This study presents an improved MOPSO algorithm, ATP-QL-MOPSO, for lightweight and crashworthiness optimization of automotive battery pack systems (BPS). Traditional MOPSO struggles with hyperparameter tuning and local optima. The proposed method integrates Q-learning (QL) and adaptive t-distribution perturbation (ATP) to address these issues. In QL, particles act as agents with independent velocity updates, using Euclidean distance and three velocity parameters as state and action spaces. ATP dynamically adjusts the t-distribution shape to avoid local optima. ATP-QL-MOPSO showed improved performance in ZDT tests with reduced Inverted Generational Distance (In ZDT1, IGD is reduced by 55.6% compared to standard MOPSO). Applied to BPS, it achieved higher hypervolume values, increased X-direction displacement by 6.044%, decreased Y-direction displacement by 2.787%, and reduced mass by 3.273%. This demonstrates that QL automates hyperparameter tuning, while ATP improves convergence, making it superior to MOPSO in optimizing BPS for weight reduction and crash resistance, with potential for broader applications.
AndwariAMPesiridisARajooS, et al. A review of battery electric vehicle technology and readiness levels. Renew Sustain Energy Rev2017; 78: 414–430.
2.
Victor ChomboPLaoonualYWongwisesS. Lessons from the electric vehicle crashworthiness leading to battery fire. Energies2021; 14(16): 4802.
3.
SinzWBreitfußCTomaschE, et al. Integration of a crashworthy battery in a fully electric city bus. Int J Crashworthiness2012; 17(1): 105–118.
4.
TrattnigGLeitgebW.Battery modelling for crash safety simulation. In: ThalerAWatzenigD (eds) Automotive battery technology. Springer Briefs in Applied Sciences and Technology. Springer, 2014, pp.19–35.
5.
LauterCTrösterTReuterC. Hybrid structures consisting of sheet metal and fibre reinforced plastics for structural automotive applications. In: ElmarakbiA (ed.) Advanced composite materials for automotive applications: structural integrity and crashworthiness. Wiley, 2013, pp.149–174.
6.
WangHWangZFanY, et al. Multi-objective lightweight design of automotive battery pack box for crashworthiness. Int J Crashworthiness2024; 29(2): 292–307.
7.
ZhangXXiongYPanY, et al. Crushing stress and vibration fatigue-life optimization of a battery-pack system. Struct Multidiscipl Optim2023; 66(3): 48.
8.
ShuiLChenFGargA, et al. Design optimization of battery pack enclosure for electric vehicle. Struct Multidiscipl Optim2018; 58(1): 331–347.
9.
XiongYPanYWuL, et al. Effective weight-reduction- and crashworthiness-analysis of a vehicle’s battery-pack system via orthogonal experimental design and response surface methodology. Eng Fail Anal2021; 128: 105635.
10.
KennedyJEberhartR.Particle swarm optimization. In: Proceedings of ICNN’95 - international conference on neural networks, Perth, WA, Australia, 27 November–1 December 1995, pp.1942–1948. New York: IEEE.
11.
CoelloCACLechugaMS. MOPSO: a proposal for multiple objective particle swarm optimization. In: Proceedings of the 2002 congress on evolutionary computation. CEC’02 (Cat. No.02TH8600), Honolulu, HI, USA, 12–17 May 2002, pp.1051–1056. New York: IEEE.
12.
XiongFWangDMaZ, et al. Structure-material integrated multi-objective lightweight design of the front end structure of automobile body. Struct Multidiscipl Optim2018; 57(2): 829–847.
13.
ZhangHLiSWuY, et al. A multiscale reliability-based design optimization method for carbon-fiber-reinforced composite drive shafts. Comput Model Eng Sci2024; 140(2): 1975–1996.
14.
ZhangHSunZZhiP, et al. Material-structure integrated design and optimization of a carbon-fiber-reinforced composite car door. Appl Sci2024; 14(2): 930.
15.
WangWYiHZhangT, et al. Crashworthiness analysis and optimization of thin-walled structures based on the TSSA-LSSVM surrogate model. Int J Struct Stab Dyn2024; 25(1): 2550003.
16.
ZhangYShanYLiuX, et al. Integrated shape-morphing and surrogate model-assisted multi-objective structural optimization of an automobile wheel made of lightweight materials to improve its impact resistance. Eng Optim2023; 56(12): 1–27.
17.
LiuFXuYLiM, et al. Optimization of automotive battery pack casing based on equilibrium response surface model and multi-objective particle swarm algorithm. Proc Inst Mech Eng Part D: J Automob Eng2023; 237(6): 1183–1194.
18.
ZäpfelGBrauneRBöglM.Metaheuristic search concepts: a tutorial with applications to production and logistics. Springer, 2010.
19.
EibenAEHinterdingRMichalewiczZ.Parameter control in evolutionary algorithms. IEEE Trans Evol Comput1999; 3(2): 124–141.
KimPLeeJ.An integrated method of particle swarm optimization and differential evolution. J Mech Sci Technol2009; 23(2): 426–434.
23.
LiuYLuHChengS, et al. An adaptive online parameter control algorithm for particle swarm optimization based on reinforcement learning. In: IEEE congress on evolutionary computation (CEC), Wellington, New Zealand, 10–13 June 2019, pp.815–822. New York: IEEE.
24.
ZhangPLiHHaQP, et al. Reinforcement learning based optimizer for improvement of predicting tunneling-induced ground responses. Adv Eng Inform2020; 45: 101097.
25.
GaoY-ZYeJ-WChenY-M, et al. Q-learning based on particle swarm optimization for positioning system of underwater vehicles. In: IEEE international conference on intelligent computing and intelligent systems, Shanghai, China, 20–22 November 2009, pp.68–71. New York: IEEE.
26.
MeerzaSIAIslamMUzzalMM. Q-learning based particle swarm optimization algorithm for optimal path planning of swarm of mobile robots. In: 1st international conference on advances in science, engineering and robotics technology (ICASERT), Dhaka, Bangladesh, 3–5 May 2019, pp.1–5. New York: IEEE.
27.
LuLZhengHJieJ, et al. Reinforcement learning-based particle swarm optimization for sewage treatment control. Complex Intell Syst2021; 7(5): 2199–2210.
28.
HuangXYangGYangC, et al. A collaborative optimization algorithm for ship damage stability design. J Phys Conf Ser2022; 2203(1): 012071.
29.
SeyyedabbasiAAliyevRKianiF, et al. Hybrid algorithms based on combining reinforcement learning and metaheuristic methods to solve global optimization problems. Knowl Based Syst2021; 223: 107044.
30.
GölcükİOzsoydanFB. Q-learning and hyper-heuristic based algorithm recommendation for changing environments. Eng Appl Artif Intell2021; 102: 104284.
31.
WangJLeiDCaiJ.An adaptive artificial bee colony with reinforcement learning for distributed three-stage assembly scheduling with maintenance. Appl Soft Comput2022; 117(2): 108371.
32.
SeyyedabbasiA.A reinforcement learning-based metaheuristic algorithm for solving global optimization problems. Adv Eng Softw2023; 178(3): 103411.
33.
SuJXueXWenX. Particle swarm optimization algorithm based on levy flight. In: GrigorasGLorenzP (eds) Frontiers in artificial intelligence and applications. IOS Press, 2023, pp.905–911.
34.
DongJDouZSiS, et al. Optimization of capacity configuration of wind–solar–diesel–storage using improved sparrow search algorithm. J Electr Eng Technol2022; 17(1): 1–14.
35.
ZhouBLiXZhangY.Improved multi-objective cuckoo search algorithm with novel search strategies for point-to-point part feeding scheduling problems of automotive assembly lines. Assem Autom2021; 41(1): 24–44.
36.
XuHDongBLiuX, et al. Adaptive stochastic fractal search algorithm for multi-objective optimization. Swarm Evol Comput2023; 83(5): 101392.
TessariMIaccaG.Reinforcement learning based adaptive metaheuristics. In: Proceedings of the genetic and evolutionary computation conference companion, Boston, MA, USA, 9–13 July 2022, pp.1854–1861. New York: Association for Computing Machinery.
ZhaoYMenL. Group intelligence optimization algorithm of adaptive trigonometric function and T-distributed perturbation strategy. In: 2024 6th international conference on communications, information system and computer engineering (CISCE), Guangzhou, China, 10–12 May 2024.
ZamfiracheIAPrecupR-ERomanR-C, et al. Neural network-based control using actor-critic reinforcement learning and Grey Wolf Optimizer with experimental servo system validation. Expert Syst Appl2023; 225(Suppl C): 120112.
44.
YuvarajNKarthikeyanTPraghashK.An improved task allocation scheme in serverless computing using Gray Wolf Optimization (GWO) based reinforcement learning (RIL) approach. Wirel Pers Commun2021; 117(3): 2403–2421.
45.
JinWZhengdongSJinhangT, et al. Multi-strategy improved honey badger algorithm based on periodic mutation and t-distribution perturbation. High Technol Lett2025; 31(1): 63–72.
46.
ThomHTMing-YuanCTuanVQ.A novel perturbed particle swarm optimization-based support vector machine for fault diagnosis in power distribution systems. Turk J Electr Eng Comput Sci2018; 26(1): 518–529.
47.
ParsafarP.A reinforcement learning-based GWO-RNN approach for energy efficiency in data centers by minimizing virtual machine migration. J Supercomput2025; 81(1): 1–38.
48.
NanMZhuYKangL, et al. A modified RL-IGWO algorithm for dynamic weapon-target assignment in frigate defensing UAV swarms. Electron2022; 11(11): 1796.
49.
GuptaSSinghN.Fog-GMFA-DRL: enhanced deep reinforcement learning with hybrid grey wolf and modified moth flame optimization to enhance the load balancing in the fog-IoT environment. Adv Eng Softw2022; 174(Suppl C): 103295.
50.
ChenRYangBLiS, et al. An effective multi-population Grey Wolf Optimizer based on reinforcement learning for flow shop scheduling problem with multi-machine collaboration. Comput Ind Eng2021; 162(Suppl C): 107738.
51.
AdamSPAlexandropoulosS-ANPardalosPM, et al. No free lunch theorem: a review. In: DemetriouICPardalosPM (eds) Approximation and optimization: algorithms, complexity and applications. Springer International Publishing, 2019, pp.57–82.
52.
KianiMYildizAR.A comparative study of non-traditional methods for vehicle crashworthiness and NVH optimization. Arch Comput Methods Eng2016; 23(4): 723–734.
53.
KianiMGandikotaIParrishA, et al. Surrogate-based optimisation of automotive structures under multiple crash and vibration design criteria. Int J Crashworthiness2013; 18(5): 473–482.
54.
TaudHMasJF.Multilayer perceptron (MLP). In: Camacho OlmedoMTPaegelowMMasJF, et al. (eds) Geomatic approaches for modeling land change scenarios. Springer International Publishing, 2018, pp.451–455.
55.
ZitzlerEThieleL.Multiobjective optimization using evolutionary algorithms — a comparative case study. In: EibenAEBäckTSchoenauerM, et al. (eds) Parallel problem solving from Nature — PPSN V. PPSN 1998. Lecture Notes in Computer Science, vol. 1498. Springer, 1998, pp.292–301.
56.
ShihH-S.TOPSIS basics. In: ShihH-SOlsonDL (eds) TOPSIS and its extensions: a distance-based MCDM approach. Springer International Publishing, 2022, pp.17–31.
57.
DiakoulakiDMavrotasGPapayannakisL.Determining objective weights in multiple criteria problems: the critic method. Comput Oper Res1995; 22(7): 763–770.
