An Enhanced Intelligent Fault Diagnosis Method to Combat Label Noise

Ruan, Hulin; Wang, Yi; Qin, Yi; Tang, Baoping

doi:10.1109/icsmd53520.2021.9670833

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the noisy labels division stage, the ultimate objective is to divide the clean dataset D clean and the noisy dataset D noise into a noisy training dataset D train . Previous study [30,31] suggests that DNNs tend to fit clean samples more quickly by comparison with noisy samples, demonstrating that during the initial training phase, losses are often smaller for clean samples and larger for noisy samples. With continuous iteration of the model, as depicted in figure 3, the clean samples' CE loss is mainly distributed to the left near the origin, while the CE loss of noisy samples is mainly distributed in the middle.…”

Section: Noisy Labels Division Based On Gmmmentioning

confidence: 95%

A robust intelligent fault diagnosis method for rotating machinery under noisy labels

Chen,

Wang,

Ruan

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Despite achieving considerable success, the fault diagnosis methods will still be disturbed by noisy labels, this causes the model’s degradation and reduced diagnostic precision. Focused on solving the above issues, a robust intelligent fault diagnosis approach for rotating machinery under noisy labels is proposed. Firstly, we maintain two deep neural networks (DNNs) and alternatively execute parameters updating and models optimization by referring to the Co-teaching strategy, which can maximize filtering different error types and implement pre-training of DNNs. Secondly, adopting a two-component Gaussian mixture model (GMM) to fit training dataset’s cross-entropy (CE) loss and realize the clean and noisy labels division according to the threshold. Then, a data augmentation method called Mixup operation is employed in semi-supervised learning (SSL) to increase noise robustness and avoid error accumulation, subsequently, performing fine-tuning and correction for clean and noisy samples. Challenging experiments on a transmission gearbox dataset under different noisy labels levels show that the proposed method has robustness to noise and significantly surpasses other approaches, which provides an important reference value for accurate fault diagnosis for rotating equipment parts with noisy labels.

show abstract

Section: Noisy Labels Division Based On Gmmmentioning

confidence: 95%