Detection of rotating stall based on deterministic learning

Author

Wenjie Si ; Cong Wang ; Binhe Wen ; Yong Wang ; Anping Hou

Author_Institution

Sch. of Autom. & Center for Control & Optimization, South China Univ. of Technol., Guangzhou, China

fYear

2013

Firstpage

3332

Lastpage

3337

Abstract

In this paper, deterministic learning theory is used to detect the stall inception signal for the axial compressor. Firstly, based on deterministic learning (DL) theory, the system dynamics underlying normal and stall inception signal are identified and stored in constant radial basis function (RBF) networks. Secondly, through the method of dynamic pattern recognition in DL, the stall inception of the axial compressor could be detected. Simulation results show the validity of the proposed approach.

Keywords

compressors; learning (artificial intelligence); mechanical engineering computing; pattern recognition; radial basis function networks; reliability; signal detection; DL theory; RBF networks; axial compressor; deterministic learning theory; dynamic pattern recognition method; radial basis function networks; rotating stall detection; stall inception signal detection; Approximation methods; Artificial neural networks; Mathematical model; Pattern recognition; Radial basis function networks; Trajectory; Vectors; Deterministic learning; Dynamic pattern recognition; Identification; Rapid detection; Rotating stall;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (CCC), 2013 32nd Chinese

Conference_Location

Xi´an

Type

conf

Filename

6639996