Yu-Bo Shao

Semi-Supervised Gearbox Anomaly Detection Under Variable Operating Conditions

Feature distributions shift under variable-speed gearbox operation, which can cause a model trained only on healthy samples to misclassify normal operating changes as anomalies. A semi-supervised anomaly detection method is proposed in this study. Using healthy data, the method first fits speed-dependent trends for the...

Dynamic Adversarial Domain Adaptation for Cross-Condition Remaining Useful Life Prediction of Rolling Bearings Guided by Initial Degradation Points