基于LS-SVM的管道腐蚀速率灰色组合预测模型

为提高管道腐蚀速率预测精度,建立了一种基于最小二乘支持向量机的灰色组合预测模型.以各种灰色模型对管道腐蚀速率的预测结果作为支持向量机的输入,以管道腐蚀速率的实测值作为支持向量机的输出,采用最小二乘支持向量机回归算法和高斯核函数对支持向量机进行训练,利用训练好的支持向量机进行组合预测.预测模型兼具灰色模型所需原始数据少、建模简单、运算方便的优势和最小二乘支持向量机具有泛化能力强、非线性拟合性好、小样本等特性,弥补了单一预测模型的不足,避免了神经网络组合预测易于陷入局部最优的弱点.模型结构简单、实用,仿真结果验证了其有效性.

Grey Combination Forecast Model for Corrosion Rate of Pipelines Based on the Least Squares Support Vector Machine

To increase the forecast precision of pipeline' corrosion rate,a grey combination forecast model based on least squares support vector machine(LS-SVM) is presented in the paper.The input of LS-SVM is the forecasting value of various grey model and the output of LS-SVM is actual value.SVM trained with LS-SVM regression algorithm and Gauss kernel function has the ability to do the combination forecast.The model has combined the advantages of grey model(less raw data required,simple to model,convenient to calculate)and the features of LS-SVM(strong generalization ability,good nonlinear fitting ability and less samples to be required).Meanwhile it remedies the defects in a single model and avoids the weakness in neural networks combination forecast.The model construction is simple and practical,and the validity of the method is proved with simulation results.