检索结果-内蒙古大学图书馆

A Novel neural network model and Two New Algorithms for Solving Multiobjective Linear Optimization Problems

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING 2025年第4期126卷

作者： Abkhizi, Mahboobe Ghaznavi, Mehrdad Skandari, Mohammad Hadi Noori Shahrood Univ Technol Fac Math Sci Shahrood Iran

In this article, the Pareto front of multiobjective linear optimization problems (MLOPs) is approximated via a new neural network (NN) model. Karush-Kuhn-Tucker (KKT) optimality conditions for multiobjective linear optimization problems are applied to construct this neural network model. Compared with the available models in the literature, the proposed approach employs the KKT optimality conditions of the main MLOP, not a scalarized problem related to the MLOP. The stability of the suggested NN model in the sense of Lyapunov, is proved. Also, it is shown that the proposed NN is globally convergent to an efficient solution of the main MLOP. Moreover, we present two algorithms to attain some nondominated points with equidistant distribution throughout the Pareto front of bi-objective and three-objective optimization problems. In the suggested algorithms we apply some filters to attain a uniform approximation of the Pareto front. Illustrative results are provided to clarify the validity and performance of the introduced model for different categories of MLOPs. Numerical results satisfy the presented theoretical aspects. In order to have a comparison with other methods, three indicators, including Hypervolume (HV), Spacing, and Even distribution (EV), are utilized. Finally, we apply the proposed idea for the sustainable development of a multinational company in automotive engineering.

关键词： efficient solution multiobjective linear optimization neural network model Pareto front stability

来源：评论

学校读者我要写书评

暂无评论

Predicting direct punching shear strength in RC flat slabs using a robust multi-layer neural network model

引用

COMPUTERS AND CONCRETE 2025年第4期35卷 401-429页

作者： Farouk, Mohamed A. Abd El-Maula, Ahmed S. El-Mandouh, Mahmoud A. Delta Univ Sci & Technol Fac Engn Dept Civil Engn Gamasa Egypt Sphinx Univ Fac Engn Dept Civil Engn New Assiut Egypt Benha Univ Shoubra Fac Engn Dept Civil Engn Banha Egypt Beni Suef Univ Fac Engn Dept Civil Engn Bani Suwayf Egypt

This research introduces a robust multilayer perceptron neural network model with a 6-7-4-1 configuration, designed to estimate the punching shear strength in flat slabs. The model's accuracy was evaluated using a validation technique called repeated random sub-sampling with a confidence level of 94.5% applied to filter the data. Numerical expressions considering factors such as slab depth, column dimensions, steel reinforcement ratio, concrete strength, steel yield, and the position of the contra flexural point were proposed to predict punching shear strength for design control purposes. Furthermore, a comparative analysis was performed between the robust multilayer perceptron neural network model and both the ACI and EC-2 codes for predicting the punching shear strength of flat slabs. The study revealed that while the different codes produced similar results for punching shear capacity, they diverged significantly from the actual experimental outcomes. In contrast, the introduced Artificial neural network (ANN) model provided predictions closely aligned with experimental results, underscoring its practical viability. The standard deviations (SD) of the differences between the experimental results and the predicted values were used as performance indicators. The ANN model exhibited a low SD of 53, while the ACI and EC-2 codes, serving as a reference for the comparative codes, showed a significantly larger SD, reaching 360.4 and 382.2 respectively. The ANN model also demonstrated superior performance in other error metrics, including the Mean Absolute Percentage Error (MAPE). The ANN model's MAPE was 13.3%, significantly lower compared to ACI 318-19's 78.3% and the EC-code's 80.1%. This highlights the ANN model's superior accuracy and practicality in estimating punching shear strength in flat slabs.

关键词： comparative analysis concrete compressive strength design codes flat slabs neural network model punching shear strength slab depth

来源：评论

学校读者我要写书评

暂无评论

Predictive control of a heat pipe-cooled reactor based on a neural network model

引用

NUCLEAR ENGINEERING AND DESIGN 2025年 436卷

作者： Bai, Xi Huang, Jiajun Chen, Zheyu Sun, Peiwei Wei, Xinyu Xi An Jiao Tong Univ Shaanxi Key Lab Adv Nucl Energy & Technol Xian 710049 Peoples R China Xi An Jiao Tong Univ Shaanxi Engn Res Ctr Adv Nucl Energy Xian 710049 Peoples R China

The adoption of heat pipes for heat transfer makes the heat pipe-cooled reactor (HPR) with significant time delays, making it difficult for traditional proportional integral derivative control systems to meet the rapid and precise power control demands. Therefore, neural network-based model predictive control is applied for HPR. NUSTER-100 model predictive control system utilizes a feedforward neural network model as the prediction model. By employing numerical optimization algorithms to obtain the optimal control variables, the system effectively overcomes the impact of significant time delays on the control system, achieving rapid and precise regulation. It can effectively suppress the impact of abnormal states on control performance, and ensure that heat pipe-cooled reactor can operate safely and stably under abnormal conditions.

关键词： Heat pipe-cooled reactor neural network model Predictive control Numerical optimization Time-delay system

来源：评论

学校读者我要写书评

暂无评论

Modular neural network model for Biometric Authentication of Personnel in Critical Infrastructure Facilities Based on Facial Images

引用

APPLIED SCIENCES-BASEL 2025年第5期15卷 2553-2553页

作者： Korchenko, Oleksandr Tereikovskyi, Ihor Ziubina, Ruslana Tereikovska, Liudmyla Korystin, Oleksandr Tereikovskyi, Oleh Karpinskyi, Volodymyr Univ Natl Educ Commiss Dept Comp Engn & Cybersecur PL-30084 Krakow Poland State Univ Informat & Commun Technol UA-03110 Kyiv Ukraine Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Dept Syst Programming & Specialized Comp Syst UA-03056 Kyiv Ukraine Univ Bielsko Biala Dept Comp Sci & Automat PL-43006 Bielsko Biala Poland Kyiv Natl Univ Construct & Architecture Dept Informat Technol Design & Appl Math UA-03037 Kyiv Ukraine Minist Internal Affairs Ukraine Criminol Res Lab State Res Inst UA-01601 Kyiv Ukraine Natl Aviat Univ Dept Informat Technol Secur UA-03058 Kyiv Ukraine Tesla Gigafactory Berlin Brandenburg D-15537 Grunheide Germany

The widespread implementation of neural network tools for biometric authentication based on facial and iris images at critical infrastructure facilities has significantly increased the level of security. However, modern requirements dictate the need to modernize these tools to increase resistance to spoofing attacks, as well as to provide a base for assessing the compliance of the psycho-emotional state of personnel with job responsibilities, which is difficult to ensure using traditional monolithic neural network models. Therefore, this article is devoted to the development of a modular neural network model that provides effective biometric authentication for critical infrastructure personnel based on facial images, taking into account the listed requirements. When developing the model, an approach was used in which the functionality of each module was defined in such a way as to correspond to a task traditionally solved by a separate neural network model. This made it possible to use in each individual module a tested and accessible toolkit that has proven its effectiveness in solving the corresponding problem, which, in turn, compared to traditional approaches, allows for a 30-40% increase in the efficiency of the development and adaptation of authentication tools for the conditions of their application. Innovative features of the developed modular model include the ability to recognize spoofing attacks based on environmental artifacts and the naturalness of emotions, as well as an increase in the accuracy of person recognition due to the use of a U-Net neural network to highlight natural facial contours in occlusions. The experimental results show that the proposed model allows for a 5-10% decrease in person recognition error, recognition of spoofing attacks based on the naturalness of emotions and images of background objects, and recognition of the emotional state of personnel, which increases the efficiency of biometric authentication tools.

关键词： biometric authentication face image iris neural network model spoofing attack emotions

来源：评论

学校读者我要写书评

暂无评论

Study on the preparation and properties of TC11 micro-arc oxidation film based on residual neural network model

引用

JOURNAL OF THE AMERICAN PHARMACISTS ASSOCIATION 2025年第4期65卷

作者： Yi, Guo Lai, Changxin Zheng, Chuanbo Ma, Han Ju, Dianchun Zhang, Jiming Mao, Rui Hu, Xianjun Xu, Lixin Jiangsu Univ Sci & Technol Sch Met Engn Zhangjiagang 215600 Jiangsu Peoples R China Jiangsu Univ Sci & Technol Coll Ocean Zhenjiang 212100 Jiangsu Peoples R China Jiangsu Marine Technol Innovat Ctr Nantong 226000 Jiangsu Peoples R China Shagang Res Inst Iron & Steel Zhangjiagang 215600 Jiangsu Peoples R China

Micro-arc oxidation technology (Mao) is widely applied in the surface modification of lightweight metals. However, as the conditions for practical engineering applications become increasingly harsh, traditional process optimization methods are often unable to meet the actual demands. Therefore, this research used an artificial neural network model, which is capable of handling complex nonlinear problems, to predict the optimal Mao process parameters. Under the optimal parameters, the film exhibits a porosity of 3.999 %, an average pore size of 0.056 mu m2, and a film thickness of 18 mu m. Electrochemical tests and friction-wear studies show that |Z|0.01 Hz and Rct of the film improve by one and two orders of magnitude, respectively, compared to the TC11 substrate, demonstrating excellent corrosion resistance. The film also shows good wear resistance, with a wear rate of 3.95 x 10-3 mm3 /N & sdot;m, which is approximately 20 % lower than that of the TC11 substrate, offering effective protection to the base material. The application of artificial neural network technology in optimizing Mao process parameters can significantly expand the application scenarios of the Mao process and further enhance the potential of this film.

关键词： Micro-arc oxidation Titanium alloy neural network model Corrosion resistance Wear resistance

来源：评论

学校读者我要写书评

暂无评论

neural network model for completing occluded contours

引用

neural networkS 2010年第4期23卷 528-540页

作者： Fukushima, Kunihiko Kansai Univ Osaka Japan

When some parts of a pattern are occluded by other objects, the visual system can often estimate the shape of occluded contours from visible parts of the contours. This paper proposes a neural network model capable of such function, which is called amodal completion. The model is a hierarchical multilayered network that has bottom-up and top-down signal paths. It contains cells of area V1, which respond selectively to edges of a particular orientation, and cells of area V2, which respond selectively to a particular angle of bend. Using the responses of bend-extracting cells, the model predicts the curvature and location of the occluded contours. Missing contours are gradually extrapolated and interpolated from the visible contours. Computer simulation demonstrates that the model performs amodal completion to various stimuli in a similar way as observed by psychological experiments. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Vision Occlusion Amodal completion neural network model Bend-extracting cell Bottom-up and top-down

来源：评论

学校读者我要写书评

暂无评论

neural network model of the primary visual cortex: From functional architecture to lateral connectivity and back

引用

JOURNAL OF COMPUTATIONAL NEUROSCIENCE 2006年第2期20卷 219-241页

作者： Blumenfeld, Barak Bibitchkov, Dmitri Tsodyks, Misha Weizmann Inst Sci Dept Neurobiol IL-76100 Rehovot Israel

The role of intrinsic cortical dynamics is a debatable issue. A recent optical imaging study (Kenet et al., 2003) found that activity patterns similar to orientation maps (OMs), emerge in the primary visual cortex (V1) even in the absence of sensory input, suggesting an intrinsic mechanism of OM activation. To better understand these results and shed light on the intrinsic V1 processing, we suggest a neural network model in which OMs are encoded by the intrinsic lateral connections. The proposed connectivity pattern depends on the preferred orientation and, unlike previous models, on the degree of orientation selectivity of the interconnected neurons. We prove that the network has a ring attractor composed of an approximated version of the OMs. Consequently, OMs emerge spontaneously when the network is presented with an unstructured noisy input. Simulations show that the model can be applied to experimental data and generate realistic OMs. We study a variation of the model with spatially restricted connections, and show that it gives rise to states composed of several OMs. We hypothesize that these states can represent local properties of the visual scene.

关键词： visual cortex spontaneous activity orientation selectivity neural network model optical imaging

来源：评论

学校读者我要写书评

暂无评论

neural network model-Based Reinforcement Learning Control for AUV 3-D Path Following

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第1期9卷 893-904页

作者： Ma, Dongfang Chen, Xi Ma, Weihao Zheng, Huarong Qu, Fengzhong Zhejiang Univ Inst Marine Sensing & Networking Hangzhou 310058 Peoples R China Zhejiang Univ Hainan Inst Sanya 813099 Peoples R China Minist Educ Engn Res Ctr Ocean Sensing Technol & Equipment Zhoushan 316021 Peoples R China Key Lab Ocean Observat Imaging Testbed Zhejiang P Zhoushan 316021 Peoples R China

Autonomous underwater vehicles (AUVs) have become important tools in the ocean exploration and have drawn considerable attention. Precise control for AUVs is the prerequisite to effectively execute underwater tasks. However, the classical control methods such as model predictive control (MPC) rely heavily on the dynamics model of the controlled system which is difficult to obtain for AUVs. To address this issue, a new reinforcement learning (RL) framework for AUV path-following control is proposed in this article. Specifically, we propose a novel actor-model-critic (AMC) architecture integrating a neural network model with the traditional actor-critic architecture. The neural network model is designed to learn the state transition function to explore the spatio-temporal change patterns of the AUV as well as the surrounding environment. Based on the AMC architecture, a RL-based controller agent named modelPPO is constructed to control the AUV. With the required sailing speed achieved by a traditional proportional-integral (PI) controller, modelPPO can control the rudder and elevator fins so that the AUV follows the desired path. Finally, a simulation platform is built to evaluate the performance of the proposed method that is compared with MPC and other RL-based methods. The obtained results demonstrate that the proposed method can achieve better performance than other methods, which demonstrate the great potential of the advanced artificial intelligence methods in solving the traditional motion control problems for intelligent vehicles.

关键词： Mathematical models Training neural networks Task analysis Intelligent vehicles Heuristic algorithms Adaptation models Path following autonomous underwater vehicles (AUVs) reinforcement learning neural network model state transition function

来源：评论

学校读者我要写书评

暂无评论

neural network model of 100 W portable PEM fuel cell and experimental verification

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2010年第17期35卷 9104-9109页

作者： Sisworahardjo, N. S. Yalcinoz, T. El-Sharkh, M. Y. Alam, M. S. Univ S Alabama Dept Elect Comp Engn Mobile AL 36688 USA Inst Technol Bandung Sch Elect Engn & Informat Bandung 40132 Indonesia Meliksah Univ Dept Elect & Elect Engn TR-38280 Kayseri Turkey

The inherent properties of artificial neural networks (ANNs) such as low sensitivity to noise and incomplete information make the ANN a promising candidate to model the fuel cell system. In this paper, an ANN-based model of 100 W portable direct hydrogen fed proton exchange membrane fuel cell (PEMFC) is presented. The model is built based on experimentally collected data from a portable 100 W direct hydrogen fed PEMFC in the authors' laboratory. A multilayer feedforward ANN with back-propagation training algorithm is used to model the portable PEMFC. The ANN consists of fully connected four layers network with two hidden layers. The PEMFC ANN model is trained using extracted data from experimentally measured and calculated parameters. To validate the model, the outputs of the PEMFC ANN are compared against experimental data and results from a dynamic model of portable direct hydrogen fed PEMFC. In addition, three statistical indices to measure variations, unbiasedness (precision), and accuracy in voltage, power, and hydrogen flow are used to evaluate the PEMFC ANN model performance. The indices indicate that the maximum variations, unbiasedness, and accuracy of the voltage, power, and hydrogen flow are 1.45%, 2.04%, and 1.90%, respectively, which shows a close agreement between the outputs of the PEMFC ANN and the experimental results. (C) 2010 Professor T. Nejat Veziroglu. Published by Elsevier Ltd. All rights reserved.

关键词： Fuel cell PEMFC neural network model Portable fuel cell Direct hydrogen fed fuel cell

来源：评论

学校读者我要写书评

暂无评论

neural network model for predicting early strength of cementing materials

引用

STRUCTURAL CONCRETE 2018年第6期19卷 1682-1688页

作者： Wang, Jian Qian, Chunxiang Zhang, Huimin Qu, Jun Guo, Jingqiang Southeast Univ Sch Mat Sci & Engn 2 Southeast Univ Rd Nanjing 211189 Jiangsu Peoples R China Southeast Univ Res Inst Green Construct Mat Nanjing 21189 Jiangsu Peoples R China Sika China Concrete Dept Suzhou 215021 Peoples R China

After judging whether the early strength of mortar after steam curing can meet the requirements of the prefabricated products, the combination of the cementitious materials can be judged. The main factors influencing early strength of mortar are analyzed by gray correlation analysis and neural network model is established through MATLAB, and then the early strength value and relative error of steam curing mortar can be predicted. From the analysis of gray correlation, the correlation factors of the volume ratio between CSH and unhydrated particle is 0.58, the correlation factors of bulk density and early strength is 0.62. The neural network model is established as the input variable, the average relative error of the test sample is 8.63%, and the average relative error of the sample to be tested is 6.72%. The prediction results show that the suitable dosage of fly ash is 6%, the suitable dosage of slag powder is 10%, and the amount of limestone powder should be controlled within 10%. The combination of gray correlation analysis and neural network model is feasible.

关键词： demoulding strength gray correlation analysis neural network model precast elements steam curing

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：