Zuxin Li

Bio: Zuxin Li is an academic researcher. The author has contributed to research in topics: Model predictive control & Scheduling (computing). The author has an hindex of 1, co-authored 2 publications receiving 10 citations.

On-line predictive control based on LS-SVM

Abstract: Aim at the robustness of predictive control and on-line modeling, an on-line predictive control based on least squares support vector machine (LS-SVM) is proposed. In order to carry out on-line learning, the training data threshold is set through discussing the theory of LS-SVM and the character of control system. Then the model of the on-line predictive control system is established, and the analytical solution of control variable is deduced integrating the method of model predictive control (MPC). The results of simulation indicate that the method has enough rapid speed to establish on-line model and strong robustness to external disturbance and parameters variation.

Predictive Feedback Scheduling for Resource-Constrained Networks with Flexible Workload

Abstract: Resource-constrained networks usually run in an unpredictable open environment due to the workload variations. In this paper, a predictive feedback scheduler based on least squares support vector machines (LSSVM) is proposed in order to guarantee the stability of the system. It periodically monitors the network resources, predicates the next period of available bandwidth, and adopts interpolated method to calculate the next sampling period from predicative value. Consequently, the system’s bandwidth is dynamically allocated by this feedback scheduling mechanism. Two different strategies, which are fixed bandwidth allocation and predictive feedback scheduling strategy based on LSSVM, are compared respectively. The results of simulation indicate that the proposed strategy can guarantee the stability of the system with flexible workload, and prove that the predictive feedback scheduling is an effective tradeoff method between quality of control and quality of service.

Application of Soft Sensor Based on LS-SVM on Estimation of Alumina Powder Flow

Abstract: Alumina powder flow in electrolytic aluminum plant for the production of alumina can not be precise measured on-line, the Least Squares Support Vector Machines ( ) was applied in the modeling of alumina powder flow estimation in the process of alumina conveying in this paper, and the soft sensor model based on was compared with the soft sensor model based on . The result of simulation research proves that the soft sensor model based on has a higher precision accuracy and better generalization ability. The soft sensor technique is effective in estimate accuracy of the alumina powder flow.

Predictive function control based on the LS-SVM for marine steam turbine system

Abstract: Due to the complication of marine steam turbine system, and the nonlinearity, uncertainty and complexity of the steam turbine model, the conventional speed regulation system can no longer meet our requirement. A predictive function control based on LS-SVM is developed, which has good robustness to disturbance and parameters variation. The results of simulation indicate that the method has strong robustness to external disturbance and parameters variation.

A nonlinear MIMO system identification based on improved Multi-Kernel Least Squares Support Vector Machines (Improved Multi-Kernel LS-SVM)

Abstract: In this paper, a new method for the identification of nonlinear Multiple Input-Multiple Output (MIMO) systems is proposed. An improved Multi-Kernel Least Squares Support Vector Machines (Improved Multi-Kernel LS-SVM) based on Constrained Particle Swarm Optimization (CPSO) is given. The basic LS-SVM idea is to map linear inseparable input data into a high dimensional linear separable feature space via a nonlinear mapping technique (kernel function) and to carry out linear classification or regression in feature space. The choice of kernel function and the corresponding parameters is an important task which is related to the system nonlinearity degrees. The suggested approach combines several kernels in order to take advantage of their performances. The CPSO technique is used to give solution for the determination of optimized kernel parameters and their evolved weights. Simulation results show that the CPSO can quickly obtain the optimal parameters and therefore satisfying the required precision.

SVM with Quadratic Polynomial Kernel Function Based Nonlinear Model One-step-ahead Predictive Control

Abstract: A support vector machine (SVM) with quadratic polynomial kernel function based nonlinear model one-step-ahead predictive controller is presented. The SVM based predictive model is established with black-box identification method. By solving a cubic equation in the feature space, an explicit predictive control law is obtained through the predictive control mechanism. The effect of controller is demonstrated on a recognized benchmark problem and on the control of continuous-stirred tank reactor (CSTR). Simulation results show that SVM with quadratic polynomial kernel function based predictive controller can be well applied to nonlinear systems, with good performance in following reference trajectory as well as in disturbance-rejection.