Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application
By Te Han, Chao Liu, Wenguang Yang, Dongxiang Jiang. ISA transactions, 2018
513 citations recorded by the source corpus.
In recent years, an increasing popularity of deep learning model for intelligent condition monitoring and diagnosis as well as prognostics used for mechanical systems and structures has been observed. In the previous studies, however, a major assumption accepted by default, is that the training and testing data are taking from same feature distribution. Unfortunately, this assumption is mostly invalid in real application, resulting in a certain lack of applicability for the traditional diagnosis approaches. Inspired by the idea of transfer learning that leverages the knowledge learnt from rich labeled data in source domain to facilitate diagnosing a new but similar target task, a new intelligent fault diagnosis framework, i.e., deep transfer network (DTN), which generalizes deep learning model to domain adaptation scenario, is proposed in this paper. By extending the marginal distribution adaptation (MDA) to joint distribution adaptation (JDA), the proposed framework can exploit the discrimination structures associated with the labeled data in source domain to adapt the conditional distribution of unlabeled target data, and thus guarantee a more accurate distribution matching. Extensive empirical evaluations on three fault datasets validate the applicability and practicability of DTN, while achieving many state-of-the-art transfer results in terms of diverse operating conditions, fault severities and fault types.
Subfields: Control and Systems Engineering, Mechanical Engineering
View Paper: https://www.semanticscholar.org/paper/1e275681352a70a16236a23ec67ba4921bda7eeb
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
In Mechanical Engineering
Citations in the corpus
- Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study (2020, background): “Two excellent review papers [55, 56] and other applications [57, 58] published recently pointed out several potential”
- Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016 (2023, methodology): “researchers proposed a JDA method to align both marginal and conditional distributions in bearing fault diagnosis [137], [138], [141], [142], and achieved better performance than aligning marginal distribution only based on experimental results.”
- A Digital-Twin-Assisted Fault Diagnosis Using Deep Transfer Learning (2019, methodology): “[32] presented a convolutional neural network with joint distribution adaptation, this method leveraged the features learnt from huge labeled dataset to improve diagnosis performance in a new but different unlabeled dataset.”
- Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks (2020, background): “[25] established a fault diagnosis framework based on deep transfer network with joint distribution adaptation, which is able to realize domain adaption with unlabeled data in a target domain.”
- Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, methodology): “Han et al. [102] and Qian et al. [103] used JDA to align both conditional and marginal distributions simultaneously to construct a more effective and robust feature representation for substantial distribution difference.”
- A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, background): “Han et al. [26] studied a deep transfer network (DTN) for fault diagnosis, and achieved many state-of-the-art transfer results in terms of diverse operating conditions, fault severities and fault types.”