In the last decade, the interest in machine learning (ML) has grown significantly within the structural health monitoring (SHM) community. Traditional supervised ML approaches for detecting faults assume that the training and test data come from similar distributions. However, real-world applications, where an ML model is trained, for example, on numerical simulation data and tested on experimental data, are deemed to fail in detecting the damage. The deterioration in the prediction performance is mainly related to the fact that the numerical and experimental data are collected under different conditions and they do not share the same underlying features. This paper proposes a domain adaptation approach for ML-based damage detection and localization problems where the classifier has access to the labeled training (source) and unlabeled test (target) data, but the source and target domains are statistically different. The proposed domain adaptation method seeks to form a feature space that is capable of representing both source and target domains by implementing a domain-adversarial neural network. This neural network uses H-divergence criteria to minimize the discrepancy between the source and target domain in a latent feature space. To evaluate the performance, we present two case studies where we design a neural network model for classifying the health condition of a variety of systems. The effectiveness of the domain adaptation is shown by computing the classification accuracy of the unlabeled target data with and without domain adaptation. Furthermore, the performance gain of the domain adaptation over a well-known transfer knowledge approach called Transfer Component Analysis is also demonstrated. Overall, the results demonstrate that the domain adaption is a valid approach for damage detection applications where access to labeled experimental data is limited.
domain adaptation, structural health monitoring, numerical modeling, deep learning
American Society of Civil Engineers. (2013). Failure to act. https://www.asce.org/uploadedFiles/Issues and Advocacy/OurInitiatives/Infrastructure/Content Pieces/failure-to-act-economic-impact-summary-report.pdf. (Accessed: 2020-05-15)
American Society of Civil Engineers. (2017). 2017 infrastructure report card. https://www.infrastructurereportcard.org/wp-content/uploads/2019/02/Full-2017-Report-Card-FINAL.pdf.
Benaim, S., & Wolf, L. (2017). One-sided unsupervised domain mapping. In Advances in neural information processing systems (pp. 752–762).
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine learning, 79(1-2), 151– 175.
Borgwardt, K. M., Gretton, A., Rasch, M. J., Kriegel, H.P., Scholkopf, B., & Smola, A. J. (2006). Integrating¨ structured biological data by kernel maximum mean discrepancy. Bioinformatics, 22(14), e49–e57.
Bouvier, V., Very, P., Hudelot, C., & Chastagnol, C. (2019). Hidden covariate shift: A minimal assumption for domain adaptation. arXiv preprint arXiv:1907.12299.
Catbas, N., Gokce, H. B., & Frangopol, D. M. (2013). Predictive analysis by incorporating uncertainty through a family of models calibrated with structural health monitoring data. Journal of Engineering Mechanics, 139(6), 712–723.
Chen, Z., Li, C., & Sanchez, R.-V. (2015). Gearbox fault identification and classification with convolutional neural networks. Shock and Vibration, 2015.
Dackermann, U., Li, J., & Samali, B. (2013). Identification of member connectivity and mass changes on a two storey framed structure using frequency response functions and artificial neural networks. Journal of Sound and Vibration, 332(16), 3636–3653.
Farrar, C. R., & Worden, K. (2012). Structural health monitoring: a machine learning perspective. John Wiley & Sons.
Figueiredo, E., Moldovan, I., Santos, A., Campos, P., & Costa, J. C. (2019). Finite element–based machine learning approach to detect damage in bridges under operational and environmental variations. Journal of Bridge Engineering, 24(7), 04019061.
Figueiredo, E., Park, G., Figueiras, J., Farrar, C., & Worden, K. (2009). Structural health monitoring algorithm comparisons using standard data sets. Los Alamos National Laboratory, Los Alamos, NM, Report No. LA-14393.
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., ... Lempitsky, V. (2016). Domainadversarial training of neural networks. The Journal of Machine Learning Research, 17(1), 2096–2030.
Gardner, P., Liu, X., & Worden, K. (2020). On the application of domain adaptation in structural health monitoring. Mechanical Systems and Signal Processing, 138, 106550.
Giraldo, D., Yoshida, O., Dyke, S. J., & Giacosa, L. (2004). Control-oriented system identification using era. Structural Control and Health Monitoring, 11(4), 311–326.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., & Scholkopf, B. (2009). Covariate shift by¨ kernel mean matching. Dataset shift in machine learning, 3(4), 5.
Huang, J., Gretton, A., Borgwardt, K., Scholkopf, B., &¨ Smola, A. J. (2007). Correcting sample selection bias by unlabeled data. In Advances in neural information processing systems (pp. 601–608).
Jing, L., Zhao, M., Li, P., & Xu, X. (2017). A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Measurement, 111, 1–10.
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2019). 1d convolutional neural networks and applications: A survey. arXiv preprint arXiv:1905.03554.
Li, J., Li, X., He, D., & Qu, Y. (2020). A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 234(1), 168–182.
Li, X., Zhang, W., & Ding, Q. (2018). Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks. IEEE Transactions on Industrial Electronics, 66(7), 5525–5534.
Li, X., Zhang, W., Ding, Q., & Sun, J.-Q. (2019). Multi-layer domain adaptation method for rolling bearing fault diagnosis. Signal processing, 157, 180–197.
Lin, Y.-z., Nie, Z.-h., & Ma, H.-w. (2017). Structural damage detection with automatic feature-extraction through deep learning. Computer-Aided Civil and Infrastructure Engineering, 32(12), 1025–1046.
Lu, W., Liang, B., Cheng, Y., Meng, D., Yang, J., & Zhang, T. (2016). Deep model based domain adaptation for fault diagnosis. IEEE Transactions on Industrial Electronics, 64(3), 2296–2305.
Mirzaee, A., Abbasnia, R., & Shayanfar, M. (2015). A comparative study on sensitivity-based damage detection methods in bridges. Shock and Vibration, 2015.
Nick, W., Asamene, K., Bullock, G., Esterline, A., & Sundaresan, M. (2015). A study of machine learning techniques for detecting and classifying structural damage. International Journal of Machine Learning and Computing, 5(4), 313.
Ozdagli, A. I., & Koutsoukos, X. (2019). Machine learning based novelty detection using modal analysis. Computer-Aided Civil and Infrastructure Engineering, 34(12), 1119–1140.
Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2010). Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 22(2), 199–210.
Park, J.-H., Kim, J.-T., Hong, D.-S., Ho, D.-D., & Yi, J.-H. (2009). Sequential damage detection approaches for beams using time-modal features and artificial neural networks. Journal of Sound and Vibration, 323(1-2), 451–474.
Phm data challenge 2009. (2009). http://www.phmsociety.org/competition/09. (Accessed: 2009-09-28)
Sejdinovic, D., Sriperumbudur, B., Gretton, A., & Fukumizu, K. (2013). Equivalence of distance-based and rkhs-based statistics in hypothesis testing. The Annals of Statistics, 2263–2291.
Singh, J., Azamfar, M., Ainapure, A., & Lee, J. (2020). Deep learning-based cross-domain adaptation for gearbox fault diagnosis under variable speed conditions. Measurement Science and Technology, 31(5), 055601.
Sohn, H., Farrar, C. R., Hemez, F. M., & Czarnecki, J. J. (2002). A review of structural health review of structural health monitoring literature 1996-2001 (Tech. Rep.). Los Alamos, New Mexico: Los Alamos National Laboratory.
Sugiyama, M., Nakajima, S., Kashima, H., Buenau, P. V., & Kawanabe, M. (2008). Direct importance estimation with model selection and its application to covariate shift adaptation. In Advances in neural information processing systems (pp. 1433–1440).
Sun, H., & Betti, R. (2015). A hybrid optimization algorithm with bayesian inference for probabilistic model updating. Computer-Aided Civil and Infrastructure Engineering, 30(8), 602–619.
Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 7167–7176).
Wang, M., & Deng, W. (2018). Deep visual domain adaptation: A survey. Neurocomputing, 312, 135–153.
Wang, Q., Michau, G., & Fink, O. (2019). Domain adaptive transfer learning for fault diagnosis. In 2019 prognostics and system health management conference (phmparis) (pp. 279–285).
Wilson, G., & Cook, D. J. (2020). A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11(5), 1–46.
World Bank. (2019). 2017 infrastructure report card. https://lpi.worldbank.org/international/global. (Accessed: 2020-05-15)
Xie, J., Zhang, L., Duan, L., & Wang, J. (2016). On cross-domain feature fusion in gearbox fault diagnosis under various operating conditions based on transfer component analysis. In 2016 ieee international conference on prognostics and health management (icphm) (pp. 1–6).
Zachariadis, I. A. (2018). Investment in infrastructure in the eu: Gaps, challenges, and opportunities. https://www.europarl.europa.eu/thinktank/ en/document .html ?reference=EPRS
BRI(2018)628245. (Accessed: 2020-05-15)
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the ieee international conference on computer vision (pp. 2223–2232).