Application of PID Control Based on RBF Neural Network in Electro-Hydraulic Servo System for Steel Strip Deviation

2012 ◽  
Vol 468-471 ◽  
pp. 434-438
Author(s):  
Xue Qin Kou ◽  
Li Chen Gu
Keyword(s):  
Neural Network ◽  
Pid Control ◽  
Control Method ◽  
Rbf Neural Network ◽  
Steel Strip ◽  
Dynamic Performance ◽  
Servo System ◽  
Pid Algorithm ◽  
Hydraulic Servo ◽  
Hydraulic Servo System

The working principle of the electrical-hydraulic servo system for steel strip deviation is introduced. The mathematical model of the system is established, and the performance indexes in time domain are analyzed with MATLAB. Aiming at the steel strip deviation, an improved PID control method based on RBF neural network is proposed. According to Jacobian information identification of RBF neural network combined with incremental PID algorithm, the self-tuning of parameters is implemented so that the performance of the system can achieve the designed requirements. Compared with traditional PID control, the simulation results show RBF- PID control has better dynamic performance and stabilization.

Fault Detection and Isolation for Hydraulic Servo System Based on Adaptive Threshold and SOM Neural Network

2015 ◽  
Vol 764-765 ◽  
pp. 691-697
Author(s):  
Yu Jie Cheng ◽  
Chen Lu ◽  
Li Mei Wang ◽  
Hong Mei Liu
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Rbf Neural Network ◽  
Servo System ◽  
Adaptive Threshold ◽  
Residual Error ◽  
Error Signal ◽  
Hydraulic Servo ◽  
Som Neural Network ◽  
Hydraulic Servo System

A fault detection and diagnosis method for the hydraulic servo system based on adaptive threshold and self-organizing map (SOM) neural network is proposed in this study. The nonlinear, time-varying, fluid-solid coupling properties of the hydraulic servo system are considered. Fault detection is realized based on a two-stage radial basis function (RBF) neural network model. The first-stage RBF neural network is adopted as a fault observer for the hydraulic servo system; the residual error signal is generated by comparing the estimated observer output with the actual measurements. To overcome the drawback of false alarms when the traditional fixed fault threshold is used, an adaptive threshold producer is established by the second-stage RBF neural network. Fault occurrence is detected by comparing the residual error signal with the adaptive threshold. When a system fault is detected, the SOM neural network is employed to implement fault classification and isolation by analyzing the features of the residual error signal. Three types of common faults are simulated to verify the performance and effectiveness of the proposed method. Experimental results demonstrate that the proposed method based on adaptive threshold and SOM neural network is effective in detecting and isolating the failure of the hydraulic servo system.

Diagonal Recurrent Neural Network-Based Electro-Hydraulic Servo System Control

2013 ◽  
Vol 336-338 ◽  
pp. 581-584 ◽  
Author(s):  
Ye Lv ◽  
Jing Ma ◽  
De Cun He ◽  
Xiang Gao
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Pid Control ◽  
Servo System ◽  
System Structure ◽  
System Control ◽  
Control Effect ◽  
External Interference ◽  
Hydraulic Servo ◽  
Hydraulic Servo System

The electro-hydraulic servo system gradually processes toward the fast, high-power and high-precision direction. The traditional PID control needs to coordinate the contradiction between rapidity and stability, and cannot meet the system performance requirements in the case of parameter variations and external interference. Based on electro-hydraulic servo system structure and principles, system mathematical model was established, and Diagonal Recurrent Neural Network (DRNN)-based adaptive PID controller was designed and compared with positional PID control. The simulation results show that: DRNN adaptive PID control effect is superior to positional PID control, which can effectively improve the system dynamic and anti-interference performance, and has strong self-learning and adaptive capacity.

Optimization of the Dynamic Performance of the Direct Drive Volume Control System Based on Orthogonal Experiment

2014 ◽  
Vol 945-949 ◽  
pp. 2680-2684
Author(s):  
Ai Qin Huang ◽  
Yong Wang
Keyword(s):  
Control System ◽  
Dynamic Response ◽  
Orthogonal Experiment ◽  
Dynamic Performance ◽  
Servo System ◽  
Volume Control ◽  
Structure Parameters ◽  
Direct Drive ◽  
Hydraulic Servo ◽  
Hydraulic Servo System

Direct drive volume control (DDVC) electro-hydraulic servo system has many advantages compared to the valve control system. However, its application scopes were restricted by its poor dynamic performance. To study the reason for the low dynamic response, mechanical model of DDVC electro-hydraulic servo system is established. Structure parameters influencing the dynamic performance are analyzed. To optimize the structure parameters, the methodology of orthogonal experiment is presented. The selection of factors and levels of the experiment and the choice of the evaluation index are also revealed. The proposed methodology is carried out by simulation software and an optimal configuration is obtained. The dynamic response of the DDVC system with the optimal parameters is simulated. The results show that the dynamic performances are improved. The cross-over frequencyincreases from 0.0046 rad/s to 0.0442 rad/s, and the rise time Tr decreases from 488.6s to 47.90s.

Research on the PID Control Strategy in BP Neural Network of Terrain Detector-Milling Cutting Depth System

2014 ◽  
Vol 945-949 ◽  
pp. 1573-1578
Author(s):  
Xiao Feng ◽  
Hao Hu ◽  
Fan Rang Kong ◽  
Shi Qiu ◽  
Ye Sun
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Bp Neural Network ◽  
Pid Control ◽  
Simulation Analysis ◽  
Dynamic Performance ◽  
Effective Control ◽  
Cutting Depth ◽  
Hydraulic Servo

Targeting at the nonlinear, time-varying characteristics of terrain detector-milling cutting depth electro-hydraulic servo system in soil milling collection machines, this paper proposed the PID control menthod in BP neural network of terrain detector - milling cutting depth system and designed PID controller in BP neural network and conducted simulation analysis by programming with Matlab. The results show that, when compared with conventional PID control, BP neural network compounded with PID control would enable the system better dynamic performance and follow-up characteristics, therefore, it is an effective control strategy.

Sign in / Sign up

Export Citation Format

Share Document