Research on Adaptive Advance System of Hydraulic Support Based on Neural Network PID

2012 ◽  
Vol 457-458 ◽  
pp. 758-763
Author(s):  
Guang Xin Zhou ◽  
Wei Li ◽  
Li Ping Zhang
Keyword(s):  
Neural Network ◽  
Coal Mining ◽  
Waiting Time ◽  
Pid Controller ◽  
Hydraulic Support ◽  
Advance Method ◽  
Simulation Results ◽  
Mining Face ◽  
Neural Network Pid

Aiming at the problem that contact advance lags seriously and automatic advance with shearer is not in time in ASQ of hydraulic support on fully mechanized coal mining face, this paper proposed a solution of adaptive advance system based on Neural Network PID. This advance method can effectively reduce invalid waiting time in advance and the probability that friction between top beam and roof increases, and thus to improve advancing velocity and achieve continuity of coal mining automation. This paper finally used SIMULINK to carry out simulation. Results show that Neural Network PID controller has better performance than conventional PID controller.

Design of Memristive Neural Network PID Controller

2014 ◽  
Vol 36 (12) ◽  
pp. 2577-2586 ◽  
Author(s):  
Si-Wei XIA ◽  
Shu-Kai DUAN ◽  
Li-Dan WANG ◽  
Xiao-Fang HU
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Memristive Neural Network ◽  
Neural Network Pid

Research on Yaw Stability Control of Active Front Steering Based on BP Neural Network PID

2013 ◽  
Vol 765-767 ◽  
pp. 1903-1907
Author(s):  
Jie Wei ◽  
Guo Biao Shi ◽  
Yi Lin
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Steering System ◽  
Stability Control ◽  
Steering Angle ◽  
System A ◽  
Active Front Steering ◽  
Yaw Stability ◽  
Neural Network Pid

This paper proposes using BP neural network PID to improve the yaw stability of the vehicle with active front steering system. A dynamic model of vehicle with active front steering is built firstly, and then the BP neural network PID controller is designed in detail. The controller generates the suitable steering angle so that the vehicle follows the target value of the yaw rate. The simulation at different conditions is carried out based on the fore established model. The simulation results show the BP neural network PID controller can improve the vehicles yaw stability effectively.

scholarly journals Wavelet neural network PID controller for a UAS transporting a cable-suspended load

2017 ◽  
Vol 50 (1) ◽  
pp. 2335-2340 ◽  
Author(s):  
Ricardo A. Barrón-Gómez ◽  
Luis E. Ramos-Velasco ◽  
Eduardo S. Espinoza Quesada ◽  
Luis R. García Carrillo
Keyword(s):  
Neural Network ◽  
Pid Controller ◽  
Suspended Load ◽  
Wavelet Neural Network ◽  
Neural Network Pid

Application of BP Neural Network PID Controller in Landing Gear Based on MRF Damper

2015 ◽  
Vol 779 ◽  
pp. 226-232 ◽  
Author(s):  
Shi Xing Zhu ◽  
Yue Han ◽  
Bo Wang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Pid Controller ◽  
Experimental Testing ◽  
Computation Time ◽  
Landing Gear ◽  
Time Varying ◽  
Control Effect ◽  
Simulation And Experiment ◽  
Neural Network Pid

For characteristics of nonlinearity and time-varying volatility of landing gear based on MR damper, a BP neural network PID controller with a momentum was designed on basis of established dynamic mathematical model. BP neural network would adjust three parameters of PID online in time. The controller was inputted the energy which was combined by the feedback of acceleration and displacement of the control system, which greatly reduced the computation time of controller and the control effect was more obvious. After compared with PID, the simulation and experiment have showed that BP neural network PID has a better effect. The arithmetic can be put into practice through experimental testing.

Sign in / Sign up

Export Citation Format

Share Document