基于最小二乘支持向量机的煤粉着火温度预测分析

针对关系到锅炉经济安全运行的煤着火温度估计难的问题,采用最小二乘支持向量机方法建立煤粉着火温度的预测模型,并和利用PLS以及BP神经网络等方法建立的预测模型进行对比,结果表明,最小二乘支持向量机克服了BP神经网络泛化能力弱以及PLS无法解决的非线性等问题,采用最小二乘支持向量机方法建立的煤粉着火温度模型具有很高的预测精度.     

基于万有引力搜索算法的电厂锅炉NO_x排放模型的参数优化

以某330MW煤粉汽包锅炉为测试对象,以支持向量回归机为基础,利用最小二乘支持向量机和一种新的寻优算法———万有引力搜索算法进行了综合建模及参数优化.结果表明:建立的模型较好地实现了对电厂锅炉NOx质量浓度排放量的预测;与遗传算法、蜂群算法和粒子群算法相比,万有引力搜索算法能更好地找到未知优化参数,使得所建模型具有更高的预测能力和泛化能力,从而有效控制燃煤电厂NOx的排放量.     

最小二乘支持向量机在煤着火特性研究中的应用

为避免煤热失重反应静态燃烧过程获取的燃烧参数与实际锅炉动态燃烧之间的误差,以及解决沉降炉实验工作量大、难以对所有煤种进行试验的问题,利用最小二乘支持向量机建立了煤粉着火特性模型,通过对热失重反应过程的机理分析确定最佳输入变量,并进行仿真实验.结果表明:利用热失重反应过程数据预测煤着火性能具有较高的预测精度,可以在实际中应用,指导大型电站锅炉及燃烧装置的设计和运行.     

基于提升小波和LS-SVM的大坝变形预测

提出了一种基于提升小波和最小二乘支持向量机的大坝变形预测方法,通过提升小波分析提取大坝监测数据效应量,分别对各效应量使用最小二乘支持向量机模型进行训练预测,再将合成各分量的预测结果作为最终的变形预测结果.算例结果表明,该方法较符合实际情况,具有很高的预测精度和良好的泛化能力.     

基于最小二乘支持向量机的生物质热值预测

生物质的热值与其组成成分有关,基于此,应用最小二乘支持向量机方法建立了生物质热值预测的有效模型,并利用Biomass Feedstock Composition and Properties Database数据库提供的数据进行了测试。以该数据库的部分生物质的固定碳、挥发分和灰分含量作为输入,以相应的热值作为输出,训练最小二乘支持向量机。训练完成后,用剩余的生物质进行测试。测试结果表明,预测方法准确,速度较快。与神经网络方法相比,基于最小二乘支持向量机的生物质的热值预测方法更有效。     

基于PSO优化LS-SVM的短期风速预测

提出了一种基于粒子群(PSO)算法优化最小二乘支持向量机(LS-SVM)的风电场风速预测方法。以相关性较高的历史风速序列作为输入,建立预测模型,并用粒子群算法优化模型参数。在对未来1 h风速进行预测时,文章所提出的模型比最小二乘支持向量机模型及BP神经网络模型具有较高的预测精度和运算速度。算例结果表明,经粒子群优化的最小二乘支持向量机算法是进行短期风速预测的有效方法。     

基于单纯形粒子群—支持向量机模型的土坝测压管水位预测方法及应用

针对土坝渗流安全监测模型中测压管水位与其影响因子之间非线性关系复杂、模型因子选择难度较大的问题,采用支持向量机模拟测压管水位与其影响因子之间的非线性映射关系,并采用单纯形粒子群算法对支持向量机中的核参数、惩罚系数及不敏感损失因子进行优化,建立了土坝测压管水位预测的单纯形粒子群—支持向量机模型（SMPSO-SVM）,通过与多元线性回归模型、逐步回归模型、遗传回归模型及最小二乘支持向量机模型进行对比,表明SMPSO-SVM预测模型预测精度高、稳定性好。     

基于FOA和LS-SVM的风电场风速预测研究

针对目前最小二乘支持向量机选取核参数和惩罚因子的各种方法尚存在着一定的局限性,文章采用果蝇优化算法对参数进行优化选择,提出了基于果蝇优化算法与最小二乘支持向量机结合的风速混合预测方法。对新疆某风电场为期5天的240个(采样间隔0.5 h)实测风速值进行了仿真测试,利用建立的预测模型,对第5天的风速值进行预测,预测结果的平均绝对百分比误差仅为8.32%。将其与单纯的LS-SVM模型和基于网格搜索优化的LS-SVM模型的预测结果作了对比,仿真结果验证了基于果蝇优化算法和最小二乘支持向量机混合预测模型的可行性和果蝇算法对最小二乘支持向量机参数优化的有效性。     

基于经验模态分解与多步预测的最小二乘支持向量机的风速预测

由于风速信号是非线性、非稳定性的动态信号,用传统预测方法难以达到满意效果。为提高预测精度,提出了基于经验模态分解与多步预测的最小二乘支持向量机相结合的方法,对风速时间序列进行建模预测,即首先对风速动态信号进行经验模式分解,将原信号分解为若干个不同特征尺度(频率)的本征模态函数,然后对不同频带的平稳IMF分量分别建立多步预测的最小二乘支持向量机模型,将各分量的预测值等权求和得到最终预测值。实例分析结果表明,与单一的最小二乘支持向量机预测方法相比,经验模态分解与多步预测的最小二乘支持向量机相结合的风速预测方法误差小,可应用于风速预测中。     

电站煤粉炉NO_x排放特性的最小二乘支持向量机模型

为获得电站煤粉炉NOx排放特性的在线预测模型,实现低NOx闭环运行控制,以某电厂300MW四角切圆燃烧煤粉炉为研究对象建立了NOx排放特性的最小二乘支持向量机模型.在建模过程中,进行了模型性能对核函数、惩罚因子γ和核函数参数σ2的敏感性分析,并运用遗传算法和交叉证实获得了γ和σ2的最佳值.最后利用不同试验工况下的样本数据检验了模型的预测性能,并将该模型的预测性能与BP神经网络模型相比较,结果说明该模型的建模特点和预测性能能够满足NOx排放的在线预测.     

Estimation of battery available capacity under variable discharge currents

In this paper, a new mathematical model in semi-empirical form for lead-acid batteries is presented, which describes the relationship between the battery terminal voltage and the variable discharge current. Based on the proposed model, a new estimation method of the battery available capacity (BAC) in the presence of variable discharge currents is developed. The method involves the real-time identification of the model parameters which are then used to estimate the BAC according to the predefined cutoff voltage and the trend of battery terminal voltage during discharging. Thus, both temperature and aging influences on the BAC are considered inherently. Comparisons between the calculated results and the measured data confirm that the proposed method can provide an accurate real-time estimation of the BAC under variable discharge currents.     

基于VAR模型的远期合同定金的定价方法

为规避电力市场改革给市场带来的风险、提高市场的运作效率、增大电力商品的交易量，提出了发电商与电网公司之间一种带定金的远期合同模型。介绍了VAR风险评估方法及其分析法——Delta类模型在电力市场金融风险评估中的应用；运用VAR风险评估方法计算出该模型中发电商存在的风险，进而确定合同定金。应用该模型对不同的合同电价和置信水平分别计算出相应的定金，结果表明，合同定金随合同电价的减小而减小，随置信水平的增大而增大，说明了该模型能较真实地反映发电商所面临市场风险的本质特征。     

遗传门限回归模型在河道洪水预报中的应用

提出了基于遗传算法的一套操作简便、通用的ＴＲ建模方案,并成功地将ＴＲ模型用于相应流量法去预测洪水,实例计算的结果说明其可行性和有效性。     

Feedback-Linearization-Based Nonlinear Control for PEM Fuel Cells

This paper presents a dynamic nonlinear model for polymer electrolyte membrane fuel cells (PEMFCs). A nonlinear controller is designed based on the proposed model to prolong the stack life of the PEM fuel cells. Since it is known that large deviations between hydrogen and oxygen partial pressures can cause severe membrane damage in the fuel cell, feedback linearization is applied to the PEM fuel cell system so that the deviation can be kept as small as possible during disturbances or load variations. A dynamic PEM fuel cell model is proposed as a nonlinear, multiple-input multiple-output system so that feedback linearization can be directly utilized. During the control design, hydrogen and oxygen inlet flow rates are defined as the control variables, and the pressures of hydrogen and oxygen are appropriately defined as the control objectives. The details of the design of the control scheme are provided in the paper. The proposed dynamic model was tested by comparing the simulation results with the experimental data previously published. The simulation results show that PEMFCs equipped with the proposed nonlinear controls have better transient performances than those with linear controls.     

An improved dynamic voltage model of PEM fuel cell stack

The voltage dynamic properties of PEM fuel cell stack have been analyzed through experimental investigation. Different behaviours between voltage overshoot and undershoot are found under load commutations. A semi-empirical dynamic model for stack voltage is introduced on the basis of experimental investigation. The proposed model can predict the transient response of stack voltage under step change in current. Comparing with previous model, the suggested model indicates a better agreement between tests and simulations.     

Lifetime prediction for proton exchange membrane fuel cell under real driving cycles based on platinum particle dissolve model

Despite the great progress of proton exchange membrane fuel cell (PEMFC) vehicle, the durability and cost of PEMFC still remain challenges. In this paper, a lifetime prediction model of PEMFC is developed by considering the platinum (Pt) electrochemical surface area (ECSA) degradation caused by steady power and transient power. The direct and continuous relationship between lifetime and real driving cycles is built by the proposed model. Firstly, the steady ECSA degradation model is deduced, and both the chemical and electrochemical dissolution of Pt particles are considered in the catalyst layer. The ECSA loss rate for steady power condition can be calculated by this model. Secondly, transient ECSA loss formula is obtained by fitting experimental data of PEMFC. This transient ECSA loss formula is used to calculate the ECSA loss rate under power changes condition. Thirdly, by applying the power voltage relationship, for a given power, the voltage can be calculated and applied to the two ECSA degradation models. Finally, the lifetime prediction method of PEMFC is proposed, and it is verified by PEMFC under three different driving cycles. Experimental test results show that the proposed lifetime prediction model accurately predict the lifetime of PEMFC under different driving cycles. The proposed method in this paper is more accurate compared with the method which divides the degradation into 4 conditions.     

Separation and compression characteristics of hydrogen by use of proton exchange membrane

Fuel cells (FC) can produce electricity through electrochemical reaction of hydrogen with oxygen with the use of a membrane and electrode assembly (MEA). In other words, the hydrogen pressure difference between the anode and cathode can produce electricity via an electrochemical process. Conversely, when we supply electricity to MEA from an external power source, we can pump up or separate hydrogen from the low pressure anode to the high pressure cathode according to the principle of the “concentration cell”. The depleted hydrogen from the FC can be recovered by the hydrogen separation pump proposed herein, or low pressure hydrogen can be pumped to high pressure hydrogen by the hydrogen compression pump proposed herein. In this study we preliminarily tested the hydrogen separation pump and hydrogen compression pump, and demonstrated their good performance. The tested performances were analyzed with the use of our simulation model of a hydrogen pump, which was made by modifying our FC simulation model, and the test results agreed well with the calculated results.     

An efficient approach for prediction of Warburg-type resistance under working currents

In the present study, an efficient approach for the prediction of Warburg-type element is proposed via the analysis of the anode-supported solid oxide fuel cell (SOFC) performance under various working conditions. The details of the performance, polarization curves, impedance behavior, and species distribution profiles within the electrode are investigated via the combination of equivalent circuit model (ECM) analysis and multiphysics numerical simulations. The multiphysics simulation is developed and calibrated with experimental results of SOFC button cells under various working currents. With the complete datasets generated from the calibrated simulations, the trends of the element parameters involved in equivalent circuit model are analyzed. Generalized empirical functions are proposed as well as the procedures of prediction of performance under different conditions. The verification cases show good agreement between the predicted results from proposed model and the reference results. This proposed approach can be utilized to quickly predict the properties for desired performance in the manufacturing processes, and it also has the potential of reducing the computational cost in the simulation of large SOFCs.     

Fractional order model for diagnosis of flooding and drying of the proton exchange membrane fuel cell

The diagnosis and control of PEMFCs hydration states depend on the reliable models and methods of monitoring of system operating. Impedance spectroscopy was generally used to describe fuel cell systems and derived impedance models. This study investigated the characterization and diagnosis of fuel cells by using fractional order impedance model as an explicit transfer function and factor design methodology (DOE) to determine the model parameters. The physical parameters appeared very sensitive to humidity and then used for monitoring and diagnosing of fuel cells. The proposed model is suitable to represent Randles impedance model equivalent electrical circuit enhanced by CPE, with the ability to generate the Nyquist impedance spectra easily for all conditions of relative humidity and operating time.The comparison between the literature experimental impedance spectra in both cases (drying and flooding), and the spectra simulated by the explicit fractional order impedance model demonstrated that the proposed model was robust and reliable and can, therefore, be integrated into the PEMFCs water management system.     

Hygrothermomechanical Effects on Laminated Composite Plates in Terms of a Higher-Order Global-Local Model

Results analytical or numerical on transverse shear stresses of laminated composite plates subjected to hygrothermomechanical effects are scarce in literature. To fill this gap, a higher-order global-local model (HGLM) satisfying the continuity conditions of transverse shear stresses at interfaces is proposed. Based on stress continuity condition between layers, the number of variables in the proposed model is independent of the number of layers of the laminate. Applying Navier's technique to equilibrium equations obtained using the principle of minimum potential energy, analytical solution of the model HGLM is derived for simply supported composite plates. Comparing the results from available three-dimensional elasticity theory and those computed from the first-order and the higher-order models, it is found that the proposed model can produce promising transverse shear stresses directly from constitutive equations without any smoothing technique. The effects of material properties, aspect ratio, side-to-thickness ratio, stacking sequence and thermal expansion coefficients on the hygrothermomechanical response have also been studied.