Application of RBF hierarchical neural network in automatic horizon control system of memory-cutting shearer

Author

Su, Xiuping ; Li, Wei ; Zhang, Lili ; Wang, Yuqiao ; Fan, Qigao ; Sun, Chuantang ; Yu, Ling

Author_Institution

Sch. of Mech. & Electr. Eng., China Univ. of Min. & Technol., Xuzhou, China

fYear

2010

fDate

26-28 May 2010

Firstpage

2015

Lastpage

2018

Abstract

The control of hydraulic servo system is the control key to automatic horizon device of memory-cutting shear. The radial basis function (RBF) hierarchical neural network (RBFHNN) is presented to control the hydraulic servo system of automatic horizon device of memory-cutting shearer. The RBFHNN can identify the sensitivity of the hydraulic servo system in real time in the learning phase, and can make the hydraulic horizon device rapidly track the roof curve of the last cycle as feed-forward controller in the control phase. The simulation results for the hydraulic servo system of shearer horizon device show the control system based on the RBFHNN is faster, and has higher accuracy and better stability.

Keywords

hydraulic control equipment; neurocontrollers; radial basis function networks; sensitivity; servomechanisms; shearing; stability; RBF hierarchical neural network; automatic horizon control system; automatic horizon device; control phase; feed-forward controller; hydraulic horizon device; hydraulic servo system; learning phase; memory-cutting shearer; radial basis function; roof curve; sensitivity; shearer horizon device; stability; Automatic control; Control system synthesis; Control systems; Feedforward neural networks; Mathematical model; Neural networks; Neurons; Real time systems; Servomechanisms; Vectors; Automatic Horizon Control; Hierarchical Neural Networks; Radial Basis Function; Shearer;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2010 Chinese

Conference_Location

Xuzhou

Print_ISBN

978-1-4244-5181-4

Electronic_ISBN

978-1-4244-5182-1

Type

conf

DOI

10.1109/CCDC.2010.5498888

Filename

5498888