Modeling of Ball Mill Pulverizing System and Research of Support Vector Machine Generalized Inverse with Internal Model Control

2013 ◽  
Vol 12 (24) ◽  
pp. 8405-8411
Author(s):  
Sun Ling-Fang ◽  
L.I. Dan . ◽  
Sun Jing-Miao .
Keyword(s):  
Support Vector Machine ◽  
Ball Mill ◽  
Internal Model ◽  
Generalized Inverse ◽  
Internal Model Control ◽  
Support Vector ◽  
Model Control

scholarly journals New Smith Internal Model Control of Two-Motor Drive System Based on Neural Network Generalized Inverse

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Guohai Liu ◽  
Jun Yuan ◽  
Wenxiang Zhao ◽  
Yaojie Mi
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Internal Model ◽  
Generalized Inverse ◽  
Control Structure ◽  
Control Method ◽  
Internal Model Control ◽  
Drive System ◽  
Motor Drive ◽  
Model Control

Multimotor drive system is widely applied in industrial control system. Considering the characteristics of multi-input multioutput, nonlinear, strong-coupling, and time-varying delay in two-motor drive systems, this paper proposes a new Smith internal model (SIM) control method, which is based on neural network generalized inverse (NNGI). This control strategy adopts the NNGI system to settle the decoupling issue and utilizes the SIM control structure to solve the delay problem. The NNGI method can decouple the original system into several composite pseudolinear subsystems and also complete the pole-zero allocation of subsystems. Furthermore, based on the precise model of pseudolinear system, the proposed SIM control structure is used to compensate the network delay and enhance the interference resisting the ability of the whole system. Both simulation and experimental results are given, verifying that the proposed control strategy can effectively solve the decoupling problem and exhibits the strong robustness to load impact disturbance at various operations.

scholarly journals An Internal Model Controller for Three-Phase APF Based on LS-Extreme Learning Machine

2014 ◽  
Vol 8 (1) ◽  
pp. 717-722
Author(s):  
Zhenhua Shao ◽  
Tianxiang Chen ◽  
Li-an Chen ◽  
Hong Tian
Keyword(s):  
Control System ◽  
Least Squares ◽  
Extreme Learning Machine ◽  
Internal Model ◽  
Internal Model Control ◽  
Support Vector ◽  
Three Phase ◽  
Model Control ◽  
Internal Model Controller ◽  
Learning Machine

Aiming at the problem that the three-phase APF’s dynamic model is a multi-variable, nonlinear and strong coupling system, an internal model controller for three-phase APF based on LS-Extreme Learning Machine is studied in this paper. As a novel single hidden layer feed-forward neural networks, extreme learning machine (ELM) has several advantages: simple net structural, fast learning speed, good generalization performance and so on. In order to improve the controller’s dynamic responses, a least squares extreme learning machine for internal model control is proposed. A least squares ELM regression (LS-ELMR) model for the three-phase APFS on-line monitoring was built from external factors with in-out datum. Moreover, the relative stable error is presented to evaluate the system performance and the features for the internal model control system based on extreme learning machine, neural network, kernel ridge regress and support vector machine. The experimental results show that the LS-internal model control system based on extreme learning machine has good dynamic performance and strong filtering result.

Decoupling control of bearingless permanent magnet synchronous motors with LSSVM inverse system method and internal model controller

2020 ◽  
pp. 1-20
Author(s):  
Ke Li ◽  
Feng Ling ◽  
Xiaodong Sun ◽  
Zebin Yang
Keyword(s):  
Control System ◽  
Permanent Magnet ◽  
Internal Model ◽  
Internal Model Control ◽  
Decoupling Control ◽  
Support Vector ◽  
Inverse Models ◽  
Control Scheme ◽  
Model Control ◽  
Internal Model Controller

In this paper, a novel decoupling control scheme combining least squares support vector machines (LSSVM) inverse models and 2-degree-of-freedom (DOF) internal model controllers is employed in the decoupling control system of the bearingless permanent magnet synchronous motor (BPMSM). This scheme can be used to enhance the control properties of high-precision, fast-response, and strong-robustness for the BPMSM system, and effectively eliminate the nonlinear and coupling influence. It introduces LSSVM inverse models into the original BPMSM system to constitute a decoupled pseudo-linear system. In addition, the particle swarm optimization algorithm (PSO) is used to optimize parameters of the LSSVM, which improves its fitting ability and prediction accuracy. What is more, the internal model control scheme is used to design additional closed-loop controllers, thereby improving the robustness of the entire control system. Therefore, this scheme successfully combines the advantages of the LSSVM inverse models and the internal model controller. It can enhance the stability and the static as well as dynamic properties of the whole BPMSM system while independently adjusting the tracking and interference rejection performances. The effectiveness of the proposed scheme has been verified by simulation results at various operations.

Sign in / Sign up

Export Citation Format

Share Document