Reduced Data Volumes through Hybrid Machine Learning Compared to Conventional Machine Learning Demonstrated on Bearing Fault Classification

Walther, Simon; Fuerst, Axel (2022). Reduced Data Volumes through Hybrid Machine Learning Compared to Conventional Machine Learning Demonstrated on Bearing Fault Classification Applied Sciences, 12(5), pp. 1-16. MDPI 10.3390/app12052287

[img]
Preview
Text
applsci-12-02287.pdf - Published Version
Available under License Creative Commons: Attribution (CC-BY).

Download (2MB) | Preview

n some real-world problems, machine learning is faced with little data due to limited resources such as sensors, time, and budget. In this case, the conventional machine learning approach may fail or perform badly. To develop a well-functioning model with a small training set the hybrid machine learning approach, the combination of different methods can be applied. Especially in the machine industry where Industry 4.0 is one of the most important topics—including condition monitoring, predictive maintenance, and automated data analyses—data are limited and costly. In this work, the conventional and hybrid approach are compared to the application of ball bearing fault classification. The dataset contains 12 different classes (11 with faults and 1 undamaged). For each approach, two different LSTM (Long Short-Term Memory) models are developed and trained on various training sets (different sensors). The hybrid model is realised by adding physical knowledge through applying fast Fourier transformation and frequency selection to the raw data. This study shows that the additional physical knowledge in the hybrid model results in a better performance of the hybrid machine learning than the conventional.

Item Type:

Journal Article (Original Article)

Division/Institute:

School of Engineering and Computer Science > Intelligente industrielle Systeme (I3S)
School of Engineering and Computer Science > Intelligente industrielle Systeme (I3S) > I3S / Prozessoptimierung in der Fertigung
School of Engineering and Computer Science

Name:

Walther, Simon0000-0001-9839-2054 and
Fuerst, Axel

Subjects:

Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TJ Mechanical engineering and machinery

ISSN:

2076-3417

Publisher:

MDPI

Language:

English

Submitter:

Simon Walther

Date Deposited:

23 Mar 2022 11:05

Last Modified:

23 Mar 2022 11:05

Publisher DOI:

10.3390/app12052287

Uncontrolled Keywords:

intelligent sensing and perception; wear; machine learning; machine conditionmonitoring; vibration and acoustics; bearings; deep learning; LSTM; fault classification

ARBOR DOI:

10.24451/arbor.16711

URI:

https://arbor.bfh.ch/id/eprint/16711

Actions (login required)

View Item View Item
Provide Feedback