scholarly journals Quasilinear Extreme Learning Machine Model Based Internal Model Control for Nonlinear Process

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Dazi Li ◽  
Qianwen Xie ◽  
Qibing Jin
Keyword(s):  
Extreme Learning Machine ◽  
Internal Model ◽  
Linear Part ◽  
Nonlinear Coefficient ◽  
Internal Model Control ◽  
Least Square ◽  
Machine Model ◽  
Nonlinear Part ◽  
Model Control ◽  
Learning Machine

A new strategy for internal model control (IMC) is proposed using a regression algorithm of quasilinear model with extreme learning machine (QL-ELM). Aimed at the chemical process with nonlinearity, the learning process of the internal model and inverse model is derived. The proposed QL-ELM is constructed as a linear ARX model with a complicated nonlinear coefficient. It shows some good approximation ability and fast convergence. The complicated coefficients are separated into two parts. The linear part is determined by recursive least square (RLS), while the nonlinear part is identified through extreme learning machine. The parameters of linear part and the output weights of ELM are estimated iteratively. The proposed internal model control is applied to CSTR process. The effectiveness and accuracy of the proposed method are extensively verified through numerical results.

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.

A novel IMC-FOF design for four wheel steering systems of distributed drive electric vehicles

2021 ◽  
pp. 095440702110314
Author(s):  
Yan Ti ◽  
Kangcheng Zheng ◽  
Wanzhong Zhao ◽  
Tinglun Song
Keyword(s):  
Fractional Order ◽  
Electric Vehicles ◽  
Internal Model ◽  
Rear Wheel ◽  
Internal Model Control ◽  
Steering Angle ◽  
Comparison Results ◽  
Model Control ◽  
Tracking Ability ◽  
Internal Model Controller

To improve handling and stability for distributed drive electric vehicles (DDEV), the study on four wheel steering (4WS) systems can improve the vehicle driving performance through enhancing the tracking capability to desired vehicle state. Most previous controllers are either a large amount of calculation, or requires a lot of experimental data, these are relatively time-consuming and laborious. According to the front and rear wheel steering angle of DDEV can be distributed independently, a novel controller named internal model controller with fractional-order filter (IMC-FOF) for 4WS systems is proposed and studied in this paper. The IMC-FOF is designed using the internal model control theory and compared with IMC and PID controller. The influence of time constant and fractional-order parameters which is optimized using quantum genetic algorithms (QGA) on tracking ability of vehicle state are also analyzed. Using a production vehicle as an example, the simulation is performed combining Matlab/Simulink and CarSim. The comparison results indicated that the proposed controller presents performance to distribute the front and rear wheel steering angle for ensuring better tracking capability to desired vehicle state, meanwhile it possesses strong robustness.

Sign in / Sign up

Export Citation Format

Share Document