检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hua, Min Chen, Dong Jiang, Kun Zhang, Fanggang Wang, Jinhai Wang, Bo Zhou, Quan Xu, Hongming The School of Engineering University of Birmingham Birmingham United Kingdom The Environmental Institute & Link Lab & Computer Science University of Virginia VA United States The School of Automation Southeast University Nanjing China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan China The Automotive New Technology Research Institute BYD Auto Shenzhen China The School of Automotive Studies Tongji University Shanghai China

Cooperative adaptive cruise control (CACC) has been recognized as a fundamental function of autonomous driving, in which platoon stability and energy efficiency are outstanding challenges that are difficult to accommodate in real-world operations. This paper studied the CACC of connected and autonomous vehicles (CAVs) based on the multi-agent reinforcement learning algorithm (MARL) to optimize platoon stability and energy efficiency simultaneously. The optimal use of communication bandwidth is the key to guaranteeing learning performance in real-world driving, and thus this paper proposes a communication-efficient MARL by incorporating the quantified stochastic gradient descent (QSGD) and a binary differential consensus (BDC) method into a fully-decentralized MARL framework. We benchmarked the performance of our proposed BDC-MARL algorithm against several several non-communicative and communicative MARL algorithms, e.g., IA2C, FPrint, and DIAL, through the evaluation of platoon stability, fuel economy, and driving comfort. Our results show that BDC-MARL achieved the highest energy savings, improving by up to 5.8%, with an average velocity of 15.26 m/s and an inter-vehicle spacing of 20.76 m. In addition, we conducted different information-sharing analyses to assess communication efficacy, along with sensitivity analyses and scalability tests with varying platoon sizes. The practical effectiveness of our approach is further demonstrated using real-world scenarios sourced from open-sourced OpenACC. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimization of Plate-Fin Heat Exchanger Performance for Heat Dissipation of Thermoelectric Cooler

SSRN

引用

SSRN 2023年

作者： He, Zixuan Yu, Qinghua Ye, Jiedong Yan, Fuwu Li, Yongliang School of Automotive Engineering Wuhan University of Technology Wuhan430070 China Hubei Key Laboratory of Advanced Technology of Automotive Components Wuhan University of Technology Wuhan430070 China Birmingham Centre for Energy Storage School of Chemical Engineering University of Birmingham BirminghamB15 2TT United Kingdom Beibu Gulf University China

The heat dissipation model of the thermoelectric cooler heat side with a plate-fin sink was established based on the computational fluid dynamics method. The heat dissipation performances of plate-fin sinks with two types of fins (rectangular and V-type) were explored in two convective conditions (lateral and vertical) and three arrangements (single-row, double-row aligned, and double-row staggered). The results show that the rectangular fins have a better overall cooling effect on the heat source in both convective conditions. Under vertical jet conditions, double-row aligned rectangular fins have the best heat dissipation capability for the hot side of the thermoelectric cooler. In order to optimize the fin geometry and maximize its overall performance, a multi-objective optimization of the fins was performed using a machine learning approach based on artificial neural networks and NSGA-ІІ. The corresponding Pareto front is obtained and the TOPSIS method is applied to take the point. Compared with the base case at the same mass flow rate, the fins designed by this method resulted in a 23.3% reduction in the mean temperature of the heat source. © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Parameter optimization of curing kinetics model of epoxy based on Ant-Lion Optimizer

Parameter optimization of curing kinetics model of epoxy bas...

引用

IEEE advanced Information technology, Electronic and Automation Control Conference (IAEAC)

作者： Wenbin Zhang Hui Wang Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan China Hubei Collaborative Innovation Center for Automotive Components Technology Wuhan China Hubei Research Center for New Energy & Intelligent Connected Vehicle Wuhan University of Technology Wuhan China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

For the sake of accurately obtain the reaction rate constant and reaction order in the curing kinetic model of epoxy resin, aiming at the problem that it is difficult to determine the parameters of the curing kinetic model of epoxy resin, the fitting problem is transformed into a multi-objective optimization problem, the coefficients to be solved are put into a vector into the fitness function, and the ant lion algorithm is used to iteratively optimize the optimal solution vector. Through coarse search and detailed search, the size of solution space is reduced, and the optimal roulette roulette strategy is added to prevent the algorithm from falling into the local optimal solution. Finally, Nash efficiency coefficient was used to test the fitting results. The test results show that the ant lion algorithm has high accuracy and application value in determining the parameters of epoxy resin curing kinetics model.

关键词： Fitting Epoxy resins Curing Kinetic theory Root mean square Information technology Optimization

来源：评论

学校读者我要写书评

暂无评论

One-dimensional convolutional neural network model driven intelligent operation phases identification of hydraulic press using energy data

引用

Engineering Applications of Artificial Intelligence 2025年 155卷

作者： Liu, Yanxiong Shu, Yuwen Xu, Zhicheng Han, Senbo Zhang, Changbang Chen, Mingzhang Hubei Key Laboratory of Advanced Technology of Automotive Components Wuhan University of Technology Wuhan430070 China National Energy Key Laboratory for New Hydrogen-ammonia Energy Technologies Foshan Xianhu Laboratory Foshan528200 China

Continuously monitoring the equipment's working condition is critical to control the quality variations of the stamping metal. In the conventional monitoring platform, numerous sensors are retrofitted to the hydraulic press to monitor its condition with the high cost and complexity. In contrast to the method of retrofitting the hydraulic press, in this work, we propose an intelligent monitoring system to effortlessly and accurately assess and determine the operation phases of hydraulic press machinery with minimal retrofitting. In this system, a one-dimensional convolutional neural network (1-DCNN) model was established to deeply mine the underlay information contained in the equipment's power consumption data to predict the working status. Subsequently, Bayesian hyperparameters optimization algorithm was adopted to systematically explore the best combination of structural parameters of the 1-DCNN model for better performance. Concurrently, sensitivity analysis of these hyperparameters was conducted to quantitatively ascertain their influence on the model performance. Furthermore, some machine learning (ML) models were compared to the proposed 1-DCNN model and this proposed intelligent monitoring system was implemented on the cloud-based server, ultimately, to achieve real-time classification of operation phases of the hydraulic press. The study results revealed that the kernel size of convolution layers can significantly influence the classification accuracy of the 1-DCNN model compared to other hyperparameters. Compared to these traditional ML models, the proposed 1-DCNN model performed better with a commendable classification accuracy of 98.89 % in predicting operation phases. With the leverage of the proposed system, accurate quantitative assessments of energy consumption of each operation phase of the targeted hydraulic press were achieved, thereby offering invaluable insights for the formulation of energy-saving strategies. © 2025 Elsevier Ltd

关键词： Hydraulic tools

来源：评论

学校读者我要写书评

暂无评论

Thermally Stable Gradient Nanostructured M50 Bearing Steel by High-Density Dislocation Cells with Solute Segregation and Nanoscale Precipitation

SSRN

引用

SSRN 2022年

作者： Yue, Xiong Wang, Xiaokang Hu, Shan Yin, Fei Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China Hubei Collaborative Innovation Center for Automotive Components Technology Wuhan University of Technology Wuhan430070 China School of Automotive Engineering Wuhan University of Technology Wuhan430070 China School of Mechanical Engineering Purdue University West LafayetteIN47907 United States School of Materials Science and Engineering Wuhan University of Technology Wuhan430070 China

Thermal stability of gradient ultrafine grains/nanograins steels are of critical importance for applications. Here, a thermally stable gradient nanostructured M50 bearing steel composed of gradient lath martensite/grain, retained austenite, and carbides were prepared by USP technology and annealing treatments. Some intragranular dislocations annihilate, and grain boundaries dislocation multiplication and entanglement due to thermal activation and strain of the gradient layer after annealing at 350 °C for 30 min. And Fe, Cr, and C elements are further segregated to form high-density dislocation cells (~300 nm) at the triple junctions with smaller and more dispersed nanoscale precipitates/clusters. Compared with samples annealed at 350 °C and 450 °C for 30 min, the average grain size of samples continues annealed at 350 °C for 100 h increased by only 3.2% and 1.4%, while the microhardness of the top surface decreased by only 1.1% and 1.5%. High-density dislocation cells with solute segregation and nanoscale precipitation are critical for the high thermal stability and high microhardness of gradient nanostructured M50 steel. It provides a novel approach to developing stable nanostructured martensitic high-strength bearing steel. © 2022, The Authors. All rights reserved.

关键词： Microhardness

来源：评论

学校读者我要写书评

暂无评论

Effect of Milling Parameter on the Surface State of Ultra-high strength Steel 16Co14Ni10Cr2Mo 6

Effect of Milling Parameter on the Surface State of Ultra-hi...

引用

2020 6th International Conference on Materials, Mechanical Engineering and Automation technology, MMEAT 2020

作者： Xu, Jin Yan, Fuwu Li, Yan Yang, Zhenchao Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology No. 122 Loushi Road Wuhan Hubei430070 China Xi'An University of Technology No.5 South Jinhua Road Xi'an Shaanxi710048 China

The machining mechanism and process parameters of ultra-high strength steel 16Co14Ni10Cr2Mo are still lack of complete understanding. By changing the milling condition, the influence of process parameters on cutting force, such as Radial milling depth, Axial milling depth, Feed per tooth and milling speed, is studied,and in the meanwhile that the surface morphology and hardness of 16Co14Ni10Cr2Mo after machining are analyzed. Indicating that the milling force increases with the increase of axial milling depth, feed rate and radial milling depth. With the increase of milling speed, the milling force reduces. The effect of axial cutting depth and radial cutting depth on cutting force is maximum. For 16Co14Ni10Cr2Mo ultra-high strength steel, it is suitable to use small cutting depth and high milling speed. On the surface of milling material, partial melting and partial oxidation of chips occur. When the milling speed and feed rate increased, the surface hardness of the material did not change significantly, and there was no work hardening. © Published under licence by IOP Publishing Ltd.

关键词： Strain hardening

来源：评论

学校读者我要写书评

暂无评论

Influence of Showerhead with Baffle on Physical Field of Hcvd Reactor

SSRN

引用

SSRN 2022年

作者： Li, Qizhong Zhang, Yixuan Ji, Baifeng Zhang, Song Tu, Rong Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology 122 Luoshi Road Wuhan430070 China School of Civil Engineering and Architecture Wuhan University of Technology 122 Luoshi Road Wuhan430070 China Chaozhou Branch of Chemistry and Chemical Engineering Guangdong Laboratory Chaozhou521000 China Wuhan University of Technology Advanced Engineering Technology Research Institute of Zhongshan City Xiangxing Road 6 Guangdong Zhongshan528400 China

The physical field in halide chemical vapour deposition film growth is strongly affected by the structure of the reaction chamber. Notably, a highly uniform film thickness can be achieved by optimising this chamber. Therefore, after modelling a reactor, computational fluid dynamics was used in this study to measure temperatures and verify the accuracy of simulations. Based on changes in the substrate surface concentration and temperature, the feasibility of optimising the size and position of the baffle and the inclination angle of the spray holes was studied. The results revealed that on increasing the diameter of the baffle gradually, the uniformity of the substrate surface initially increased and then decreased. The most critical influence of the baffle position is the amount of gas on the substrate surface. As the inclination angle of the spray holes increased, the concentration at the centre of the substrate surface decreased, whereas that at the edge of the substrate increased. Meanwhile, the temperature field remained uniform after optimization. This study demonstrates that the showerhead and baffle can improve the physical field and that it is feasible to optimise the structure by analysing the physical field. © 2022, The Authors. All rights reserved.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Coordinated Control of Path Tracking and Yaw Stability for Distributed Drive Electric Vehicle Based on AMPC and DYC

arXiv

引用

arXiv 2023年

作者： Wu, Dongmei Guan, Yuying Xia, Xin Du, Changqing Yan, Fuwu Li, Yang Hua, Min Liu, Wei Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China Foshan Xianhu Laboratory of the Advanced Energy Science and Technology Guangdong Laboratory Foshan528200 China Hubei Research Center for New Energy & Intelligent Connected Vehicle Wuhan University of Technology Wuhan430070 China Department of Civil and Environmental Engineering University of California Los AngelesCA90024 United States Technical Center of Dongfeng Commercial Vehicle Wuhan China School of Engineering University of Birmingham BirminghamB15 2TT United Kingdom School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States

Maintaining both path-tracking accuracy and yaw stability of distributed drive electric vehicles (DDEVs) under various driving conditions presents a significant challenge in the field of vehicle control. To address this limitation, a coordinated control strategy that integrates adaptive model predictive control (AMPC) path-tracking control and direct yaw moment control (DYC) is proposed for DDEVs. The proposed strategy, inspired by a hierarchical framework, is coordinated by the upper layer of path-tracking control and the lower layer of direct yaw moment control. Based on the linear time-varying model predictive control (LTV MPC) algorithm, the effects of prediction horizon and weight coefficients on the path-tracking accuracy and yaw stability of the vehicle are compared and analyzed first. According to the aforementioned analysis, an AMPC path-tracking controller with variable prediction horizon and weight coefficients is designed considering the vehicle speed's variation in the upper layer. The lower layer involves DYC based on the linear quadratic regulator (LQR) technique. Specifically, the intervention rule of DYC is determined by the threshold of the yaw rate error and the phase diagram of the sideslip angle. Extensive simulation experiments are conducted to evaluate the proposed coordinated control strategy under different driving conditions. The results show that, under variable speed and low adhesion conditions, the vehicle's yaw stability and path-tracking accuracy have been improved by 21.58% and 14.43%, respectively, compared to AMPC. Similarly, under high speed and low adhesion conditions, the vehicle's yaw stability and path-tracking accuracy have been improved by 44.30% and 14.25%, respectively, compared to the coordination of LTV MPC and DYC. The results indicate that the proposed adaptive path-tracking controller is effective across different speeds. Furthermore, the proposed coordinated control strategy successfully enhances the vehicle's stabili

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Joining Performance and Microstructure of the 2024/7075 Aluminium Alloys Welded Joints by Vaporizing Foil Actuator Welding

引用

Journal of Wuhan University of technology(Materials Science) 2019年第2期34卷 368-372页

作者：孟正华 WANG Xu GUO Wei HU Zhili Anupam Vivek HUA Lin Glenn S DAEHN Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Department of Materials Science and Engineering The Ohio State University

Vaporizing foil actuator welding(VFAW) was used for joining 2024-T3 and 7075-T6 aluminum alloy sheets, and the resulting joint microstructure was analyzed. 2024/7075 aluminum alloy pairs with suitable processing parameters can be prepared by using VFAW. Dynamic preform addresses the poor formability problem of target material and advantage of VFAW on dissimilar materials in some conditions. But with standoff sheet inserting in the flyer and target, 2024/7075 welded pairs gets the better weld strength, compared with flyer preformed method. The microstructure of the circular weld area of the welded joint showed a wave interface, in which a thin melt layer formed at the center and edge parts. The crystal grains near the bonding interface were remarkably elongated and refined. Therefore, the joining of the 2024/7075 pairs was facilitated through plastic forming and melting.

关键词： impact welding dissimilar materials vaporizing foil actuator joining interface

来源：评论

学校读者我要写书评

暂无评论

The Influences of Process Parameters on the Preparation of Closed-cell Aluminum foam by Friction Stir Processing

Research Square

引用

Research Square 2021年

作者： Pang, Qiu Wu, Zhengjian Hu, Zhili Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China

In the present investigation, the closed-cell Al foam was fabricated by friction stir processing (FSP) combined with heat treatment. The influences of process parameters on microstructures of closed-cell Al foam precursor were investigated by optical metallographic microscope and scanning electronic microscope (OM/SEM). Fluent CFD software was developed to simulate the temperature field and flow field in friction stir processing. The cupping test values were compared for base metal and different weld passes. The results show that the welding speeds have little effect on the mixing of powder in the stir zone because of the relatively small welding heat input. However, the pore size and pore morphology are highly sensitive to change in the rotating speeds. When the welding speed is 50mm/min and the rotating speed is 2000rpm, the powder ring is continuous and uniform due to sufficient plastic deformation and flow. When the foaming time is 110s, the expansion rate of the whole foam increases rapidly, and the diameter of the pore is uniform. Numerical simulation shows that the welding heat mainly comes from the shoulder of the stirring head and the welding temperature peak appears near the stirring pin. The maximum flow velocity appears at the outer edge of the shaft shoulder in which the aluminum matrix is softened preferentially. When the rotating speed increases to 2000r/min, the velocity of the outermost edge of the shaft shoulder increases by 59.96%, and the maximum temperature at the stirring pin reaches 491℃ which is consistent with the experimental results. The formability of the joint interface is improved. The cupping test values increase with the increase of deformation temperature. Especially the cupping test value of foamed preform is close to that of base metal at 450℃. © 2021, CC BY.

关键词： Microstructure

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：