检索结果-内蒙古大学图书馆

multi-objective optimization design of foam concrete mechanical properties through the integration of FEM and DL

ADVANCED ENGINEERING INFORMATICS 2025年 64卷

作者： Ruan, Bin Li, Juncheng Zhou, Zhenglong Huang, Hao Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Hubei Peoples R China Nanjing Tech Univ Inst Geotech Engn Nanjing 210009 Jiangsu Peoples R China

The factors influencing the microstructural characteristics and energy absorption capacity of foam concrete are numerous and complex, making it challenging to accurately characterize them using mathematical functions. This paper proposes an integral implementation framework based on convolutional neural network (CNN), gated recurrent unit (GRU) and channel attention mechanism. By utilizing X-ray Computed Tomography (X-CT) scanning, the complete pore structure of foam concrete is obtained, and establish its finite element method (FEM) model. A comprehensive analysis of the regularities related to material parameters and external loading conditions is conducted, focusing on the compressive strength 6 c and energy absorption ability WEA. Parameters that significantly influence 6 c and W EA are selected as input variables for the deep learning (DL) model. Employing the combined CNN-GRU-Attention neural network as the predictive model, and integrating mechanisms for prediction error compensation and dynamic updating of the dataset, the model achieves accurate predictions of foam concrete performance. Based on the DL model, objective functions for 6 c and W EA are developed, and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to solve for the optimal design characteristics that correspond to maximum 6 c and WEA, thus realizing the optimal performance design of foam concrete. The results demonstrate that: (1) the stress-strain curve outcomes from numerical simulations align well with the experimental findings, accurately reflecting the mechanical behaviour of foam concrete. (2) The CNN-GRU-Attention model facilitates precise predictions of 6 c and WEA, with R 2 values of the training set reaching 0.993 and 0.981, maintaining high predictive precision even with small data samples. (3) Following optimization using the NSGAII algorithm, 6 c increased by 24.17%, and W EA by 27.46%, signifying a significant enhancement in the performance of foam concrete.

关键词： Foam concrete Deep learning multi-objective optimization Numerical simulation Compressive strength Energy absorption capacity

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of automotive seat frames using machine learning

引用

ADVANCES IN ENGINEERING SOFTWARE 2025年 199卷

作者： Chen, Haifeng Yu, Ping Long, Jiangqi Wenzhou Univ Coll Mech & Elect Engn Chashan St Wenzhou 325035 Peoples R China

The optimal design of automobile seats plays an important role in passenger safety in high-speed accidents. In order to enhance the accuracy of the prediction of the input variables and output response of the seat, a hybrid machine learning prediction model that combines the improved gray wolf optimizer (IGWO) and back propagation neural network (BPNN) has been proposed, and the prediction effect of the model was validated using the seat simulation data. Initially, based on the experimental data, finite element models were developed for eight typical working conditions of automobile seats and their accuracy was validated. Subsequently, the energy absorption to mass ratio method was employed to screen the design variables, resulting in the selection of 17 thickness variables and 15 material variables. Thereafter, the gray wolf optimizer (GWO) algorithm underwent enhancement through the incorporation of the dynamic leadership hierarchy (DLH) mechanism and the revision of the positional formula, yielding the IGWO algorithm. Following this, the IGWO algorithm was applied to optimize the hyperparameters of BPNN, culminating in the establishment of the IGWO-BPNN model. Ultimately, the seat multi-objective optimization design process was addressed using multi-objective gray wolf optimizer (MOGWO) to achieve the Pareto frontier, while the decision-making was conducted using the combined compromise solution (CoCoSo) method to determine the best trade-off solution. Furthermore, the effectiveness of the proposed optimal design method is evidenced by comparing the baseline design, simulation analysis, and optimal design methods. The results indicate that the optimized automotive seat frame achieves a reduction in cost by 20.7 % and mass by 22.9 %, simultaneously maintaining safety performance. Consequently, the proposed optimization design methodology is demonstrated to be highly effective for the multi-objective optimization design of automotive seat frames.

关键词： Seat frame Machine learning Improved grey wolf optimizer multi-objective optimization multi-criteria decision-making

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization and experimental investigation of friction stir welding under Minimum quantity lubrication

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING 2025年第2期239卷 993-1004页

作者： Al-Wajidi, Wisam Eltaggaz, Abdelkrem Defersha, Fantahun M. Deiab, Ibrahim Univ Guelph Sch Engn Adv Mfg Lab Guelph ON Canada Mustansiriyah Univ Fac Engn Mat Engn Dept Baghdad Iraq

Aluminium is widely used in the aerospace, marine, and transportation industries. However, achieving defect-free, high-quality welds using conventional welding processes is challenging. Friction stir welding (FSW) is a promising solid-state welding process that is environmentally friendly, produces high-quality welds, and improves the mechanical and other properties of aluminium and other lightweight materials. This study examines the welding force, power consumption, and surface roughness of friction stir-welded 6061-T651 and 5052-H32 aluminium alloys under similar and dissimilar circumstances using the minimum quantity lubrication (MQL) process. The main variables of the MQL system, including flow rate, nozzle orientation, and nozzle diameter, were analysed using analysis of variance. A multi-objective model was used to predict the optimal levels, and grey relational analysis techniques were applied for optimization. Furthermore, this study provides a clear mechanism for using MQL during FSW. The results indicate that a flow rate of 7.5 ml/h reduces welding forces by 25% and 4% compared to 5 ml/h and 10 ml/h, respectively. Additionally, the 7.5 ml/h flow rate reduces power consumption by 20% and 10% compared to 5 ml/h and 10 ml/h, respectively. In addition, it improves the surface quality. The orientation nozzle angle of 60 degrees yielded slightly better results than those at the other levels. Similarly, for the nozzle diameter, both 2.5 mm and 3.75 mm showed slightly better results in terms of welding forces, power consumption, and surface roughness.

关键词： Friction stir welding minimum quantity lubrication aluminium alloys analysis of variance multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of geometrical parameters of a pipe with internal baffle using artificial neural networks and genetic algorithm

引用

APPLIED THERMAL ENGINEERING 2025年 262卷

作者： Shoaei, Mersad Kowsary, Farshad Univ Tehran Sch Mech Engn Tehran Iran Univ Tehran Dept Renewable Energies & Environm Engn Tehran Iran

The significant importance of energy and its extensive utilization in recent years has compelled researchers to conduct investigations in order to discover methods for conserving and utilizing energy resources in the most efficient manner. This study examines the influence of the geometric characteristics of a baffled pipe on its thermal efficiency, including heat transfer rate and power consumption, by employing Computational Fluid Dynamics (CFD) methods. Subsequently, the neural network was employed on the numerical simulation data, utilizing evolutionary algorithms and machine learning techniques. The NSGA-II method will then be utilized to optimize the two inverse objectives of heat transfer and power consumption through reduction. The investigated Reynolds values vary from 10,000 to 70,000, and the fluids used are water and air. The findings indicate that when the Reynolds number increases, there is a drop in the maximum rate of heat transfer and an increase in the amount of power consumption needed. In addition, the best values of geometric variables remain unaffected by the kind of fluid at particular velocity intervals. Furthermore, the proportion between the length of the baffle and the diameter of the pipe will significantly enhance heat transfer. Consequently, pipes with baffles exhibit superior thermal efficiency compared to pipes without baffles.

关键词： Baffled heat exchanger Heat transfer multi-objective optimization Neural networks NSGA-II

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization in the design of load sharing systems with mixed redundancy strategies under random shocks

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2025年 85卷

作者： Yaghtin, Mohammad Javid, Youness Ardakan, Mostafa Abouei Kharazmi Univ Engn Fac Ind Engn Dept Tehran Iran

The redundancy allocation problem (RAP) focuses on assigning one or more components in parallel to enhance the overall reliability of a system. Selecting a redundancy type (active or standby) for each component is a critical challenge in system design. Active components can share the load among themselves (unlike standby components), and standby components are not subjected to shock attacks (unlike active components). This research presents a multi-objective optimization model to enhance system reliability and minimize costs. The proposed model is designed for a load-sharing system with a series-parallel structure, subject to shock attacks. Reliability (availability) is calculated using a stochastic approach based on the Markov chain, and the NSGA-II algorithm solves the multi-objective optimization problem. Two numerical examples investigate the proposed approach, identifying appropriate solutions through Pareto frontiers and analyzing the impact of load-sharing and shock attacks on optimization results.

关键词： Reliability Load sharing Shock attacks multi-objective optimization Mixed redundancy strategies

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization of the appendages of a sailing yacht using the Normal Boundary Intersection method

引用

MATHEMATICS AND COMPUTERS IN SIMULATION 2025年 229卷 885-895页

作者： Peri, Daniele CNR Ist Applicazioni Calcolo M Picone Via Taurini 19 I-00185 Rome Italy

In this paper, a multidisciplinary design optimization algorithm, the Normal Boundary Intersection (NBI) method, is applied to the design of some devices of a sailing yacht. The full Pareto front is identified for two different design problems, and the optimal configurations are compared with standard devices. The great efficiency of the optimization algorithm is demonstrated by the wideness and density of the identified Pareto front.

关键词： multi-objective optimization Normal boundary intersection Yacht design Sailing yacht

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization design of recycled concrete based on the physical characteristics of aggregate

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 458卷

作者： Wang, Dayang Ji, Yongcheng Xu, Wenyuan Lu, Junkai Dong, Qingjie Northeast Forestry Univ Sch Civil Engn & Transportat Harbin 150040 Peoples R China

A methodology based on the characterization of aggregate's physical properties is proposed to meet the diverse demands for compression resistance, flexural resistance, and cost-effectiveness of various recycled aggregate concrete (RAC). Firstly, the physical properties of three recycled aggregates (RA) with different proportions are investigated. The effects of coarse and fine aggregate types, RA content, and polyvinyl alcohol (PVA) additions on the mechanical properties of RAC are studied. Secondly, a database is created based on the experimental results. Potential combinations of input parameters are selected using correlation coefficient and collinearity diagnosis. Moreover, a neural network handles the complex nonlinear relationship between the input parameters and the target requirements. Thirdly, the Pareto frontier is solved by combining the algorithm with the highest fitting accuracy as the objective function with the Non-dominated Sorting Genetic Algorithm II (NSGA-II). Finally, the Ideal Point Method is employed to search for Pareto solutions to find the optimal mix ratio schemes with different preferences. The proposed method achieves a maximum error of 10.27 % between actual and calculated concrete mix costs, validating its effectiveness. It can simultaneously optimize various RAC mix proportions to achieve desired mechanical and economic targets.

关键词： Recycled aggregate concrete Mixture design multi-objective optimization Machine learning Mechanical properties

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization and thermodynamic analysis of a supercritical CO2 Brayton cycle in a solar-powered multigeneration plant for net-zero emission goals

引用

ENERGY CONVERSION AND MANAGEMENT 2025年 328卷

作者： Bakircioglu, Veli Jond, Hossein B. Yilmaz, Fatih Czech Tech Univ Fac Elect Engn Dept Cybernet Prague 2 Czech Republic Aksaray Univ TR-68100 Aksaray Turkiye Isparta Univ Appl Sci Fac Technol Dept Mechatron Engn TR-32200 Isparta Turkiye

The development, design, examination, and optimization of carbon-free power generation models are essential to achieve a sustainable future with net-zero emissions. This study introduces a novel multigeneration system, uniquely combining a supercritical CO2 Brayton cycle and a transcritical CO2 Rankine cycle, supported by a solar parabolic trough collector. The system integrates a reverse osmosis desalination unit, enabling simultaneous production of clean water, heating, and power. A multi-objective optimization framework is implemented by the NSGA-II algorithm, coupled with the TOPSIS method, to explore and identify optimal operational conditions. The innovation lies in the comprehensive consideration of solar incident angles and their impact on system performance, a rarely addressed aspect in the literature. Detailed thermodynamic analysis highlights system performance, achieving a net power capacity of 1052 kW, freshwater generation of 90.44 m3/h, and hot water generation of 1614 kW. The optimized results demonstrate significant improvements in overall energy (50.28 %) and exergy efficiency (22.31 %), showcasing the system's potential as a benchmark for sustainable, zero-emission energy solutions.

关键词： Energy Exergy Freshwater Solar energy multi-objective optimization TOPSIS

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization OF A356 ENGINE BLOCK CASTING PROCESS PARAMETERS BASED ON RESPONSE SURFACE METHOD AND NSGA-II GENETIC ALGORITHM

引用

INTERNATIONAL JOURNAL OF METALCASTING 2025年 1-19页

作者： Deng, Wei Song, Zhongmo Lei, Jilin Luo, Kun Zhang, Yong Yu, Mingjiang Kunming Univ Sci & Technol Prov Key Lab Internal Combust Engine Kunming Yunnan Peoples R China Chengdu Zhengheng Power Co Ltd Chengdu Sichuan Peoples R China Kunming Yunnei Power CO LTD Kunming 650200 Yunnan Peoples R China

In order to improve the casting quality of the engine block and reduce the casting cost, this paper takes the an A356 alloy engine block as the research object, takes the alloy pouring temperature, mold preheating temperature, filling time and holding pressure four process parameters as the influencing factors, and takes the solidification time and shrinkage volume as the evaluation objectives, and uses the response surface method(RSM) to design 29 sets of test schemes, and conducts multi-objective analysis based on NSGA-II genetic algorithm and satisfaction function. The results show that the optimized process parameters are as follows: alloy pouring temperature 680 degrees C, mold preheating temperature 20 degrees C, filling time 12s and holding pressure 50 kPa. Compared with the initial process, the solidification time was shortened by 12.55% and the shrinkage volume was improved by 2.24% under the combination of optimized process parameters. After production verification, the casting molding quality is good and the mechanical properties to meet the requirements, which well verifies the rationality of the optimized process parameters, and the research can provide effective guidance for the actual production of engine blocks.

关键词： engine block response surface method NSGA-II genetic algorithm multi-objective optimization production validation

来源：评论

学校读者我要写书评

暂无评论

multi-objective optimization for Data Collection in UAV-Assisted Agricultural IoT

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第4期74卷 6488-6503页

作者： Liu, Lingling Wang, Aimin Sun, Geng Li, Jiahui Pan, Hongyang Quek, Tony Q. S. Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Singapore Univ Technol & Design Informat Syst Technol & Design ISTD Pillar Singapore 487372 Singapore Hainan Univ Sch Informat & Commun Engn Haikou 570228 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Peoples R China Nanyang Technol Univ Data Sci Singapore 639798 Singapore Singapore Univ Technol & Design Pillar Engn Syst & Design ESD Singapore 487372 Singapore Dalian Maritime Univ Informat Sci & Technol Coll Dalian 116026 Peoples R China Singapore Univ Technol & Design Singapore 487372 Singapore

To enhance the observation and management of agricultural plants, it is critical to collect data from Internet of Things (IoT) devices in agriculture. However, the use of fixed ground-based stations (BSs) often results in inflexible deployment, high overhead costs, and increased vulnerability to damage from natural disasters, which can impede continuous data collection. To address these challenges, this work explores the use of Unmanned Aerial Vehicles (UAVs) as aerial BSs to gather data from IoT devices. First, we formulate a UAV-assisted data collection multi-objective optimization problem (UDCMOP) to efficiently collect agricultural data. Specifically, we aim to collaboratively optimize the hovering positions of UAV, visit sequence of UAV, speed of UAV, and the transmit power of devices, to simultaneously maximize the minimum transmit rate of devices, minimize the total energy consumption of devices and UAV. Second, the proposed UDCMOP is characterized as a non-convex mixed integer nonlinear optimization problem, containing both continuous and discrete variables, which presents considerable challenges in terms of solvability. Therefore, we solve it by proposing an improved multi-objective artificial hummingbird algorithm (IMOAHA) with several specific improvement factors, including the hybrid initialization operator, Cauchy mutation foraging operator, and the discrete mutation operator. Simulations are carried out to testify that the proposed IMOAHA can effectively improve the system performance in comparison to existing benchmarks. Additionally, to verify the effective working time of the UAV system, we investigate both random and uniform UAV deployment strategies and consider the impact of varying farm topology on the system model. Finally, practical implementation experiments using a Raspberry Pi confirm the feasibility and effectiveness of the proposed UAV-assisted communication system in real-world environment.

关键词： Autonomous aerial vehicles Internet of Things Data collection Sensors Wireless sensor networks Agriculture optimization Wireless communication Energy consumption Transportation UAV agricultural Internet of Things data collection multi-objective 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：