Data-driven learning approaches have gained a lot of interest in evaluating and validating complex dynamic systems. One of the main challenges for developing a reliable learning model is the lack of training data covering a large range of various operational conditions. Extensive training data can be generated using a physics-based simulation model. On the other hand, the learning algorithm should be still tested with experimental data obtained from the actual system. Modeling errors may lead to a statistical divergence between the simulation training data and the experimental testing data, causing poor performance, especially for domain-agnostic black-box learning methods. To close the gap between the simulation and experimental domains, this paper proposes a physics-guided learning approach that combines the power of the neural network with domain-specific physics knowledge. Specifically, the proposed architecture integrates physical parameters extracted from the physics-based simulation model into the intermediate layers of the neural network to constrain the learning process. To demonstrate the effectiveness of the proposed approach, the architecture is adopted to a damage classification problem for a three-story structure. Our results show that the accuracy for localizing the damage correctly based on experimental data improves significantly over black-box models, especially under large modeling errors. In this paper, we also use the physics-based intermediate layers to analyze the interpretability of the classification results.
How to Cite
physics-guided neural network, intermediate variable layer, interpretability
[Balageas et al., 2010] Daniel Balageas, Claus-Peter Fritzen, and Alfredo Guemes.¨ Structural health monitoring, volume 90. John Wiley & Sons, 2010.
[Chen et al., 1996] SY Chen, Ming-Shaung Ju, and YG Tsuei. Estimation of mass, stiffness and damping matrices from frequency response functions. Journal of Vibration and Acoustics, 118(1):78–82, 1996.
[Craig Jr and Kurdila, 2006] Roy R Craig Jr and Andrew J Kurdila. Fundamentals of structural dynamics. John Wiley & Sons, 2006.
[Farrar and Worden, 2012] Charles R Farrar and Keith Worden. Structural health monitoring: a machine learning perspective. John Wiley & Sons, 2012.
[Figueiredo et al., 2009] Eloi Figueiredo, Gyuhae Park, Joaquim Figueiras, Charles Farrar, and Keith Worden. Structural health monitoring algorithm comparisons using standard data sets. Los Alamos National Laboratory, Los Alamos, NM, Report No. LA-14393, 2009.
[Fritzen, 1986] Claus-Peter Fritzen. Identification of Mass, Damping, and Stiffness Matrices of Mechanical Systems. Journal of Vibration, Acoustics, Stress, and Reliability in Design, 108(1):9–16, 01 1986.
[Gardner et al., 2020] P Gardner, X Liu, and K Worden. On the application of domain adaptation in structural health monitoring. Mechanical Systems and Signal Processing, 138:106550, 2020.
[Ghanem and Shinozuka, 1995] Roger Ghanem and Masanobu Shinozuka. Structural-system identification. i: Theory. Journal of Engineering Mechanics, 121(2):255–264, 1995.
[Hernandez-Garcia et al., 2010] Miguel R HernandezGarcia, Sami F Masri, Roger Ghanem, Eloi Figueiredo, and Charles R Farrar. An experimental investigation of change detection in uncertain chain-like systems. Journal of Sound and Vibration, 329(12):2395–2409, 2010.
[Jaishi and Ren, 2006] Bijaya Jaishi and Wei-Xin Ren. Damage detection by finite element model updating using modal flexibility residual. Journal of sound and vibration, 290(1-2):369–387, 2006.
[Jia et al., 2018] Xiaowei Jia, Anuj Karpatne, Jared Willard,
Michael Steinbach, Jordan Read, Paul C Hanson, Hilary A Dugan, and Vipin Kumar. Physics guided recurrent neural networks for modeling dynamical systems: Application to monitoring water temperature and quality in lakes. arXiv preprint arXiv:1810.02880, 2018.
[Karpatne et al., 2017] Anuj Karpatne, William Watkins, Jordan Read, and Vipin Kumar. Physics-guided neural networks (pgnn): An application in lake temperature modeling. arXiv preprint arXiv:1710.11431, 2017.
[Kim et al., 2003] Jeong-Tae Kim, Yeon-Sun Ryu, HyunMan Cho, and Norris Stubbs. Damage identification in beam-type structures: frequency-based method vs modeshape-based method. Engineering structures, 25(1):57– 67, 2003.
[Lin et al., 2017] Yi-zhou Lin, Zhen-hua Nie, and Hong-wei Ma. Structural damage detection with automatic featureextraction through deep learning. Computer-Aided Civil and Infrastructure Engineering, 32(12):1025–1046, 2017.
[McKenna et al., 2010] Frank McKenna, Michael H. Scott, and Gregory L. Fenves. Nonlinear finite-element analysis software architecture using object composition. Journal of Computing in Civil Engineering, 24(1):95–107, 2010.
[Muralidhar et al., 2019] Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, and Anuj Karpatne. Physics-guided design and learning of neural networks for predicting drag force on particle suspensions in moving fluids. arXiv preprint arXiv:1911.04240, 2019.
[Sadoughi and Hu, 2019] Mohammadkazem Sadoughi and Chao Hu. Physics-based convolutional neural network for fault diagnosis of rolling element bearings. IEEE Sensors Journal, 19(11):4181–4192, 2019.
[Sun and Betti, 2015] Hao Sun and Raimondo Betti. A hybrid optimization algorithm with bayesian inference for probabilistic model updating. Computer-Aided Civil and Infrastructure Engineering, 30(8):602–619, 2015.
[Teughels and De Roeck, 2005] Anne Teughels and Guido De Roeck. Damage detection and parameter identification by finite element model updating. Revue europeenne´ de genie civil´ , 9(1-2):109–158, 2005.
[Wang et al., 1997] Z Wang, RM Lin, and MK Lim. Structural damage detection using measured frf data. Computer methods in applied mechanics and engineering, 147(12):187–197, 1997.
[Zhang and Sun, 2020] Zhiming Zhang and Chao Sun.
Structural damage identification via physics-guided machine learning: a methodology integrating pattern recognition with finite element model updating. Structural Health Monitoring, page 1475921720927488, 2020.
[Zhang et al., 2020] Ruiyang Zhang, Yang Liu, and Hao Sun. Physics-guided convolutional neural network (phycnn) for data-driven seismic response modeling. Engineering Structures, 215:110704, 2020.
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.