A data-based inverse problem-solving method for predicting structural orderings

Abstract

Inverse problem-solving methods have found applications in various fields, such as structural mechanics, acoustics, and non-destructive testing. However, accurately solving inverse problems becomes challenging when observed data are incomplete. Fortunately, advancements in computer science have paved the way for data-based methods, enabling the discovery of nonlinear relationships within diverse data sets. In this paper, a step-by-step completion method of displacement information is introduced and a data-driven approach for predicting structural parameters is proposed. The accuracy of the proposed approach is 23.83% higher than that of the Genetic Algorithm, demonstrating the outstanding accuracy and efficiency of the data-driven approach. This work establishes a framework for solving mechanical inverse problems by leveraging a data-based method, and proposes a promising avenue for extending the application of the data-driven approach to structural health monitoring.

Graphical abstract

Keywords

mechanical inverse problem / displacement information completion / digital structural orderings / data-based method / genetic algorithm

References

[1] TarantolaA. Inverse Problem Theory: Methods for Data Fitting and Model Parameter Estimation. New York, NY: Elsevier, 1987

[2] TarantolaA. Inverse Problem Theory and Methods for Model Parameter Estimation. Philadelphia, PA: SIAM, 2005

[3] KirschA. An Introduction to the Mathematical Theory of Inverse Problems. New York, NY: Springer, 2021

[4] Tarantola A. Popper, bayes and the inverse problem. Nature Physics, 2006, 2(8): 492–494

[5] Mohammadi Estakhri N, Edwards B, Engheta N. Inverse-designed metastructures that solve equations. Science, 2019, 363(6433): 1333–1338

[6] Ronellenfitsch H, Stoop N, Yu J, Forrow A, Dunkel J. Inverse design of discrete mechanical metamaterials. Physical Review Materials, 2019, 3(9): 095201

[7] Goh H, Kallivokas L F. Inverse metamaterial design for controlling band gaps in scalar wave problems. Wave Motion, 2019, 88: 85–105

[8] SigmundO. Some Inverse Problems in Topology Design of Materials and Mechanisms. Dordrecht: Springer Netherlands, 1996, 277–284

[9] Zunger A. Inverse design in search of materials with target functionalities. Nature Reviews. Chemistry, 2018, 2(4): 0121

[10] Molesky S, Lin Z, Piggott A Y, Jin W, Vucković J, Rodriguez A W. Inverse design in nanophotonics. Nature Photonics, 2018, 12(11): 659–670

[11] McCann M T, Jin K H, Unser M. Convolutional neural networks for inverse problems in imaging: A review. IEEE Signal Processing Magazine, 2017, 34(6): 85–95

[12] Jin K H, McCann M T, Froustey E, Unser M. Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 2017, 26(9): 4509–4522

[13] Backus G, Gilbert F. The resolving power of gross earth data. Geophysical Journal International, 1968, 16(2): 169–205

[14] Seeber L, Armbruster J G. Earthquakes as beacons of stress change. Nature, 2000, 407(6800): 69–72

[15] Weissleder R, Pittet M J. Imaging in the era of molecular oncology. Nature, 2008, 452(7187): 580–589

[16] Gómez-González M, Latorre E, Arroyo M, Trepat X. Measuring mechanical stress in living tissues. Nature Reviews. Physics, 2020, 2(6): 300–317

[17] Kullaa J. Detection, identification, and quantification of sensor fault in a sensor network. Mechanical Systems and Signal Processing, 2013, 40(1): 208–221

[18] Nagayama T, Sim S H, Miyamori Y, Spencer B F J. Issues in structural health monitoring employing smart sensors. Smart Structures and Systems, 2007, 3(3): 299–320

[19] Mufti A A. Structural health monitoring of innovative Canadian civil engineering structures. Structural Health Monitoring, 2002, 1(1): 89–103

[20] GroetschC. The Theory of Tikhonov Regularization for Fredholm Equations of the First Kind. Boston, MA: Pitman Publication, 1984

[21] Defrise M, Vanhove C, Liu X. An algorithm for total variation regularization in high-dimensional linear problems. Inverse Problems, 2011, 27(6): 065002

[22] Gallet A, Rigby S, Tallman T N, Kong X, Hajirasouliha I, Liew A, Liu D, Chen L, Hauptmann A, Smyl D. Structural engineering from an inverse problems perspective. Proceedings of the Royal Society: Mathematical, Physical and Engineering Sciences, 2022, 478(2257): 20210526

[23] Zhao T, Li Y, Zuo L, Zhang K. Machine-learning optimized method for regional control of sound fields. Extreme Mechanics Letters, 2021, 45: 101297

[24] Li X, Liu Z, Cui S, Luo C, Li C, Zhuang Z. Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning. Computer Methods in Applied Mechanics and Engineering, 2019, 347: 735–753

[25] Luo C, Ning S, Liu Z, Zhuang Z. Interactive inverse design of layered phononic crystals based on reinforcement learning. Extreme Mechanics Letters, 2020, 36: 100651

[26] Zhang J, Li Y, Zhao T, Zhang Q, Zuo L, Zhang K. Machine-learning based design of digital materials for elastic wave control. Extreme Mechanics Letters, 2021, 48: 101372

[27] Guo H, Zhuang X, Rabczuk T. A deep collocation method for the bending analysis of Kirchhoff plate. Computers, Materials & Continua, 2019, 59(2): 433–456

[28] Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh V M, Guo H, Hamdia K, Zhuang X, Rabczuk T. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362: 112790

[29] Zhuang X, Guo H, Alajlan N, Zhu H, Rabczuk T. Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning. European Journal of Mechanics. A, Solids, 2021, 87: 104225

[30] Kadeethum T, O’Malley D, Fuhg J N, Choi Y, Lee J, Viswanathan H S, Bouklas N. A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networks. Nature Computational Science, 2021, 1(12): 819–829

[31] Yaji K, Yamasaki S, Fujita K. Data-driven multifidelity topology design using a deep generative model: Application to forced convection heat transfer problems. Computer Methods in Applied Mechanics and Engineering, 2022, 388: 114284

[32] Hu X, Zhang H, Ma D, Wang R. A tnGAN-Based leak detection method for pipeline network considering incomplete sensor data. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3510610

[33] Li Y, Zhang J, Yi J, Zhang K. Convolutional-generative adversarial network: Data-driven mechanical inverse method for intelligent tactile perception. Advanced Intelligent Systems, 2022, 4(9): 2100187

[34] Della Giovampaola C, Engheta N. Digital metamaterials. Nature Materials, 2014, 13(12): 1115–1121

[35] Wang Z, Zhang Q, Zhang K, Hu G. Tunable digital metamaterial for broadband vibration isolation at low frequency. Advanced Materials, 2016, 28(44): 9857–9861

[36] Liu H, Zhang Q, Zhang K, Hu G, Duan H. Designing 3D digital metamaterial for elastic waves: From elastic wave polarizer to vibration control. Advanced Science, 2019, 6(16): 1900401

[37] Rosenblatt F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 1958, 65(6): 386–408

[38] AbadiMBarham PChenJChenZDavisA DeanJDevin MGhemawatSIrvingGIsardM, . TensorFlow: A System for Large-Scale Machine Learning. Savannah, GA: USENIX Association, 2016, 265–283

[39] HollandJ H. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. Cambridge, MA: MIT Press, 1992

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant Nos. 11991030, 11991031, and 11972205).

Competing interests

The authors declare that they have no competing interests.

RIGHTS & PERMISSIONS

2025 Higher Education Press