Speed extraction from vibration signal using ANNs and broadband features

Ziemowit Dworakowski; Kajetan Dziedziech; Oussama Graja; Adam Jablonski

doi:10.12783/shm2017/13980

Speed extraction from vibration signal using ANNs and broadband features

Ziemowit Dworakowski, Kajetan Dziedziech, Oussama Graja, Adam Jablonski

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The authors provide a method based on ensembles of artificial neural networks (ANNs) that, fed with supervised training data, are able to estimate rotational speed of the machine under investigation. Ensembles of various ANNs trained using different algorithms provide reliability of the method and protection from unfortunate initial weights distribution. The method is validated on the basis of data gathered in large amount of experiments performed in epicyclic gearbox test bed.

Original language	English
Title of host publication	Structural Health Monitoring 2017
Subtitle of host publication	Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017
Editors	Fu-Kuo Chang, Fotis Kopsaftopoulos
Publisher	DEStech Publications Inc.
Pages	1148-1153
Number of pages	6
ISBN (Electronic)	9781605953304
DOIs	https://doi.org/10.12783/shm2017/13980
Publication status	Published - 12 Sep 2017
Externally published	Yes
Event	11th International Workshop on Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Stanford, United States Duration: 12 Sep 2017 → 14 Sep 2017 Conference number: 11

Conference

Conference	11th International Workshop on Structural Health Monitoring 2017
Abbreviated title	IWSHM 2017
Country/Territory	United States
City	Stanford
Period	12/09/17 → 14/09/17

Access to Document

10.12783/shm2017/13980Licence: Unspecified

Cite this

Dworakowski, Z., Dziedziech, K., Graja, O., & Jablonski, A. (2017). Speed extraction from vibration signal using ANNs and broadband features. In F-K. Chang, & F. Kopsaftopoulos (Eds.), Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017 (pp. 1148-1153). DEStech Publications Inc.. https://doi.org/10.12783/shm2017/13980

Dworakowski, Ziemowit ; Dziedziech, Kajetan ; Graja, Oussama et al. / Speed extraction from vibration signal using ANNs and broadband features. Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017. editor / Fu-Kuo Chang ; Fotis Kopsaftopoulos. DEStech Publications Inc., 2017. pp. 1148-1153

@inproceedings{2cc92d9bc51f4e4a8c8b81197ce055e9,

title = "Speed extraction from vibration signal using ANNs and broadband features",

abstract = "The authors provide a method based on ensembles of artificial neural networks (ANNs) that, fed with supervised training data, are able to estimate rotational speed of the machine under investigation. Ensembles of various ANNs trained using different algorithms provide reliability of the method and protection from unfortunate initial weights distribution. The method is validated on the basis of data gathered in large amount of experiments performed in epicyclic gearbox test bed.",

keywords = "Initial weights, Large amounts, Rotational speed, Supervised trainings, Vibration signal, Structural health monitoring",

author = "Ziemowit Dworakowski and Kajetan Dziedziech and Oussama Graja and Adam Jablonski",

note = "Funding Information: The work presented in this paper was supported by the National Centre for Research and Development in Poland under the research project no. PBS3/B6/21/2015; 11th International Workshop on Structural Health Monitoring 2017 : Real-Time Material State Awareness and Data-Driven Safety Assurance, IWSHM 2017 ; Conference date: 12-09-2017 Through 14-09-2017",

year = "2017",

month = sep,

day = "12",

doi = "10.12783/shm2017/13980",

language = "English",

pages = "1148--1153",

editor = "Fu-Kuo Chang and Fotis Kopsaftopoulos",

booktitle = "Structural Health Monitoring 2017",

publisher = "DEStech Publications Inc.",

address = "United States",

}

Dworakowski, Z, Dziedziech, K, Graja, O & Jablonski, A 2017, Speed extraction from vibration signal using ANNs and broadband features. in F-K Chang & F Kopsaftopoulos (eds), Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017. DEStech Publications Inc., pp. 1148-1153, 11th International Workshop on Structural Health Monitoring 2017, Stanford, California, United States, 12/09/17. https://doi.org/10.12783/shm2017/13980

Speed extraction from vibration signal using ANNs and broadband features. / Dworakowski, Ziemowit; Dziedziech, Kajetan; Graja, Oussama et al.

Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017. ed. / Fu-Kuo Chang; Fotis Kopsaftopoulos. DEStech Publications Inc., 2017. p. 1148-1153.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Speed extraction from vibration signal using ANNs and broadband features

AU - Dworakowski, Ziemowit

AU - Dziedziech, Kajetan

AU - Graja, Oussama

AU - Jablonski, Adam

N1 - Conference code: 11

PY - 2017/9/12

Y1 - 2017/9/12

N2 - The authors provide a method based on ensembles of artificial neural networks (ANNs) that, fed with supervised training data, are able to estimate rotational speed of the machine under investigation. Ensembles of various ANNs trained using different algorithms provide reliability of the method and protection from unfortunate initial weights distribution. The method is validated on the basis of data gathered in large amount of experiments performed in epicyclic gearbox test bed.

AB - The authors provide a method based on ensembles of artificial neural networks (ANNs) that, fed with supervised training data, are able to estimate rotational speed of the machine under investigation. Ensembles of various ANNs trained using different algorithms provide reliability of the method and protection from unfortunate initial weights distribution. The method is validated on the basis of data gathered in large amount of experiments performed in epicyclic gearbox test bed.

KW - Initial weights

KW - Large amounts

KW - Rotational speed

KW - Supervised trainings

KW - Vibration signal

KW - Structural health monitoring

UR - http://www.scopus.com/inward/record.url?scp=85032447785&partnerID=8YFLogxK

U2 - 10.12783/shm2017/13980

DO - 10.12783/shm2017/13980

M3 - Conference contribution

AN - SCOPUS:85032447785

SP - 1148

EP - 1153

BT - Structural Health Monitoring 2017

A2 - Chang, Fu-Kuo

A2 - Kopsaftopoulos, Fotis

PB - DEStech Publications Inc.

T2 - 11th International Workshop on Structural Health Monitoring 2017

Y2 - 12 September 2017 through 14 September 2017

ER -

Dworakowski Z, Dziedziech K, Graja O, Jablonski A. Speed extraction from vibration signal using ANNs and broadband features. In Chang F-K, Kopsaftopoulos F, editors, Structural Health Monitoring 2017: Real-Time Material State Awareness and Data-Driven Safety Assurance - Proceedings of the 11th International Workshop on Structural Health Monitoring, IWSHM 2017. DEStech Publications Inc. 2017. p. 1148-1153 doi: 10.12783/shm2017/13980

Speed extraction from vibration signal using ANNs and broadband features

Abstract

Conference

Access to Document

Other files and links

Cite this