论文部分内容阅读
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.
In order to improve the prediction accuracy of pipeline corrosion rate, a gray combination forecasting model based on least square support vector machine was established.With the gray model prediction of pipeline corrosion rate as input of support vector machine, measured by pipeline corrosion rate Value as the output of support vector machine, the least square support vector machine regression algorithm and Gaussian kernel function are used to train support vector machine, and the combined forecast is made by using the trained support vector machine.The forecasting model has less original data required by gray model , The advantages of simple modeling and convenient operation and least square support vector machine have the advantages of generalization ability, good non-linear fitting and small sample, which make up for the deficiencies of the single prediction model and avoid the neural network combination prediction easy to fall into Local optimum weakness.The model structure is simple and practical, the simulation results verify its effectiveness.