检索结果-内蒙古大学图书馆

Modeling and optimal control of fast filling process of hydrogen to fuel cell vehicle

JOURNAL OF ENERGY STORAGE 2021年 35卷

作者： Bai, Yunfeng Zhang, Caizhi Duan, Hao Jiang, Shangfeng Zhou, Zhiming Grouset, Didier Zhang, Mingjun Ye, Xuefeng Chongqing Univ Sch Automot Engn Chongqing 400044 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China Chongqing Univ Chongqing Automot Collaborat Innovat Ctr Chongqing 400044 Peoples R China Zhengzhou Yutong Bus Co Ltd Yutong Ind PkYutong Rd Zhengzhou 450061 Henan Peoples R China IMT Mines Albi CNRS UMR 5302 RAPSODEE Campus Jarlard F-81013 Albi 09 France Beijing PERIC Hydrogen Technol Co Ltd Damei Ctr Qingnian Rd Beijing 100123 Peoples R China Chongqing Changan New Energy Vehicle Technol Co L Prop Res Inst Chongqing 400000 Peoples R China

Due to the rapid compression of hydrogen and the Joule-Thompson effect specific to hydrogen during the fast filling process, the internal temperature of the cylinder rises sharply which may lead to hidden safety hazards. In this study, a high-pressure hydrogen filling process is considered, and a simple mathematical model of a cascade storage system of a hydrogen refilling station is developed to analyze the temperature rise in hydrogen cylinders under different working conditions. The results show the pressure switching coefficient has a great impact on the filling time, and the pre-cooling of hydrogen has a significant impact on the temperature rise and the states of charge (SOC) within cylinder. Herein, a multi-objective iterative optimization algorithm is proposed to calculate the above two controllable variables (pressure switching coefficient, pre-cooling temperature of hydrogen) with the objectives of faster refueling, lower energy consumption and higher SOC within cylinders in cascade hydrogen refueling. Besides, this method could significantly decrease energy consumption, improve SOC and allow acceptable refueling time.

关键词： Cascade storage system Fast filling Pressure switching coefficient Pre-cooling temperature optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

AG-SGD: Angle-Based Stochastic Gradient Descent

引用

IEEE ACCESS 2021年 9卷 23007-23024页

作者： Song, Chongya Pons, Alexander Yen, Kang Florida Int Univ Dept Elect & Comp Engn Miami FL 33174 USA

In the field of neural network, stochastic gradient descent is often employed as an effective method of accelerating the result's convergence. Generating the new gradient from the past gradient is a common method adopted by many existing optimization algorithms. Since the past gradient is not computed based on the most updated stochastic gradient descent state, it can introduce a deviation to the new gradient computation, negatively impacting its rate of convergence. To resolve this problem, we propose an algorithm that quantifies this deviation based on the angle between the past and the current gradients, which is then applied to calibrate these two gradients, generating a more accurate new gradient. To demonstrate the broad applicability of the algorithm, the proposed method is implemented into a neural network and a logistic regression classifier which are evaluated on the datasets MNIST and NSL-KDD, respectively. An in-depth analysis is performed to compare our algorithm with nine optimization algorithms in two experiments, demonstrating the advantages in the cost and the error rate reductions from adopting the proposed method.

关键词： Neural networks optimization Classification algorithms Trajectory Rendering (computer graphics) Reliability Object recognition Stochastic gradient descent optimization algorithm gradient deviation neural network

来源：评论

学校读者我要写书评

暂无评论

Using Deep Learning and Swarm Intelligence to Achieve Personalized English-Speaking Education

引用

INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH 2024年第1期15卷 1页

作者： Liu, Yang Huanghe Sci & Technol Univ Zhengzhou Peoples R China

This paper presents a pioneering approach to personalized English oral education through the integration of deep learning and swarm intelligence algorithms. Leveraging deep learning techniques, our system offers precise evaluation of various aspects of spoken language, including pronunciation, fluency, and grammatical accuracy. Furthermore, we combine swarm intelligence algorithms to optimize model parameters to achieve optimal performance. We compare the proposed optimization algorithm based on swarm intelligence and its corresponding original algorithm for training comparison to test the effect of the proposed optimizer. Experimental results show that in most cases, the accuracy of the test set using the optimization algorithm based on the swarm intelligence algorithm is better than the corresponding original version, and the training results are more stable. Our experimental results demonstrate the efficacy of the proposed approach in enhancing personalized English oral education, paving the way for transformative advancements in language learning technologies.

关键词： ACO Deep Learning Multi-Feature Neural Networks optimization algorithm Personalized English Speaking Education Swarm Intelligence

来源：评论

学校读者我要写书评

暂无评论

Novel Rewinding-Time Technique Applied for Enhancing Meta-heuristic algorithms

Novel Rewinding-Time Technique Applied for Enhancing Meta-he...

引用

International Conference on Advanced Mechanical Engineering, Automation and Sustainable Development, AMAS 2021

作者： Dat, Nguyen Tien Kien, Cao Van Anh, Ho Pham Huy 268 Ly Thuong Kiet Street District 10 Ho Chi Minh Viet Nam Linh Trung Ward Thu Duc District Ho Chi Minh Viet Nam

ISBN: (纸本)9783030996659

This paper proposes a new rewinding-time algorithm applied in meta-heuristic optimization techniques including PSO, JAYA to quickly and robustly obtain accurate and stable identified result. In standard optimization algorithms, initiated population are installed to look for the optimum solution with the fitness function value is responded to output requirements. With the proposed rewinding-time technique, the state of each generation, included all of information of population and gradient of fitness function, is stored. During optimize process, the rollback event will be triggered when gradient of fitness function satisfied the jumping condition. The current state is return to the previous state which is chosen if the rollback event active. The proposed technique is fully tested on benchmark test-functions including Shubert, Rosenbrock, Griewank, Salomon, Ackley and Michalewicz. The simulation results indicate that the proposed technique yield a competitive performance in both of precision and stability criteria compared to the standard algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmark function JAYA optimization technique Novel rewinding-time algorithm optimization algorithm Particle Swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Testing coverage criteria for optimized deep belief network with search and rescue

引用

JOURNAL OF BIG DATA 2021年第1期8卷 1-20页

作者： Jammalamadaka, Kiran Parveen, Nikhat Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Guntur Andhra Pradesh India

A new data-driven programming model is defined by the deep learning (DL) that makes the internal structure of a created neuron system over a fixed of training data. DL testing structure only depends on the data labeling and manual group. Nowadays, a lot of coverage criteria have been developed, but these criteria basically count the neurons' quantity whose activation during the implementation of a DL structure fulfilled certain properties. Also, existing criteria are not adequately fine-grained to capture delicate behaviors. This paper develops an optimized deep belief network (DBN) with a search and rescue (SAR) algorithm for testing coverage criteria. For an optimal selection of DBN structure, the SAR algorithm is introduced. The main objective is to test the DL structure using different criteria to enhance the coverage accuracy. The different coverage criteria such as KMNC, NBC, SNAC, TKNC, and TKNP are used for the testing of DBN. Using the generated test inputs, the criteria is validated and the developed criteria are capable to capture undesired behaviors in the DBN structure. The developed approach is implemented by Python platform using three standard datasets like MNIST, CIFAR-10, and ImageNet. For analysis, the developed approach is compared with the three LeNet models like LeNet-1, LeNet-4 and LeNet-5 for the MNIST dataset, the VGG-16, and ResNet-20 models for the CIFAR-10 dataset, and the VGG-19 and ResNet-50 models for the ImageNet dataset. These models are tested on the four adversarial test input generation approaches like BIM, JSMA, FGSM, and CW, and one DL testing method like DeepGauge to validate the efficiency of the suggested approach. The simulation results proved that the proposed approach obtained high coverage accuracy for each criterion on four adversarial test inputs and one DL testing method as compared to other models.

关键词： Deep learning Coverage criteria optimization algorithm Adversarial example Software testing

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Resource Scheduling in Hybrid Edge-Cloud Networks

引用

IEEE ACCESS 2021年 9卷 85350-85366页

作者： Zhang, Qi Gui, Lin Zhu, Shichao Lang, Xiupu Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Computation-intensive mobile applications are explosively increasing and cause computation overload for smart mobile devices (SMDs). With the assistance of mobile edge computing and mobile cloud computing, SMDs can rent computation resources and offload the computation-intensive applications to edge clouds and remote clouds, which reduces the application completion delay and energy consumption of SMDs. In this paper, we consider the mobile applications with task call graphs and investigate the task offloading and resource scheduling problem in hybrid edge-cloud networks. Due to the interdependency of tasks, time-varying wireless channels, and stochastic available computation resources in the hybrid edge-cloud networks, it is challenging to make task offloading decisions and schedule computation frequencies to minimize the weighted sum of energy, time, and rent cost (ETRC). To address this issue, we propose two efficient algorithms under different conditions of system information. Specifically, with full system information, the task offloading and resource scheduling decisions are determined based on semidefinite relaxation and dual decomposition methods. With partial system information, we propose a deep reinforcement learning framework, where the future system information is inferred by long short-term memory networks. The discrete offloading decisions and continuous computation frequencies are learned by a modified deep deterministic policy gradient algorithm. Extensive simulations evaluate the convergence performance of ETRC with various system parameters. Simulation results also validate the superiority of the proposed task offloading and resource scheduling algorithms over baseline schemes.

关键词： Task analysis Cloud computing Processor scheduling Scheduling Energy consumption Computational modeling Wireless communication Mobile edge computing task offloading resource scheduling optimization algorithm deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Extensions of the resource-constrained project scheduling problem

引用

AUTOMATION IN CONSTRUCTION 2023年第1期153卷

作者： Ding, Hongyan Zhuang, Cunbo Liu, Jianhua Beijing Inst Technol Sch Mech Engn Lab Digital Mfg Beijing 100081 Peoples R China Beijing Inst Technol Yangtze Delta Reg Acad Jiaxing 314000 Peoples R China

The resource-constrained project scheduling problem (RCPSP) aims to schedule a set of activities subject to resource and precedence constraints to minimize the project makespan. The construction schedule optimization is modeled and solved as the RCPSP, and research on the RCPSP has had a positive impact on construction projects. However, given the narrow assumptions of the standard RCPSP model, it fails to capture many practical engineering requirements. Consequently, various extended problems and more competitive solutions have been developed. However, few studies have discussed the extensions of the RCPSP and corresponding optimization algorithms. This paper reviews the literature on project scheduling over the last decade. First, the standard RCPSP is described, and extended models are summarized based on objectives, constraints, and activities. Then, the research progress of the algorithm and other variants of the RCPSP are investigated. Finally, based on sta-tistics obtained previously, current limitations, challenges, and future research directions are discussed.

关键词： Project scheduling Resource constraints Extension model optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fake Profile Detection Using Logistic Regression and Gradient Descent algorithm on Online Social Networks

引用

EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS 2024年第1期11卷

作者： Raja, Eswara Venkata Sai Aditya, Bhrugumalla L. V. S. Mohanty, Sachi Nandan VIT AP Univ Sch Comp Sci & Engn Scope Amaravati Andhra Pradesh India

One of the most challenging issues on online social networks is identifying spam accounts. The concern stems from the fact that these personas pose a significant threat, as they may engage in harmful activities against other users, extending beyond mere annoyance or low-quality advertisements. The demand for accurate and effective spam detection algorithms for online social networks is increasing due to this risk. To address the problem of spam detection in online social networks, this research proposes a hybrid machine learning model based on logistic regression and a contemporary metaheuristic method called the Gradient Descent algorithm. The proposed approach automates spammer identification and provides insights into the factors that have the greatest impact on the detection process. Additionally, the model is evaluated and implemented on multiple datasets, and the experiments and findings demonstrate that the proposed model outperforms many other algorithms in terms of accuracy and delivers robust results in terms of precision, recall, f-measure, and AUC. It also aids in identifying the factors that influence detection the most.

关键词： social media spammers detection logistic regression optimization algorithm gradient descent accuracy precision

来源：评论

学校读者我要写书评

暂无评论

Gravitational search algorithm: a comprehensive analysis of recent variants

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第5期80卷 7581-7608页

作者： Mittal, Himanshu Tripathi, Ashish Pandey, Avinash Chandra Pal, Raju Jaypee Inst Informat Technol Noida India Malaviya Natl Inst Technol Jaipur Rajasthan India

Gravitational search algorithm is a nature-inspired algorithm based on the mathematical modelling of the Newton's law of gravity and motion. In a decade, researchers have presented many variants of gravitational search algorithm by modifying its parameters to efficiently solve complex optimization problems. This paper conducts a comparative analysis among ten variants of gravitational search algorithm which modify three parameters, namely Kbest, velocity, and position. Experiments are conducted on two sets of benchmark categories, namely standard functions and CEC2015 functions, including problems belonging to different categories such as unimodal, multimodal, and unconstrained optimization functions. The performance comparison is evaluated and statistically validated in terms of mean fitness value and convergence graph. In experiments, IGSA has achieved better precision with balanced trade-off between exploration and exploitation. Moreover, triple negative breast cancer dataset has been considered to analysis the performance of GSA variants for the nuclei segmentation. The variants performance has been analysed in terms of both qualitative and quantitive with aggregated Jaccard index as performance measure. Experiments affirm that IGSA-based method has outperformed other methods.

关键词： optimization algorithm Nature-inspired algorithm Gravitational search algorithm

来源：评论

学校读者我要写书评

暂无评论

Specific Error Mode Correction for Deformable Reflector by Structure-Actuator Simultaneous optimization

引用

JOURNAL OF SPACECRAFT AND ROCKETS 2020年第4期57卷 728-739页

作者： Satou, Yasutaka Furuya, Hiroshi Kogiso, Nozomu Japan Aerosp Explorat Agcy Dept Space Flight Syst Inst Space & Astronaut Sci Sagamihara Kanagawa 2528510 Japan Tokyo Inst Technol Dept Mech Engn Yokohama Kanagawa 2268502 Japan Osaka Prefecture Univ Dept Aerosp Engn Sakai Osaka 5998531 Japan

This paper proposes an efficient shape correction method for high-precision deformable reflectors. To this end, the specific error modes that affect the antenna performance are selectively corrected by simultaneous optimization of the structure and the actuator locations. First, a method to correct the specific error modes by design optimization is formulated, where a residual surface error vector is introduced to evaluate the contribution of each error mode. A constraint parameter for the actuator location, which helps the optimization algorithm find the global minimum, is proposed to improve the optimization performance. The results of the optimization indicated that the proposed constraint parameter as well as the simultaneous optimization of the structure and actuator distribution improve optimization performance. The optimized deformable reflector with the shape control actuators is then manufactured for experimental verification. The experimental results are in good agreement with the numerical results obtained in the design phase, thereby confirming the feasibility of the optimum design. Thus, the effectiveness of the proposed shape correction method is indicated.

关键词： Piezo Actuators Antenna Design Shape Control optimization algorithm Finite Element Analysis Particle Swarm optimization Electric Field Intensity Space Environment Numerical Simulation Institute of Space and Astronautical Science

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：