Distribution adaptation deep transfer learning method for cross-structure health monitoring using guided waves

Structural Health Monitoring - Tập 21 Số 3 - Trang 853-871 - 2022
Bin Zhang1, Xiaobin Hong1, Yuan Liu1
1School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China

Tóm tắt

Deep learning algorithm can effectively obtain damage information using labeled samples, and has become a promising feature extraction tool for ultrasonic guided wave detection. But it is difficult to apply the monitoring expertise of structure A to structure B in most cases due to the differences in the dispersion and receiving modes of different waveguides. For multi-structure monitoring at the system level, how to transfer a trained structural health monitoring model to another different structure remains a major challenge. In this article, a cross-structure ultrasonic guided wave structural health monitoring method based on distribution adaptation deep transfer learning is proposed to solve the feature generalization problem in different monitoring structures. First, the joint distribution adaptation method is employed to adapt both the marginal distribution and conditional distribution of the guided wave signals from different structures. Second, convolutional long short-term memory network is constructed to learn the mapping relationship from adapted training samples in source domain. Batch normalization layer is implemented to balance the input tensors of each sample to the same distribution. Finally, the multi-sensor damage indexes are utilized to visually present the damage by probability imaging. The experimental results show that proposed method can utilize the single-sensor monitoring data in one structure to implement the multi-sensor damage monitoring in another structure and achieve the damage imaging visualization. The imaging performance is significantly superior to the existing principal component analysis, transfer component analysis, and other state-of-art comparison methods.

Từ khóa


Tài liệu tham khảo

10.1109/TUFFC.2019.2932227

10.1177/1475921720958082

10.1016/j.compositesb.2020.107906

10.1177/1475921718791134

10.1177/1475921719861908

10.1177/1475921719842385

10.1016/j.jsv.2020.115704

10.1177/1475921713510756

10.1016/j.ymssp.2019.04.013

10.1016/j.compind.2018.12.016

10.1016/j.ymssp.2019.04.053

10.1177/1475921716650997

10.1016/j.renene.2017.03.052

10.1098/rsta.2019.0581

Zhang S, 2019, IEEE T Fuzzy Syst, 28, 1205

10.1007/s42791-019-0012-2

10.1016/j.compstruct.2020.112403

10.1109/TIM.2019.2951891

10.1364/OE.397509

10.1016/j.renene.2019.06.135

10.1016/j.compstruct.2019.110973

Khurjekar I, Harley J. Deep neural network-based guided wave damage localization. In: Review of progress in quantitative nondestructive evaluation, 2019, https://www.ndt.net/article/aero2019/papers/fp_thu1c6_m_rautela.pdf

10.1109/JSEN.2019.2908838

Rathod VT, Nondestructive characterization and monitoring of advanced materials, aerospace, civil infrastructure, and transportation IX, Online Only

10.1002/stc.2651

Liao Y, 2020, IEEE T Instrum Meas, 69, 8064

10.1109/ACCESS.2018.2886343

10.1016/j.ymssp.2019.106272

10.1109/TMECH.2020.3025615

10.1088/1361-665X/ab58d6

10.1109/JSEN.2020.3009194

10.1007/s12205-019-0437-z

Long M, Proceedings of the IEEE international conference on computer vision, 2200

Shi X, 2015, Adv Neur In, 1, 802

10.1016/j.measurement.2020.108087

Thông tin
Thông tin xuất bản

Structural Health Monitoring

Tập 21 Số 3

853-871

Thông tin tác giả