基于神经网络辨识的DMFC电压模型研究

介绍并分析了直接甲醇燃料电池(DMYC)的工作原理及理论电压模型,并针对直接甲醇燃料电池系统过于复杂,理论电压模型存在明显不足的特点,试图绕开DMYC的内部复杂性,基于实验数据,利用神经网络逼近任意复杂非线性函数的能力,将神经网络辨识方法应用到DMYC这种高度非线性系统的建模中去,以1000组电池电压、电流密度实验数据作为训练样本,采用基于LM算法的改进BP神经网络,建立了不同温度下电池电压一电流密度的神经网络辨识模型。仿真结果表明这种方法是可行的,建立的模型精度较高。     

基于启发式动态规划的固体氧化物燃料电池优化控制研究

固体氧化物燃料电池(SOFC)系统是一个非线性系统,现存的建模方法和优化控制算法很难对其进行精确的建模及优化控制;针对此问题,采用基于数据的建模方法,对固体氧化物燃料电池系统进行BP神经网络建模,然后在此基础上,首次采用启发式动态规划(HDP)算法对固体氧化物燃料电池系统中的各种气体分压、输出电压以及温度进行优化控制;Matlab仿真结果表明,基于BP神经网络的HDP优化算法具有收敛速度快、鲁棒性强、控制精度高等优点,并使固体氧化物燃料电池系统在负载变化时很快稳定输出电压,实现了优化控制,减少能耗。     

基于改进BP神经网络辨识的DMFC建模研究

针对直接甲醇燃料电池（DMFC）系统过于复杂,难以建模的特点,该文试图绕开DMFC的内部复杂性,基于实验数据。利用神经网络逼近任意复杂非线性函数的能力,将神经网络辨识方法应用到DMFC这种高度非线性系统的建模。以1000组电池电压、电流密度实验数据作为训练样本,采用基于LM算法的改进BP神经网络,建立了不同温度下电池电压-电流密度动态响应模型。仿真结果表明这种方法是可行的,建立的模型精度较高,它使得设计DMFC的实时控制器成为可能。     

基于WNN-PSO的压力测量与校正方法

对压力(差压)传感器普遍存在的温度影响问题,以及目前常规压力(差压)传感器无法直接准确测量较高温气体压力的问题,本文提出了基于小波神经网络(WNN)与粒子群优化(PSO)方法的动态测量与校正方法,通过与已有方法的仿真比较,以及对阳极焙烧系统中高温烟气压力的实际测量应用表明,该方法优于原有的BP、WNN测量和校正方法.     

基于广义回归神经网络的SOFC电压模型研究靠

首先介绍并分析了固体氧化物燃料电池(SOFC)的工作原理和理论电压模型.然后,针对SOFC系统过于复杂,理论电压模型存在明显不足的特点,试图绕开SOFC的内部复杂性,利用广义回归神经网络(GRNN)对SOFC系统进行辨识建模.模型以电池工作温度为神经网络辨识模型的输入量,电池电压/电流密度为输出量,利用750组实验数据作为训练样本,建立了SOFC在不同工作温度下的电池电压/电流密度动态响应模型.仿真结果表明了该方法的有效性,所建模型精度也较高.     

粗糙集约简的WNN隐层节点优化方法

在确保网络性能的前提下,如何确定最佳隐层节点,获得最简网络结构是小波神经网络(WNN)应用推广的关键.对此,引入粗糙集理论,提出了基于信息熵的卡方离散化算法和启发式的属性约简递归算法,利用粗糙集约简过程对WNN隐层节点进行精简,并将其应用于飞行器气动力建模.仿真结果表明,采用改进的粗糙集方法设计WNN,不仅能够简化网络结构,而且与未经结构优化的WNN相比,其模型精度和训练速度都得到了实质性改善.     

燃料电池电能与热能建模研究

为分析燃料电池的动态特性,对其发电和发热过程进行了建模研究。燃料电池划分为阳极动态模型、阴极动态模型、电化学电压模型和温度动态模型,分别从流量平衡、能量平衡和经验公式角度进行了机理建模;并采用改变负载和冷却水流量的方式进行测试。仿真结果表明,该模型能模拟燃料电池的电热动态过程,可用于辅助控制设计。     

基于PSO-WNN的MEMS陀螺随机误差建模普适性分析

针对MEMS陀螺仪随机误差对系统导航精度影响以及现有建模方案存在个体普遍适用性问题,提出将粒子群优化算法(PSO)与小波神经网络(WNN)结合后对MEMS陀螺随机误差进行预测的建模方法,完成小波神经网络的构建。利用小波函数作为神经网络中隐含层的激励函数,同时将小波神经网络各层的连接权值作为粒子群优化算法中粒子的位置,使得建立的模型函数逼近能力更加灵活有效且增强其容错能力,同型号不同个体MEMS传感器建模补偿实验结果表明,论文提出的PSO-WNN误差建模方法预测的MEMS陀螺仪随机误差均值和标准差分别优于0.025°/s和0.13°/s,补偿后的MEMS陀螺Allan方差分析结果进一步验证了论文所提方法的可行性与普适性。     

含有误差校正的小波神经网络交通流量预测

交通流量的准确预测对于高速路管理者进行决策至关重要;建立了小波神经网络(WNN)交通流量预测模型,并通过预测训练误差和测试误差校正预测结果来提高预测精度;首先构建WNN模型对交通流量进行初步预测,然后利用经验模态分解(EMD)和WNN模型对训练误差和测试误差进行预测;分别用训练误差预测值、测试误差预测值和两种误差预测值的加权对流量初步预测结果进行修正得到最终预测值;采用四川省成灌高速路交通流量数据进行了仿真对比实验,仿真结果表明含有误差校正的小波神经网络模型能有效提高交通流量预测精度,并且利用两种误差加权修正模型的预测精度高于利用测试误差的修正模型和利用训练误差的修正模型。     

基于Fluent的微型直接甲醇燃料电池阳极流场结构分析

微型直接甲醇燃料电池中阳极流场结构对电池的性能有着重要的影响。为了合理设计阳极流场结构,改善甲醇燃料在阳极流场中的分布,采用计算流体动力学(CFD)软件Fluent对微型直接甲醇燃料电池进行建模并仿真分析。分析比较了点型、平行和蛇形3种不同流场图案下得到的压降与流速分布,得出蛇形流场能够更有利于甲醇燃料的均匀分配。在此基础上分别建立不同流道宽度(800,400,200,100μm)的蛇形流场模型,通过仿真计算甲醇燃料的分布情况来分析其对燃料电池性能的影响,并结合实验结果进行对比得出流道宽度为200～400μm之间为优化值。     

Plug_in电动车能量管理控制器研究

基于模糊神经网络算法研究设计Plug_in混合动力汽车整车能量管理控制器。将驾驶行为用神经网络进行建模,驾驶模式、踏板(油门和刹车)位置以及当前车轮力矩作为神经网络输入,目标力矩作为输出;将道路类型、目标力矩、电池SOC、当前车轮力矩为模糊输入变量,以满足整车动力性能、燃油经济性和极限边界极值为约束条件,对混合动力汽车的能量进行分配与管理,并在DSP硬件平台设计实现能量管理控制器。测试表明,行驶里程在40 km内时,样车等价燃油经济性最好,随着行驶里程的增加,燃油经济性下降,整个测试过程中样车动力性能以及各部件工况良好。     

A forecasting system for car fuel consumption using a radial basis function neural network

A predictive system for car fuel consumption using a radial basis function (RBF) neural network is proposed in this paper. The proposed work consists of three parts: information acquisition, fuel consumption forecasting algorithm and performance evaluation. Although there are many factors affecting the fuel consumption of a car in a practical drive procedure, in the present system the relevant factors for fuel consumption are simply decided as make of car, engine style, weight of car, vehicle type and transmission system type which are used as input information for the neural network training and fuel consumption forecasting procedure. In fuel consumption forecasting, to verify the effect of the proposed RBF neural network predictive system, an artificial neural network with a back-propagation (BP) neural network is compared with an RBF neural network for car fuel consumption prediction. The prediction results demonstrated the proposed system using the neural network is effective and the performance is satisfactory in terms of fuel consumption prediction.     

插电式混合动力汽车车速预测及整车控制策略

本文针对插电式混合动力汽车(plug-in hybrid electric vehicle,PHEV)这一典型混杂系统,提出了一种基于车速预测的混合逻辑动态(mixed logical dynamical,MLD)模型预测控制策略.首先,通过对发动机和电动机能量消耗模型进行线性化,建立双轴并联插电式混合动力城市公交车的动力传动系统数学模型;其次,运用模糊推理进行驾驶意图分析,提出基于驾驶意图识别和历史车速数据相结合的非线性自回归(nonlinear auto-regressive models,NAR)神经网络车速预测方法进行未来行驶工况预测.然后,以最小等效燃油消耗为目标建立PHEV的混合逻辑动态模型,运用预测控制思想对车速预测时域内最优电机转矩控制序列进行求解.最后,通过仿真实验验证了本文所提出控制策略在特定的循环工况下与电动助力策略相比,能够提高燃油经济性.     

Modeling and simulation of injection control system on a four-stroke type diesel engine development platform using artificial neural networks

Efficiency, reliability and emission demands on fuel consumptions have directed us to develop a microcontroller-based electromechanical educational platform that emulates the basic injection process of common four-stroke type diesel engines. Modeling of a system provides rapid programming and implementation capabilities. This study focuses on modeling and simulation of the platform in order to observe the results of novel methods and development strategies. The model determines the injection time (IT) and injection order (IO) of the related pistons. Determination of the IO has standard steps, where of IT which directly affects the fuel consumption lets novel optimization methods. In traditional applications, IT is assigned by a lookup table, whose inputs are crankshaft speed (CS) and manifold absolute pressure (MAP) values. In this study, an alternative relation surface created by feedforward artificial neural networks (ANNs) is suggested to determine the IT. The novel method could interpolate precise intermediate values of IT which bring about optimization in fuel consumption. Performances of the traditional method and the ANNs method are compared.     

An application of a merit function for solving convex programming problems

This paper presents a gradient neural network model for solving convex nonlinear programming (CNP) problems. The main idea is to convert the CNP problem into an equivalent unconstrained minimization problem with objective energy function. A gradient model is then defined directly using the derivatives of the energy function. It is also shown that the proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem. It is also found that a larger scaling factor leads to a better convergence rate of the trajectory. The validity and transient behavior of the neural network are demonstrated by using various examples.     

Hardware-in-the-loop simulation for the design and verification of the control system of a series–parallel hybrid electric city-bus

Hybrid electric buses have been a promising technology to dramatically lower fuel consumption and carbon dioxide (CO₂) emission, while energy management strategy (EMS) is a critical technology to the improvements in fuel economy for hybrid electric vehicles (HEVs). In this paper, a suboptimal EMS is developed for the real-time control of a series–parallel hybrid electric bus. It is then investigated and verified in a hardware-in-the-loop (HIL) simulation system constructed on PT-LABCAR, a commercial real-time simulator. First, an optimal EMS is obtained via iterative dynamic programming (IDP) by defining a cost function over a specific drive cycle to minimize fuel consumption, as well as to achieve zero battery state-of-charge (SOC) change and to avoid frequent clutch operation. The IDP method can lower the computational burden and improve the accuracy. Second, the suboptimal EMS for real-time control is developed by constructing an Elman neural network (NN) based on the aforementioned optimal EMS, so the real-time suboptimal EMS can be used in the vehicle control unit (VCU) of the hybrid bus. The real VCU is investigated and verified utilizing a HIL simulator in a virtual forward-facing HEV environment consisting of vehicle, driver and driving environment. The simulation results demonstrate that the proposed real-time suboptimal EMS by the neural network can coordinate the overall hybrid powertrain of the hybrid bus to optimize fuel economy over different drive cycles, and the given drive cycles can be tracked while sustaining the battery SOC level.     

Development of a predictive system for car fuel consumption using an artificial neural network

A predictive system for car fuel consumption using a back-propagation neural network is proposed in this paper. The proposed system is constituted of three parts: information acquisition system, fuel consumption forecasting algorithm and performance evaluation. Although there are many factors which will effect the fuel consumption of a car in a practical drive procedure, however, in the present system the impact factors for fuel consumption are simply decided as make of car, engine style, weight of car, vehicle type and transmission system type which are used as input information for the neural network training and fuel consumption forecasting procedure. In the fuel consumption forecasting, to verify the effect of the proposed predictive system, an artificial neural network with back-propagation neural network has a learning capability for car fuel consumption prediction. The prediction results demonstrated that the proposed system using neural network is effective and the performance is satisfactory in fuel consumption prediction.     

一种改进的神经网络算法及其在烧结成本预测中的应用研究

在烧结生产过程中,固体燃耗占据了生产能耗的70%左右,而与固体燃耗相关的工艺参数与固体燃耗之间呈现出非线性关系。为了实现优化生产和达到降低生产能耗的目的,本文采用改进后的BP神经网络挖掘两者之间存在的映射关系。本文提出了一种基于广义Curry原则非精确线搜索的共轭梯度算法,利用新的线搜索规则来确定算法的学习步长,在保证算法全局收敛的前提下,优化学习步长,提高了算法的收敛速度。利用改进的算法对烧结生产成本进行分析和预测,仿真结果说明改进算法具有很好的收敛性,预测的均方误差为0.0098,准确率达到94.31%。     

基于RBF神经网络的风光互补路灯系统MPPT研究

为了提高风光互补路灯的稳定性和使用寿命,根据风光互补路灯系统非线性、多物理量等特性,分别对风力发电和光伏发电采取最大功率点跟踪(MPPT)控制。该方法基于径向基函数(RBF)神经网络,分别以风力发电整流器输出的电压、电流和太阳能电池板输出的电压、电流作为RBF神经网络的输入,通过RBF神经网络直接改变Boost电路的占空比,使风光互补系统工作在最大功率点。仿真和试验结果表明,所提出的MPPT算法与扰动观察法算法相比,有更好的快速性和能量利用效率。