检索结果-内蒙古大学图书馆

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ba, Yunpeng Zheng, Ruihao Wang, Zhenkun School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350308365

The heterogeneous fleet vehicle routing problem (HFVRP) is of great significance in logistics and transportation. This paper considers a crucial and challenging HFVRP variant, namely multi-objective fleet size and mix vehicle routing problem with unlimited fleet, fixed cost, and dependent cost (MO-FSMVRPFD). A decomposition-based memetic algorithm called MOEA/D-ALS is proposed to cope with MO-FSMVRPFD. MOEA/D-ALS uses the multi-objective evolutionary algorithm based on decomposition (MOEA/D) as the backbone. Beyond that, it adopts a replacement strategy based on maximal fitness improvement (MFI). In addition, the local search is conducted on difficult subproblems for further refinement. The experimental studies on 18 instances show that MOEA/D-ALS exhibits a significant performance superiority over two other representative algorithms. The effectiveness of both the MFI strategy and the adaptive local search procedure is also validated. © 2024 IEEE.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Knowledge and data jointly driven aeroengine gas path performance assessment method

引用

Chinese Journal of Aeronautics 2024年第5期37卷 533-557页

作者： Zhe WANG Xuyun FU Rui ZHANG Zhengfeng BAI Xiangzhao XIA Wei JIANG Department of Mechanical Engineering Harbin Institute of TechnologyWeihai 264209China Weihai Key Laboratory of Intelligent Operation and Maintenance Harbin Institute of TechnologyWeihai 264209China Control System Design Laboratory AECC ShenYang Engine Research InstituteShenyang 110015China

Aeroengines,as the sole power source for aircraft,play a vital role in ensuring flight *** gas path,which represents the fundamental pathway for airflow within an aeroengine,directly impacts the aeroengine's performance,fuel efficiency,and ***,timely and accurate evaluation of gas path performance is of paramount *** paper proposes a knowledge and data jointly driven aeroengine gas path performance assessment method,combining Fingerprint and gas path parameter deviation ***,Fingerprint is used to correct gas path parameter deviation values,eliminating parameter shifts caused by non-component performance ***,coarse errors are removed using the Romanovsky criterion for short-term data divided by an equal-length overlapping sliding ***,an Ensemble Empirical Mode Decomposition and Non-Local Means(EEMD-NLM)filtering method is designed to“clean”data noise,completing the preprocessing for gas path parameter deviation ***,based on the characteristics of gas path parameter deviation values,a Dynamic Temporary Blended Network(DTBN)model is built to extract its temporal features,cascaded with Multi-Layer Perceptron(MLP),and combined with Fingerprint to construct a Dynamic Temporary Blended AutoEncoder(DTB-AutoEncoder).Eventually,by training this improved autoencoder,the aeroengine gas path multi-component performance assessment model is formed,which can sufficiently decouple the nonlinear mapping relationship between aeroengine gas path multi-component performance degradation and gas path parameter deviation values,thereby achieving the performance assessment of engine gas path *** practical application cases,the effectiveness of this model in assessing the aeroengine gas path multi-component performance is verified.

关键词： Performance assessment Aeroengine Fingerprint Gas path parameter deviation values Jointly drive

来源：评论

学校读者我要写书评

暂无评论

Tuning mechanical behaviors of highly entangled hydrogels with the random distribution of mobile entanglements

引用

Applied Mathematics and Mechanics(English Edition) 2024年第2期45卷 277-294页

作者： Jinlong LIU Di LU Bin CHEN Department of Engineering Mechanics Zhejiang UniversityHangzhou 310027China Beijing System Design Institute of Electro-Mechanic Engineering Beijing 100854China Intelligent Robotic Research Center Zhejiang LaboratoryHangzhou 310027China Key Laboratory of Soft Machines and Smart Devices of Zhejiang Province Hangzhou 311100China

Highly entangled hydrogels exhibit excellent mechanical properties,including high toughness,high stretchability,and low *** considering the evolution of randomly distributed entanglements within the polymer network upon mechanical stretches,we develop a constitutive theory to describe the large stretch behaviors of these *** the theory,we utilize a representative volume element(RVE)in the shape of a cube,within which there exists an averaged chain segment along each edge and a mobile entanglement at each *** employing an explicit method,we decouple the elasticity of the hydrogels from the sliding motion of their entanglements,and derive the stress-stretch relations for these *** present theoretical analysis is in agreement with experiment,and highlights the significant influence of the entanglement distribution within the hydrogels on their *** also implement the present developed constitutive theory into a commercial finite element software,and the subsequent simulations demonstrate that the exact distribution of entanglements strongly affects the mechanical behaviors of the structures of these ***,the present theory provides valuable insights into the deformation mechanism of highly entangled hydrogels,and can aid in the design of these hydrogels with enhanced performance.

关键词： highly entangled hydrogel constitutive theory entanglement gamma distribution

来源：评论

学校读者我要写书评

暂无评论

Dual-State-Driven Evolutionary Optimization for Expensive Optimization Problems with Continuous and Categorical Variables 5

Dual-State-Driven Evolutionary Optimization for Expensive Op...

引用

5th International Conference on Data-Driven Optimization of Complex systems, DOCS 2023

作者： Xie, Lindong Li, Genghui Lin, Kangnian Wang, Zhenkun School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350393521

The surrogate-assisted evolutionary algorithm (SAEA) is one of the most efficient approaches for addressing expensive continuous or combinatorial optimization problems. However, it encounters significant challenges in expensive mixed-variable optimization problems (EMVOPs). To overcome this limitation, a dual-state-driven evolutionary optimization (called DSDEO), integrating a surrogate-assisted mixed-variable evolutionary optimization stage (MVEOS) and a surrogate-assisted continuous-variable evolutionary optimization stage (CVEOS), is proposed in this paper. Specifically, MVEOS employs global and local search to enhance the exploration and exploitation of the mixed-variable space. Global and local searches are alternately executed if one search fails to yield a better solution. CVEOS utilizes a continuous-improvement strategy to refine the continuous variables of the best solution obtained so far. Experimental results demonstrate the advantages of DSDEO compared to some state-of-the-art SAEAs on many benchmark problems. © 2023 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep learning from three-dimensional Lithium-ion battery multiphysics model Part II:Convolutional neural network and long short-term memory integration

引用

Energy and AI 2024年第3期17卷 569-578页

作者： Yiheng Pang Anqi Dong Yun Wang Zhiqiang Niu Renewable Energy Resources Lab(RERL) Department of Mechanical and Aerospace EngineeringUniversity of CaliforniaIrvineCaliforniaUSA92697-3975 College of Engineering School of System Design and Intelligent ManufacturingSouthern University of Science and TechnologyChina Department of Aeronautical and Automotive Engineering Loughborough UniversityUnited KingdomLE113TU

Lithium-ion (Li-ion) batteries have emerged as a cornerstone of electric vehicles (EVs), enabling the road transportation towards net zero. The success of electric vehicles largely hinges on the battery performance and safety. It is challenging to test and predict battery performance and safety issues by conventional methods, which are usually time-consuming and expensive, involving significant human and measurement errors. To enable the quick estimation of battery performance and safety, we developed three data-driven machine learning (ML) models, namely a convolutional neural network (CNN), a long short-term memory (LSTM), and a CNN-LSTM to predict battery discharge curves and local maximum temperature (hot spot) under various operating conditions. The developed ML models mitigated data scarcity by employing a three-dimensional multi-physics Li-ion battery model to generate enormous and diverse high-quality data. It was found the CNN-LSTM model outperforms the others and achieved high accuracy of 98.68% to learn discharge curves and battery maximum temperature, owing to the integration of spatial and sequential feature extraction. The battery safety can be improved by comparing the predicted maximum battery temperature against safe temperature threshold. The proposed data development and data-driven ML models are of great potential to provide digital tools for engineering high-performance and safe EVs.

关键词： Li-ion batteries CNN LSTM Integration Performance Hot spot

来源：评论

学校读者我要写书评

暂无评论

A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials

引用

International Journal of Extreme Manufacturing 2023年第3期5卷 620-644页

作者： Chunlei He Jiwang Yan Shuqi Wang Shuo Zhang Guang Chen Chengzu Ren Tianjin Key Laboratory of Equipment Design and Manufacturing Technology Department of Mechanical EngineeringTianjin UniversityTianjin 30054People’s Republic of China Department of Mechanical Engineering Keio UniversityYokohama 223-8522Japan Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System School of Mechanical EngineeringTianjin University of TechnologyTianjin 300384People’s Republic of China School of Mechanical Engineering Yanshan UniversityQinhuangdao 066004People’s Republic of China

Polycrystalline materials are extensively employed in *** surface roughness significantly affects the working *** defects,particularly grain boundaries,have a great impact on the achieved surface roughness of polycrystalline ***,it is difficult to establish a purely theoretical model for surface roughness with consideration of the grain boundary effect using conventional analytical *** this work,a theoretical and deep learning hybrid model for predicting the surface roughness of diamond-turned polycrystalline materials is *** kinematic–dynamic roughness component in relation to the tool profile duplication effect,work material plastic side flow,relative vibration between the diamond tool and workpiece,etc,is theoretically *** material-defect roughness component is modeled with a cascade forward neural *** the neural network,the ratio of maximum undeformed chip thickness to cutting edge radius RT S,work material properties(misorientation angle θ_(g) and grain size d_(g)),and spindle rotation speed n s are configured as input *** material-defect roughness component is set as the output *** validate the developed model,polycrystalline copper with a gradient distribution of grains prepared by friction stir processing is machined with various processing parameters and different diamond *** with the previously developed model,obvious improvement in the prediction accuracy is observed with this hybrid prediction *** on this model,the influences of different factors on the surface roughness of polycrystalline materials are *** influencing mechanism of the misorientation angle and grain size is quantitatively *** fracture modes,including transcrystalline and intercrystalline fractures at different RTS values,are ***,optimal processing parameters are obtained with a simulated annealing *** experiments are performed with

关键词： diamond turning material-defect roughness component polycrystalline copper neural network simulated annealing algorithm

来源：评论

学校读者我要写书评

暂无评论

Lithium-Ion Battery State-of-Charge and State-of-Health Co-Estimation with Feasible Real-Time Implementation 8

Lithium-Ion Battery State-of-Charge and State-of-Health Co-E...

引用

8th CAA International Conference on Vehicular Control and Intelligence, CVCI 2024

作者： Shao, Mingding Chen, Jian Xu, Ke Wang, Yong School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of Mechanical Engineering Zhejiang University Hangzhou China Wanxiang Al23 Systems Corp. Department of System Engineering Hangzhou China

ISBN: (纸本)9798331504892

The key to improving the efficiency of lithium-ion battery systems and reducing safety incidents is that the battery management system can accurately estimate the state of lithiumion batteries, including the state of charge and the state of health. At present, the commonly used algorithms do not achieve an effective balance between accuracy and complexity, and it is difficult to apply them in practice. Therefore, on the basis of the existing algorithms, this paper proposes to reduce the order of the equivalent circuit model, simplify the observer polynomial, achieve low computational complexity, and use a processor with limited storage to complete the estimations. The simulation and experimental results confirm that the maximum absolute error of the state of charge and state of health of the lithium-ion battery systems fully meet the requirements of practical use. Compared with the reference method, there is no obvious difference in convergence speed and stability, but the run time is relatively faster. The proposed method has a significant simplification effect. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 18-36页

作者： Ding Wang Ning Gao Derong Liu Jinna Li Frank L.Lewis IEEE the Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent SystemBeijing Laboratory of Smart Environmental Protectionand Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China the School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China the Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA the School of Information and Control Engineering Liaoning Petrochemical UniversityFushun 113001China the UTA Research Institute the University of Texas at ArlingtonArlington TX 76118 USA

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, ***, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation ***, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

关键词： Adaptive dynamic programming(ADP) advanced control complex environment data-driven control event-triggered design intelligent control neural networks nonlinear systems optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Supportless Cylindrical Printing of Rotating Components with Overhangs on a Rotary FDM 3D Printer

Supportless Cylindrical Printing of Rotating Components with...

引用

International Conference on Mechanical design, ICMD 2023

作者： Zhao, Donghua Ruan, Kaicheng Zhang, Guoquan Wang, Yaohui Chen, Ziwen Zha, Xinmeng Dong, Ke Xiong, Yi School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Kowloon Hong Kong

ISBN: (纸本)9789819709212

In Additive Manufacturing (AM), the need for curved layer path planning and printing has emerged as a significant advancement beyond 2.5D printing, particularly for rotating components with overhang structures like propellers that require supports. However, existing slicing methods for cylindrical surfaces, both direct and parametrised, fall short of meeting the diverse filling pattern requirements of general rotating components, creating a process planning gap. Moreover, existing mapping-based process planning research primarily centres around metal printing utilising costly printing equipment, including robots or printers with more than four axes, rather than the affordable Fused Deposition Modeling (FDM) technology. To address these challenges, this paper introduces an innovative surface-plane mapping-based cylindrical slicing strategy that utilises a triangle mesh model. This approach overcomes the limitations of costly equipment by leveraging low-cost three-axis FDM 3D printers with a rotary build platform. The proposed technique can generate cylindrical paths of various patterns such as line-arc-line, helix, circle-line-circle, and contours and offers the potential for supportless printing of rotating components with overhangs, which is not achievable with traditional bottom-up printing methods. Experimental results demonstrate the effectiveness of the cylindrical slicing method for printing propellers with different patterns. The findings provide process designers with an innovative slicing and supportless printing approach for rotating components with overhangs on a rotary economical 3D printer with three-axis, enabling improved geometric accuracy, reduced material waste, and enhanced mechanical performance in AM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Indentation behavior of a semi-infinite piezoelectric semiconductor under a rigid flat-ended cylindrical indenter

引用

Applied Mathematics and Mechanics(English Edition) 2024年第4期45卷 649-662页

作者： Shijing GAO Lele ZHANG Jinxi LIU Guoquan NIE Weiqiu CHEN State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures Shijiazhuang Tiedao UniversityShijiazhuang 050043China School of Mechanical Engineering Shijiazhuang Tiedao UniversityShijiazhuang 050043China Hebei Key Laboratory for Mechanics of Intelligent Materials and Structures Department of Engineering MechanicsShijiazhuang Tiedao UniversityShijiazhuang 050043China State Key Laboratory of Computer Aided Design and Computer Graphics Key Laboratory of Soft Machines and Smart Devices of Zhejiang ProvinceDepartment of Engineering MechanicsZhejiang UniversityHangzhou 310027China

This paper theoretically studies the axisymmetric frictionless indentation of a transversely isotropic piezoelectric semiconductor(PSC)half-space subject to a rigid flatended cylindrical *** contact area and other surface of the PSC half-space are assumed to be electrically *** the Hankel integral transformation,the problem is reduced to the Fredholm integral equation of the second *** equation is solved numerically to obtain the indentation behaviors of the PSC half-space,mainly including the indentation force-depth relation and the electric potential-depth *** results show that the effect of the semiconductor property on the indentation responses is limited within a certain range of variation of the steady carrier *** dependence of indentation behavior on material properties is also analyzed by two different kinds of *** element simulations are conducted to verify the results calculated by the integral equation technique,and good agreement is demonstrated.

关键词： piezoelectric semiconductor(PSC) insulating indenter electromechanical response singular integral equation finite element simulation

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：