A precise BP neural network-based online model predictive control strategy for die forging hydraulic press machine

2016 ◽  
Vol 29 (9) ◽  
pp. 585-596 ◽  
Author(s):  
Y. C. Lin ◽  
Dong-Dong Chen ◽  
Ming-Song Chen ◽  
Xiao-Min Chen ◽  
Jia Li
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Control Strategy ◽  
Bp Neural Network ◽  
Hydraulic Press ◽  
Die Forging

Application of Model Predictive Control Based on BPNN to Heating Boiler

2011 ◽  
Vol 383-390 ◽  
pp. 2242-2248
Author(s):  
Yan Ping Wang
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Bp Neural Network ◽  
Control Algorithm ◽  
Closed Loop ◽  
Control Method ◽  
Feedback Information ◽  
Heating Boiler ◽  
Controlled Object

This paper presents the algorithm of model predictive control (MPC) based on BP neural network to the burden system of the heating boiler. Because the burden system of the heating boiler is complex, the proposed approach uses steady, effective way to control the boiler. There is a closed-loop, repeating online optimization, model-based control algorithm which deals with the feedback information and the quantity of the fuel entering the boiler by the way of multi-step future predicting and compensating based on BP neural network. By simulation, it is demonstrated that the burden system of the heating boiler using MPC as control method is better in performance than the traditional PID. Besides, it is compliant to the model of the controlled object, especially to those which parameters of the model are variable.

scholarly journals Model Predictive Control of Nonlinear System Based on GA-RBP Neural Network and Improved Gradient Descent Method

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Youming Wang ◽  
Didi Qing
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Bp Neural Network ◽  
Gradient Descent ◽  
Tracking Error ◽  
Hessian Matrix ◽  
Descent Method ◽  
Local Optimum ◽  
Gradient Descent Method

A model predictive control (MPC) method based on recursive backpropagation (RBP) neural network and genetic algorithm (GA) is proposed for a class of nonlinear systems with time delays and uncertainties. In the offline modeling stage, a multistep-ahead predictor with GA-RBP neural network is designed, where GA-BP neural network is used as a one-step prediction model and GA is employed to train the initial weights and bias of the BP neural network. The incorporation of GA into RBP can reduce the possibility of the BP neural network falling into a local optimum instead of reaching global optimization. In the online optimizing stage, a multistep-ahead GA-RBP neural network predictor and an improved gradient descent method (IGDM) are proposed to efficiently solve the online optimization problem of nonlinear MPC by minimizing a modified quadratic criterion. The designed MPC strategy can avoid information loss while linearizing the controlled system and computing the Hessian matrix and its inverse matrix. Experimental results show that the proposed approach can reduce the computational burden and improve the performance of MPC (i.e., the maximum overshoots, calculation time, rise time, and RMSE tracking error value) for the solution of nonlinear controlled systems.

Sign in / Sign up

Export Citation Format

Share Document