节点文献
基于LS-SVM的淬火炉Hammerstein故障预测模型应用研究
Vertical Quench Furnace Hammerstein Fault Predicting Model Based on Least Squares Support Vector Machine and Its Application
【Author】 JIANG Shao-hua~(1,2),GUI Wei-hua~1,YANG Chun-hua~1 1.School of Information Science and Engineering,Central South University,410083,Changsha,China 2.School of Computer Science,Shaoguan University,512024,Shaoguan,China
【机构】 中南大学信息科学与工程学院； 韶关学院计算机科学学院；
【摘要】 针对大型立式淬火炉体积庞大,工况复杂,炉内温度分布呈本征非均匀性,具有多输入/多输出、非线性、强耦合等特性,建立了淬火炉的Hammerstein故障预测模型。首先采用最小二乘支持向量机回归方法构造淬火炉Hammerstein模型非线性函数部分,再运用奇异值分解的方法辨识Hammerstein模型参数。最后利用淬火炉的故障预测模型对温度进行预测,试验结果表明,该模型预测输出与实际输出相比较所形成的残差,能够准确预测故障,具有较好的应用价值。
【Abstract】 Since large-scale vertical quench furnace is voluminous,whose working condition is a typically complex process with distributed parameter,nonlinear,multi-inputs/multi-outputs,close coupled variables,etc,Hammerstein model of the furnace is presented.Firstly,the nonlinear function of Hammerstein model is constructed by least squares support vector machines regression.A numerical algorithm for subspace system(singular value decomposition,SVD) is utilized to identify the Hammerstein model.Finally,the model is used to predict the furnace temperature.The simulation research shows this model provides accurate prediction and is with desirable application value.
【Key words】 Hammerstein Model； Least Squares Support Vector Machine(LS-SVM)； System Identification； Fault Diagnosis； Large-scale Vertical Quench Furnace；
- 【会议录名称】 2009中国控制与决策会议论文集（1）
- 【会议名称】2009中国控制与决策会议
- 【会议时间】2009-06-17
- 【会议地点】中国广西桂林
- 【分类号】TG155.3
- 【主办单位】Northeastern University,China、IEEE Industrial Electronics (IE) Chapter,Singapore、Guilin University of Electronic Technology,China