Explainable Remaining Useful Life Prediction of Air Circuit Breakers via Physics-Informed Electro-Mechanical Feature Fusion
Jiaqing Zhou, Wei Chen, Jintao Chen, Xinhao Chen · 2026
Read Explainable Remaining Useful Life Prediction of Air Circuit Breakers via Physics-Informed Electro-Mechanical Feature Fusion by Jiaqing Zhou, Wei Chen, Jintao Chen, Xinhao Chen (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/pmc-13611172.txt.
Description
Jiaqing Zhou, Wei Chen, Jintao Chen, and Xinhao Chen shared a study in twenty twenty-six. It predicts how much life is left in air circuit breakers. It explains each prediction too. Utilities must plan maintenance before failure hits. But models trained on one breaker often fail on the next one. Optimistic errors are the dangerous kind, so the team took care with them.
New degradation indicators fuse two kinds of wear signals. They join electrical and mechanical wear across the breaker's whole life. A normalization trick strips out factory tolerances. That lets a random forest move between devices. It needs just fifty calibration operations to do so. An asymmetric penalty score punishes one error type. It punishes overestimates of remaining life, the hazardous direction. Fit on full lifecycles was near perfect. The authors frame explainability and safety-biased scoring as features, not afterthoughts.
Catalog record
| CREATOR | Jiaqing Zhou, Wei Chen, Jintao Chen, Xinhao Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |