基于光圈模式识别的直拉晶体生长温度测量技术研究

针对直拉硅晶体生长引晶流程中生长界面温度无法自动测量和校准的问题,本文提出一种基于光圈图像特征与最小二乘支持向量机相结合的温度模式分类检测方法.以数字相机获取的籽晶熔接处的光圈图像作为输入数据,利用图像处理算法提取光圈特征,并以人工校准产生的分类数据和持续生长的后验数据为训练样本,对最小二乘支持向量机分类模型进行训练.实际生长测试证明,可通过多个分类器的组合使用,将生长界面温度在红外测温仪的基础上校准到满足自动引晶所需要的温度.     

基于云模型的电力系统负荷组合预测

电力系统负荷预测的精确度决定着电网安全稳定、高效的运行.最小二乘支持向量机(LSSVM)被广泛应用电力系统负荷预测上,然而该方法在处理不确定性问题上有很多不足之处.为了更精确的选择核函数的参数,处理不确定性因素,提高短期负荷预测的精度,提出了一种将云模型、粒子群优化(PSO)和LSSVM相结合的组合模型.首先通过对各影响因子的不确定性分析,按不确定性高低将各影响因子分别应用Cloud-LSSVM和PSO-LSSVM进行预测,然后通过组合模型的加权计算的得到最终预测值.最后,通过仿真对比证明该模型能更好的处理不确定性,从而提高电力系统短期负荷预测精度.     

基于粗糙集和ACO-LSSVM的Cr12MoV刀具磨损量预测

针对Cr12MoV刀具磨损量预测问题,提出了一种新的粗糙集和最小二乘支持向量机(LSSVM)相结合的预测方法。将声发射信号提取的能量值和切削要素作为预测模型的输入参数,为了降低运算的复杂性,提出采用粗糙集理论对多维输入参数进行降维处理的方法;为提高预测准确性和精度,利用蚁群算法对LSSVM的参数进行优化,建立基于粗糙集和ACO-LSSVM的Cr12MoV刀具磨损量预测模型。仿真结果表明,所建立的Cr12Mo V刀具磨损量预测模型合理有效,具有较强的推广能力和较高的预测精度。     

基于二阶振荡微粒群最小二乘支持向量机的物流需求预测

为了提高物流需求的预测精度,在分析物流需求影响因素基础上,建立了物流需求的二阶振荡微粒群最小二乘支持向量机预测模型。利用最小二乘支持向量机(LSSVM)描述物流需求与其影响因素间的复杂非线性关系,并通过二阶振荡微粒群(TOOPSO)算法优化选择LSSVM参数。实例分析表明,模型具有较高的预测精度,TOOPSO算法搜索LSSVM最优参数时间明显少于传统交叉验证法,是一种有效的物流需求预测方法。     

基于最小二乘支持向量机的煤矿瓦斯预测

瓦斯涌出量受多种自然因素和开发技术的影响,是一个非线性、高维的问题.提出了改进的PSO算法与LSSVM算法相结合对瓦斯涌出量进行预测的新方法.实验结果表明,该模型预测精度更高,泛化能力更强.     

基于经验模式分解和最小二乘支持向量机的胎儿心电信号提取

针对心电信号的非平稳特性,将非平稳信号处理方法与非线性估计方法相结合,提出一种从母体腹壁混合信号中提取胎儿心电信号的新方法。采用经验模式分解(EMD)方法将非平稳的母体心电信号分解为有限个本征模函数(IMF)和一个残差信号;母体腹壁混合信号中的母体心电成分为母体心电信号的非线性变换,采用最小二乘支持向量机(LSSVM)拟合这一非线性变换;将EMD分解所得的本征模函数和残差信号经由所拟合的非线性变换得到母体腹壁混合信号中母体心电成分的最优估计,从母体腹壁混合信号中减去该最优估计得到胎儿心电信号。引入基于特征值分析和基于互相关系数计算信噪比的方法,评估胎儿心电信号提取方法的性能。实验结果表明,在胎儿心电信号和母体心电信号QRS波分离或者重叠的情况下,通过本文提出的方法均可得到清晰的胎儿心电信号,且信噪比相对于传统方法有明显提高。实验结果验证了该方法的有效性。     

Mid-term electricity market clearing price forecasting: A hybrid LSSVM and ARMAX approach

A hybrid mid-term electricity market clearing price (MCP) forecasting model combining both least squares support vector machine (LSSVM) and auto-regressive moving average with external input (ARMAX) modules is presented in this paper. Mid-term electricity MCP forecasting has become essential for resources reallocation, maintenance scheduling, bilateral contracting, budgeting and planning purposes. Currently, there are many techniques available for short-term electricity market clearing price (MCP) forecasting, but very little has been done in the area of mid-term electricity MCP forecasting. PJM interconnection data have been utilized to illustrate the proposed model with numerical examples. The proposed hybrid model showed improved forecasting accuracy compared to a forecasting model using a single LSSVM.     

The application of direct orthogonal signal correction for linear and non-linear multivariate calibration

Traditionally, the direct orthogonal signal correction (DOSC) is always used together with a latent variable method such as partial least square (PLS) or principal component regression (PCR), to build a linear calibration model. In this study, PLS and least square support vector machine (LSSVM) were used to develop the linear and non-linear relation between spectra and components, respectively. DOSC was used to preprocess the input data, and the effect of DOSC pretreatment on linear and non-linear calibration model was investigated. The experiment was performed with three data sets. The first one was the acousto-optic tunable filter near infrared (AOTF-NIR) spectra of apples, the second one was the temperature-induced spectra of a ternary mixture of ethanol, water and 2-propanol, and the third one was the NIR spectra of corn. For all of the applications, the relation between spectra and components can be clearly observed in the spectra plot or the score plot after DOSC pretreatment. DOSC improved the predictive ability of PLS model. However, DOSC removed useful non-linear information that was related to components, thus, was not able to improve the performance of LSSVM model. DOSC pretreatment seems to be not suitable for non-linear calibration.     

改进果蝇优化LSSVM超声波萃取产物浓度软测量

针对超声波天然产物萃取过程中产物浓度难以在线检测的问题,提出了一种改进果蝇优化最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)的超声波萃取产物浓度软测量建模方法。首先将混沌优化与迭代步长动态调节方法相融合,提出了一种混沌动态步长改进果蝇优化算法(Chaos Dynamic Step Fluit Fly Optimization Algorithm,CDSFOA),该算法引入动态调节因子对步长动态更新,并利用混沌优化实现各变量之间映射等操作,能够有效提高果蝇优化算法的收敛精度和收敛速度,然后利用CDSFOA对LSSVM进行参数寻优,构建最优CDSFOA-LSSVM软测量模型,最后利用超声波斛皮素萃取实验数据进行验证。结果表明,提出的模型不仅有较好的学习和泛化能力,而且具有良好的预测精度,可为超声波天然产物萃取工艺优化提供理论指导。     

基于最小二乘支持向量机的时用水量预测模型

针对神经网络存在结构较难确定,训练易陷入局部最优以及容易过学习等问题,提出将最小二乘支持向量机用于预测时用水量.最小二乘支持向量机(LSSVM)基于结构风险最小化,能够较好地协调经验风险最小化和学习机器VC维之间的关系,并且LSSVM在支持向量机(SVM)的基础上,通过将价值函数改为最小二乘价值函数以及用等式约束代替不等式约束,将求解的二次规划问题转变为一组等式方程,采用径向基核函数,得到LSSVM模型的待定参数比标准支持向量机少,仅为2个.根据时用水序列具有周期性和趋势性的特点,建立了基于最小二乘支持向量机的时用水量模型.实例分析表明,与基于BP网络的时用水量模型相比,基于最小二乘支持向量机的时用水量模型具有更强的预测能力.