Damage Diagnostics of Miter Gates Using Domain Adaptation and Normalizing Flow-Based Likelihood-Free Inference
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Miter gates are vital civil infrastructure components in inland waterway transportation networks. To provide risk-informed insights for decisions related to repair and maintenance, sensors have been installed on some miter gates for monitoring. Despite the monitoring system's ability in collecting a large volume of monitoring data, accurately diagnosing damage state in such large structures remains challenging due to the lack of labeled monitoring data, since these structures are designed with high reliability and for a long operation life. This paper addresses this challenge by proposing a damage diagnostics approach for miter gates based on domain adaptation. The proposed approach consists of two main modules. In the first module, Cycle-Consistent generative adversarial network (CycleGAN) is employed to map monitoring data of a miter gate of interest and other similar yet different miter gates into the same analysis domain. Subsequently, a normalizing flow-based likelihood-free inference model is constructed within this common domain using data from source miter gates whose damage states are labeled from historical inspections. The trained normalizing flow model is then used to predict the damage state of the target miter gate based on the translated monitoring data. A case study is presented to demonstrate the effectiveness of the proposed method. The results indicate that the proposed method in general can accurately estimate the damage state of the target miter gate in the presence of uncertainty.
How to Cite
##plugins.themes.bootstrap3.article.details##
Miter gate, Damage Diagnostics, Bayesian, Domain adaptation
Chen, Z., Wang, C., Wu, J., Deng, C., & Wang, Y. (2023, Mar 01). Deep convolutional transfer learning based structural damage detection with domain adaptation. Applied Intelligence, 53(5), 5085-5099. doi: 10.1007/s10489-022-03713-y
Demir, U., & Unal, G. (2018). Patch-based image inpainting with generative adversarial networks. Retrieved from https://arxiv.org/abs/1803.07422
Eick, B. A., Treece, Z. R., Spencer Jr, B. F., Smith, M. D., Sweeney, S. C., Alexander, Q. G., & Foltz, S. D. (2018a). Automated damage detection in miter gates of navigation locks. Structural Control and Health Monitoring, 25(1), e2053.
Eick, B. A., Treece, Z. R., Spencer Jr, B. F., Smith, M. D., Sweeney, S. C., Alexander, Q. G., & Foltz, S. D. (2018b). Automated damage detection in miter gates of navigation locks. Structural Control and Health Monitoring, 25(1), e2053. (e2053 STC-16-0245.R2)
Estes, A. C., Frangopol, D. M., & Foltz, S. D. (2004). Updating reliability of steel miter gates on locks and dams using visual inspection results. Engineering Structures, 26(3), 319-333.
Foltz, S. D. (2017). Investigation of mechanical breakdowns leading to lock closures investigation of mechanical breakdowns leading to lock closures. Construction Engineering Research Laboratory (U.S.) Engineer Research and Development Center (U.S.).
Gardner, P., Bull, L., Gosliga, J., Dervilis, N., & Worden, K. (2021). Foundations of population-based shm, part iii: Heterogeneous populations–mapping and transfer. Mechanical Systems and Signal Processing, 149, 107142.
Gosliga, J., Gardner, P., Bull, L., Dervilis, N., & Worden, K. (2021). Foundations of population-based shm, part ii: Heterogeneous populations–graphs, networks, and communities. Mechanical Systems and Signal Processing, 148, 107144.
Hu, Z., Hu, C., & Hu, W. (2024). A tutorial on digital twins for predictive maintenance. Structural Health Monitoring/ Management (SHM) in Aerospace Structures, 453– 501.
Huang, X., Xie, T., Wang, Z., Chen, L., Zhou, Q., & Hu, Z. (2022). A transfer learning-based multi-fidelity point cloud neural network approach for melt pool modeling in additive manufacturing. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, 8(1), 011104.
Kwak, M., & Lee, J. (2023). Diagnosis-based domain-adaptive design using designable data augmentation and bayesian transfer learning: Target design estimation and validation. Applied Soft Computing, 143, 110459. doi: https://doi.org/10.1016/j.asoc.2023.110459
Levine, N., Golecki, T., Gomez, F., Eick, B., & Spencer, B. F. (2023). Bayesian model updating of concrete embedded miter gate anchorages and implications for design. Structural and Multidisciplinary Optimization, 66(3), 60.
Li, J., & He, D. (2020). A bayesian optimization adabnd-cnn method with self-optimized structure and hyperparameters for domain adaptation remaining useful life prediction. IEEE Access, 8, 41482-41501. doi: 10.1109/ACCESS.2020.2976595
Nemani, V., Thelen, A., Hu, C., & Daining, S. (2023). Degradation-aware ensemble of diverse predictors for remaining useful life prediction. Journal of Mechanical Design, 145(3), 031706.
Qian, G.,Wu, Z., Hu, Z., & Todd, M. D. (0). Pitting corrosion diagnostics and prognostics for miter gates using multiscale simulation and image inspection data. Structural Health Monitoring, 0(0), 14759217241264291. doi: 10.1177/14759217241264291
Qian, G., Zeng, J., Hu, Z., & Todd, M. (2024, 07). Bayesian Model Updating of Multiscale Simulations Informing Corrosion Prognostics Using Conditional Invertible Neural Networks. ASCE-ASME J Risk and Uncert in Engrg Sys Part B Mech Engrg, 1-33. doi: 10.1115/1.4065845
Radev, S. T., Mertens, U. K., Voss, A., Ardizzone, L., & Kothe, U. (2020). Bayesflow: Learning complex stochastic models with invertible neural networks. IEEE transactions on neural networks and learning systems, 33(4), 1452–1466.
Ramancha, M. K., Vega, M. A., Conte, J. P., Todd, M. D., & Hu, Z. (2022). Bayesian model updating with finite element vs surrogate models: Application to a miter gate structural system. Engineering Structures, 272, 114901.
Thelen, A., Zhang, X., Fink, O., Lu, Y., Ghosh, S., Youn, B. D., . . . Hu, Z. (2022). A comprehensive review of digital twin—part 1: modeling and twinning enabling technologies. Structural and Multidisciplinary Optimization, 65(12), 354.
Vega, M. A., Hu, Z., Fillmore, T. B., Smith, M. D., & Todd, M. D. (2021). A novel framework for integration of abstracted inspection data and structural health monitoring for damage prognosis of miter gates. Reliability Engineering & System Safety, 211, 107561.
Venkateswara, H., & Panchanathan, S. (2020). Introduction to domain adaptation. In H. Venkateswara & S. Panchanathan (Eds.), Domain adaptation in computer vision with deep learning (pp. 3–21). Cham: Springer International Publishing. doi: 10.1007/978- 3-030-45529-31
Vistasp M. Karbhari, F. A. (2009). Structural health monitoring of civil infrastructure systems. Woodhead Publishing Series in Civil and Structural Engineering. Wang, Z., Huang, H.-Z., & Du, X. (2010). Optimal design accounting for reliability, maintenance, and warranty. Journal of Mechanical Design, 132(1), 011007- 011015.
Whalen, E., & Mueller, C. (2022). Toward reusable surrogate models: Graph-based transfer learning on trusses. Journal of Mechanical Design, 144(2), 021704. Zeng, Y., Zeng, J., Todd, M., & Hu, Z. (2024a). Augmenting bayesian inference-based damage diagnostics of miter gates based on image translation. In International design engineering technical conferences and computers and information in engineering conference.
Zeng, Y., Zeng, J., Todd, M., & Hu, Z. (2024b). Data augmentation based on image translation for bayesian inference-based damage diagnostics of miter gates. ASCE-ASME J Risk and Uncert in Engrg Sys Part B Mech Engrg, 1–62.
Zeng, Y., Zhao, Z., Qian, G., Todd, M., & Hu, Z. (2024). Data augmentation based on image translation for bayesian inference-based damage diagnostics of miter gates. ASME Journal of Mechanical Design, Under Review.
Zhu, J., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR, abs/1703.10593. Retrieved from http://arxiv.org/abs/1703.10593
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.