Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation
The article describes an innovative method for detecting conveyor belt damage using a strain gauge system and deep learning techniques. The strain gauge system records measurement data from conveyor belts. A major challenge encountered during the research was the insufficient amount of measurement d...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6784 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849433440016924672 |
|---|---|
| author | Iwona Komorska Andrzej Puchalski Damian Bzinkowski |
| author_facet | Iwona Komorska Andrzej Puchalski Damian Bzinkowski |
| author_sort | Iwona Komorska |
| collection | DOAJ |
| description | The article describes an innovative method for detecting conveyor belt damage using a strain gauge system and deep learning techniques. The strain gauge system records measurement data from conveyor belts. A major challenge encountered during the research was the insufficient amount of measurement data for effectively training deep neural networks. To address this issue, the authors implemented a hybrid data augmentation method that combines generative artificial intelligence techniques and signal analysis. The TimeGAN model, based on Generative Adversarial Networks (GANs), was used to augment data from undamaged belts. Meanwhile, the superposition of one-dimensional observation sequences was applied to generate data representing damages by combining signals from randomly selected undamaged runs with strain gauge system responses to damage, effectively increasing the number of samples while accurately replicating defect conditions. For damage diagnosis, a Long Short-Term Memory Network with an attention mechanism (LSTM-AM) was employed, enabling anomaly detection in strain gauge signals. The application of the LSTM-AM algorithm allows for real-time monitoring of conveyor operation and facilitates precise localization and estimation of damage size through data synchronization. |
| format | Article |
| id | doaj-art-9f3afd628f43455e9b501ea9c2a99fec |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-9f3afd628f43455e9b501ea9c2a99fec2025-08-20T03:27:02ZengMDPI AGApplied Sciences2076-34172025-06-011512678410.3390/app15126784Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data AugmentationIwona Komorska0Andrzej Puchalski1Damian Bzinkowski2Faculty of Machanical Engineering, Kazimierz Pulaski Radom University, 26-600 Radom, PolandFaculty of Machanical Engineering, Kazimierz Pulaski Radom University, 26-600 Radom, PolandMAN Bus Ltd., 1 Maja 12, 27-200 Starachowice, PolandThe article describes an innovative method for detecting conveyor belt damage using a strain gauge system and deep learning techniques. The strain gauge system records measurement data from conveyor belts. A major challenge encountered during the research was the insufficient amount of measurement data for effectively training deep neural networks. To address this issue, the authors implemented a hybrid data augmentation method that combines generative artificial intelligence techniques and signal analysis. The TimeGAN model, based on Generative Adversarial Networks (GANs), was used to augment data from undamaged belts. Meanwhile, the superposition of one-dimensional observation sequences was applied to generate data representing damages by combining signals from randomly selected undamaged runs with strain gauge system responses to damage, effectively increasing the number of samples while accurately replicating defect conditions. For damage diagnosis, a Long Short-Term Memory Network with an attention mechanism (LSTM-AM) was employed, enabling anomaly detection in strain gauge signals. The application of the LSTM-AM algorithm allows for real-time monitoring of conveyor operation and facilitates precise localization and estimation of damage size through data synchronization.https://www.mdpi.com/2076-3417/15/12/6784anomaly detectionstrain gauges systemconveyor defectsdeep neural networkdata augmentationLSTM network |
| spellingShingle | Iwona Komorska Andrzej Puchalski Damian Bzinkowski Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation Applied Sciences anomaly detection strain gauges system conveyor defects deep neural network data augmentation LSTM network |
| title | Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation |
| title_full | Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation |
| title_fullStr | Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation |
| title_full_unstemmed | Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation |
| title_short | Localization of Conveyor Belt Damages Using a Deep Neural Network and a Hybrid Method for 1D Sequential Data Augmentation |
| title_sort | localization of conveyor belt damages using a deep neural network and a hybrid method for 1d sequential data augmentation |
| topic | anomaly detection strain gauges system conveyor defects deep neural network data augmentation LSTM network |
| url | https://www.mdpi.com/2076-3417/15/12/6784 |
| work_keys_str_mv | AT iwonakomorska localizationofconveyorbeltdamagesusingadeepneuralnetworkandahybridmethodfor1dsequentialdataaugmentation AT andrzejpuchalski localizationofconveyorbeltdamagesusingadeepneuralnetworkandahybridmethodfor1dsequentialdataaugmentation AT damianbzinkowski localizationofconveyorbeltdamagesusingadeepneuralnetworkandahybridmethodfor1dsequentialdataaugmentation |