Inverse system identification of nonlinear systems using least square support vector machine based on FCM clustering

The algorithm of least square support vector machine (LSSVM) based on fuzzy c-means (FCM) clustering is presented in this paper, which can select the number of clusters automatically depending on different parameters and samples. We adopt the method to identify the inverse system with crucial spanless process variables and the inenarrable nonlinear character. In the course of identification, we construct the allied inverse system by the left inverse soft-sensing function and the right inverse system, then utilize the proposed method to approach the nonlinear allied inverse system via offline training. Simulation experiments are performed and indicate that the proposed method is effective and provides satisfactory performance with excellent accuracy and low computational cost comparing with the conventional method using LSSVM.