An AM-CNN-BiGRU network with spatiotemporal feature fusion for industrial robot predictive maintenance
Zihao Zang, Yiwen Zhang, Shouxin Ruan, Lei Wang, Xinming Zhang, Linsen Song, Yibo Huang, Shuhong Ye · 2025
Read An AM-CNN-BiGRU network with spatiotemporal feature fusion for industrial robot predictive maintenance by Zihao Zang, Yiwen Zhang, Shouxin Ruan, Lei Wang, Xinming Zhang, Linsen Song, Yibo Huang, Shuhong Ye (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12749340.txt.
Description
Zihao Zang and co-authors forecast factory robot failures with a hybrid neural network in a 2025 paper. Ageing robots under heavy loads break down without warning, and catching faults early saves downtime. Their model stacks a convolutional net, which reads local patterns, with a two way recurrent unit that tracks time in both directions.
Joint vibration, current, and torque feed in as separate channels, while an attention block weighs which source matters most for each fault sign. Against recent rival forecasters, the model scored best on all four error measures used. Stripping parts away in ablation tests confirmed each block earns its place.
Catalog record
| CREATOR | Zihao Zang, Yiwen Zhang, Shouxin Ruan, Lei Wang, Xinming Zhang, Linsen Song, Yibo Huang, Shuhong Ye |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 108 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |