Metamodel Selection and Hyperparameter Tuning for Hybrid Optimization with a Quantum-Inspired Evolutionary Algorithm in Multiple Drop-Test Simulation

Downloads

Authors

  • Adam RURAŃSKI Department of Computational Mechanics and Engineering, Faculty of Mechanical Engineering, Silesian University of Technology, Gliwice, Poland
  • Wacław KUŚ Department of Computational Mechanics and Engineering, Faculty of Mechanical Engineering, Silesian University of Technology, Gliwice, Poland

Abstract

This study introduces a hybrid optimization framework for the multi-drop testing of a lithium-ion battery enclosure. The framework integrates a quantum-inspired evolutionary algorithm (QEA) with surrogate modeling techniques. The contribution of the present study lies in metamodel selection, hyperparameter tuning, and the evaluation of two hybrid integration strategies built on a previously published QEA framework. Three types of metamodels were applied, artificial neural networks (ANNs), Kriging, and polynomial regression (PNR), using datasets generated via Latin hypercube sampling and from prior QEA iterations. Hyperparameter tuning methods constitute the main part of the study. Two fitness functions were analyzed, including a logarithmically scaled variant designed to compress the output range for damaged cases and enhance classification accuracy near the damage/no-damage boundary. A dual-model strategy was employed for the ANN, with model switching determined by a plastic strain threshold. Across the tested datasets, the ANN frequently identified low-objective individuals, while PNR occasionally exhibited instability. Two hybrid schemes were implemented: HYBRID1 yielded the lowest objective values in the reported runs, whereas HYBRID2 reduced runtime and showed a steadier optimization course, at a slight cost to the best obtained objective value. Within the analyzed QEA-based workflow, the combination of QEA, ANN, and the second objective fitness function (FF2) reduced finite element method (FEM) computational time by an order of magnitude while maintaining decision-making effectiveness. These results support the proposed hybridization as a practical improvement of the existing QEA workflow for the studied multi-drop test problem.

Keywords:

surrogate modeling, metamodel selection, hyperparameter tuning, artificial neural network, Kriging, polynomial regression, quantum-inspired evolutionary algorithm, multi-drop test, battery housing

References


[1] Sebastjan P., Kuś W., Method for parameter tuning of hybrid optimization algorithms for problems with high computational costs of objective function evaluations, Applied Sciences, 13(10): 6307, 2023. https://doi.org/10.3390/app13106307
[2] Sebastjan P., Kuś W., For forged automotive components using hybrid optimization techniques, Computer Methods in Materials Science, 21(2): 63–74, 2021, https://doi.org/10.7494/cmms.2021.2.0746
[3] Burczyński T., Kuś W., Beluch W., Długosz A., Poteralski A., Szczepanik M., Intelligent Computing in Optimal Design, Springer International Publishing, Cham, 2020, https://doi.org/10.1007/978-3-030-34161-9
[4] Jarosz J., Długosz A., Shape optimization of the muffler shield with regard to strength properties, Engineering Transactions, 71(3): 351–366, 2023, https://doi.org/10.24423/engtrans.3093.20230727
[5] Park H.-S., Dang X.-P., Structural optimization based on CAD–CAE integration and metamodeling techniques, Computer-Aided Design, 42(10): 889–902, 2010, https://doi.org/10.1016/j.cad.2010.06.003
[6] Fatiha I.C., Santosa S.P., Widagdo D., Pratomo A.N., Design optimisation of metastructure configuration for lithium-ion battery protection using machine learning methodology, Batteries, 10(2): 52, 2024, https://doi.org/10.3390/batteries10020052
[7] Rajput S.P.S., Datta S., A review on optimization techniques used in civil engineering material and structure design, Materials Today: Proceedings, 26: 1482–1491, 2020, https://doi.org/10.1016/j.matpr.2020.02.305
[8] Kuś W., Mucha W., Memetic inverse problem solution in cyber-physical systems, [in:] Advances in Technical Diagnostics, Springer International Publishing, Cham, 2018, pp. 335–341, https://doi.org/10.1007/978-3-319-62042-8_30
[9] Keane A.J., Scanlan J.P., Design search and optimization in aerospace engineering, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1859): 2501–2529, 2007, https://doi.org/10.1098/rsta.2007.2019
[10] AI and Machine Learning in Simulation, Dassault Systèmes, 2024, https://www.3ds.com/products/simulia/ai-and-machine-learning-simulation
[11] Ansys AI – AI-Augmented Simulation Technology, https://www.ansys.com/ai
[12] AI and Machine Learning for Engineering Design Generation and Optimization, Default, https://altair.com/resource/ai-and-machine-learning-for-engineering-design-generation-and-optimization
[13] Ma C., Xu C., Souri M., Hosseinzadeh E., Jabbari M., Multi-objective optimisation of the battery box in a racing car, Technologies, 12(7): 93, 2024, https://doi.org/10.3390/technologies12070093
[14] Mucha W., Application of dynamic condensation for model order reduction in real-time hybrid simulations, Meccanica, 58(7): 1409–1425, 2023, https://doi.org/10.1007/s11012-023-01675-0
[15] Jin R., Chen W., Simpson T.W., Comparative studies of metamodelling techniques under multiple modelling criteria, Structural and Multidisciplinary Optimization, 23(1): 1–13, 2001, https://doi.org/10.1007/s00158-001-0160-4
[16] Rurański A., Kuś W., The quantum-inspired evolutionary algorithm in the parametric optimization of lithium-ion battery housing in the multiple-drop test, Batteries, 10(9): 308, 2024, https://doi.org/10.3390/batteries10090308
[17] Bai Y., Wierzbicki T., A new model of metal plasticity and fracture with pressure and Lode dependence, International Journal of Plasticity, 24(6): 1071–1096, 2008, https://doi.org/10.1016/j.ijplas.2007.09.004
[18] Dean A., Morris M., Stufken J., Bingham D., Latin Hypercubes and Space-Filling Designs, Chapman and Hall/CRC, 2015, pp. 613–646, https://doi.org/10.1201/b18619-27
[19] Zhu H., Liu L., Long T., Peng L., A novel algorithm of maximin Latin hypercube design using successive local enumeration, Engineering Optimization, 44(5): 551–564, 2012, https://doi.org/10.1080/0305215X.2011.591790
[20] Zhong H. et al., Metamodeling for policy simulations with multivariate outcomes, Medical Decision Making, 42(7): 872–884, 2022, https://doi.org/10.1177/0272989X221105079
[21] Iooss B., Boussouf L., Feuillard V., Marrel A., Numerical studies of the metamodel fitting and validation processes, International Journal on Advances in Systems and Measurements, 3(1 & 2): 11–21, 2010.
[22] Kalita K., Chakraborty S., Madhu S., Ramachandran M., Gao X.-Z., Performance analysis of radial basis function metamodels for predictive modelling of laminated composites, Materials, 14(12): 3306, 2021, https://doi.org/10.3390/ma14123306
[23] Williams B., Cremaschi S., Novel tool for selecting surrogate modeling techniques for surface approximation, Computer Aided Chemical Engineering, 50: 451–456, 2021, https://doi.org/10.1016/B978-0-323-88506-5.50071-1
[24] Akiba T., Sano S., Yanase T., Ohta T., Koyama M., Optuna: A next-generation hyperparameter optimization framework, [in:] KDD ’19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, Anchorage, AK, USA, 2019, pp. 2623–2631, https://doi.org/10.1145/3292500.3330701
[25] Lee S., Park S., Kim T., Lieu Q.X., Lee J., Damage quantification in truss structures by limited sensor-based surrogate model, Applied Acoustics, 172: 107547, 2021, https://doi.org/10.1016/j.apacoust.2020.107547
[26] Torzoni M., Manzoni A., Mariani S., A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks, Mechanical Systems and Signal Processing, 197: 110376, 2023, https://doi.org/10.1016/j.ymssp.2023.110376
[27] Raiaan M.A.K. et al., A systematic review of hyperparameter optimization techniques in convolutional neural networks, Decision Analytics Journal, 11: 100470, 2024, https://doi.org/10.1016/j.dajour.2024.100470
[28] Hanifi S., Cammarono A., Zare-Behtash H., Advanced hyperparameter optimization of deep learning models for wind power prediction, Renewable Energy, 221: 119700, 2024, https://doi.org/10.1016/j.renene.2023.119700
[29] Sacks J., Welch W.J., Mitchell T.J., Wynn H.P., Design and analysis of computer experiments, Statistical Science, 4(4): 409–423, 1989, https://doi.org/10.1214/ss/1177012413
[30] Hutter M., The loss rank principle for model selection, [in:] N.H. Bshouty, C. Gentile [Eds], Learning Theory. COLT 2007. Lecture Notes in Computer Science, Vol. 4539, Springer, Berlin, Heidelberg, 2007, pp. 589–603, https://doi.org/10.1007/978-3-540-72927-3_42
[31] Wang B., Ding X., Wang F.-Y., Determination of polynomial degree in the regression of drug combinations, IEEE/CAA Journal of Automatica Sinica, 4(1): 41–47, 2017, https://doi.org/10.1109/JAS.2017.7510319
[32] Kingma D.P., Ba L.J., Adam: A method for stochastic optimization, Paper presented at International Conference on Learning Representations 2015, San Diego, California, United States, 2015, https://doi.org/10.48550/arXiv.1412.6980