检索结果-内蒙古大学图书馆

Structural Damage Semantic Segmentation Using Dual-Network Fusion 10th

学校读者我要写书评

暂无评论

Structural Damage Semantic Segmentation Using Dual-Network F...

10th International Conference on Computer engineering and Networks, CENet 2020

作者： Mei, Lingrui Yin, Jiaqi Zhou, Donghao Kang, Kai Zhang, Qiang State Key Laboratory of Vehicle NVH and Safety Technology China Automotive Engineering Research Institute Chongqing401122 China Chongqing University Chongqing400000 China Chongqing Communications Planning Survey and Design Institute Chongqing401121 China The Hong Kong University of Science and Technology Hong Kong China

ISBN: (纸本)9789811584619

Road cracks seriously affect road life and driving safety, and road crack segmentation has been a key task in many research fields and industries. Scenes of existing road crack datasets are relatively homogeneous, most datasets only have local crack images taken from a single perspective, and the images lack complex interference pattern other than the cracks and the road itself. However, real-world images of roads are much more complex, and roads may have other dark patterns that interfere with crack segmentation. Perspective and lighting conditions may also be different between every image in the dataset, which makes many road crack segmentation methods extremely low accuracy and severely affects the generalization ability of the semantic segmentation model, while many applications require higher precision rather than recall. In this paper, two methods are proposed to improve the accuracy: augmenting complex patterns in road images and the fusion of classification networks. The methods greatly improve the performance of road crack segmentation. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

Guided Control for Plug-In Fuel Cell Hybrid Electric vehicles Via vehicle to Traffic Communication

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Wei, Xiaodong Liu, Bo Sun, Chao Huo, Weiwei Sun, Fengchun National Engineering Laboratory for Electric Vehicles Beijing Institute of Technology Beijing100081 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Mechanical Electrical Engineering School Beijing Information Science and Technology University Beijing100192 China

A guided proportional integral controller-based Pontryagin’s minimum principle (PI-PMP) energy management control strategy based on dynamic traffic information for plug-in fuel cell vehicles is proposed in this paper. Combined with the real-world traffic flow data of high-way driving scenarios, an improved equivalent consumption minimization strategy (ECMS) based on dichotomy is used to quickly search for the optimal initial costate value and reference battery state of charge (SOC) trajectory. A horizon velocity predictor based on artificial neural networks (ANNs) is used to achieve shortterm velocity prediction, and PI-PMP control strategy is adopted to realize SOC trajectory following. Simultaneously, the sensitivity of the costate in ECMS and PI-PMP is analyzed in depth. The simulation results of three scenarios with no/static/dynamic traffic flow information show that the guided PI-PMP energy management strategy based on dynamic traffic flow information has significant energy saving effect and real-time optimization potential. © 2022, The Authors. All rights reserved.

关键词： Charging (batteries)

Intercalation-Deposition Mechanism Induced by Aligned Carbon Fiber Toward Dendrite-Free Metallic Potassium Batteries

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Jilei Xiao, Kuikui Wu, Jian-Fang Yan, Hanghang Mo, Ying Zhou, Wang Peng, Yufan Chen, Shi Cui, Xiangyang Chen, Lei Xu, Chaohe College of Materials Science and Engineering Hunan Joint International Laboratory of Advanced Materials and Technology of Clean Energy Hunan Province Key Laboratory for Advanced Carbon Materials and Applied Technology Hunan University Hunan Changsha410082 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Hunan 410082 China Joint Key Laboratory of the Ministry of Education Institute of Applied Physics and Materials Engineering University of Macau Avenida da Universidade Taipa 999078 China Department of Mechanical Engineering University of Michigan-Dearborn DearbornMI48128-1491 United States College of Aerospace Engineering Chongqing University Chongqing400044 China

Metallic potassium (K) anode is highly desirable for high energy density batteries. However, challenges lie in uncontrollable dendrite growth and/or inevitable dead K generation. Here a composite anode, covering a layer of aligned carbon fiber on the surface of a K metal anode (K-ACF), is constructed. Symmetrical K-ACF//K-ACF cells can work stably for over 600 h without short circuit, which is quite longer than cells with unaligned carbon fiber modified K metal (K-UCF) and bare K metal. Comprehensive characterizations reveal a step-wise intercalation-deposition process occurs on the K-ACF anode at the initial state of the K plating process, in which the intercalation is proved to be necessary for the uniform K+ flux due to the improved potassiophility. Besides, the aligned structure of ACF plays a key role in offering the uniform current density and K+ over the surface of the anode, successfully promoting the stable K stripping/plating. Consequently, the K-ACF//Prussian blue (PB) cell exhibits a high reversible capacity of 83.6 mAh g-1 (267.4 Wh kg-1 based on the mass of PB) under a charge/discharge rate of 200 mA g-1 with a capacity loss rate of 0.044% per cycle. This work opens new avenue toward high energy and dendrite-free potassium batteries. © 2022, The Authors. All rights reserved.

关键词： Anodes

A novel multi-stage concurrent topology optimization for variable-stiffness structures

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Zhang, Yaya Wang, Hu Yin, Jichao Li, Shuhao Yang, Mengzhu State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Beijing Institute of Technology Shenzhen Automotive Research Institute Shenzhen518000 China Department of Aerospace Engineering University of Bristol BristolBS8 1TR United Kingdom

The concurrent optimization of topology and fibre orientation is a promising approach to pursue higher strength and lighter weight of variable-stiffness structure. This study proposes a novel discrete-continuous scheme for the concurrent optimization. Considering the global convergence, Discrete Material Optimization (DMO) is firstly utilized to select a dominant angle for each element from several predefined candidate angles. However, it is still difficult to obtain excellent fibre angle convergence due to difficulty in selection of candidate materials for some elements. Therefore, the Sequential Binary-Phase Topology Optimization is proposed to guarantee the uniqueness of the element to candidate angle mapping. Moreover, to obtain better mechanical properties, Continuous Fibre Angle Optimization (CFAO) with spatial filter is introduced to optimize fibre continuity. Several classic numerical examples are used to verify the excellent performance of the proposed method in terms of fibre angle convergence and stable optimization ability. © 2023, CC BY.

关键词： Shape optimization

Mechanical Characterization and Numerical Modeling on Temperature and Strain Rate Effects on Polymethacrylimide (Pmi) Foam Materials

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Sun, Guangyong Huo, Xintao Gu, Xianguang Luo, Quantian Jiang, Zhongcheng Li, Qing School of Automotive and Transportation Engineering Hefei University of Technology Hefei230009 China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha410082 China The State Key Laboratory of Heavy-duty and Express High-power Electric Locomotive CRRC Zhuzhou Locomotive Co. Ltd. Zhuzhou412001 China School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney SydneyNSW2006 Australia

Polymethacrylimide (PMI) foams exhibit great potentials in engineering applications thanks to its excellent mechanical properties. However, the temperature and loading rate can greatly affect its mechanical behaviors, which are the key factors in analysis and design of the PMI foam structures. Unfortunately, there is lack of constitutive data concerning the PMI foam at different ambient temperatures and different strain rates;therefore, this study aimed to investigate the effects of temperature and strain rate on elastic and plastic properties of the PMI foams. The compressive, tensile, and shearing tests were conducted at different temperatures to explore the thermal softening effect of the PMI foam. The cyclic loading responses of the PMI foam are also scrutinized by the loading and unloading tests. To investigate the strain rate effects, the dynamic uniaxial compression tests were performed in a range up to 300 s-1. Based on the experimental data, the initial and subsequent yield surfaces of the PMI foam were calibrated and analyzed, in which different temperatures ranging from 25 to 175 ℃ are taken into account. It is found that the elastic and plastic responses can be considerably affected by temperature;and the elastic modulus decreases with increasing temperature;meanwhile, the yield surface contracts with rising ambient temperature. In this study, the thermal and strain rate dependent constitutive models were established based on the in-house experimental data, which are further applied to finite element (FE) modelling for validation. It is found that accurate predictions on the effects of temperature and strain rate are achieved based on the calibrated constitutive models for the PMI foam. This study is anticipated to provide an effective constitutive model for practical applications of PMI foam materials under different thermal and strain rate conditions. © 2023, The Authors. All rights reserved.

关键词： Numerical models

Vibration Performance Analysis of a Mining vehicle with Bounce and Pitch Tuned Hydraulically Interconnected Suspension

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical engineering 2019年第1期32卷 195-211页

作者： Jie Zhang Yuanwang Deng Nong Zhang Bangji Zhang Hengmin Qi Minyi Zheng State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body College of Mechanical and Vehicle Engineering Hunan University Automotive Research Institute Hefei University of Technology School of Automotive and Transportation Engineering Hefei University of Technology

The current investigations primarily focus on using advanced suspensions to overcome the tradeo design of ride comfort and handling performance for mining vehicles. It is generally realized by adjusting spring sti ness or damping parameters through active control methods. However, some drawbacks regarding control complexity and uncertain reliability are inevitable for these advanced suspensions. Herein, a novel passive hydraulically interconnected suspension(HIS) system is proposed to achieve an improved ride-handling compromise of mining vehicles. A lumped-mass vehicle model involved with a mechanical–hydraulic coupled system is developed by applying the free-body diagram method. The transfer matrix method is used to derive the impedance of the hydraulic system, and the impedance is integrated to form the equation of motions for a mechanical–hydraulic coupled system. The modal analysis method is employed to obtain the free vibration transmissibilities and force vibration responses under di erent road excitations. A series of frequency characteristic analyses are presented to evaluate the isolation vibration performance between the mining vehicles with the proposed HIS and the conventional suspension. The analysis results prove that the proposed HIS system can e ectively suppress the pitch motion of sprung mass to guarantee the handling performance, and favorably provide soft bounce sti ness to improve the ride comfort. The distribution of dynamic forces between the front and rear wheels is more reasonable, and the vibration decay rate of sprung mass is increased e ectively. This research proposes a new suspension design method that can achieve the enhanced cooperative control of bounce and pitch motion modes to improve the ride comfort and handling performance of mining vehicles as an e ective passive suspension system.

关键词： Hydraulically interconnected suspension Transfer matrix method Modal vibration analysis Ride comfort Handling performance Mining vehicle

Experimental and Theoretical Study of the Pyrolysis of Β-O-4 Type Lignin Model Compounds: The Catalytic Effects of Potassium and Calcium Additives

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Guo, Yilin Fang, Yang Gong, Xun Liu, Shuai Tian, Hong Chen, Jingwei Jiaqiang, E. Leng, Erwei College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China Innovation Institute of Industrial Design and Machine Intelligence Quanzhou-Hunan University Quanzhou362006 China State Key Laboratory of Coal Combustion School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan430074 China Hunan province Key Laboratory of Efficient & Clean Thermal Power Generation Technologies State Grid Hunan Electric Power Corporation Research Institute Changsha410007 China School of Energy and Power Engineering Key Laboratory of Renewable Energy Electric Technology of Hunan Province Changsha University of Science & Technology Hunan Changsha410114 China

In this work, to investigate the catalytic effects of potassium and calcium additives on lignin pyrolysis, two β-O-4 type model compounds for lignin containing different oxygen-containing functional groups (a carbonyl group or a hydroxyl group) on C α were prepared, and their catalytic fast pyrolysis experiments were carried out on Py-GC/MS. Furthermore, the possible catalytic mechanism of potassium and calcium additives was further investigated using density functional theory (DFT) calculations. The experimental results show that the addition of potassium acetate and calcium acetate is beneficial to the formation of phenol, while the promotion effect of potassium addition is stronger than that of calcium addition. Moreover, considering the contributions of temperature and activation entropy ΔS ‡ , the activation Gibbs free energy ΔG ‡ was required as the basis to explain the pyrolysis mechanism of lignin. It was determined that the C β -O homolytic reaction performs the most favorable in the initial depolymerization of both dimers. By comparing the ΔG ‡ , it was confirmed that the addition of K + and Ca 2+ are beneficial to the C β -O homolytic reaction and further promoted the conversion of the intermediate to phenol. Furthermore, the different effects of K + and Ca 2+ additives on the side chains were compared cleavage through homolytic reaction and concerted decomposition. The calculation results showed that K + is more conducive to the simple homolytic reaction, while Ca 2+ is more conducive to the concerted decomposition. © 2022, The Authors. All rights reserved.

关键词： Density functional theory

Intelligent prediction on air intake flow of spark ignition engine by a chaos radial basis function neural network

学校读者我要写书评

暂无评论

Journal of Central South University 2020年第9期27卷 2687-2695页

作者： LI Yue-lin LIU Bo-fu WU Gang LIU Zhi-qiang DING Jing-feng ABUBAKAR Shitu Key Laboratory of Safety and Design and Reliability Technology of Engineering Vehicles in Hunan Province Changsha 410114China College of Automotive and Mechanical Engineering Changsha University of Science and TechnologyChangsha 410114China College of Mechanical and Electrical Engineering Central South UniversityChangsha 410083China

To ensure the control of the precision of air-fuel ratio(AFR)of port fuel injection(PFI)spark ignition(SI)engines,a chaos radial basis function(RBF)neural network is used to predict the air intake flow of the *** data of air intake flow is proved to be multidimensionally nonlinear and *** RBF neural network is used to train the reconstructed phase space of the *** chaos algorithm is employed to optimize the weights of output layer connection and the radial basis center of Gaussian function in hidden *** simulation results obtained from Matlab/Simulink illustrate that the model has higher accuracy compared to the conventional RBF *** mean absolute error and the mean relative error of the chaos RBF model can reach 0.0017 and 0.48,respectively.

关键词： intake air flow spark ignition engine chaos RBF neural network

Accessing negative Poisson's ratio of graphene by machine learning interatomic potentials

学校读者我要写书评

暂无评论

arXiv

arXiv 2022年

作者： Wu, Jing Zhou, E. Qin, Zhenzhen Zhang, Xiaoliang Qin, Guangzhao State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China International Laboratory for Quantum Functional Materials of Henan School of Physics and Microelectronics Zhengzhou University Zhengzhou450001 China Key Laboratory of Ocean Energy Utilization and Energy Conservation of Ministry of Education School of Energy and Power Engineering Dalian University of Technology Dalian116024 China

The negative Poisson's ratio (NPR) is a novel property of materials, which enhances the mechanical feature and creates a wide range of application prospects in lots of fields, such as aerospace, electronics, medicine, etc. Fundamental understanding on the mechanism underlying NPR plays an important role in designing advanced mechanical functional materials. However, with different methods used, the origin of NPR is found different and conflicting with each other, for instance, in the representative graphene. In this study, based on machine learning technique, we constructed a moment tensor potential (MTP) for molecular dynamics (MD) simulations of graphene. By analyzing the evolution of key geometries, the increase of bond angle is found to be responsible for the NPR of graphene instead of bond length. The results on the origin of NPR are well consistent with the start-of-art first-principles, which amend the results from MD simulations using classic empirical potentials. Our study facilitates the understanding on the origin of NPR of graphene and paves the way to improve the accuracy of MD simulations being comparable to first-principle calculations. Our study would also promote the applications of machine learning interatomic potentials in multiscale simulations of functional materials. © 2022, CC BY.

关键词： Graphene