Title :
An intelligent approach to fault detection and identification
Author :
Mufti, Muid ; Vachtskvanos, G.
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
A new approach is proposed for improving the performance of an intelligent fault detection and identification scheme for dynamic systems. The methodology uses short time Fourier transform to analyze the frequency contents of the input signal in real time through a moving window. Measures of detectability and identifiability are defined for this algorithm. Finally experimental test and simulation results are used to demonstrate the efficiency of the proposed approach
Keywords :
artificial intelligence; failure analysis; fast Fourier transforms; identification; detectability measures; dynamic systems; fault detection; fault identification; frequency contents; identifiability measures; intelligent approach; real-time analysis; short time Fourier transform; Algorithm design and analysis; Automatic control; Electrical fault detection; Fault detection; Fault diagnosis; Fourier transforms; Jet engines; Symmetric matrices; System testing; Time frequency analysis;
Conference_Titel :
American Control Conference, Proceedings of the 1995
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2445-5
DOI :
10.1109/ACC.1995.529781
