Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2107.03645 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910602152116224 |
|---|---|
| author | Heindel, Leonhard Hantschke, Peter Kästner, Markus |
| author_facet | Heindel, Leonhard Hantschke, Peter Kästner, Markus |
| contents | The prediction of system responses for a given fatigue test bench drive signal is a challenging task, for which linear frequency response function models are commonly used. To account for non-linear phenomena, a novel hybrid model is suggested, which augments existing approaches using Long Short-Term Memory networks. Additional virtual sensing applications of this method are demonstrated. The approach is tested using non-linear experimental data from a servo-hydraulic test rig and this dataset is made publicly available. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes, are employed in the evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2107_03645 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs Heindel, Leonhard Hantschke, Peter Kästner, Markus Signal Processing Machine Learning 93-08 The prediction of system responses for a given fatigue test bench drive signal is a challenging task, for which linear frequency response function models are commonly used. To account for non-linear phenomena, a novel hybrid model is suggested, which augments existing approaches using Long Short-Term Memory networks. Additional virtual sensing applications of this method are demonstrated. The approach is tested using non-linear experimental data from a servo-hydraulic test rig and this dataset is made publicly available. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes, are employed in the evaluation. |
| title | Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs |
| topic | Signal Processing Machine Learning 93-08 |
| url | https://arxiv.org/abs/2107.03645 |