基于彩色图像处理的浮选尾煤灰分软测量研究

浮选尾煤灰分是浮选产品的一个重要指标。针对选煤厂浮选尾煤灰分多采用离线检测而无法实现在线准确测量，以及当前浮选软测量多采用单一的灰度图像从而导致软测量模型精度及适应性较差的问题，提出了一种基于彩色图像处理的浮选尾煤软测量方法，建立了基于最小二乘支持向量机(LSSVM)的浮选尾煤灰分软测量模型。模型以不同颜色空间的彩色特征、灰度均值以及浓度特征为输入变量，以尾煤灰分作为输出变量，采用粒子群优化算法对LSSVM模型参数进行优化。结果表明：所建立的尾煤灰分软测量模型可以较好地实现浮选尾矿灰分的在线预测，引入浮选尾矿图像的彩色特征可以提高尾煤图像分析的精度，预测精度达96.89%。研究成果在柳湾选煤厂现场应用，并取得了较好的尾矿灰分测量效果。     

基于LSSVM的真空玻璃传热过程建模

真空玻璃传热过程隔热性能和质量评价关键指标-传热系数(U值)受真空度影响,难以精确检测。为实现真空玻璃隔热性能和质量的快速评定,建立了基于LSSVM的真空玻璃传热过程智能模型,应用MATLAB软件和实验数据,对真空玻璃传热过程进行了模拟,在线预测了真空玻璃传热后侧(非热源侧)的中心温度。结果表明:模型理论正确,预测迅速(时间1 s),误差小(相对误差1.2%),为真空玻璃隔热性能和真空玻璃质量的快速评定提供了一种新的技术手段。同时,也为后续研究能将温度参数预测转化为传热系数预测奠定一定的理论和应用基础。     

On the prediction of solubility of alkane in carbon dioxide using the LSSVM algorithm

The increasing global energy demand and declination of oil reservoir in recent years cause the researchers attention focus on the enhancement of oil recovery approaches. One of the extensive applicable methods for enhancement of oil recovery, which has great efficiency and environmental benefits, is carbon dioxide injection. The CO₂ injection has various effects on the reservoir fluid, which causes enhancement of recovery. One of these effects is extraction of lighter components of crude oil, which straightly depends on solubility of hydrocarbons in carbon dioxide. In order to better understand of this parameter, in this study, Least squares support vector machine (LSSVM) algorithm was developed as a novel predictive tool to estimate solubility of alkane in CO₂ as function of carbon number of alkane, carbon dioxide density, pressure, and temperature. The predicting model outputs were compared with the extracted experimental solubility from literature statistically and graphically. The comparison showed the great ability and high accuracy of developed model in prediction of solubility.     

Modeling dynamic viscosity of n-alkanes using LSSVM technique

One of the important thermophysical properties is viscosity which expresses the resistance of fluid to flow. The least squares support vector machine (LSSVM) algorithm is proposed as a novel method for prediction of dynamic viscosity of different normal alkanes in a wide range of pressure and temperature. As this study is purely computational, 228 experimental data points were gathered from literature for training and validation of the model. The outcomes of the LSSVM algorithm were compared with the actual data with acceptable average absolute relative deviation and the coefficient of determination (R²) of 1.014 and 0.9968, respectively. The comparisons showed that the predicting model has the potential of prediction of n-alkane dynamic viscosity in terms of pressure, temperature, and carbon number of n-alkane, so this strategy can be used as a simple tool for predicting the behavior of reservoir fluids.     

基于LASSO-WOA-LSSVM的海洋管线外腐蚀速率预测

目的 构建海洋管线外腐蚀速率预测模型,提高海底油气管线外腐蚀速率预测的准确性.方法 建立基于套索(LASSO)回归和鲸鱼优化算法(WOA)的最小二乘支持向量机(LSSVM)腐蚀速率预测模型,采用LASSO回归方法对指标进行筛选,提取海洋管线腐蚀的主要影响因素.应用最小二乘支持向量机算法建立海洋管线外腐蚀速率预测模型,并使用鲸鱼优化算法对模型参数进行优化,避免了参数取值对模型回归性能的影响.以海洋挂片实验为例,通过MATLAB进行模拟仿真,分析验证模型预测结果,并将预测结果与其他模型进行对比分析.结果 LASSO回归算法筛选得到影响腐蚀速率的主要因素为:温度、溶解氧含量、pH值.采用WOA-LSSVM模型所预测的结果与实际值较为吻合,其平均相对误差为2.23％,均方根误差(RMSE)为0.3248,决定系数R2达到0.9708,均优于其他两种模型.结论 基于LASSO回归和鲸鱼优化算法的最小二乘支持向量机预测模型具有更优的泛化能力和预测精度,为海底管道腐蚀研究工作提供了新思路,也为海洋油气输送系统的结构安全与风险防范提供了参考.     

基于IHSA_LSSVM的供应链绩效评估研究

为有效评估供应链绩效,结合和声搜索算法(IHSA)与最小二乘支持向量机,提出一种评估算法(IHS_LSSVM)。研究和声搜索算法的原理,对基音调整概率和基音调整步长进行动态调整,给出一种改进的和声搜索算法。利用该算法的全局搜索能力优化选取LSSVM的惩罚因子r和高斯核函数的半径σ。采用供应链绩效评估实例,构建供应链评估模型。仿真实验结果表明,与已有的BP神经网络和LSSVM等评估算法相比,IHS_LSSVM具有更小的预测误差和更高的预测精度。     

一种基于KPCA-LSSVM的可用带宽在线预测算法

针对目前端到端可用带宽预测方面研究工作较少的现状,提出一种基于核主成分分析KPCA(Kernel Principle Component Analysis)和最小二乘支持向量机LSSVM(Least Squares Support Vector Machine)的可用带宽在线预测算法ABOP。在采集网络状态样本数据并对其进行相空间重构的基础上,采用KPCA对数据进行降维降噪处理,最后基于LSSVM对可用带宽进行在线预测。为减小计算开销,提出一种递推计算的方法加快模型更新速度,并采用粒子群优化算法对模型参数进行多步更新,确保了在线预测的时效性。仿真表明,提出的ABOP算法具有较高的预测精度和较快的预测速度,能够满足可用带宽在线预测的要求。     

高速列车转向架故障信号的聚合经验模态分解和 模糊熵特征分析

为了对高速列车转向架关键部件进行状态监测,利用转向架故障振动信号的特点,提出了一种结合聚合经验模态分解和模糊熵的特征提取方法.对故障信号进行聚合经验模态分解,得到一系列具有不同物理意义的简单成分信号,采用相关分析法选取最能反映原信号特征的本征模态函数.对这些本征模态函数和原信号分别计算模糊熵值构成多尺度复杂性度量的特征向量,输入最小二乘支持向量机中进行分类识别,与模糊熵特征相比得到了更好的识别效果,证明了算法的有效性.     

基于最小二乘支持向量机的多属性决策*

分析多属性决策问题, 提出了基于最小二乘支持向量机的多属性决策方法。该方法从决策问题本身出发,构造学习样本,再通过最小二乘支持向量机拟合出多属性效用函数,从而实现对方案的排序。该模型与支持向量机相比,参数少,算法简单、可靠。最后通过算例表明方法的可行性与有效性。     

Prediction method for surface finishing of spiral bevel gear tooth based on least square support vector machine

The predictive model of surface roughness of the spiral bevel gear (SBG) tooth based on the least square support vector machine (LSSVM) was proposed.A nonlinear LSSVM model with radial basis function (RBF) kernel was presented and then the experimental setup of PECF system was established.The Taguchi method was introduced to assess the effect of finishing parameters on the gear tooth surface roughness,and the training data was also obtained through experiments.The comparison between the predicted values and...