This paper presents a modeling method for a non-uniformly sampled system bused on support vector regression （ SVR ）. First, a lifted discrete-time state-space model for a non-uniformly sampled system is derived by u...This paper presents a modeling method for a non-uniformly sampled system bused on support vector regression （ SVR ）. First, a lifted discrete-time state-space model for a non-uniformly sampled system is derived by using the lifting technique to reduce the modeling difficulty caused by multirate sampling. Then, the system is divided into several parallel subsystems and their input-output model is presented to satisfy the SVR model. Finally, an on-line SVR technique is utilized to establish the models of all subsystems to deal with uncertainty. Furthermore, the presented method is applied in a multichannel electrohydraulic force servo synchronous loading system to predict the system outputs over the control sample interval and the prediction mean absolute percentage error reaches 0. 092%. The results demonstrate that the presented method has a high modeling precision and the subsystems have the same level of prediction error.展开更多
文摘This paper presents a modeling method for a non-uniformly sampled system bused on support vector regression （ SVR ）. First, a lifted discrete-time state-space model for a non-uniformly sampled system is derived by using the lifting technique to reduce the modeling difficulty caused by multirate sampling. Then, the system is divided into several parallel subsystems and their input-output model is presented to satisfy the SVR model. Finally, an on-line SVR technique is utilized to establish the models of all subsystems to deal with uncertainty. Furthermore, the presented method is applied in a multichannel electrohydraulic force servo synchronous loading system to predict the system outputs over the control sample interval and the prediction mean absolute percentage error reaches 0. 092%. The results demonstrate that the presented method has a high modeling precision and the subsystems have the same level of prediction error.
