Abstract:

The random delay of networked control system is difficult to predict accurately. Firstly the kernel principal component analysis (KPCA) and the least squares support vector machine (LSSVM) algorithm are combined to predict the random time delay. The KPCA can reduce dimensionality of input random timedelay sequence, eliminate the noise and interference and reduce the amount of computation of the LSSVM algorithm. The timedelay is predicted by the LSSVM algorithm through the timedelay sequence after dimensionality reduction. The simulation results show that the prediction accuracy of the timedelay prediction based on the KPCA and LSSVM algorithm is higher than the other prediction methods.