The Study of Bearing Vibration of Large-Scale Centrifugal Ventilator Forecast Based-On Support Vector Autoregressive

In order to forecast the bearing vibration of large-scale centrifugal ventilator, increase its operating safety and economy, the kernel algorithm of Statistical Learning Theory (SLT), Support Vector Machine (SVM) is applied to set up a forecast model of large-scale centrifugal ventilator bearing vibration. The model based on SVAR is compared with the model based-on Autoregressive by a case. The result indicates that the forecast model of bearing vibration based-on SVAR has many advantage, such as high-precision, high calculation velocity, modeling easily. The model based on SVAR can forecast the vibration condition of bearing, and avoid the fault due to the vibration.