Napredna pretraga

Pregled bibliografske jedinice broj: 14470

Rudder Servo-System Fault Diagnosis using Neural Network Fault Modeling


Vukić, Zoran; Pavleković, Dean; Ožbolt, Henrieta
Rudder Servo-System Fault Diagnosis using Neural Network Fault Modeling // Oceans '98 : Conference proceedings
Piscataway: Oceans '98 IEEE/OES Conference Organizing Committee, 1998. str. 538-544 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Rudder Servo-System Fault Diagnosis using Neural Network Fault Modeling

Autori
Vukić, Zoran ; Pavleković, Dean ; Ožbolt, Henrieta

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Oceans '98 : Conference proceedings / - Piscataway : Oceans '98 IEEE/OES Conference Organizing Committee, 1998, 538-544

ISBN
978-0-78035-045-8

Skup
Oceans '98 : IEEE/OES Conference

Mjesto i datum
Nica, Francuska, 28.09-01.10.1998

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Fault diagnosis; fault detection; rudder servo system; identification

Sažetak
The model based fault detection and identification scheme for the rudder servo system as the actuator in the closed loop course keeping control system is presented. The nonlinear process model that enables description of wide class of fault types is given and the fault function as the residual for detecting and identifying the fault is introduced. Fault detection scheme with variable tresholds is suggested and its performance has been tested via simulation in the presence of modeling uncertainty and noise. Fault identification scheme based on comparison between fault function estimate and the output of predifined analytical fault model is suggested.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika



POVEZANOST RADA


Projekt / tema
036003

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb