A multi-task learning framework for diagnosing partial discharge types and assessing severity
Jin Zhang · 2026
Read A multi-task learning framework for diagnosing partial discharge types and assessing severity by Jin 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/PMC13518910.txt.
Description
Jin Zhang proposes PD-IntelliFusionNet in 2026, a single system that both sorts partial discharge types in power transformers and grades their severity. Partial discharges are tiny sparks inside insulation that slowly destroy it, and catching them early prevents costly failures. Most earlier systems tackled one task at a time.
The design fuses acoustic and ultra-high-frequency sensor signals, physics-based models, and signals drawn at several scales, from raw waveforms to wavelet patterns. A multi-task neural network with attention then sorts type and grades severity in one pass, sharing what it learns. Zhang frames the output as feed for a reinforcement learning system that could plan maintenance. Field testing remains a next step the design invites.
Catalog record
| CREATOR | Jin Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49258 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |