In this study, we develop a sparse regression framework to predict the frequency response of a complex zigzag structure using frequency domain data from experimental setups. Such structures are widely used in MEMS (Micro-Electro-Mechanical Systems) and vibration energy harvesters where small structures with low-natural frequencies are desired. Our approach employs sparsity-promoting techniques, including LASSO (Least Absolute Shrinkage and Selection Operator) regression, to selectively identify the most relevant nonlinear terms based on the LASSO regression technique, thereby avoiding exhaustive searches across all potential models. The machine learning framework proposed in this research consists of standard scaling for data normalization, trigonometric and polynomial feature transformations, and regularization through LASSO regression, followed by optimization using a genetic algorithm to fine-tune LASSO parameters like regularization strength, maximum iterations, and tolerance. This method ensures a generalized and interpretable model capable of addressing the complexities of dynamic systems with external excitations. The present model achieves an R2 score of 0.9998, a root mean squared error (RMSE) of 0.021947, and a mean absolute error (MAE) of 0.002580, demonstrating exceptional predictive accuracy. The accuracy and robustness of our model are verified by comparing its predictions with those of the finite element simulations using COMSOL (Computational Software for Multiphysics Simulation). The integration of machine learning with symbolic regression in this framework allows for precise characterizations of system performance and provides a methodological bridge between data-driven models and conventional physics-based analyses. This research demonstrates significant potential for advancing dynamic system modeling and analysis in complex structures, where governing equations are unknown or difficult to determine.
AnsariMKaramiMA (2017) Experimental investigation of fan-folded piezoelectric energy harvesters for powering pacemakers. Smart Materials and Structures26(6): 065001. https://doi.org/10.1088/1361-665X/aa6cfd
2.
AnsariMKaramiMA (2018) A sub-cc nonlinear piezoelectric energy harvester for powering leadless pacemakers. Journal of Intelligent Material Systems and Structures29(3): 438–445. https://doi.org/10.1177/1045389X17708344
3.
BattagliaPWHamrickJBBapstV, et al. (2018) Relational inductive biases, deep learning, and graph networks. ArXiv Preprint arXiv:1806.01261.
4.
BelausteguiIXArangoMORossi-PoolR, et al. (2024) Sparse dynamic network reconstruction through L1-regularization of a Lyapunov equation. ArXiv Preprint arXiv:2403.05457.
5.
BerdyDFSrisungsitthisuntiPJungB, et al. (2012) Low-frequency meandering piezoelectric vibration energy harvester. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control59(5): 846–858. https://doi.org/10.1109/TUFFC.2012.2269
6.
BongardJLipsonH (2007) Automated reverse engineering of nonlinear dynamical systems. Proceedings of the National Academy of Sciences104(24): 9943–9948. https://doi.org/10.1073/pnas.0609476104
7.
BruntonS (2017) Discovering governing equations from data by sparse identification of nonlinear dynamics. APS March Meeting AbstractsX49: 004.
8.
BruntonSLProctorJLKutzJN (2016) Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proceedings of the National Academy of Sciences113(15): 3932–3937. https://doi.org/10.1073/pnas.1517384113
9.
BruntonSLZolmanNKutzJN, et al. (2025) Machine learning for sparse nonlinear modeling and control. Annual Review of Control, Robotics, and Autonomous Systems8: 127–152. https://doi.org/10.1146/annurev-control-030123-015238
10.
CavaleriLBarkhordariMSRepapisCC, et al. (2022) Convolution-based ensemble learning algorithms to estimate the bond strength of the corroded reinforced concrete. Construction and Building Materials359: 129504. https://doi.org/10.1016/j.conbuildmat.2022.129504
11.
ChampionKLuschBKutzJN, et al. (2019a) Data-driven discovery of coordinates and governing equations. Proceedings of the National Academy of Sciences116(45): 22445–22451. https://doi.org/10.1073/pnas.1906995116
12.
ChampionKPBruntonSLKutzJN (2019b) Discovery of nonlinear multiscale systems: sampling strategies and embeddings. SIAM Journal on Applied Dynamical Systems18(1): 312–333. https://doi.org/10.1137/18m1188227
13.
ChinTRuthJSanfordC, et al. (2024) Enabling equation-free modeling via diffusion maps. Journal of Dynamics and Differential Equations36(Suppl 1): 415–434. https://doi.org/10.1007/s10884-021-10127-w
de Lima NogueiraSCOchSHMouraLM, et al. (2023) Prediction of the NOx and CO2 emissions from an experimental dual fuel engine using optimized random forest combined with feature engineering. Energy280: 128066. https://doi.org/10.1016/j.energy.2023.128066
16.
dos Santos CoelhoLAyalaHVHMarianiVC (2024) CO and NOx emissions prediction in gas turbine using a novel modeling pipeline based on the combination of deep forest regressor and feature engineering. Fuel355: 129366. https://doi.org/10.1016/j.fuel.2023.129366
17.
DutoitNEWardleBLKimS-G (2005) Design considerations for MEMS-scale piezoelectric mechanical vibration energy harvesters. Integrated Ferroelectrics71(1): 121–160. https://doi.org/10.1080/10584580590964574
18.
GearCWHymanJMKevrekididPG, et al. (2003) Equation-free, coarse-grained multiscale computation: enabling mocroscopic simulators to perform system-level analysis. Communications in Mathematical Sciences1(4): 715–762. Available at: https://doi.org/10.4310/CMS.2003.v1.n4.a5
19.
HastieTTibshiraniRFriedmanJH, et al. (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.
20.
JamesGWittenDHastieT, et al. (2013) An Introduction to Statistical Learning. Springer.
21.
KhalidSRaoufIKhanA, et al. (2019) A review of human-powered energy harvesting for smart electronics: recent progress and challenges. International Journal of Precision Engineering and Manufacturing-Green Technology6: 821–851. https://doi.org/10.1007/s40684-019-00144-y
22.
KlusSNüskeFPeitzS, et al. (2020) Data-driven approximation of the Koopman generator: model reduction, system identification, and control. Physica D: Nonlinear Phenomena406: 132416. https://doi.org/10.1016/j.physd.2020.132416
23.
LiYDuanJ (2021) A data-driven approach for discovering stochastic dynamical systems with Non-Gaussian Lévy noise. Physica D: Nonlinear Phenomena417: 132830. https://doi.org/10.1016/j.physd.2020.132830
NabaviSZhangL (2016) Portable wind energy harvesters for low-power applications: a survey. Sensors16(7): 1101. https://doi.org/10.3390/s16071101
26.
NandaAKaramiMA (2017) Energy harvesting from arterial blood pressure for powering embedded micro sensors in human brain. Journal of Applied Physics121(12): 124506. https://doi.org/10.1063/1.4977842
27.
NandaAKaramiMA (2018) One-way sound propagation via spatio-temporal modulation of magnetorheological fluid. Journal of the Acoustical Society of America144(1): 412–420. https://doi.org/10.1121/1.5048181
28.
NapoletaniDSauerTD (2008) Reconstructing the topology of sparsely connected dynamical networks. Physical Review E: Statistical, Nonlinear, and Soft Matter Physics77(2): 026103. https://doi.org/10.1103/PhysRevE.77.026103
29.
ParkJSugiharaGPaoG (2024) Control of complex systems with generalized embedding and empirical dynamic modeling. PLoS One19(8): e0305408. https://doi.org/10.1371/journal.pone.0305408
30.
PathakJHuntBGirvanM, et al. (2018) Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Physical Review Letters120(2): 024102. https://doi.org/10.1103/PhysRevLett.120.024102
31.
ProctorJLBruntonSLBruntonBW, et al. (2014) Exploiting sparsity and equation-free architectures in complex systems. The European Physical Journal Special Topics223(13): 2665–2684. https://doi.org/10.1140/epjst/e2014-02285-8
32.
ReillyEKMillerLMFainR, et al. (2009) A study of ambient vibrations for piezoelectric energy conversion. Proc PowerMEMS2009: 312–315.
33.
RobertsAJ (2014) Model Emergent Dynamics in Complex Systems. SIAM.
34.
RudySHBruntonSLProctorJL, et al. (2017) Data-driven discovery of partial differential equations. Science Advances3(4): e1602614. https://doi.org/10.1126/sciadv.1602614
35.
SchaefferHCaflischRHauckCD, et al. (2013) Sparse dynamics for partial differential equations. Proceedings of the National Academy of Sciences110(17): 6634–6639. https://doi.org/10.1073/pnas.1302752110
SeghierMEABHöcheDZheludkevichM (2022) Prediction of the internal corrosion rate for oil and gas pipeline: implementation of ensemble learning techniques. Journal of Natural Gas Science and Engineering99: 104425. https://doi.org/10.1016/j.jngse.2022.104425
TibshiraniR (1996) Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology58(1): 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
40.
UchidaDDuraisamyK (2024) Data-driven Koopman operator-based prediction and control using model averaging. ArXiv Preprint arXiv:2412.02984.
41.
VerdejoHAwerkinAKliemannW, et al. (2019) Modelling uncertainties in electrical power systems with stochastic differential equations. International Journal of Electrical Power & Energy Systems113: 322–332. https://doi.org/10.1016/j.ijepes.2019.05.054
42.
WangW-XYangRLaiY-C, et al. (2011) Predicting catastrophes in nonlinear dynamical systems by compressive sensing. Physical Review Letters106(15): 154101. https://doi.org/10.1103/PhysRevLett.106.154101
43.
WangW-XLaiY-CGrebogiC (2016) Data based identification and prediction of nonlinear and complex dynamical systems. Physics Reports644: 1–76. https://doi.org/10.1016/j.physrep.2016.06.004
44.
WickenheiserAM (2013) Eigensolution of piezoelectric energy harvesters with geometric discontinuities: analytical modeling and validation. Journal of Intelligent Material Systems and Structures24(6): 729–744. https://doi.org/10.1177/1045389x12448447
45.
Zounemat-KermaniMStephanDBarjenbruchM, et al. (2020) Ensemble data mining modeling in corrosion of concrete sewer: a comparative study of network-based (MLPNN & RBFNN) and tree-based (RF, CHAID, & CART) models. Advanced Engineering Informatics43: 101030.
