检索结果-内蒙古大学图书馆

optimization of cathode catalyst layer of membrane electrode assembly for polymer electrolyte fuel cells using machine learning

引用

JOURNAL OF POWER SOURCES 2023年第1期573卷

作者： Uenishi, Toru Imoto, Rui Toyota Motor Co Ltd Adv Mat Engn Div 1200 Mishuku Susono Shizuoka 4101193 Japan Kitami Inst Technol Sch Earth Energy & Environm Engn 165 Koen Cho Kitami Hokkaido 0908507 Japan

To optimize the cathode catalyst layer of MEAs for polymer electrolyte fuel cells, we developed a data-driven model to predict the performance of MEAs by using the physical properties of the catalyst layer as a property variable. To use the physical properties of the catalyst layer as an input variable, feature extraction through image processing and measurement data profiles from electron microscopy images, and XRD, were automated to eliminate variation due to differences among analysts. Furthermore, a sensitivity analysis using a data-driven model extracted important features and revealed that diffusion in the interparticle voids within the catalyst layer and intra-particle diffusion of carbon aggregates were the key factors. These results are consistent with the findings of previous numerical and experimental approaches for cathode catalyst layers and demonstrate that data-driven modeling is a powerful tool for developing cathode catalyst layers for MEAs. Furthermore, the combination of data-driven modeling and genetic algorithm optimization techniques guides the optimization of material properties to improve the performance of membrane electrode assemblies. These results are expected to provide valuable insights into improving the performance of polymer electrolyte fuel cells, promoting their widespread use, and realizing CO2 recycling in a carbon-neutral and green manner.

关键词： Polymer electrolyte membrane fuel cell Cathode catalyst layer Machine learning Data -driven model Sensitivity analysis genetic algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Thermodynamic analysis of supercritical Brayton cycles using CO2-based binary mixtures for solar power tower system application

引用

ENERGY 2022年第PartA期254卷

作者： Niu, Xiaojuan Ma, Ning Bu, Zhengkun Hong, Wenpeng Li, Haoran Northeast Elect Power Univ Sch Energy & Power Engn Jilin 132012 Peoples R China

Supercritical CO2 Brayton cycle has the advantages of high thermoelectric conversion efficiency and compact structure. However, the high ambient temperature in the desert environment would reduce the cycle thermal efficiency. In this paper, three additive gases were mixed with CO2 to reduce the effect of ambient temperature on cycle efficiency. The thermodynamic analysis method based on the optimal split ratio was applied to evaluate the potential of CO2-based binary mixtures in the SPT systems application for the first time. Meanwhile, the impact of critical cycle parameters on system performance was analyzed and the internal connection of the phenomenon was investigated by discussing the exergy loss of each component under typical operating conditions. The results show that the optimal split ratio decreases with the increase of main compressor inlet temperature and turbine inlet pressure. The change of turbine inlet temperature has little effect on the optimal split ratio. CO2-propane has the potential for practical application because the pressure ratio has little effect on the optimal split ratio. Moreover, it is found that the thermal and exergy efficiencies of CO2-propane are increased by 2.34% and 1.51% compared with CO2 under typical operating conditions based on genetic algorithm optimization. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Supercritical brayton cycles CO 2-Based binary mixtures Solar power tower system application Thermodynamic analysis genetic algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

A novel grey model based on traditional Richards model and its application in COVID-19

引用

CHAOS SOLITONS & FRACTALS 2021年 142卷 110480-110480页

作者： Luo, Xilin Duan, Huiming Xu, Kai Chongqing Univ Posts & Telecommun Sch Sci Chongqing 400065 Peoples R China Sichuan Int Studies Univ Sch Int Business Chongqing 400031 Peoples R China

In 2020, a new type of coronavirus is in the global pandemic. Now, the number of infected patients is increasing. The trend of the epidemic has attracted global attention. Based on the traditional Richards model and the differential information principle in grey prediction model, this paper uses the modified grey action quantity to propose a new grey prediction model for infectious diseases. This model weakens the dependence of the Richards model on single-peak and saturated S-shaped data, making Richards model more applicable, and uses genetic algorithm to optimize the nonlinear terms and the background value. To illustrate the effectiveness of the model, groups of slowly growing small-sample and large-sample data are selected for simulation experiments. Results of eight evaluation indexes show that the new model is better than the traditional GM(1,1) and grey Richards model. Finally, this model is applied to China, Italy, Britain and Russia. The results show that the new model is better than the other 7 models. Therefore, this model can effectively predict the number of daily new confirmed cases of COVID-19, and provide important prediction information for the formulation of epidemic prevention policies. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Grey prediction model COVID-19 Traditional Richards model genetic algorithm optimization GERM(1,1,e(at))

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis: Exergetic and economic assessment of LNG cold energy power generation systems with different cold utilization methods

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2024年 54卷

作者： Cai, Dongxu Zhao, Yiming Wang, Yingguang Liu, Haoshuang Liang, Yong Hu, Dapeng Dalian Univ Technol Dept Chem Machinery Dalian 116012 Peoples R China PipeChina Engn Technol Innovat Co Ltd Tianjin 300450 Peoples R China

Harnessing the cold energy inherent in LNG transportation processes can significantly mitigate energy wastage. Employing an innovative incremental analysis methodology, this study scrutinizes six LNG cold energy power generation systems, featuring a newly proposed parallel and cascade combined cycle (PAC) system. A novel approach that setting the minimum pressure within the systems higher than atmospheric levels has been adopted, for the optimal working fluid selection. The net power output (Wnet) of the direct expansion (DC) system registers at -129.51 kW, while both the Single-Stage Organic Rankine Cycle (SORC) and Combined Cycle (CC) systems yield Wnet of 2868.46 kW and 3081.46 kW with R32 as working fluid. Despite the lower available exergy extraction of the working fluid, the CC system outperforms due to its superior efficiency in converting pressure exergy into power output. Sensitivity analysis suggests the optimal Tcon in CC is limited by the normal boiling point temperature (NBPT) of working fluid, while that in SORC remains unrestricted. The maximum Wnet of two-stage Parallel Combined Cycle (PCC) and Cascade Combined Cycle (CCC) can reach 3291.65 kW and 4268.78 with the optimal working fluid combinations R32 + propane, and ethane + propane. The reason Wnet of CCC outperforms is the cascade utilization of LNG cold exergy enables the working fluid in its second stage obtains significantly 9.49 times higher amount of exergy compared to PCC. Through sensitivity analysis, while Tcon1 mostly predominates the performance of PCC, both Tcon1 and Tcon2 exert substantial influence on CCC. For the three-stage PAC, its Wnet can reach the highest 4700.82 kW with ethane + propane + propane. It is because the PAC not only utilizes LNG's cold exergy in a cascaded manner, but also obtains the exergy from working fluid. According to economic analysis, the PAC system exhibits an advantage with the highest annul total net income (ATNI). And the CC emerges as a cost-effective c

关键词： Cold energy power generation genetic algorithm optimization Liquefied natural gas Economic analysis

来源：评论

学校读者我要写书评

暂无评论

Modeling and optimization of biomethane production from solid-state anaerobic co-digestion of organic fraction municipal solid waste and other co-substrates

引用

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS 2024年第1期46卷 8564-8580页

作者： Saghouri, Mohsen Abdi, Reza Ebrahimi-Nik, Mohammadali Rohani, Abbas Maysami, Mohammadali Univ Tabriz Dept Biosyst Engn Fac Agr Tabriz Iran Ferdowsi Univ Mashhad Dept Biosyst Engn Fac Agr Mashhad Razavi Khorasan Iran

One of the simplest methods for increasing productivity in biogas production is co-digestion. Co-digestion leads to more biogas yield as well as more nutrient bioavailability. This study reports the modeling and optimization of biomethane potential tests from different combinations of organic fraction of municipal solid wastes (OFMSW), cow manure (CM), and municipal sewage sludge (MSS) in solid-state. The simplex-centroid mixture design (SCMD) and artificial neural network (ANN) models were validated with a high correlation to the real data (R-2 = 0.99). Experimental results indicated that the maximum amount of CH4 production of 436 mL CH4/g VS occurs at the identical weight percent of the three substances (33.33%). The maximum methane yield was found to be 445.9 mL CH4/g VS as obtained by the genetic algorithm (GA) optimization process, while 448.5 mL CH4/g VS (448.5 +/- 3.05) of methane was produced experimentally. Therefore, integration of the SCMD and ANN model with the GA optimization is useful in the prediction of biomethane production. This research is the first in providing the best combination of co-treating and co-utilizing OFMSW with CM and MSS in the solid-state for biowaste management.

关键词： Anaerobic digestion artificial neural network modeling genetic algorithm optimization methane production statistical regression model

来源：评论

学校读者我要写书评

暂无评论

Systematic micro heat sink optimization based on hydrofoil shape pin fins

引用

CASE STUDIES IN THERMAL ENGINEERING 2021年 26卷

作者： Ismayilov, Fuad Akturk, Ali Peles, Yoav SIEMENS Energy 11842 Corp Blvd Orlando FL 32817 USA Univ Cent Florida 4000 Cent Florida Blvd Orlando FL 32816 USA

Multi-objective optimization of the hydrofoil shaped pin fins for micro heat sinks was studied. optimization tool utilized a multi objective genetic algorithm (MOGA) and a numerical model that was validated against previously obtained experimental single-phase heat transfer results on a hydrofoil shape micro scale pin fin. The numerical model was built using StarCCM + software. Several turbulence models were examined against single-phase experimental data and the Lag-EB k-epsilon turbulence model was chosen for validation. optimization tool varied the shape of the hydrofoil pin fin through flexible parametrization utilizing an ellipse and polynomials. An algorithm coupling pin fin parametrization code, validated the 3D CFD solutions and a MOGA interface was implemented. Subsequently, multi-objective optimization was performed to maximize the heat transfer coefficient while minimizing pressure drop. A broad range of novel geometries were obtained with a tradeoff between thermal and hydraulic performance for low Reynolds number. Novel pin fin shape, bird design, is proposed as a result of the study. Additional 3D steady state conjugate CFD simulations including the bird design pin fin were performed using already verified setup, and it was shown that the enhancement in the average heat transfer coefficient dominates over the pressure drop increase at higher Reynolds numbers.

关键词： Micro/mini-channel Heat sink Conjugate heat transfer modelling Hydrofoil pin fin genetic algorithm optimization Thermal performance enhancement

来源：评论

学校读者我要写书评

暂无评论

Optimizing displacement-based seismic design of mass timber rocking walls using genetic algorithm

引用

ENGINEERING STRUCTURES 2021年 229卷 111603-111603页

作者： Huang, Da Pei, Shiling Busch, Aleesha Colorado Sch Mines Dept Civil & Environm Engn Golden CO 80401 USA

This paper presents a rational procedure to optimize design for mass timber rocking wall systems utilizing a genetic algorithm (GA) beyond typical displacement-based design metrics for wood buildings. Traditional displacement-based design is limited to simple displacement targets, with optimization techniques (GA), it is feasibly to consider more performance chrematistics (e.g. costs, serviceability, etc.). By formulating drift targets and other structural design limit states within an elimination step of the GA optimization process, the method proposed here optimizes rocking wall design with multiple criteria that factor much more than lateral displacement targets in the seismic analysis. This type of optimization is difficult to perform using traditional manual trial-and-error approaches. An existing simplified nonlinear time-history simulation model (validated through full-scale shake table test data) of a wood rocking wall is employed in this process. The design for an example building in Seattle with a six-story rocking wall is presented using the proposed procedure. The results revealed that the optimization of the mass timber rocking wall lateral system can be achieved in a reasonable time frame using the proposed method. Even though the same drift limits were applied, final designs produced by GA varied, depending on the other optimization objectives. This demonstrates how the seismic design of wood rocking wall systems could be readily improved with computerized optimization tools that factor in other aspects of the design including cost.

关键词： Displacement-based design genetic algorithm optimization Mass timber rocking wall Nonlinear time-history analysis

来源：评论

学校读者我要写书评

暂无评论

H7N9 avian influenza diagnosis based on a multilayer belief rule-based inference methodology

引用

EXPERT SYSTEMS 2023年第7期40卷 e13296-e13296页

作者： Xu, Xiaojian Gao, Yucai Xu, Xiaobin Dai, Libo Liu, Shelan Zhang, Shuo Weng, Xu China Waterborne Transport Res Inst Beijing 100088 Peoples R China Hangzhou Dianzi Univ Sch Automation Hangzhou 310018 Zhejiang Peoples R China Zhejiang Univ Affiliated Hosp 1 Coll Med Dept Otolaryngol Hangzhou 310018 Zhejiang Peoples R China Zhejiang Prov Ctr Dis Control & Prevent Hangzhou 310018 Zhejiang Peoples R China Zhejiang Univ Tradit Chinese Med Hangzhou 310018 Zhejiang Peoples R China

H7N9 avian influenza is a novel virus with high morbidity and mortality that threatens human health and life. Therefore, it is necessary to diagnose H7N9 avian influenza in a timely and rapid manner to prevent further transmission of the virus and greatly reduce the infection and mortality rates. This paper proposes an H7N9 avian influenza diagnostic model that is based on a multilayer belief rule-based (BRB) inference methodology by considering five typical characteristics of influenza: epidemiology, clinical manifestations, complications, characteristics of imaging tests and positive pathogen test results. Specifically, the severity of H7N9 avian influenza is gradually identified by a multilayer BRB model, and then the diagnostic model is optimized by a genetic algorithm (GA) to improve the diagnostic accuracy. Finally, the feasibility of the model is verified by fivefold cross-validation with a real clinical dataset. The performance of the proposed diagnostic model is compared with those of the BP neural network (BPNN) model and support vector machine (SVM) model, and the results show that the multilayer BRB model can achieve rapid and satisfactory diagnostic results for H7N9 avian influenza. The experiment shows that the accuracy of the BRB model for H7N9 avian influenza hierarchical diagnosis provided in this paper is 0.903, which is higher than 0.818 of the BP neural network (BPNN) modules and 0.844 of the support vector machine (SVM) models. Especially when diagnosing the suspected and confirmed degree of H7N9 disease, it is more realized satisfactory diagnostic accuracy.

关键词： belief rule-based inference genetic algorithm optimization multilayer diagnostic model

来源：评论

学校读者我要写书评

暂无评论

Linear Phase Second Order Recursive Digital Integrators and Differentiators

Linear Phase Second Order Recursive Digital Integrators and ...

引用

作者： Jain, M. Brno University of Technology

In this paper, design of linear phase second order recursive digital integrators and differentiators is discussed. New second order integrators have been designed by using genetic algorithm (GA) optimization method. Thereafter, by modifying the transfer function of these integrators appropriately, new digital differentiators have been obtained. The proposed digital integrators and differentiators accurately approximate the ideal ones and have linear phase response over almost entire Nyquist frequency range. The proposed operators also outperform the existing operators in terms of both magnitude and phase response.

关键词： Linear optimization genetic algorithm optimization digital integrator digital differentiator

来源：评论

学校读者我要写书评

暂无评论

Development of diesel surrogates for reproducing the effect of fuel properties on engine combustion and emissions using an optimized decoupling physical-chemical surrogate (DPCS) model

引用

FUEL 2022年第PartB期310卷 122424-122424页

作者： Zhu, Yongfei Jia, Ming Niu, Bo Tian, Jiangping Li, Haiying Fan, Juting Dalian Univ Technol Key Lab Ocean Energy Utilizat & Energy Conservat Minist Educ Dalian 116024 Peoples R China China North Engine Res Inst Tianjin 300400 Peoples R China

An optimized decoupling physical-chemical surrogate (DPCS) model was carried out to formulate different diesel surrogates effectively. In the optimized DPCS model, the physical candidates of ten components and the chemical candidates of four components are coupled by the rule of hydrocarbon type to match the physical-chemical properties of diesel fuel. The composition of the physical components is determined using genetic algorithm (GA), and then the coupling rule is applied to derive the composition of the chemical components. To validate the robustness of the optimized DPCS model, the prediction results are compared with the experimental results containing vapor penetration distance in a constant volume bomb (CVB) and the combustion and emission characteristics in a convention diesel combustion (CDC) engine utilizing different diesel fuels. The results show that the predictions of the diesel surrogates formulated by the optimized DPCS model accurately fit the experimental results, and the impacts of diesel fuel properties on the spray and combustion behaviors can be well reproduced. Besides, the factors that dominate the spray and combustion features of different diesel fuels are identified.

关键词： Diesel fuel Physical-chemical properties Multi-component surrogate Numerical simulation genetic algorithm optimization

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：