Session: CIE-01-01: AMS General

Paper Number: 114851

114851 - Cross-Domain Health Conditions Identification Based on Joint Distribution Modeling of Fused Prototypes 

Intelligent diagnostic models with deep learning networks have been widely used for health conditions identification of complex mechanical systems. However, the distributional shift and data scarcity phenomenon inevitably exist in practical and real-world scenarios, which further affect the generalization and representation capability of neural networks. Recently, meta-learning has provided an effective way to solve domain shifts and extremely limited data problems. By introducing non-parametric similarity measures into meta-knowledge learning, metric-based meta-learning can seek embedding spaces to compare class prototypes to identify unseen testing samples. This article proposes a novel meta-neural network based on joint distribution modeling of fused prototypes (IFJPN) to alleviate distribution discrepancy in embedding spaces between different domains. First, multi-source time-series data are transformed into images for modality alignment and information aggregation. Second, a feature embedding module with multiple convolutions is developed to obtain fused prototypes from converted images. Then, the Brownian distance covariance is used for efficient joint distribution modeling of fused prototypes, which improves the discriminative capability of cross-domain health conditions with extremely limited data. Extensive experiments on a benchmark dataset in different cross-domain scenarios under two limited data settings show that the proposed IFJPN has more robust recognition and generalization capability than typical transfer-learning or meta-learning methods.

Presenting Author: Tingli Xie Georgia Institute of Technology

Presenting Author Biography: Tingli Xie received the B.S. degree in mechanical design manufacturing and automation, in 2016, and the M.S. degree in mechanical engineering, in 2019, both from Huazhong University of Science and Technology (HUST), Wuhan, China. She is currently working toward the Ph.D. degree in mechanical engineering at Georgia lnstitute of Technology, Atlanta, GA, USA from Fall 2019.
Her current research interest includes deep learning, uncertainty quantification and fault diagnosis.

Authors:

Tingli Xie Georgia Institute of Technology
Xufeng Huang Huazhong University of Science & Technology
Seung-Kyum Choi Georgia Institute of Technology