Electric Bicycle Series Arc Fault Identification Method Based on Improved PCA and SVM
Kai Yang, Jiaqi Chen, Zuxuan Yang, Ziyu Ma, Rencheng Zhang · 2026
Read Electric Bicycle Series Arc Fault Identification Method Based on Improved PCA and SVM by Kai Yang, Jiaqi Chen, Zuxuan Yang, Ziyu Ma, Rencheng Zhang (2026) 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/PMC13364199.txt.
Description
Kai Yang and colleagues present a 2026 study on spotting series arc faults in electric bicycles, a hidden spark fault behind many e-bike fires. Faults can strike on either the battery or motor side while charge, torque, and speed all vary. The team drew eight time and frequency features from current signals, fused them with an improved principal component method into five combined features, and classified with a support vector machine.
The fused system reached about 99 percent test accuracy with strong balance across classes. A classifier comparison and timing analysis weighed accuracy against cost for real controllers. The authors offer the method as a light, readable safety layer for bike controllers and battery managers.
Catalog record
| CREATOR | Kai Yang, Jiaqi Chen, Zuxuan Yang, Ziyu Ma, Rencheng Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36103 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |