基于NWAPSO参数全局寻优的LS-SVM电站风机性能预测

风机的性能曲线是风机选型和优化运行的重要依据.通常该曲线通过试验试验数据和性能图表上的数据进行曲线拟合获得.由于该曲线非线性很强,传统方法复杂昂贵,而且拟合精度不高。针对以上不足,提出了一种基于非线性权重自适应粒子群优化(NWAPSO)参数全局寻优的最小二乘支持向量机(LS-SVM)风机性能预测方法。通过最小二乘支持向量机建模,并应用非线性权重自适应粒子群优化算法对模型参数进行全局寻优,得到具有较高精度的风机性能曲线。计算结果表明,根据本文方法建立的模型很简洁,只需要知道少量的训练样本就能建立,可以比较精确的预测风机性能,具有较显著的工程应用价值。     

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。     

基于加权最小二乘支持向量机的月度负荷预测

考虑到实际电力负荷预测中各数据的重要程度并不相同,在标准最小二乘支持向量机回归算法的训练样本中设置权值系数,建立了加权最小二乘支持向量机模型,以实现样本的优化选择,达到历史数据"重近轻远"的学习效果;同时考虑到粒子群优化算法收敛速度快和混沌运动遍历性、随机性等特点,提出了一种基于混沌思想的粒子群优化算法对模型参数进行优化,引入优势粒子和劣势粒子的权重自适应调节机制,使算法具有动态适应性。将改进的模型应用于江西省萍乡市月度负荷预测中,结果表明本文方法与常规方法相比降低了预测误差,且速度较快。     

基于CPSO-LSSVM的汽轮机热耗率软测量模型

为了准确建立汽轮机热耗率预测模型,提出了一种基于变空间Logistic混沌粒子群算法(CPSO)优化最小二乘支持向量机(LSSVM)的汽轮机热耗率软测量模型。采用变空间Logistic混沌搜索策略和粒子镜像越界处理策略来改善粒子群算法(PSO)的全局优化性能,提出了CPSO优化最小二乘支持向量机的超参数以改善模型预测精度,并以某600 MW汽轮机组为研究对象,利用该机组的运行数据建立CPSO-LSSVM的热耗率预测模型。结果表明:CPSO-LSSVM模型具有更高的预测精度和更强的泛化能力,能够准确有效地预测热电厂的汽轮机热耗率。     

APSO-WLSSVM算法在水质预测中的应用研究

针对参数选择是影响加权最小二乘支持向量机水质预测效果的关键,给出了基于自适应粒子群优化算法参数优选的WLSSVM回归预测的建模过程,以大伙房水库为例,预测了库区水质主要影响因素,并与未优选的WLSSVM预测结果进行对比。结果表明,该方法参数寻优更可靠、快速,预测精度高。     

大型风电场超短期风电功率预测

针对大规模风电场风电功率的非线性特性,采用最小二乘支持向量机（LS—SVM）的预测模型。由于LS—SVM的参数选择直接影响着模型的预测精度,于是采用一种基于量子粒子群优化方法来选择模型的超参数。为了弥补模型损失的鲁棒性,通过给每个样本误差不同的权系数,建立了具有良好泛化性能的WLS—SVM回归模型,从而进一步提高了模型预测的精度。本文提出一种基于量子粒子群优化（0uantum—behaved Particle Swarm Optimization,QPSO）参数选择的加权最小二乘支持向量机（Weighted Least Squares Support Vector Machine,WLS—SVM）的超短期风电功率预测模型。应用上述方法对内蒙古地区大型风电场进行了预测,结果证明了该方法的有效性。     

基于改进LSSVM的太阳辐射量预测

为准确预测太阳辐射量,提出一种基于变分模态分解和粒子群优化算法的最小二乘支持向量机组合预测模型。针对太阳辐射量序列具有不稳定性的特点,首先利用变分模态分解将历史太阳辐射量数据分解成一系列相对稳定的分量序列,再应用粒子群优化最小二乘支持向量机参数,以预测各分量序列,将各分量太阳辐射量预测值集成,从而得到最终太阳辐射量预测值。实例分析和对比研究表明,该模型预测太阳辐射量有效可行,具有较高的预测精度。研究成果可为太阳辐射量预测提供参考。     

基于GSA-LSSVM的循环流化床锅炉飞灰含碳量预测

为了控制循环流化床锅炉飞灰含碳量,提高锅炉燃烧效率。以某电厂循环流化床锅炉燃烧数据为样本,应用最小二乘支持向量机(LSSVM)建立了以锅炉运行参数为输入量,以锅炉飞灰含碳量为输出的模型。由于最小二乘支持向量机的参数决定了模型精度及泛化能力,将万有引力搜索算法(GSA)运用到模型参数寻优过程中,得到了飞灰含碳量最优模型GSA-LSSVM;并利用不同工况下的样本数据检验了模型的预测性能,并将该模型分别与粒子群(PSO)和遗传算法(GA)优化的LSSVM模型进行比较,仿真实验证明GSALSSVM模型具有很好的辨识能力及泛化能力。     

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。     

基于改进经验小波变换和最小二乘支持向量机的短期风速预测

针对原始风速信号非线性和非平稳性的特征,提出一种新的改进经验小波变换(IEWT)方法,该方法可将风速信号分解成一组有限带宽的子序列,以降低其不稳定性。在此基础上,结合最小二乘支持向量机(LSSVM),提出基于改进经验小波变换和最小二乘支持向量机(IEWT-LSSVM)的短期风速预测方法,并通过模拟退火粒子群优化算法(SAPSO)对相空间重构参数以及LSSVM模型的2个超参数进行共同优化。最后以华北某风电场采集的风速信号为算例,结果表明基于IEWT-LSSVM的预测模型能有效追踪风速信号的变化,在单步预测和多步预测上均具有较高的预测精度。     

Rotary-gradient fitting algorithm for polarization curves of Proton Exchange Membrane Fuel Cells (PEMFCs)

Experimental data obtained in electrochemistry traditionally have been fitted to models in order to obtain relevant parameters of the underlying processes. Polarization curves are among the most important representations of fuel cell performance, as they are useful tools for studying the performance of these cells in operation. On this basis, we developed an algorithm to fit the experimental polarization curves employing two different models. This algorithm combines different optimization techniques, such as rotary optimization and gradient optimization. Seven experimental polarization curves, obtained with different experimental proton exchange membrane fuel cell (PEMFC) membrane electrode assemblies (MEAs), are used to evaluate the proposed fitting techniques and theoretical models. The average quadratic errors of the models fitted by the algorithm are below 9 mV in all the curves, much less than the 750–1000 mV voltage variation in them. Therefore, we propose that the algorithm and the models are good options for use in fitting these data.     

电站离心式风机性能在线监测的研究及其在DCS中的实现

针对风机设计，运行和性能特点，分析了进行电站风机性能监测重要性和必要性，建立了以曲面拟合理论和神经网络拟合为基础的离心式风机性能监测模型，并与DCS结合完成了通风机性能监测，最后通过现场实践进行了验证。     

国产超临界直接空冷机组冷端性能特性的研究

空冷岛运行优化中,需要将汽轮机、空冷凝汽器及空冷岛风机的特性综合起来进行分析。在综合直接空冷机组冷端各个组成部分,包括空冷凝汽器、低压缸至空冷凝汽器之间排汽管道及空冷岛风机特性的基础上,建立汽轮机排汽背压与空冷岛风机转速的特性关系,为空冷岛运行优化计算创造了条件。     

轴流风机通用性能数学模型

鉴于现有的动叶调节或静叶调节轴流风机性能数学模型静态精度不高,动态调节过程特性与实际 风机相差较大的问题,根据动（静）叶调节轴流风机静态性能曲线特点,依据风机的有关定律和原理,建立了动（静）叶调节轴流风机的功能通用数学模型,算例与应用实践表明：模型和静态精度,动态调节特性好,可用于轴流风机的实时仿真,性能在监测,故障预报等,具有广泛适用性。     

两种水泵性能曲线拟合方法的研究

采用基于最小二乘法的多项式拟合与改进的BP神经网络法分别对同一水泵性能参数进行拟合,并通过算例比较分析了两者拟合效果、精度。结果表明,改进的BP神经网络拟合曲线效果和精度较高,在样本数量不多情况下两者拟合曲线效果较接近。     

Development of a novel mop fan

A novel fan that operates as an air moving device as well as a filter has been investigated. The unit utilizes a brush disk, instead of bladed impellers, within a centrifugal fan casing and is known as a ‘mop fan’. The performance of the mop impellers as fans was tested and their characteristic curves were found to be similar to those of centrifugal fans. The characteristics of the mop fan in terms of airflow rate, pressure, and efficiency were tested using a standard method, BS 848. The tests allowed mops of different fibre number and fibre diameter to be constructed and so optimize mop fan performance. Copyright © 2001 John Wiley & Sons, Ltd.     

Performance prediction of an improved air-cooled steam condenser with deflector under strong wind

For an air-cooled steam condenser (ACSC), environmental wind can cause a large flow rate reduction in the axial fans mainly near the windward side of the air-cooled platform due to cross-flow effects, resulting in a heat transfer reduction. This leads to an increase of turbine back pressure, and occasional turbine trips occur under extremely gusty conditions. A new method is proposed in this paper to remove the strong wind effect by adding deflecting plates under the air-cooled platform, which contributes to forming a uniform air mass flow rate in the axial fans by leading enough cooling air to the fans in the upwind region. Numerical simulation is made of the thermal-flow characteristics and heat transfer performance of the improved ACSC with deflectors. A heat exchanger model is used for simulating the flow and heat transfer in the ACSC, in which the heat exchanger is simplified to a porous medium and all flow losses are taken into account by a viscous and an inertial loss coefficient. A fan model is used for reaching the flow condition at the heat exchanger inlet with the actual performance curves of the fan. It is found that the improved ACSC with deflector shows a significant enhancement in both the cooling air mass flow rate and the heat rejection rate compared with the conventional ACSC. The higher the wind speed is, the larger the heat transfer enhancement of the improved ACSC is. The effect of the plate inclination is also investigated, and the inclination angle of 45° is found to be the optimum value for the arrangement of the deflector.     

Numerical and experimental study on aerodynamic performance of small axial flow fan with splitter blades

To improve the aerodynamic performance of small axial flow fan, in this paper the design of a small axial flow fan with splitter blades is studied. The RNG k-ε turbulence model and SIMPLE algorithm were applied to the steady simulation calculation of the flow field, and its result was used as the initial field of the large eddy simulation to calculate the unsteady pressure field. The FW-H noise model was adopted to predict aerodynamic noise in the six monitoring points. Fast Fourier transform algorithm was applied to process the pressure signal. Experiment of noise testing was done to further investigate the aerodynamic noise of fans. And then the results obtained from the numerical simulation and experiment were described and analyzed. The results show that the static characteristics of small axial fan with splitter blades are similar with the prototype fan, and the static characteristics are improved within a certain range of flux. The power spectral density at the six monitoring points of small axial flow fan with splitter blades have decreased to some extent. The experimental results show sound pressure level of new fan has reduced in most frequency bands by comparing with prototype fan. The research results will provide a proof for parameter optimization and noise prediction of small axial flow fans with high performance.     

Optimum tip gap and orientation of multi-piezofan for heat transfer enhancement of finned heat sink in microelectronic cooling

Piezoelectric fans can be manipulated to generate airflow for cooling microelectronic devices. Their outstanding features include noise-free operation, low power consumption and suitability for confined spaces. This paper presents experimental optimization of tip gap and orientation angle of three piezoelectric fans (multi-piezofan) to maximize the heat removal performance of finned heat sink for microelectronic cooling. Design of experiments (DOE) approach is used for the optimization, and a three dimensional simulation using FLUENT 6.3.2 is carried out to better understand the flow induced by the multi-piezofan and the resulting heat transfer from the heat sink surface. For the optimization, the Central Composite Design (CCD) of response surface methodology (RSM) is exploited from the Design Expert software. In the numerical model, the flow induced by the piezofan is treated as incompressible and turbulent; the turbulence is taken care by the shear stress transport (SST) k–ω model. The experimental results are found to be in good agreement with the predictions. Out of 13 experimental trials determined by CCD, the optimum tip gap and fan orientation are found to be δ = 0.17 and 90° respectively. At this condition, an enhancement in convective heat transfer coefficient exceeding 88% is achieved, compared to natural convection.