RAKAR, Andrej ;JURIČIĆ, Đani . Modelling for Fault Detection of Electric Motors. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 50, n.5, p. 267-276, july 2017. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/>. Date accessed: 20 dec. 2024. doi:http://dx.doi.org/.
Rakar, A., & Juričić, . (2004). Modelling for Fault Detection of Electric Motors. Strojniški vestnik - Journal of Mechanical Engineering, 50(5), 267-276. doi:http://dx.doi.org/
@article{.,
author = {Andrej Rakar and Đani Juričić},
title = {Modelling for Fault Detection of Electric Motors},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {50},
number = {5},
year = {2004},
keywords = {fult detection; modelling; identifications; universal motors; adaptive networks; },
abstract = {A semi-physical model aimed at detection of incipient faults in electric motors is presented. In order to gain high sensitivity to faults a physical model is combined with a black-box model based on an AdaptiveNetwork-based Fuzzy Inference System (ANFIS) as a corrective term. The method is applied to vacuumcleaner motors. The architecture and hybrid learning procedure is presented. In the first step, the parameters of the physical model are identified by a simple least-squares method. Then, the modelling error is compensated using an adaptive-network learning procedure. In this way, the meaning of the physical parameters can be preserved. Next, the detection of the electrical faults of the motor sparking of the brushes, changes in electrical parameters, etc. are presented, where there is the most significant physical modelling error. The diagnostic results show a higher sensitivity to faults, which enables reliable fault detection. Consequently, the false and missed alarm ratio is reduced as well.},
issn = {0039-2480}, pages = {267-276}, doi = {},
url = {https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/}
}
Rakar, A.,Juričić, . 2004 July 50. Modelling for Fault Detection of Electric Motors. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 50:5
%A Rakar, Andrej %A Juričić, Đani %D 2004 %T Modelling for Fault Detection of Electric Motors %B 2004 %9 fult detection; modelling; identifications; universal motors; adaptive networks; %! Modelling for Fault Detection of Electric Motors %K fult detection; modelling; identifications; universal motors; adaptive networks; %X A semi-physical model aimed at detection of incipient faults in electric motors is presented. In order to gain high sensitivity to faults a physical model is combined with a black-box model based on an AdaptiveNetwork-based Fuzzy Inference System (ANFIS) as a corrective term. The method is applied to vacuumcleaner motors. The architecture and hybrid learning procedure is presented. In the first step, the parameters of the physical model are identified by a simple least-squares method. Then, the modelling error is compensated using an adaptive-network learning procedure. In this way, the meaning of the physical parameters can be preserved. Next, the detection of the electrical faults of the motor sparking of the brushes, changes in electrical parameters, etc. are presented, where there is the most significant physical modelling error. The diagnostic results show a higher sensitivity to faults, which enables reliable fault detection. Consequently, the false and missed alarm ratio is reduced as well. %U https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/ %0 Journal Article %R %& 267 %P 10 %J Strojniški vestnik - Journal of Mechanical Engineering %V 50 %N 5 %@ 0039-2480 %8 2017-07-07 %7 2017-07-07
Rakar, Andrej, & Đani Juričić. "Modelling for Fault Detection of Electric Motors." Strojniški vestnik - Journal of Mechanical Engineering [Online], 50.5 (2004): 267-276. Web. 20 Dec. 2024
TY - JOUR AU - Rakar, Andrej AU - Juričić, Đani PY - 2004 TI - Modelling for Fault Detection of Electric Motors JF - Strojniški vestnik - Journal of Mechanical Engineering DO - KW - fult detection; modelling; identifications; universal motors; adaptive networks; N2 - A semi-physical model aimed at detection of incipient faults in electric motors is presented. In order to gain high sensitivity to faults a physical model is combined with a black-box model based on an AdaptiveNetwork-based Fuzzy Inference System (ANFIS) as a corrective term. The method is applied to vacuumcleaner motors. The architecture and hybrid learning procedure is presented. In the first step, the parameters of the physical model are identified by a simple least-squares method. Then, the modelling error is compensated using an adaptive-network learning procedure. In this way, the meaning of the physical parameters can be preserved. Next, the detection of the electrical faults of the motor sparking of the brushes, changes in electrical parameters, etc. are presented, where there is the most significant physical modelling error. The diagnostic results show a higher sensitivity to faults, which enables reliable fault detection. Consequently, the false and missed alarm ratio is reduced as well. UR - https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/
@article{{}{.},
author = {Rakar, A., Juričić, .},
title = {Modelling for Fault Detection of Electric Motors},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {50},
number = {5},
year = {2004},
doi = {},
url = {https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/}
}
TY - JOUR AU - Rakar, Andrej AU - Juričić, Đani PY - 2017/07/07 TI - Modelling for Fault Detection of Electric Motors JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 50, No 5 (2004): Strojniški vestnik - Journal of Mechanical Engineering DO - KW - fult detection, modelling, identifications, universal motors, adaptive networks, N2 - A semi-physical model aimed at detection of incipient faults in electric motors is presented. In order to gain high sensitivity to faults a physical model is combined with a black-box model based on an AdaptiveNetwork-based Fuzzy Inference System (ANFIS) as a corrective term. The method is applied to vacuumcleaner motors. The architecture and hybrid learning procedure is presented. In the first step, the parameters of the physical model are identified by a simple least-squares method. Then, the modelling error is compensated using an adaptive-network learning procedure. In this way, the meaning of the physical parameters can be preserved. Next, the detection of the electrical faults of the motor sparking of the brushes, changes in electrical parameters, etc. are presented, where there is the most significant physical modelling error. The diagnostic results show a higher sensitivity to faults, which enables reliable fault detection. Consequently, the false and missed alarm ratio is reduced as well. UR - https://www.sv-jme.eu/article/modelling-for-fault-detection-of-electric-motors/
Rakar, Andrej, AND Juričić, Đani. "Modelling for Fault Detection of Electric Motors" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 50 Number 5 (07 July 2017)
Strojniški vestnik - Journal of Mechanical Engineering 50(2004)5, 267-276
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.
A semi-physical model aimed at detection of incipient faults in electric motors is presented. In order to gain high sensitivity to faults a physical model is combined with a black-box model based on an AdaptiveNetwork-based Fuzzy Inference System (ANFIS) as a corrective term. The method is applied to vacuumcleaner motors. The architecture and hybrid learning procedure is presented. In the first step, the parameters of the physical model are identified by a simple least-squares method. Then, the modelling error is compensated using an adaptive-network learning procedure. In this way, the meaning of the physical parameters can be preserved. Next, the detection of the electrical faults of the motor sparking of the brushes, changes in electrical parameters, etc. are presented, where there is the most significant physical modelling error. The diagnostic results show a higher sensitivity to faults, which enables reliable fault detection. Consequently, the false and missed alarm ratio is reduced as well.