Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring

Nurudeen Alegeh; Munavar Thottoli; Naeem Mian; Andrew Longstaff; Simon Fletcher

doi:10.3233/ATDE210069

Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring

Nurudeen Alegeh, Munavar Thottoli, Naeem Mian, Andrew Longstaff, Simon Fletcher

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

8 Citations (Scopus)

Abstract

This paper investigates the use of the discrete wavelet transform (DWT) and Fast Fourier Transform (FFT) to improve the quality of extracted features for machine learning. The case study in this paper is detecting the health state of the
ballscrew of a gantry type machine tool. For the implementation of the algorithm for feature extraction, wavelet is first applied to the data, followed by FFT and then useful features are extracted from the resultant signal. The extracted features were then used in various machine learning algorithms like decision tree, K-nearest neighbour (KNN) and support vector machine (SVM) for binary classification of the ballscrew state. The result shows significant improvement in the classification
accuracy after the wavelet transform and FFT has been performed on the data.

Original language	English
Title of host publication	Proceedings of the 18th International Conference in Manufacturing Research
Subtitle of host publication	ICMR 2021
Editors	Mahmoud Shafik, Keith Case
Publisher	IOS Press
Pages	402-407
Number of pages	6
ISBN (Electronic)	9781614994398
DOIs	https://doi.org/10.3233/ATDE210069
Publication status	Published - 21 Aug 2021
Event	18th International Conference on Manufacturing Research - University of Derby, Derby, United Kingdom Duration: 7 Sep 2021 → 10 Sep 2021 Conference number: 18

Publication series

Name	Advances in Manufacturing Technology
Publisher	IOS Press
Volume	15

Conference

Conference	18th International Conference on Manufacturing Research
Abbreviated title	ICMR 2021
Country/Territory	United Kingdom
City	Derby
Period	7/09/21 → 10/09/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3233/ATDE210069Licence: CC BY-NC

Cite this

Alegeh, N., Thottoli, M., Mian, N., Longstaff, A., & Fletcher, S. (2021). Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring. In M. Shafik, & K. Case (Eds.), Proceedings of the 18th International Conference in Manufacturing Research: ICMR 2021 (pp. 402-407). (Advances in Manufacturing Technology; Vol. 15). IOS Press. https://doi.org/10.3233/ATDE210069

@inproceedings{a64092ac05d54f3c891cdd43d7da9db9,

title = "Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring",

abstract = "This paper investigates the use of the discrete wavelet transform (DWT) and Fast Fourier Transform (FFT) to improve the quality of extracted features for machine learning. The case study in this paper is detecting the health state of theballscrew of a gantry type machine tool. For the implementation of the algorithm for feature extraction, wavelet is first applied to the data, followed by FFT and then useful features are extracted from the resultant signal. The extracted features were then used in various machine learning algorithms like decision tree, K-nearest neighbour (KNN) and support vector machine (SVM) for binary classification of the ballscrew state. The result shows significant improvement in the classificationaccuracy after the wavelet transform and FFT has been performed on the data.",

keywords = "ballscrew, feature extraction, fast fourier transform, discrete wavelet transform, machine learning, Ballscrew, Machine learning, Fast Fourier Transform, Feature extraction, Discrete Wavelet Transform",

author = "Nurudeen Alegeh and Munavar Thottoli and Naeem Mian and Andrew Longstaff and Simon Fletcher",

note = "Funding Information: The authors gratefully acknowledge the UK{\textquoteright}s Engineering and Physical Sciences Research Council (EPSRC) funding of the Future Metrology Hub (Grant Ref: EP/P006930/1) and InnovateUK and all partners of the project Servitization Project “Metrology and Digital Manufacturing for Servitisation of Manufacturing Machines” (P/N 102787). Publisher Copyright: {\textcopyright} 2021 The authors and IOS Press. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 18th International Conference on Manufacturing Research, ICMR 2021 ; Conference date: 07-09-2021 Through 10-09-2021",

year = "2021",

month = aug,

day = "21",

doi = "10.3233/ATDE210069",

language = "English",

series = "Advances in Manufacturing Technology",

publisher = "IOS Press",

pages = "402--407",

editor = "Mahmoud Shafik and Keith Case",

booktitle = "Proceedings of the 18th International Conference in Manufacturing Research",

address = "Netherlands",

}

Alegeh, N, Thottoli, M, Mian, N , Longstaff, A & Fletcher, S 2021, Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring. in M Shafik & K Case (eds), Proceedings of the 18th International Conference in Manufacturing Research: ICMR 2021. Advances in Manufacturing Technology, vol. 15, IOS Press, pp. 402-407, 18th International Conference on Manufacturing Research, Derby, United Kingdom, 7/09/21. https://doi.org/10.3233/ATDE210069

Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring. / Alegeh, Nurudeen; Thottoli, Munavar; Mian, Naeem et al.

Proceedings of the 18th International Conference in Manufacturing Research: ICMR 2021. ed. / Mahmoud Shafik; Keith Case. IOS Press, 2021. p. 402-407 (Advances in Manufacturing Technology; Vol. 15).

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

TY - GEN

T1 - Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring

AU - Alegeh, Nurudeen

AU - Thottoli, Munavar

AU - Mian, Naeem

AU - Longstaff, Andrew

AU - Fletcher, Simon

N1 - Conference code: 18

PY - 2021/8/21

Y1 - 2021/8/21

N2 - This paper investigates the use of the discrete wavelet transform (DWT) and Fast Fourier Transform (FFT) to improve the quality of extracted features for machine learning. The case study in this paper is detecting the health state of theballscrew of a gantry type machine tool. For the implementation of the algorithm for feature extraction, wavelet is first applied to the data, followed by FFT and then useful features are extracted from the resultant signal. The extracted features were then used in various machine learning algorithms like decision tree, K-nearest neighbour (KNN) and support vector machine (SVM) for binary classification of the ballscrew state. The result shows significant improvement in the classificationaccuracy after the wavelet transform and FFT has been performed on the data.

AB - This paper investigates the use of the discrete wavelet transform (DWT) and Fast Fourier Transform (FFT) to improve the quality of extracted features for machine learning. The case study in this paper is detecting the health state of theballscrew of a gantry type machine tool. For the implementation of the algorithm for feature extraction, wavelet is first applied to the data, followed by FFT and then useful features are extracted from the resultant signal. The extracted features were then used in various machine learning algorithms like decision tree, K-nearest neighbour (KNN) and support vector machine (SVM) for binary classification of the ballscrew state. The result shows significant improvement in the classificationaccuracy after the wavelet transform and FFT has been performed on the data.

KW - ballscrew

KW - feature extraction

KW - fast fourier transform

KW - discrete wavelet transform

KW - machine learning

KW - Ballscrew

KW - Machine learning

KW - Fast Fourier Transform

KW - Feature extraction

KW - Discrete Wavelet Transform

UR - http://www.icmr.org.uk/

UR - http://www.scopus.com/inward/record.url?scp=85116394979&partnerID=8YFLogxK

U2 - 10.3233/ATDE210069

DO - 10.3233/ATDE210069

M3 - Conference contribution

T3 - Advances in Manufacturing Technology

SP - 402

EP - 407

BT - Proceedings of the 18th International Conference in Manufacturing Research

A2 - Shafik, Mahmoud

A2 - Case, Keith

PB - IOS Press

T2 - 18th International Conference on Manufacturing Research

Y2 - 7 September 2021 through 10 September 2021

ER -

Feature Extraction of Time-Series Data using DWT and FFT for Ballscrew Condition Monitoring

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this