What does this research mean for the field?

A systematic fault diagnosis framework combining Envelope Analysis, Cepstrum Prewhitening Analysis, and Random Forest classification achieves highly accurate and robust real-time fault identification in rolling element bearings across varying load conditions. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop and validate a robust, leakage-free diagnostic framework for multi-class rolling element bearing fault identification under variable mechanical load conditions.

September 2, 2026Journal of Engineering and Applied ScienceOpen Access

A robust multi-class bearing fault diagnosis framework using envelope analysis, cepstrum prewhitening and machine learning

View Full Paper

Ask AI

Bookmark

To develop and validate a robust, leakage-free diagnostic framework for multi-class rolling element bearing fault identification under variable mechanical load conditions.
Extracted 36 time, frequency, and hybrid envelope-cepstrum prewhitening features from Case Western Reserve University bearing vibration signals recorded under 0–3 HP loads.
Optimized the feature space to the 10 most discriminative features using variance thresholding, correlation analysis, Z-score normalization, ANOVA F-tests, and recursive feature elimination.
Evaluated six machine learning classifiers using a leakage-free Nested GroupKFold cross-validation protocol and tested generalization across unseen load conditions.
Envelope analysis resolved 66.67% of fault signals, while selective cepstrum prewhitening resolved 75% of remaining noisy signals, yielding an overall signal detection rate of 91.67%.
XGBoost achieved the highest mean classification accuracy at 97.62%, while Random Forest attained a comparable 97.51% accuracy with lower fold-to-fold variation.
Random Forest trained solely on 0 HP operating conditions generalized successfully to unseen 1 HP, 2 HP, and 3 HP datasets, with bearing defect frequencies dominating feature importance.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Computational framework reveals highly accurate bearing fault diagnosis across varying operational loads, indicating robust predictive maintenance potential for industrial rotating machinery.

Cite This Study

Rohit Mishra (2026) studied this question.

synapsesocial.com/papers/6a97e2d9c562ede874ec73e1 https://doi.org/10.1186/s44147-026-01189-y

View Full Paper

Ask AI

Bookmark

Implication

Computational framework reveals highly accurate bearing fault diagnosis across varying operational loads, indicating robust predictive maintenance potential for industrial rotating machinery.

A robust multi-class bearing fault diagnosis framework using envelope analysis, cepstrum prewhitening and machine learning

Key Points

Discussion

Implication

Cite This Study

A robust multi-class bearing fault diagnosis framework using envelope analysis, cepstrum prewhitening and machine learning

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider