键词： ultra dense networks resource allocation combinatorial auction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

High-Dimensional Multiple Fractional-Order Optimizer for Rotor Side Converter of Doubly-Fed Induction Generators

引用

IEEE ACCESS 2023年 11卷 141456-141472页

作者： Tao, Xinghua Mo, Nan Qin, Jianbo Yang, Xiaozhe Yin, Linfei Hu, Likun Nanning Univ Sch Intelligent Mfg Nanning 530000 Guangxi Peoples R China Guangxi Univ Sch Elect Engn Nanning 530004 Guangxi Peoples R China

The work proposes high-dimensional multiple fractional-order optimization algorithm (HMFOA) to tune the controller parameters of the rotor side converter of doubly-fed induction generator-based wind turbines to achieve higher control performance. The case studies are verified in eight benchmark mathematical optimization problems;the results illustrate that the proposed optimizer has fast convergence speed, high computational precision, and avoidance of falling into local optimums. Compared to four other algorithms, the results show that HMFOA obtains the optimal parameters of controllers and achieves more accurate power point tracking capability and certain fault ride-through capability, which verifies the feasibility and effectiveness of the algorithm.

关键词： High dimension fractional-order optimization algorithm DFIG rotor side converter

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Trim and Stability Analysis for a Wingtip-Chained Aircraft

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第5期48卷 1187-1195页

作者： He, Jiamin Liu, Haojie Huang, Rui Zhao, Yonghui Nanjing Univ Aeronaut & Astronaut Sch Aeronaut & Astronaut State Key Lab Mech & Control Aerosp Struct Coll Aerosp Engn Nanjing 210016 Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Spatiotemporal Tree Search Method for Planning Multi-Asteroid Successive Rendezvous

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第5期48卷 1138-1147页

作者： Zhang, Jia-cheng Zhu, Yue-he Luo, Ya-zhong Natl Univ Def Technol Coll Aerosp Sci & Engn Changsha 410073 Peoples R China Natl Univ Def Technol Hunan Key Lab Intelligent Planning & Simulat Aeros Changsha 410073 Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Vina-FPGA: A Hardware-Accelerated Molecular Docking Tool With Fixed-Point Quantization and Low-Level Parallelism

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2023年第4期31卷 484-497页

作者： Ling, Ming Lin, Qingde Chen, Ruiqi Qi, Haimeng Lin, Mengru Zhu, Yanxiang Wu, Jiansheng Southeast Univ Natl ASIC Syst Engn Technol Res Ctr Nanjing 210096 Peoples R China Fudan Univ Zhangjiang Fudan Int Innovat Ctr Shanghai 200433 Peoples R China Nanjing Renmian Integrated Circuit Co Ltd VeriMake Innovat Lab Nanjing 210088 Peoples R China Nanjing Univ Posts & Telecommun Sch Geog & Biol Informat Nanjing 210023 Peoples R China

Molecular docking (MD) is one of the core steps in the expensive and time-consuming process of drug design, which is basically an optimization problem based on scoring functions. AutoDock series MD software is widely accepted by academia and industry, among which AutoDock Vina (Vina) is the latest and most popular version due to its accuracy and relatively high speed. However, contrast to its prior version, i.e., AutoDock4, hardware acceleration approaches of Vina are rarely reported. In this article, we propose Vina-field-programmable gate array (FPGA), a hardware-accelerated Vina implementation with FPGA that exploits the low-level parallelism. First, the fixed-point quantization is analyzed and realized to accelerate the MD algorithm with a better energy efficiency in hardware. To boost the performance of the module-level computation, multiple in-module hardware pipelines have been designed and implemented. Besides, a strategy for fast accessing to block RAM (BRAM) is implemented by utilizing the layout of data, which brings four times memory access speed to the intermolecular and intramolecular energy computing modules. Under the same 140 ligand-receptor benchmarks, Vina-FPGA performs up to 6.9 times (average 3.7 times) faster than a state-of-the-art CPU does while consuming only 2.5% energy with similar docking accuracies. Compared to the GPU-accelerated implementation or Vina-GPU, the average energy consumption of Vina-FPGA is merely 45%.

关键词： AutoDock Vina field-programmable gate array (FPGA) hardware accelerator optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Tropical Artificial Forests With Cubic Picture Fuzzy Fairly Aggregation Operators

引用

IEEE ACCESS 2023年 11卷 112362-112383页

作者： Al-Quran, Ashraf Kausar, Rukhsana Jameel, Toqeer Riaz, Muhammad King Faisal Univ Basic Sci Dept Al Hufuf 31982 Saudi Arabia Univ Punjab Dept Math Lahore 54590 Pakistan

The creation of sustainable artificial tropical forests is of utmost importance for addressing critical environmental issues like deforestation, habitat loss, and climate change. This research paper presents an innovative approach that considers ecological, socioeconomic, and technological factors. The proposed approach integrates multi-criteria decision-making (MCDM) methods that take into account the preferences and opinions of stakeholders. To analyze the various criteria involved, cubic picture fuzzy numbers (CPFNs) are utilized. To ensure fairness in evaluating CPFNs, the study focuses on developing operational laws and aggregation operators that promote neutrality and fairness. Specifically, the paper introduces the "cubic picture fuzzy fairly weighted average (CPFFWA) operator" and the "cubic picture fuzzy fairly ordered weighted averaging (CPFFOWA) operator." By considering stakeholders and prioritizing their long-term sustainability and resilience, this approach proves to be highly valuable for policymakers, forest managers, and other relevant parties. This research avenue bridges the gap in current literature where limited exploration of fairly aggregation operators in tandem with picture fuzzy sets within tropical forest contexts exists. Ultimately, the research strives to contribute to the practical management of these vital ecosystems, fostering environmental conservation and sustainability through a cross-disciplinary approach amalgamating ecology, fuzzy logic, decision theory, and environmental science.

关键词： Cubic picture fuzzy sets aggregation operators fairly operations optimization algorithm artificial tropical forests

来源：评论

学校读者我要写书评

暂无评论

Secure Data Transmission Using Optimized Cryptography and Steganography Using Syndrome-Trellis Coding

引用

WIRELESS PERSONAL COMMUNICATIONS 2023年第1期130卷 551-578页

作者： Varghese, Fredy Sasikala, P. Vinayaka Missions Kirupananda Variyar Engn Coll Salem Tamilnadu India Naipunnya Inst Management & Informat Technol Dept Comp Sci Trichur Kerala India Vinayaka Missions Kirupananda Variyar Engn Coll Dept Math Salem Tamilnadu India

The establishment of secure data transmission among two communicating parties has become challenging. It is due to unexpected attacks during communication over an unsecured transmission channel. The security of secret data is secured by cryptography and steganography. Hence, this work introduces a secure data transmission model by improving the strength of hybrid cryptography and steganography approaches. It is based on an optimized substitution box (S-box) and a texture-based distortion function. The secret data is initially encrypted using a substitution-permutation network-based chaotic system in this approach. This cryptographic algorithm contains two stages: confusion and diffusion stages. The substitution box attains confusion, and the permutation box attains diffusion. However, the security of this cryptosystem strongly depends on the quality of the S-boxes. Hence, a new arithmetic optimization algorithm (AOA) is proposed to create a robust S-box with a high non-linearity score. After encrypting the secret data, the cover elements have been extracted from the embedded domain created using the sign of DCT (Discrete cosine transform) coefficients. Here, the cover elements selection is optimized by re-compressing the cover JPEG image to exclude the zero-valued DCT coefficients. Then, the embedding cost is calculated by developing a new texture-based distortion function to embed more secret data into the texture portion because the visual quality of the texture portions is not affected due to the embedding process. Finally, the encrypted data has been embedded into cover elements using Syndrome-Trellis Coding (STC) to obtain the stego elements. The overall implementation is carried out in the MATLAB platform. The developed model is evaluated based on imperceptibility and undetectability.

关键词： Cryptography Substitution box Permutation Steganography optimization algorithm Syndrome-trellis coding Security

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：