支持向量机回归算法在连铸漏钢预报中的应用研究  

Support Vector Machine Regression Algorithm in Continuous Casting Breakout Prediction

作　　者：田晴[1] 

机构地区：[1]河北联合大学电气工程学院,河北唐山063000

出　　处：《工业控制计算机》2015年第5期49-50,共2页Industrial Control Computer

基　　金：河北联合大学科学研究基金项目(Z201011)

摘　　要：支持向量机SVM在模式识别方面广泛应用,其表现出很好的预测能力。连铸结晶器的粘结漏钢预报系统具有非线性、复杂性的特点。根据粘结漏钢原理,采用最小二乘支持向量机LSSVM方法对结晶器温度样本进行识别研究,从而实现连铸过程的漏钢预报。仿真结果表明,LSSVM模型在小样本下同样能快速训练样本参数,识别能力很强,精度较高。SVM is widely used in the pattern recognition.lt shows prediction ability wel .For the bonding breakout prediction system of the continuous casting is nonlinear,complexity.According to the principle of sticking breakout,the least squares support vector machine LSSVM method has been adopt for identification of the crystal ize temperature sample,so as to realize the prediction of breakout in continuous casting process.The simulation results show that the LSSVM model cans quickly the training sample parameters in the smal sample.lt shows strong recognition ability,high precision.

关 键 词：最小二乘支持向量机 漏钢预报 温度识别 

分 类 号：TF341.6[冶金工程—冶金机械及自动化] TP18[自动化与计算机技术—控制理论与控制工程]