基于支持向量自回归的水泵振动预测模型研究  

Water Pump Vibration Forecast Based-on Support Vector Autoregressive

作　　者：吴兴伟[1,2] 王雷[2] 迟道才[1] 

机构地区：[1]沈阳农业大学水利学院,沈阳110161 [2]沈阳工程学院动力工程系,沈阳110136

出　　处：《沈阳农业大学学报》2008年第6期708-712,共5页Journal of Shenyang Agricultural University

基　　金：水利部“948”科技创新项目(CT200516);辽宁省教育厅科技公关项目(05L385)

摘　　要：为了预测水泵在运行中的振动状态,提高水泵运行的安全性和经济性,采用了统计学习理论中的核心算法——支持向量机与自回归方法相结合,建立了水泵振动预测模型(SVAR)。并通过实例,与基于灰色理论建立的预测模型(GM)和基于自回归方法建立的预测模型(AR)进行了比较。结果表明:基于支持向量自回归的水泵振动预测模型(SVAR)具有精度高、速度快、易于建模的特点。应用该方法建立的预测模型能够很好地预测水泵运行中的振动情况,有效地避免水泵运行中由振动引起的故障。In order to forecast the water pump operating vibration, increase the operating safety and efficiency of water pump, the kernel algorithm of statistical learning theory （SLT）, support vector machine （SVM）, was applied to set up a forecast model of water pump vibration. The model based on SVAR was compared with the model based-on Gray Model and the model based-on Autoregressive by a case. The result indicated that the forecast model of water pump vibration based-on SVAR had many advantages, such as highprecision, high calculation velocity and easy application. The model based on SVAR can forecast the vibration condition of operating water pump, and avoid the fault due to the vibration.

关 键 词：支持向量机 统计学习理论 水泵 振动预测 

分 类 号：TK262[动力工程及工程热物理—动力机械及工程]