Name
Title | ||
|---|---|---|
Automatic feature extraction and selection for condition monitoring and related datasets |
Abstract | ||
|---|---|---|
In this paper a combination of methods for feature extraction and selection is proposed suitable for extracting highly relevant features for machine condition monitoring and related applications from time domain, frequency domain, time-frequency domain and the statistical distribution of the measurement values. The approach is fully automated and suitable for multiple condition monitoring tasks such as vibration and process sensor based analysis. This versatility is demonstrated by evaluating two condition monitoring datasets from our own experiments plus multiple freely available time series classification tasks and comparing the achieved results with the results of algorithms previously suggested or even specifically designed for these datasets. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/i2mtc.2018.8409763 | instrumentation and measurement technology conference |
Field | DocType | Citations |
Time domain,Frequency domain,Pattern recognition,Control engineering,Feature extraction,Machine condition monitoring,Condition monitoring,Artificial intelligence,Engineering,Statistical classification,Approximation error,Principal component analysis | Conference | 0 |
PageRank | References | Authors |
0.34 | 4 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tizian Schneider | 1 | 0 | 0.68 |
| nikolai helwig | 2 | 9 | 0.99 |
| Andreas Schütze | 3 | 15 | 3.57 |