检索结果-内蒙古大学图书馆

Machine Learning-Based Optimization of a Mini-Channel Heatsink Geometry

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2023年第9期48卷 12107-12124页

作者： Saeed, Muhammed Kalule, Ramanzani S. S. Berrouk, Abdallah S. S. Alshehhi, Mohamed Almatrafi, Eydhah Khalifa Univ Sci & Technol Mech Engn Dept POB 127788 Abu Dhabi U Arab Emirates Khalifa Univ Sci & Technol Ctr Catalysis & Separat CeCas POB 127788 Abu Dhabi U Arab Emirates Abu Dhabi Maritime Acad POB 54477 Abu Dhabi U Arab Emirates King Abdulaziz Univ Mech Engn Dept POB 80200 Jeddah Saudi Arabia

The research on cooling electronics devices in workstations, servers, and other devices has become one of the rapidly growing technologies today, with the generation of high heat fluxes associated with component compactness and increased power consumption. Hence, the current study aims to enhance the thermohydraulic performance of a compact mini-channel heat removal system based on a machine learning-based optimization technique. The design variables considered for the optimization study are the channel's Reynolds number (Re), fin thickness (t(f)), fin spacing (s(f)), and fin height (h(f)). Initially, the performance of the heat sink geometry with different fin configurations is computed using 3D-RANS simulations. The generated data are then used to train six regression techniques in machine learning to propose the best approach capable of accurately predicting the heat transfer coefficient and pressure drop data. The selected machine learning model is then coupled with the multi-objective genetic algorithm to find the optimal heat sink geometry. It is found that the multilayered perceptron approach re-designed to a deep neural network model efficiently predicts both the heat transfer coefficient and the pressure drop from the available data. The overall performance of the optimized channel geometry is found up to 2.1 times improved than the best available channel configuration in the data pool. Further, the optimized channel geometry's heat transfer coefficient was 14% higher, and the corresponding pressure drop was five times lower.

关键词： Heatsinks Machine learning Neural networks Mini channels multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Spatial quantification method of grassland utilization intensity on the Qinghai-Tibetan Plateau: A case study on the Selinco basin

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2022年第PartB期302卷 114073-114073页

作者： Ma, Changhui Xie, Yaowen Duan, Hanming Wang, Xiaoyun Bie, Qiang Guo, Zecheng He, Lei Qin, Wenhua Lanzhou Univ Coll Earth & Environm Sci Lanzhou 730000 Gansu Peoples R China China West Normal Univ Sch Geog Sci Nanchong 637002 Sichuan Peoples R China Lanzhou Jiaotong Univ Fac Geomat Lanzhou 730070 Gansu Peoples R China

Existing methods for spatial quantification of grassland utilization intensity cannot meet the demand for accurate detection of the spatial distribution of grassland utilization intensity in the Qinghai-Tibetan Plateau with high spatial resolution. In this paper, a method based on remote-sensing observations and simulations of grassland growth dynamics is proposed. The grassland enhanced vegetation index (EVI) time-series curve during the growing season characterizes the growth of grassland in the corresponding pixel;The deviation between the observed and potential EVI curves indicates the disturbance on grassland growth imposed by human activities, and it can characterize the grassland utilization intensity during the growing season. Based on the main idea described above, absolute and relative disturbances are calculated and used as quantitative indicators of grassland utilization intensity defined from different perspectives. Livestock amount at the pixel scale is obtained by pixel-by-pixel calculations based on the function relationship at the township scale between absolute disturbance and livestock density, which is specific quantitative indicator that considers the mode of grassland utilization. In simulating the potential EVI of grassland, the lag and accumulation effects of meteorological factors are investigated at the daily scale using a multi-objective genetic algorithm. Further, the nonlinear functions between multiple environmental factors (e.g., grassland type, topography, soil, meteorology) and the grassland EVI are established using an error back-propagation feedforward artificial neural network (ANN-BP) with parameter optimization. Finally, the potential EVIs of all grassland pixels are simulated on the basis of this model. The method is applied to the Selinco basin on the Qinghai-Tibetan Plateau and validated by examining the spatial consistency of the results with township-scale livestock density and grazing pressure. The final results indicate t

关键词： Grassland utilization intensity Spatial quantification method Qinghai-Tibetan plateau Disturbance Artificial neural networks multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Geometry design for maximizing output power of segmented skutterudite thermoelectric generator by evolutionary computation

引用

APPLIED ENERGY 2020年 274卷 115296-115296页

作者： Chen, Wei-Hsin Chiou, Yi-Bin Natl Cheng Kung Univ Dept Aeronaut & Astronaut Tainan 701 Taiwan Tunghai Univ Coll Engn Dept Chem & Mat Engn Taichung 407 Taiwan Natl Chin Yi Univ Technol Dept Mech Engn Taichung 411 Taiwan Natl Cheng Kung Univ Res Ctr Energy Technol & Strategy Tainan 701 Taiwan

This study focuses on the design of a segmented thermoelectric generator system to maximize the system output power. Skutterudite, (Sr, Ba, Yb)(y)Co4Sb12 with 9.1% In0.4Co4Sb12, is used as the n-type element, while DD0.59Fe2.7Co1.3Sb11.8Sn0.2 is used as the p-type one. They both are employed as the hot side segments. Alternatively, hydrothermal synthesized nanostructure thermoelectric material (Bi0.4Sb1.6Te3) is chosen as the cold side segments. To achieve the optimum design, a numerical method is developed, while the multi-objective genetic algorithm is adopted. The evolutionary computation processes during seeking the optimum combination of the segments are visualized, and it is found that four generations are enough for reaching the target. With the leg length of 3 mm, the optimum n-type and p-type cold side segment lengths are 0.5 mm and 0.78 mm, respectively. Compared to the equal-segmented thermoelectric couple, the optimized couple at a temperature difference of 400 K can increase the output power by 21.94% and its efficiency is 14.05% which is much higher than conventional thermoelectric generators. The theory of impedance matching does not apply to the segmented thermoelectric generator. The heat flux distribution in the couple is dependent on the temperature difference. Overall, the segmented elements with evolutionary computation design is a promising tool for intensifying thermoelectric generator performance.

关键词： Segmented elements Skutterudite Thermoelectric generators Optimization multi-objective genetic algorithm Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Simulation-based evolutionary multi-objective optimisation approach for integrated decision-making in supplier selection

引用

INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY 2008年第3-4期31卷 144-157页

作者： Ding, Hongwei Benyoucef, Lyes Xie, Xiaolan IBM China Res Lab Beijing 100094 Peoples R China INRIA COSTEAM Project F-57000 Metz France Ecole Natl Super Mines St Etienne ENSM F-42023 St Etienne 2 France

In the design of modern supply chains, integrating supplier selection, order splitting, transportation allocation and inventory control is a challenging issue. Existing optimisation approaches handle the different problems separately and for the sake of solvability, neglect impact of strategic decisions on operational decisions and do not take into account uncertainties. In this paper, a simulation-based evolutionary multi-objective optimisation approach is proposed to deal with this problem. The approach consists of an optimiser and a simulator. The optimiser, based on a multi-objective genetic algorithm, is used to find best-compromised solutions with respect to various criteria, such as the total cost and customer service level. Candidate solutions are evaluated through simulation, which enables realistic evaluation taking into account uncertainties and dynamics along the whole supply chain. A simple case study from the textile industry is presented to illustrate the applicability of the proposed approach for the real-world applications.

关键词： multi-objective genetic algorithm simulation-based optimisation supplier selection textile industry

来源：评论

学校读者我要写书评

暂无评论

multi-objective route planning approach for timely searching tasks of a supervised robot

引用

Journal of Beijing Institute of Technology 2014年第4期23卷 481-489页

作者：刘鹏熊光明李勇姜岩龚建伟 School of Mechanical Engineering Beijing Institute of Technology

To performance efficient searching for an operator-supervised mobile robot, a multiple objectives route planning approach is proposed considering timeliness and path cost. An improved fitness function for route planning is proposed based on the multi-objective genetic algorithm （MOGA） for multiple objectives traveling salesman problem （MOTSP）. Then, the path between two route nodes is generated based on the heuristic path planning method A ＊. A simplified timeliness function for route nodes is proposed to represent the timeliness of each node. Based on the proposed timeliness function, experiments are conducted using the proposed two-stage planning method. The experimental results show that the proposed MOGA with improved fitness function can perform the searching function well when the timeliness of the searching task needs to be taken into consideration.

关键词： multiple objective optimization multi-objective genetic algorithm supervised robots route planning timeliness

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Enhanced Second-Order Sliding Mode Controller Design for an Experimental Twin Rotor System Under External Disturbances

引用

JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES 2024年第SUPPL 1期12卷 1103-1117页

作者： Ozer, Hasan Omur Hacioglu, Yuksel Yagiz, Nurkan Istanbul Univ Cerrahpasa Vocat Sch Tech Sci Dept Elect & Energy Istanbul Turkiye Istanbul Univ Cerrahpasa Fac Engn Dept Mech Engn Istanbul Turkiye

BackgroundThe twin rotor model is frequently studied by researchers because although it has a basic structure the coupled pitch and yaw motions are adequately represented. However, it is quite difficult to obtain an efficient controller due to external disturbances. Classical sliding mode controller (SMC), which is of first order, is recognized to be robust in case of parameter changes and external disturbances especially when the sliding motion takes place, but it possesses chattering in the control input which may damage the mechanical parts of the *** this study it was aimed to design a robust controller without chattering effect which will be used for the control of the twin rotor system in real time *** remedy the chattering issue, a novel fuzzy logic enhanced second-order sliding mode controller (FSOSMC) based on super twisting algorithm is proposed. This controller suppresses chattering while enhancing the robustness of the controller where the sliding surface slope parameter is updated online via a fuzzy logic unit. Then the proposed controller is implemented on an experimental twin-rotor system which has highly nonlinear and coupled *** time experiments were performed on the twin rotor system using the proposed FSOSMC. For comparison purpose the SMC and second-order sliding mode controller (SOSMC) were also applied to the same system. The results have shown that the proposed controller increased the tracking performance without increasing the control effort while reducing the *** experimental results verified the success of the designed FSOSMC, therefore it may be recommended for the robust and precise control of aerial vehicles.

关键词： Fuzzy second order sliding mode control Twin rotor model Experimental results multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Numerical investigation on the application of elliptical tubes in a spiral-wound heat exchanger used in LNG plant

引用

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER 2019年 130卷 333-341页

作者： Jian, Guanping Wang, Simin Sun, Lijuan Wen, Jian Xi An Jiao Tong Univ Sch Chem Engn & Technol Xian 710049 Shanxi Peoples R China Xi An Jiao Tong Univ Sch Energy & Power Engn Xian 710049 Peoples R China

The elliptical tubes were proposed to use in a spiral-wound heat exchanger to boost the shell-side transfer rate with the decrease of shell-side pressure drop. The effects of major axis and minor axis of elliptical tubes on thermal hydraulic performance are numerically investigated. The results show that, compared with the circular tube, the SWHE with elliptical tubes have a better heat transfer ability when the shell-side pressure drop is equal to that with circular tubes. With the increase of the major axis of the elliptical tube, the friction factor f decrease firstly and then increase. While with the increase of the minor axis, the variations of the f have an opposite trend with the increase of the major axis. For the heat transfer, the Nu decreases firstly with the increase of major axis and then increases. However, Nu number increases monotonously with the minor axis because elliptical tube bundle promotes the shell-side turbulent mixing. Based on the numerical data, the multi-objective optimization is performed by genetic algorithm. The optimal results show that, by contrast with the original structure, the comprehensive performance (K/Delta P) of the optimized structures increases by an average of 315.4% and the pumping consumption decreases by an average of 65.5%. (C)2018 Elsevier Ltd. All rights reserved.

关键词： Spiral-wound heat exchanger Elliptical tube multi-objective genetic algorithm Optimization

来源：评论

学校读者我要写书评

暂无评论

Double-objective economic statistical design of the VP T² control chart: Wald's identity approach

引用

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION 2014年第10期84卷 2123-2137页

作者： Faraz, Alireza Heuchenne, Cedric Saniga, Erwin Costa, Antonio F. B. Univ Liege HEC Management Sch B-4000 Liege Belgium Univ Delaware Dept Business Adm Newark DE 19716 USA FEG UNESP Dept Prod BR-12500000 Guaratingueta SP Brazil

Research has shown that applying the T-2 control chart by using a variable parameters (VP) scheme yields rapid detection of out-of-control states. In this paper, the problem of economic statistical design of the VP T-2 control chart is considered as a double-objective minimization problem with the statistical objective being the adjusted average time to signal and the economic objective being expected cost per hour. We then find the Pareto-optimal designs in which the two objectives are met simultaneously by using a multi-objective genetic algorithm. Through an illustrative example, we show that relatively large benefits can be achieved by applying the VP scheme when compared with usual schemes, and in addition, the multi-objective approach provides the user with designs that are flexible and adaptive.

关键词： Hotelling's T-2 control chart adjusted average time to signal variable parameters economic statistical design Wald's identity multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of an effective data-driven model for hourly typhoon rainfall forecasting

引用

JOURNAL OF HYDROLOGY 2013年 495卷 52-63页

作者： Lin, Gwo-Fong Jhong, Bing-Chen Chang, Chia-Chuan Natl Taiwan Univ Dept Civil Engn Taipei 10617 Taiwan

In this paper, we proposed a new typhoon rainfall forecasting model to improve hourly typhoon rainfall forecasting. The proposed model integrates multi-objective genetic algorithm with support vector machines. In addition to the rainfall data, the meteorological parameters are also considered. For each lead time forecasting, the proposed model can subjectively determine the optimal combination of input variables including rainfall and meteorological parameters. For 1- to 6-h ahead forecasts, an application to high- and low-altitude metrological stations has shown that the proposed model yields the best performance as compared to other models. It is found that meteorological parameters are useful. However, the use of the optimal combination of input variables determined by the proposed model yields more accurate forecasts than the use of all input variables. The proposed model can significantly improve hourly typhoon rainfall forecasting, especially for the long lead time forecasting. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Typhoon rainfall forecasting Support vector machine multi-objective genetic algorithm Meteorological parameters

来源：评论

学校读者我要写书评

暂无评论

Interdisciplinary application of numerical and machine-learning-based models to predict half-hourly suspended sediment concentrations during typhoons

引用

JOURNAL OF HYDROLOGY 2019年 573卷 661-675页

作者： Huang, Cheng-Chia Fang, Hsi-Ting Ho, Hao-Che Jhong, Bing-Chen Natl Taiwan Univ Dept Civil Engn Taipei 10617 Taiwan Taiwan Integrated Disaster Prevent Technol Engn C New Taipei 23678 Taiwan Kyoto Univ Grad Sch Engn Dept Civil & Earth Resources Engn Kyoto 6158540 Japan

Accurate forecasting of hourly suspended sediment concentration is a critical issue for reservoir management, especially during typhoon periods. This research proposes a two-stage forecasting approach integrating numerical and machine-learning-based models to provide accurate real-time forecasts of half-hourly suspended sediment concentration. In the first stage, the density current model, SRH2D, was verified and applied by the historical typhoon events due to the lack of measured suspended sediment concentration. Next, in the second stage, the calculated results from SRH2D based on the spatial-temporal relation were employed as the input of the MGSVM-based model. Finally, an application in the Shi-Men reservoir was conducted to demonstrate the forecasting performance of the proposed approach. The results indicated that the calculated data from the SRH2D model corresponded to the trend of measured data in spatial-temporal variation. Moreover, the proposed forecasting approach enables reasonably acceptable 0.5- to 3-h ahead forecasts of suspended sediment concentration by using the simulated data of half-hourly suspended sediment concentration. The accurate forecast conducted by the proposed approach is expected to be properly applied to reservoir management.

关键词： Suspended sediment concentration forecasting Density current Reservoir multi-objective genetic algorithm Support vector machine Typhoon

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：