Multi-Layer domain adaptation method for rolling bearing fault diagnosis

By Xiang Li, Qian Ding, Jianqiao Sun. Signal Processing, 2019

435 citations recorded by the source corpus.

Abstract In the past years, data-driven approaches such as deep learning have been widely applied on machinery signal processing to develop intelligent fault diagnosis systems. In real-world applications, domain shift problem usually occurs where the distribution of the labeled training data, denoted as source domain, is different from that of the unlabeled testing data, known as target domain. That results in serious diagnosis performance degradation. This paper proposes a novel domain adaptation method for rolling bearing fault diagnosis based on deep learning techniques. A deep convolutional neural network is used as the main architecture. The multi-kernel maximum mean discrepancies (MMD) between the two domains in multiple layers are minimized to adapt the learned representations from supervised learning in the source domain to be applied in the target domain. The domain-invariant features can be efficiently extracted in this way, and the cross-domain testing performance can be significantly improved. Experiments on two rolling bearing datasets are carried out to validate the effectiveness of the domain adaptation approach. Comparisons with other approaches and related works demonstrate the superiority of the proposed method. The experimental results of this study suggest the proposed domain adaptation method offers a new and promising tool for intelligent fault diagnosis.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/d6cf6b3dc9bbbc98586c3ec2296c16d7cbf7423d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Chuang Sun
2. Xuefeng Chen
3. Ruqiang Yan
4. Paulo da Costa
5. Uzay Kaymak
6. Shibin Wang
7. Qin Wang
8. Yingqian Zhang

In Mechanical Engineering

1. Paulo da Costa
2. Uzay Kaymak
3. Shibin Wang
4. Qin Wang
5. Yingqian Zhang
6. Olga Fink
7. Fengshou Gu
8. Markus Svensén

Citations in the corpus

• Potential, challenges and future directions for deep learning in prognostics and health management applications (2020, methodology): “AdaBN (Zhang et al., 2017b), adversarial training (Zhang et al., 2018; Wang et al., 2019b), and MMD-minimization (Li et al., 2018, 2019) were used to align the full source and target distributions for rotating machines.”
• Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing (2023, methodology): “Second, a general MMD-based domain adaptation method [28] is established for comparison, in which the MMD loss is introduced at the shared feature layer of the source and target domains.”
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, methodology): “Collected signals may contain domain shift, which means that the distribution of data may differ significantly under different working conditions [23].”
• Remaining Useful Lifetime Prediction via Deep Domain Adaptation (2019, methodology): “Another CNN approach was proposed by Li et al. [48] where an MMD parameterised by multiple kernels is proposed to address the domain shift problem.”