检索结果-南通市图书馆

同方期刊数据库

Effective thermal conductivity estimation using a convolutional neural network and its application in topology optimization

在线全文

学校读者我要写书评

暂无评论

Energy and AI 2024年第1期15卷 236-247页

作者： Andre Adam huazhen fang Xianglin Li Department of Mechanical Engineering University of Kansas1530 W 15th St.Lawrence66045KSUSA Department of Mechanical Engineering and Materials Science Washington University in St.LouisOne Brookings DriveSt.Louis63130MOUSA

Topology optimization of heterogeneous structures can find significant use in a wide range of applications,and its fabrication has been made possible by recent advances in additive ***,the optimization procedure is computationally expensive,as each structural update requires the re-evaluation of the *** computational time is the major limiting factor in large-scale and complex structural *** this study,a convolutional neural network(CNN)model for predicting effective thermal conductivity inspired by the VGG networks is *** using 130,000 unique binary images,the model achieves high predictive ***,it shows a mean absolute percent error(MAPE)of 0.35%in testing when the thermal conductivity of the solid is ten times larger than the fluid,and when the thermal conductivities assigned are that of aluminum and water,the MAPE is 2.35%.The prediction time is 15 ms for a single image with 128×128 pixels,which is 3 to 5 orders of magnitude faster than a finite volume *** employed in topology optimization,the CNN retains a MAPE between 0.67%and 11.8%for different *** CNN model correctly predicts trends in effective thermal conductivity and improves the structure to close proximity of a theoretical maximum in all cases.

关键词： Machine learning Effective thermal conductivity Convolutional neural network VGG Numerical heat transfer Topology optimization

Nonlinear Bayesian Estimation： From Kalman Filtering to a Broader Horizon

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第2期5卷 401-417页

作者： huazhen fang Ning Tian Yebin Wang Meng Chu Zhou Mulugeta A. Haile IEEE Department of Mechanical Engineering University of Kansas Lawrence KS 66045 USA Mitsubishi Electric Research Laboratories Cambridge MA 02139 USA the Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 USA the Vehicle Technology Directorate US Army Research Laboratory Aberdeen MD 21005 USA

This article presents an up-to-date tutorial review of nonlinear Bayesian estimation. State estimation for nonlinear systems has been a challenge encountered in a wide range of engineering fields, attracting decades of research effort. To date,one of the most promising and popular approaches is to view and address the problem from a Bayesian probabilistic perspective,which enables estimation of the unknown state variables by tracking their probabilistic distribution or statistics(e.g., mean and covariance) conditioned on a system's measurement *** article offers a systematic introduction to the Bayesian state estimation framework and reviews various Kalman filtering(KF)techniques, progressively from the standard KF for linear systems to extended KF, unscented KF and ensemble KF for nonlinear systems. It also overviews other prominent or emerging Bayesian estimation methods including Gaussian filtering, Gaussian-sum filtering, particle filtering and moving horizon estimation and extends the discussion of state estimation to more complicated problems such as simultaneous state and parameter/input estimation.

关键词： Index Terms-Kalman filtering (KF) nonlinear Bayesian esti-mation state estimation stochastic estimation.

Data-Driven Discovery of Stochastic Differential Equations

在线全文

学校读者我要写书评

暂无评论

Engineering 2022年第10期17卷 244-252页

作者： Yasen Wang huazhen fang Junyang Jin Guijun Ma Xin He Xing Dai Zuogong Yue Cheng Cheng Hai-Tao Zhang Donglin Pu Dongrui Wu Ye Yuan Jorge Gonçalves Jürgen Kurths Han Ding School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Mechanical Engineering University of KansasLawrenceKS 66045USA HUST-Wuxi Research Institute Wuxi 214174China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Department of Plant Sciences University of CambridgeCambridge CB23EAUK Luxembourg Centre for Systems Biomedicine University of LuxembourgBelvaux 4367Luxembourg Department of Physics Humboldt University of BerlinBerlin 12489Germany Department of Complexity Science Potsdam Institute for Climate Impact ResearchPotsdam 14473Germany

Stochastic differential equations(SDEs)are mathematical models that are widely used to describe complex processes or phenomena perturbed by random noise from different *** identification of SDEs governing a system is often a challenge because of the inherent strong stochasticity of data and the complexity of the system’s *** practical utility of existing parametric approaches for identifying SDEs is usually limited by insufficient data *** study presents a novel framework for identifying SDEs by leveraging the sparse Bayesian learning(SBL)technique to search for a parsimonious,yet physically necessary representation from the space of candidate basis *** importantly,we use the analytical tractability of SBL to develop an efficient way to formulate the linear regression problem for the discovery of SDEs that requires considerably less time-series *** effectiveness of the proposed framework is demonstrated using real data on stock and oil prices,bearing variation,and wind speed,as well as simulated data on well-known stochastic dynamical systems,including the generalized Wiener process and Langevin *** framework aims to assist specialists in extracting stochastic mathematical models from random phenomena in the natural sciences,economics,and engineering fields for analysis,prediction,and decision making.

关键词： Data-driven method System identification Sparse Bayesian learning Stochastic differential equations Random phenomena

在线全文

学校读者我要写书评

暂无评论

自动驾驶车辆换道意图识别研究现状

工程科学学报 2024年第10期46卷 1845-1855页

作者：方华珍刘立顾青肖小凤孟宇北京科技大学机械工程学院北京100083

近年来基于数据驱动的自动驾驶车辆换道意图识别研究取得了显著进展,学者们发布了大量的研究成果.针对该领域面临的一些共性的技术挑战,如换道过程的认定、换道标签的缺失以及数据类别不均衡等问题,从不同的数据驱动方法进行分类,主要... 详细信息

近年来基于数据驱动的自动驾驶车辆换道意图识别研究取得了显著进展,学者们发布了大量的研究成果.针对该领域面临的一些共性的技术挑战,如换道过程的认定、换道标签的缺失以及数据类别不均衡等问题,从不同的数据驱动方法进行分类,主要包括基于传统机器学习、基于深度学习和基于集成学习的换道意图识别方法,对近年来这些方法的研究成果进行了回顾和总结.关于换道行为的认定,存在两种主流方案,即车辆穿越车道线和未穿越车道线.对于未穿越车道线的车辆,主要应用于驾驶者换道意图的早期识别方法;而当车辆穿越过车道线时,则通常被用于完整的换道过程的识别.在换道意图标注的研究中,研究者们针对固定时间窗口和航向角阈值对标注精度的影响进行了深入探讨.为了找到最优参数,如最佳的固定时间窗口和航向角阈值,研究者们采用了网格搜索进行寻优.虽然这种方法在固定的驾驶场景中表现良好,但在不同的驾驶场景中,如何实现参数的自适应调节仍然是一个挑战.针对换道数据类别不均衡的问题,研究者采用两种策略:一是调整数据采样方法,利用欠采样和过采样技术平衡各类别样本数量;二是采用对不均衡数据适应性强的分类模型,如集成学习算法或代价敏感学习,以维持较好的分类性能.

关键词：交通工程自动驾驶车辆数据驱动换道意图识别

Preparation and applications of calcium ferrite as a functional material:A review

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第2期32卷 292-310页

作者： Xiuli Han Bowen Duan Lei Liu Shilong fang Weiwei Wang College of Mining Engineering North China University of Science and TechnologyTangshan 063210China Collaborative Innovation Center of Green Development and Ecological Restoration of Mineral Resources of Hebei Province Tangshan 063210China Key Laboratory of Mining Development and Security Technology of Hebei Province Tangshan 063210China

Calcium ferrite(CF)is recognized as a potential green and efficient functional material because of its advantages of magnetism,electrochemistry,catalysis,and biocompatibility in the fields of materials chemistry,environmental engineering,and ***-fore,the obtained research results need to be systematically summarized,and new perspectives on CF and its composite materials need to be *** on the presented studies of CF and its composite materials,the types and structures of the crystal are *** addition,the current application technologies and theoretical mechanisms with various properties in different fields are ***,the various preparation methods of CF and its composite materials are elaborated in *** importantly,the advantages and disadvantages of the synthesis methods of CF and its composite materials are discussed,and the existing problems and emerging challenges in practical production are ***,the key future research directions of CF and its composite materials have been prospected from the potential application technologies to provide references for its synthesis and efficient utilization.

关键词： calcium ferrite mineral functional materials preparation application perspectives

在线全文

学校读者我要写书评

暂无评论

基于换道意图和强化学习的车辆匝道汇入决策

无人系统技术 2024年第5期7卷 111-119页

作者：方华珍刘立顾青肖小凤孟宇北京科技大学机械工程学院北京100083

对高速公路匝道汇入决策开展了基于换道意图识别和深度强化学习的研究。首先,根据目标车辆及其周围车辆的特征参数,识别车辆换道意图并设计环境状态空间。其次,根据车辆的离散横向换道行为与连续纵向加减速行为,设计了混合的动作空间。... 详细信息

对高速公路匝道汇入决策开展了基于换道意图识别和深度强化学习的研究。首先,根据目标车辆及其周围车辆的特征参数,识别车辆换道意图并设计环境状态空间。其次,根据车辆的离散横向换道行为与连续纵向加减速行为,设计了混合的动作空间。然后,基于车辆的乘坐舒适度、通行效率、行车安全和汇入成功四方面,设计了环境奖励函数;依据匝道汇入任务特点,设计了环境终止条件。最后,基于实际道路和城市交通仿真软件搭建匝道汇入仿真平台来验证模型的可行性,多组对比分析实验结果表明,所提出方法在碰撞率和成功率上均表现最优,并且模型在不同道路车流密度条件下均取得90%以上的成功率。今后将对不同场景开展更为鲁棒的决策。

关键词：自动驾驶高速公路匝道汇入换道意图识别深度强化学习交通仿真车辆行为决策

Efficient and simple synthesis of B_(2)O_(3)-Al_(2)O_(3)nanocomposites assisted by deep eutectic solvent for production of 5-hydroxymethylfurfural from glucose

在线全文

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 236-248页

作者： Yuchen Wang Kai Rong Shanlei Chang Youxing fang Shaojun Dong State Key Laboratory of Electroanalytical Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China School of Applied Chemistry and Engineering University of Science and Technology of ChinaHefei 230026China College of Chemistry Jilin UniversityChangchun 130012China

The catalytic conversion of glucose to high valueadded platform chemical 5-hydroxymethylfurfural(HMF)is a promising biorefinery process,and alumina-boria catalysts are considered to be green and mild solid acid catalysts for this catalytic ***,compared to the common synthesis methods with complicated steps,we reported a simple and efficient strategy to prepare B_(2)O_(3)-Al_(2)O_(3)nanocomposites by calcining cost-effective glucose-urea deep eutectic solvent(DES)solution containing the *** prepared B_(2)O_(3)-Al_(2)O_(3)nanocomposites exhibited an open three-dimensional skeleton and two-dimensional porous lamellar substructure,endowing them with a high specific surface area(228.27 m2/g).The introduction of boron changed the ratios of different aluminum species(AlⅣ,AlⅤ,and AlⅥ)and borate species(BO3 and BO4),thus further affecting the acidity and the types of acid sites of the *** prepared B_(2)O_(3)-Al_(2)O_(3)bifunctional acid catalysts possessing abundant Lewis acid sites and adjustable Brønsted acid sites showed complete glucose conversion and 55.38%of HMF yield under the optimum *** study proposed a concise method to synthesize alumina-boria solid acid catalysts assisted by glucose-urea *** hope to extend the application and prospect of this efficient and simple synthesis strategy.

关键词： 5-hydroxymethylfurfural(HMF) deep eutectic solvent glucose alumina-boria acid catalyst

Treadmill exercise in combination with acousto-optic and olfactory stimulation improves cognitive function in APP/PS1 mice through the brain-derived neurotrophic factor-and Cygb-associated signaling pathways

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第9期20卷 2706-2726页

作者： Biao Xiao Chaoyang Chu Zhicheng Lin Tianyuan fang Yuyu Zhou Chuxia Zhang Jianghui Shan Shiyu Chen Liping Li Department of Physiology and Pharmacology Health Science CenterNingbo UniversityNingboZhejiang ProvinceChina Ningbo Key Laboratory of Behavioral Neuroscience Health Science CenterNingbo UniversityNingboZhejiang ProvinceChina Key Laboratory of Addiction Research of Zhejiang Province NingboZhejiang ProvinceChina

A reduction in adult neurogenesis is associated with behavioral abnormalities in patients with Alzheimer's ***,enhancing adult neurogenesis represents a promising therapeutic approach for mitigating disease symptoms and ***,nonpharmacological interventions aimed at inducing adult neurogenesis are currently *** individual non-pharmacological interventions,such as aerobic exercise,acousto-optic stimulation,and olfactory stimulation,have shown limited capacity to improve neurogenesis and cognitive function in patients with Alzheimer's disease,the therapeutic effect of a strategy that combines these interventions has not been fully *** this study,we observed an age-dependent decrease in adult neurogenesis and a concurrent increase in amyloid-beta accumulation in the hippocampus of amyloid precursor protein/presenilin 1 mice aged 2-8 *** deposition became evident at 4 months,while neurogenesis declined by 6 months,further deteriorating as the disease ***,following a 4-week multifactor stimulation protocol,which encompassed treadmill running(46 min/d,10 m/min,6 days per week),40 Hz acousto-optic stimulation(1 hour/day,6 days/week),and olfactory stimulation(1 hour/day,6 days/week),we found a significant increase in the number of newborn cells(5'-bromo-2'-deoxyuridine-positive cells),immature neurons(doublecortin-positive cells),newborn immature neurons(5'-bromo-2'-deoxyuridine-positive/doublecortin-positive cells),and newborn astrocytes(5'-bromo-2'-deoxyuridine-positive/glial fibrillary acidic protein-positive cells).Additionally,the amyloid-beta load in the hippocampus *** findings suggest that multifactor stimulation can enhance adult hippocampal neurogenesis and mitigate amyloid-beta neuropathology in amyloid precursor protein/presenilin 1 ***,cognitive abilities were improved,and depressive symptoms were alleviated in amyloid precursor protein/presenilin 1 mice

关键词： acousto-optic stimulation adult neurogenesis Alzheimer's disease amyloid precursor protein/presenilin 1 mice amyloid-beta deposition brain cell apoptosis cognitive impairment depression-like behavior involuntary treadmill exercise olfactory stimulation serum metabolites

Inhibitory gamma-aminobutyric acidergic neurons in the anterior cingulate cortex participate in the comorbidity of pain and emotion

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第10期20卷 2838-2854页

作者： Lu Guan Mengting Qiu Na Li Zhengxiang Zhou Ru Ye Liyan Zhong Yashuang Xu Junhui Ren Yi Liang Xiaomei Shao Jianqiao fang Junfan fang Junying Du Department of Neurobiology and Acupuncture Research Third School of Clinical MedicineZhejiang Chinese Medical UniversityHangzhouZhejiang ProvinceChina Key Laboratory for Research of Acupuncture Treatment and Transformation of Emotional Diseases Third School of Clinical MedicineZhejiang Chinese Medical UniversityHangzhouZhejiang ProvinceChina Fuchun Community Health Service Center of Fuyang District HangzhouZhejiang ProvinceChina

Pain is often comorbid with emotional disorders such as anxiety and *** of the anterior cingulate cortex has been implicated in pain and pain-related negative emotions that arise from impairments in inhibitory gamma-aminobutyric acid *** review primarily aims to outline the main circuitry(including the input and output connectivity)of the anterior cingulate cortex and classification and functions of different gamma-aminobutyric acidergic neurons;it also describes the neurotransmitters/neuromodulators affecting these neurons,their intercommunication with other neurons,and their importance in mental comorbidities associated with chronic pain *** understanding on their role in pain-related mental comorbidities may facilitate the development of more effective treatments for these ***,the mechanisms that regulate gamma-aminobutyric acidergic systems remain *** is also unclear as to whether the mechanisms are presynaptic or *** exploration of the complexities of this system may reveal new pathways for research and drug development.

关键词： anterior cingulate cortex anxiety chronic pain circuit communication comorbidity depression gamma-aminobutyric acidergic neurons parvalbumin neurons synaptic transmission