Title :
Neural PCA based fault diagnosis
Author :
Moya, E. ; Sainz, G.I. ; Grande, B. ; Fuente, M.J. ; Peran, J.R.
Author_Institution :
Dept. of Syst. Eng. & Control, Univ. of Valladolid., Valladolid, Spain
Abstract :
This paper presents a new system for fault diagnosis based in a neural network approach to Principal Component Analysis (PCA). An index set is defined based on neural PCA in order to detect and characterize faults, which has been tested on a hydraulic three-thanks system and on an electrical engine obtaining high success ratio of fault detection and characterization.
Keywords :
fault diagnosis; hydraulic systems; neurocontrollers; principal component analysis; electrical engine; fault characterization; fault detection; hydraulic three-thanks system; index set; neural PCA based fault diagnosis; neural network approach; principal component analysis; Fault diagnosis; Graphics; Neural networks; Principal component analysis; Trajectory; Principal Component Analysis (PCA); fault diagnosis; neural network;
Conference_Titel :
Control Conference (ECC), 2001 European
Conference_Location :
Porto
Print_ISBN :
978-3-9524173-6-2
