Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1131230

CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis


Kolar, Davor; Lisjak, Dragutin; Gudlin, Mihael
CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis // Conference Proceedings od 5th Lean Spring Summit / Stefanic, Nedeljko ; Cajner, Hrvoje (ur.).
Zagreb, 2020. str. 18-24 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1131230 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis

Autori
Kolar, Davor ; Lisjak, Dragutin ; Gudlin, Mihael

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

Izvornik
Conference Proceedings od 5th Lean Spring Summit / Stefanic, Nedeljko ; Cajner, Hrvoje - Zagreb, 2020, 18-24

Skup
LEAN SPRING SUMMIT 2020

Mjesto i datum
Online, 25.06.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks

Sažetak
Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. Traditional data-driven techniques for fault diagnosis require signal processing for feature extraction, as they are unable to work with raw signal data, consequently leading to need for both expert knowledge and human work. This paper presents authors research in deep learning-based data-driven fault diagnosis of rotating subsystems. Different combinations of hyperparameters are prepared for training and testing. Then, convolutional artificial neural network is used for training a model that can predict class identifying the state of the rotary machinery based on the collected data. Accuracy on test data is used as a metric for hyperparameters combination effectiveness.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo



POVEZANOST RADA


Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb

Profili:

Avatar Url Mihael Gudlin (autor)

Avatar Url Dragutin Lisjak (autor)

Avatar Url Davor Kolar (autor)


Citiraj ovu publikaciju:

Kolar, Davor; Lisjak, Dragutin; Gudlin, Mihael
CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis // Conference Proceedings od 5th Lean Spring Summit / Stefanic, Nedeljko ; Cajner, Hrvoje (ur.).
Zagreb, 2020. str. 18-24 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Kolar, D., Lisjak, D. & Gudlin, M. (2020) CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis. U: Stefanic, N. & Cajner, H. (ur.)Conference Proceedings od 5th Lean Spring Summit.
@article{article, author = {Kolar, Davor and Lisjak, Dragutin and Gudlin, Mihael}, year = {2020}, pages = {18-24}, keywords = {condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks}, title = {CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis}, keyword = {condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks}, publisherplace = {Online} }
@article{article, author = {Kolar, Davor and Lisjak, Dragutin and Gudlin, Mihael}, year = {2020}, pages = {18-24}, keywords = {condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks}, title = {CNN Hyperparameters Selection for Rotating Subsystems Fault Diagnosis}, keyword = {condition-based maintenance, rotating systems, fault diagnosis, convolutional neural networks}, publisherplace = {Online} }




Contrast
Increase Font
Decrease Font
Dyslexic Font