%0 Journal Article %1 binanzer2025robustness %A Binanzer, Lisa %A Dazer, Martin %D 2025 %J Forschung im Ingenieurwesen %K L_Binanzer M_Dazer antriebstechnik %N 24 %R https://doi.org/10.1007/s10010-025-00815-0 %T Robustness and transferability of an autoencoder based anomaly detection approach to detect gear damage %V 89 %X Using an autoencoder (AE) based approach enables damage detection in a very early stage and does not require labeled training data. The earliest possible damage detection in gearboxes provides a precise insight into the state of health. The aim of this investigation is to use extended training datasets that include multiple operating conditions, thus robust damage detection is investigated independent of the operating state. In a first evaluation the operating states with same speed, but different torques of a healthy gear pair are used as a training dataset. In a second evaluation, operating states of different speeds and torques are used as a training dataset. In addition, the transferability of the algorithm to other gear pairs is examined without training the AE again. The vibration data used for damage detection are recorded on the test bench with a single stage spur gearbox. The test runs are carried out at different damage sizes, speeds and torques. The AE is trained on datasets without damage. The trained AE receives datasets of the tests with and without damage and encodes them. After a subsequent decoding step, the loss of the AE is calculated. The loss varies depending on the damage size. The investigation of the extended training datasets and the transferability of the AE provides valuable insights for the further development of robust damage detection algorithms.

@article{binanzer2025robustness, abstract = {Using an autoencoder (AE) based approach enables damage detection in a very early stage and does not require labeled training data. The earliest possible damage detection in gearboxes provides a precise insight into the state of health. The aim of this investigation is to use extended training datasets that include multiple operating conditions, thus robust damage detection is investigated independent of the operating state. In a first evaluation the operating states with same speed, but different torques of a healthy gear pair are used as a training dataset. In a second evaluation, operating states of different speeds and torques are used as a training dataset. In addition, the transferability of the algorithm to other gear pairs is examined without training the AE again. The vibration data used for damage detection are recorded on the test bench with a single stage spur gearbox. The test runs are carried out at different damage sizes, speeds and torques. The AE is trained on datasets without damage. The trained AE receives datasets of the tests with and without damage and encodes them. After a subsequent decoding step, the loss of the AE is calculated. The loss varies depending on the damage size. The investigation of the extended training datasets and the transferability of the AE provides valuable insights for the further development of robust damage detection algorithms.}, added-at = {2025-02-24T17:56:51.000+0100}, author = {Binanzer, Lisa and Dazer, Martin}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d776d72e4b746e0dc2c2ea85d9132773/ima-publ}, doi = {https://doi.org/10.1007/s10010-025-00815-0}, interhash = {9c7b67d6ad3f6e4af8b321f400bbc9a5}, intrahash = {d776d72e4b746e0dc2c2ea85d9132773}, journal = {Forschung im Ingenieurwesen}, keywords = {L_Binanzer M_Dazer antriebstechnik}, month = {2}, note = {(peer-review)}, number = 24, timestamp = {2025-02-25T10:21:07.000+0100}, title = {Robustness and transferability of an autoencoder based anomaly detection approach to detect gear damage}, volume = 89, year = 2025 }