检索结果-南通市图书馆

Remaining Useful life Estimation of lithium-Ion Battery Based on Gaussian Mixture Ensemble Kalman Filter

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2022年第4期31卷 340-349页

作者： ruoxia li Siyuan Zhang Peijun Yang School of Information and Control Engineering Xi’an University of Architecture and TechnologyXi’an 710055China School of Mechanical Engineering Xi’an University of Architecture and TechnologyXi’an 710055China Xi’an Boiler&Environmental Protection Engineering Co. LtdXi’an 710054China

The remaining useful life(RUL)prediction is a crucial indicator for the lithium-ion battery health *** particle filter(PF),used together with an empirical model,has become one of the most well-accepted techniques for RUL *** this work,a novel filtering algorithm,named the Gaussian mixture model(GMM)-ensemble Kalman filter(EnKF)is *** embeds the Gaussian mixture model in the EnKF framework to cope with the non-Gaussian feature of the system state space,and meanwhile address some of the major shortcomings of the *** GMM-EnKF and the PF are both applied on public data sets for RUL prediction and the simulation results show superiority of our proposed approach to the PF.

关键词： lithium-ion battery Gaussian mixture model ensemble Kalman filter(EnKF) remaining useful life(RUL)

State estimation for delayed neural networks with reaction-diffusion terms:Hardy-Poincare inequality 36

在线全文

学校读者我要写书评

暂无评论

State estimation for delayed neural networks with reaction-d...

Traffic network equilibrium problems with demands uncertainty and capacity constraints of arcs by scalarization approaches

第36届中国控制会议

作者： ruoxia li Jinde Cao School of Mathematics and Research Center for Complex Systems and Network Sciences Southeast University

ISBN: (纸本)9781538629185

This paper pay attention to the state estimation problem for a class of delayed neural networks with reaction-diffusion *** constructing a Lyapunov functional,together with the Hardy-Poincare inequality,a less conservative sufficient condition for the existence of state estimator is formulated in terms of linear matrix inequality（LMI）.Finally,a numerical example is given to demonstrate the effectiveness of the presented results.

关键词： State estimation neural networks reaction-diffusion terms Hardy-Poincare inequality

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2018年第11期61卷 1642-1653页

作者： CAO JinDe li ruoxia HUANG Wei GUO JianHua WEI Yun School of Mathematics Research Center for Complex Systems and Network SciencesSoutheast UniversityNanjing 210096China Intelligent Transportation System Research Center Southeast UniversityNanjing 210096China National Engineering Laboratory for Green & Safe Construction Technology in Urban Rail Transit Beijing 100037China

This paper focuses on the vector traffic network equilibrium problem with demands uncertainty and capacity constraints of arcs, in which, the demands are not exactly known and assumed as a discrete set that contains finite scenarios. For different scenario, the demand may be changed, which seems much more reasonable in practical programming. By using the linear scalarization method,we introduce several definitions of parametric equilibrium flows and reveal their mutual relations. Meanwhile, the relationships between the scalar variational inequality as well as the(weak) vector equilibrium flows are explored, meanwhile, some necessary and sufficient conditions that ensure the(weak) vector equilibrium flows are also considered. Additionally, by means of nonlinear scalarization functionals, two kinds of equilibrium principles are derived. All of the derived conclusions contain the demands uncertainty and capacity constraints of arcs, thus the results proposed in this paper improved some existing works. Finally, some numerical examples are employed to show the merits of the improved conclusions.

关键词： traffic network demands uncertainty capacity equilibrium flow scalarization

A novel RUL prediction method for lithium-ion Batteries via hybrid modeling and BAS based particle filter

在线全文

学校读者我要写书评

暂无评论

A novel RUL prediction method for Lithium-ion Batteries via ...

第40届中国控制会议

作者： Ning He Cheng Qian ruoxia li School of Mechanical and Electrical Engineering Xi'an University of Architecture and Technology School of Information and Control Engineering Xi'an University of Architecture and Technology

As an important energy source, lithium-ion batteries have vast applications in daily production and life. Therefore, the life prediction of such batteries is of great significance, which can help us maintain the efficacy and reliability of the system powered by lithium-ion batteries. In this paper, a hybrid battery model and an improved particle filter（PF） are developed to better estimate the remaining useful life（RUL） of lithium-ion battery. Firstly, a hybrid model is constructed as the degradation model of the battery. The developed hybrid model is a combination of the empirical battery model and neural network model such that it could characterize both the internal mechanism of the battery and the change of external environment in a more accurate ***, the beetle antennae search（BAS） based PF（BAS-PF） is utilized to compute the battery parameters online based on the proposed hybrid model. Compared with the existing PF based method, BAS-PF can well handle the problem of diversity loss and improve the estimation accuracy. Finally, the battery data set published by NASA is used as the experiment *** show that the proposed hybrid model can well represent the internal and external changes of the battery, and the BAS-PF based method has a great improvement in the estimation accuracy. Those results illustrate that the developed technique could achieve an improved life prediction for lithium-ion batteries.

关键词： Remaining useful life Optimization algorithm lithium-ion battery Particle filter Hybrid model

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

自适应模型与改进粒子滤波的电池RUL预测

哈尔滨工业大学学报 2022年第9期54卷 111-121页

作者：贺宁钱成李若夏西安建筑科技大学机电工程学院西安710055 智能网络与网络安全教育部重点实验室(西安交通大学) 西安710049 西安建筑科技大学信息与控制工程学院西安710055

为提高锂电池运行的安全性和可靠性并维护系统稳定运行,提出一种自适应混合模型与改进粒子滤波(particle filter,PF)算法的锂电池剩余使用寿命(remaining useful life,RUL)预测方法。采用经验模型与神经网络模型结合建立自适应混合模型... 详细信息

为提高锂电池运行的安全性和可靠性并维护系统稳定运行,提出一种自适应混合模型与改进粒子滤波(particle filter,PF)算法的锂电池剩余使用寿命(remaining useful life,RUL)预测方法。采用经验模型与神经网络模型结合建立自适应混合模型描述电池容量退化趋势,并使用天牛须搜索(beetle antennae search,BAS)算法优化PF重采样步骤解决粒子多样性丧失问题,从而提高估计精度进而实现RUL的精准预测。应用NASA和CALCE公开的两组不同类型锂电池作为实验对象,验证模型的有效性并通过对比PF与改进PF算法验证RUL预测的准确性。结果表明:自适应混合模型对于电池容量变化的表达能力更强,既能考虑电池内部的参数变化又能反应电池外部环境的变化,基于BAS改进的PF(BAS⁃PF)方法相较于传统PF算法的估计精度更高而且RUL预测更准确,对于不同的预测起点,两块测试电池的RUL预测误差分别为5.88%、3.92%、1.96%和3.75%、1.25%、0%。自适应混合模型能更加有效地描述电池容量特征,基于自适应混合模型的BAS⁃PF算法的电池RUL预测能力更好,可靠性更强,有助于提高RUL预测的精度和表现。

关键词：粒子滤波剩余寿命优化算法神经网络锂电池混合模型

EXACT EXPliCIT SOLUTIONS OF THE NONliNEAR SCHRDINGER EQUATION COUPLED TO THE BOUSSINESQ EQUATION

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2003年第4期23卷 453-460页

作者：姚若侠李志斌 Department of Computer Science Weinan Teachers' College Weinan 714000 China Department of Computer Science East China Normal University Shanghai 200062 China

A system comprised of the nonlinear Schrodinger equation coupled to the Boussinesq equation (S-B equations) which dealing with the stationary propagation of coupled non-linear upper-hybrid and magnetosonic waves in magnetized plasma is proposed. To examine its solitary wave solutions, a reduced set of ordinary differential equations are considered by a simple traveling wave transformation. It is then shown that several new solutions (either functional or parametrical) can be obtained systematically, in addition to rederiving all known ones by means of our simple and direct algebra method with the help of the computer algebra system Maple.

关键词： Coupled Schrodinger-Boussinesq equations traveling wave transformation Riccati equations solitary wave solution

粒子滤波和GRU神经网络融合的锂电池RUL预测

在线全文

学校读者我要写书评

暂无评论

哈尔滨工业大学学报 2024年第5期56卷 142-151页

作者：贺宁张思媛李若夏高峰王家栋西安建筑科技大学机电工程学院西安710055 西安建筑科技大学信息与控制工程学院西安710055 浙江中控技术股份有限公司杭州310000

随着锂电池在移动电子设备和电动汽车等领域中得到广泛应用,其剩余使用寿命(remaining useful life,RUL)的精确预测对锂电池的健康管理更具重要意义。本文提出一种基于粒子滤波(particle filter,PF)和门控循环单元(gated recurrent unit... 详细信息

随着锂电池在移动电子设备和电动汽车等领域中得到广泛应用,其剩余使用寿命(remaining useful life,RUL)的精确预测对锂电池的健康管理更具重要意义。本文提出一种基于粒子滤波(particle filter,PF)和门控循环单元(gated recurrent unit,GRU)神经网络融合(PF-GRU)的预测方法预测锂电池的RUL。这种融合方法结合了PF在估计RUL概率分布上的优势以及GRU能够进行时间序列长期预测的能力,获得融合的预测结果。再利用每个预测周期的容量预测结果,采用带移动窗口迭代更新训练数据集的方法对GRU模型进行再训练,提高了GRU的长期预测性能。以上预测步骤迭代进行,直到容量衰减至寿命阈值以下。最后将粒子代表的预测结果外推至寿命阈值,得到电池RUL分布直方图。本文采用美国NASA卓越诊断学中心(PCoE)实验室所提供的锂电池数据对所提方法进行验证,将所提出的融合方法与GRU、PF和无窗口移动融合方法进行RUL预测比较。实验结果表明,本文所提出的融合方法具有良好的性能,在状态和参数估计、RUL预测方面明显优于PF和无窗口移动融合方法,预测精度均高于其他3种预测方法。

关键词：锂电池剩余使用寿命粒子滤波 GRU神经网络融合方法

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

计及源荷不确定性的BIPV鲁棒优化调度

哈尔滨工业大学学报 2024年第12期56卷 132-142页

作者：贺宁茹成意李若夏蒋德润西安建筑科技大学机电工程学院西安710055 西安建筑科技大学信息与控制工程学院西安710055

为提高光伏建筑一体化(BIPV)能源系统运行的经济性和鲁棒性,降低光伏出力和电热冷负荷的不确定性对BIPV能源系统经济稳定运行带来的不利影响,提出了一种预测—配置—调度一体化策略实现BIPV能源系统鲁棒优化调度。首先,通过多任务高斯过... 详细信息

为提高光伏建筑一体化(BIPV)能源系统运行的经济性和鲁棒性,降低光伏出力和电热冷负荷的不确定性对BIPV能源系统经济稳定运行带来的不利影响,提出了一种预测—配置—调度一体化策略实现BIPV能源系统鲁棒优化调度。首先,通过多任务高斯过程(MTGP)综合考虑光伏出力和电、热、冷负荷间的相关性,得到精确的源荷预测结果及其概率信息,以此为基础建立基于MTGP的源荷不确定集。其次,针对建筑类型和负荷需求设计能源系统结构,以系统年投资成本和年运营成本最小化为目标函数建立经济最优容量配置模型并求解。最后,在确定源荷不确定集和设备容量配置的基础上建立BIPV能源系统两阶段鲁棒优化调度模型,通过列与约束生成算法和KKT条件求解模型,得到系统经济最优调度方案。本研究采用美国亚利桑那州州立大学某教学楼电、热、冷负荷数据对所提优化策略进行验证,仿真试验结果表明:所提优化策略可以通过改变不确定集置信度灵活调整调度方案的保守性,在考虑分时电价机制下,储能设备充分发挥削峰填谷作用,降低了系统运营成本,与传统的确定性优化和采用盒式不确定集的鲁棒优化策略相比,调度方案的经济性和鲁棒性均有所提升。

关键词：光伏建筑一体化能源系统源荷不确定性多任务高斯过程容量优化配置鲁棒优化调度

维普期刊数据库博看期刊

在线全文

学校读者我要写书评

暂无评论

关于幸福与幸福观的思考

学园 2009年第1期 27-31页

作者：余若峡李贤华南师范大学

本文在梳理中外关于幸福及幸福观的历史形态基础上,从'幸福的含义由幸福观决定、幸福是目的也在过程中、幸福不等同于快乐以及幸福的要素'四个方面进行论述。这些思考未必都成熟、完善,但是,作这样的思考,对于我们加深对幸福的理解,对... 详细信息

本文在梳理中外关于幸福及幸福观的历史形态基础上,从'幸福的含义由幸福观决定、幸福是目的也在过程中、幸福不等同于快乐以及幸福的要素'四个方面进行论述。这些思考未必都成熟、完善,但是,作这样的思考,对于我们加深对幸福的理解,对于追求有质量的生活,对于我们精神的丰满,必将有所裨益。

关键词：幸福幸福观