Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks
Read the original on arXiv AI →The paper presents a neutrosophic decomposition of a Random Forest + XGBoost + Logistic Regression ensemble for bearing fault detection, yielding four uncertainty indicators: top‑class evidence (T‑hat), best‑competitor evidence (F‑hat), predictive entropy (I1‑hat), and decision disagreement (I2‑hat). Evaluated on CWRU and JNU benchmarks under a leave‑one‑condition‑out protocol, the ensemble achieves perfect accuracy on most CWRU loads but performs poorly on JNU, where Logistic Regression outperforms the tree ensembles. Additional experiments show that fusing time‑ and frequency‑domain models and using Jensen‑Shannon divergence improves uncertainty estimation, and that envelope‑spectrum features can separate fault classes with 99.57 % accuracy on CWRU. "whyItMatters":"The study demonstrates that refined neutrosophic uncertainty indicators can reveal limitations of conventional confidence scores and guide more reliable fault detection in variable‑speed industrial settings."
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.