基于支持向量机的缓存预估模型的设计与实现

采用支持向量机(SVM)对网络业务流数据进行预测估计，通过训练样本，从而获得样本以外数据的分布规律。在此基础上，设计了一种网络排队队列缓存的预估模型。实验表明，该模型具有较高的训练效率和很高的估计精确度。     

Frequency support capability of variable speed wind turbine based on electromagnetic coupler

In the variable speed wind turbine based on electromagnetic coupler (WT-EMC), a synchronous generator is directly coupled with grid. So like conventional power plants WT-EMC is able to support grid frequency inherently. But due to the reduced inertia of synchronous generator, its frequency support capability has to be enhanced. In this paper, the frequency support capability of WT-EMC is studied at three typical wind conditions and with two control strategies—droop control and inertial control to enhance its frequency support capability. The synchronous generator speed, more stable than the grid frequency which is the input signal for Type 3 and Type 4 wind turbine frequency support controller, is used for the calculation of WT-EMC supplementary torque command. The integrated simulation environment based on the aeroelastic code HAWC2 and software Matlab/Simulink is used to build a 2 MW WT-EMC model and study the frequency support capability of a wind farm consisting of WT-EMC.     

An Extraction of the Dominant Rotor-Stator Interaction Modes by the Use of Proper Orthogonal Decomposition （POD）

The Proper Orthogonal Decomposition method is applied to the instantaneous velocity field within the rotor-stator inter-row region of a high-speed high-pressure centrifugal compressor. The processed data come from experiments and numerical simulations. In comparison with a Fourier transform, the POD gives the best modal approximation for both initial fields, in terms of the energy expressed on any given number of modes to be taken into account: to reach 98% of the total energy of the velocity field, the required number of POD modes is around nine times smaller than the number of Fourier harmonics. The individual POD modes are given and show that the unsteady rotor-stator interaction is already present in the very first modes.     

支持向量机回归模型在径流预测中的应用

为了探索提高径流中长期预测精度的有效途径,尝试建立了基于支持向量机的径流预测模型,并应用于西江流域梧州站的年、月径流预测中,取得了很好的效果。并与神经网络预测进行对比,结果表明该模型的预测精度要高于人工神经网络模型。     

600MW汽轮发电机定子线圈水接头中频焊接的自动控制

本文对目前国内外汽轮发电机定子线圈水接头的钎焊工艺与设备现状进行了分析。同时介绍了新近研制成功的一套600MW汽轮发电机定子线圈水接头自动控温焊接设备.通过本文的介绍.可以对国内外中频焊接设备的温度自动控制方法有所了解。     

支持向量机模型在渗流监测中的应用

提出了基于一种支持向量机(SVM)的渗流监测方法。该方法采用结构风险最小化原则，能够在对小样本学习的基础上，对其他样本进行快速、准确的拟合预测，具有更好的泛化性能和精度，减少了对经验的依赖。在算例中，基于SVM的非线性特点，根据土石坝的实测资料建立了渗流监测模型，为水头预报和安全监测奠定了基础。     

Unsteady rotor-stator interaction in high speed compressor and turbine stages

The blade row interaction can alter the time-mean flow and therefore be of interest for aerodynamic design analysis. Whereas results within low subsonic turbomachines are quite numerous in the literature, there have been far fewer works which give results of blade row interaction within high speed cases. Two cases are related in this paper. First, the effects of an incoming wake on the rotor flow field of a transonic compressor are analyzed. The blade row interaction proved to be positive regarding the total pressure ratio, but negative regarding the losses. The second case concerns a transonic turbine. Particular emphasis is placed on the assessment of the deterministic correlations included in the Averaged Passage Equation System.     

525t/h CFB锅炉旋风分离器制造工艺简介

大型循环流化床锅炉中的管式旋风分离器的制造所涉及的工艺复杂,装配难度高。以525t/hCFB旋风分离器的制造工艺为例,描述了分片出厂的大型旋风分离器在厂内分片制造、试拼装的工艺方案,分析了制造中重要的工艺难点,诸如大弯曲半径的圆弧形、锥体形管排的成形及组装等,并提出相应的工艺解决方案,重点在于保证旋风分离器的对口装配上。为今后同类大型CFB锅炉的制造,确保产品质量、简化工艺装备设计、加快制造进度提供了工艺措施,积累了经验。     

基于遗传优化SVM的通信信号的分类

为了充分利用遗传算法的全局寻优能力和SVM（支持向量机）的分类能力,文章设计了遗传优化SVM的分类算法。用遗传算法优化SVM中核函数的两个参数,再利用优化后的SVM进行分类。通过对方波和白噪声两种信号的分类仿真,证明了其优越性,同时也展现了遗传优化SVM在通信领域很好的应用前景。     

图像分割的新理论和新方法

图像分割是是计算机视觉研究中的一个经典难题,已成为图像理解领域关注的一个热点.本文对近年来图像分割方法的研究现状与新进展进行了归纳总结.首先,简单介绍了图像分割的传统方法,包括基于区域的、基于边缘的和两者结合的图像分割方法.然后,分别从数学形态学、模糊集、神经网络、支持向量机、免疫算法、图论和粒度计算等方面对图像分割方法进行了重点讨论,并对应用每一种理论的最新研究进展作了评述.最后,对图像分割方法的发展趋势进行了展望.