The performance of automatic transmission (AT) is influenced to some extent by its characteristic parameters. In the past, the design of characteristic parameters tends to take into account only the gear ratio or a very few aspects. With the increasing complexity of AT configuration, the design of the characteristic parameters should also consider more performance indicators. Therefore, this paper proposes a method for designing characteristic parameters using a multi-objective evolutionary algorithm (MOEA), which integrates five performance indicators that are affected by the characteristic parameters. Firstly, a novel 13-speed AT configuration is taken as an example, and a new optimization model of AT is proposed. The characteristic parameters of the AT are designed using a MOEA based on adaptive reference vectors. The algorithm has been tested and shown to outperform eight other algorithms in dealing with characteristic parameters design problem. Finally, the optimized characteristic parameters of 13-speed AT are obtained, and the results show that its performance can be comparable to the existing classic AT, or even better in some performances, which further demonstrates the feasibility and effectiveness of the method.
XueHLLiuGYangXH. A review of graph theory application research in gears. Proc IMechE, Part C: J Mechanical Engineering Science2016; 230(10): 1697–1714.
2.
KeTDingHFGengMJ, et al. Automatic configuration analysis method of planetary gear automatic transmission. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. Epub ahead of print 4April2015. DOI: 10.1177/09544070231207163.
3.
XuXYDongPLiuYF, et al. Progress in automotive transmission technology. Automot Innov2018; 1: 187–210.
4.
TrivediASrinivasanDSanyalK, et al. A survey of multiobjective evolutionary algorithms based on decomposition. IEEE Trans Evol Comput2016; 21(3): 440–462.
5.
ZhouAMQuBYLiH, et al. Multiobjective evolutionary algorithms: a survey of the state of the art. Swarm and Evol Comput2011; 1(1): 32–49.
6.
BrockhoffDFriedrichTHebbinghausN, et al. On the effects of adding objectives to plateau functions. IEEE Trans Evol Comput2009; 13(3): 591–603.
7.
IshibuchiHTsukamotoNNojimaY.Evolutionary many-objective optimization: a short review. In: IEEE congress on evolutionary computation (IEEE world congress on computational intelligence), Hong Kong, China, 2008, pp. 2419–2426.
8.
BatistaL. S.CampeloF.GuimarãesF. G., et al., 2011, “A comparison of dominance criteria in many-objective optimization problems,”IEEE Congress of evolutionary computation (CEC), pp.2359-2366.
9.
GaoWFLiuLLWangZK, et al. Survey on multiobjective optimization evolutionary algorithm based on decomposition. J Software2023; 34(10): 4743–4771 [in Chinese].
10.
WangZKZhangQFLiH, et al. On the use of two reference points in decomposition based multiobjective evolutionary algorithms. Swarm Evol Comput2017; 34: 89–102.
11.
ChengRJinYOlhoferM, et al. A reference vector guided evolutionary algorithm for many-objective optimization. IEEE Trans Evol Comput2016; 20(5): 773–791.
12.
ChengRRodemannTFischerM, et al. 2017, “Evolutionary many-objective optimization of hybrid electric vehicle control: From general optimization to preference articulation. IEEE Trans Emerging Top Comput Intell2017; 1(2): 97–111.
13.
SinghPPDasSWenFS, et al. Multi-objective planning of electric vehicles charging in distribution system considering priority-based vehicle-to-grid scheduling. Swarm Evol Comput2023; 77: 101234.
14.
GeHWZhaoMDSunL, et al. A many-objective evolutionary algorithm with two interacting processes: cascade clustering and reference point incremental learning. IEEE Trans Evol Comput2019; 23(4): 572–586.
15.
MaLBLiNGuoYN, et al. Learning to optimize: reference vector reinforcement learning adaption to constrained many-objective optimization of industrial copper burdening system. IEEE Trans Cybern2022; 52(12); 12698–12711.
16.
KahramanALigataHKienzleK, et al. A kinematics and power flow analysis methodology for automatic transmission planetary gear trains. ASME J Mech Des2004; 126(6): 1071–1081.
17.
HsuCHHuangRH, 2008, Design of parallel-connected epicyclic-type automatic transmissions with two fundamental geared entities. Proc IMechE, Part D: J Automobile Engineering2008; 222(3): 371–381.
18.
HsuCHHuangRH. Systematic design of six-speed automatic transmissions with an eight-link two-DOF Ravigneaux gear mechanism. ASME J Mech Des2009; 131: 011004.
19.
ChenHChenXA. A new methodology for multistage multispeed planetary transmission design based on geometry. ASME J Mech Des2021; 143(11): 113401.
20.
YuRZhaoWLiY. Rules and optimization-based topology and parameter synthesis of multi-speed Ravigneaux automatic transmissions. J Braz Society of Mech Sci Eng2022; 44(8): 334.
21.
SimionescuPABealeDDozierGV. Teeth-number synthesis of a multispeed planetary transmission using an estimation of distribution algorithm. ASME J Mech Des2006; 128(1): 108–115.
22.
ShamekhiAHBidgolyANoureinyEN. Optimization of the gear ratios in automatic transmission systems using an artificial neural network and a genetic algorithm. Proc IMechE, Part D: J Automobile Engineering2014; 228(11): 1338–1343.
23.
YueHJLiuYFMaMY, et al. Scheme optimization of AT shifting element based on genetic algorithm. J Central South Univ2015; 22(2): 539–545.
24.
DongPLiuYFXuXY, et al. Design and analysis of a novel multi-speed automatic transmission with four degrees-of-freedom. Mech Mach Theory2017; 108: 83–96.
25.
DingHFCaiCW. Patent analysis and structural synthesis of epicyclic gear trains used in automatic transmissions. Appl Sci2019; 10(1): 82.
26.
YangFCFengJXZhangHC. Power flow and efficiency analysis of multi-flow planetary gear trains. Mech Mach Theory2015; 92: 86-99.
27.
WanYQLiuTL. Planetary transmission scheme selection theory and optimization. Beijing: National Defense Industry Press, 1997 [in Chinese].
28.
TianYChengRZhangXY, et al. An indicator-based multiobjective evolutionary algorithm with reference point adaptation for better versatility. IEEE Trans Evol Comput2017; 22(4): 609–622.
29.
WangZKZhenHLDengJD, et al. Multiobjective optimization-aided decision-making system for large-scale manufacturing planning. IEEE Trans Cybern2022; 52(8): 8326–8339.
30.
ChengRJinYC. A competitive swarm optimizer for large scale optimization. IEEE Trans Cybern2015; 45(2): 191–204.
31.
ChengRJinYCNarukawaK, et al. A multiobjective evolutionary algorithm using gaussian processbased inverse modeling. IEEE Trans Evol Comput2015; 19(6): 838–856.
DebKGoyalM. A combined genetic adaptive search (GeneAS) for engineering design. Comput Sci Inf1996; 26(4): 30–45.
34.
WangL. P.ZhangQ. F. 2016, “Constrained Subproblems in Decomposition Based Multiobjective Evolutionary Algorithm,”IEEE Transactions on Evolutionary Computation, 20(3), pp.475-480.
35.
ZhengRHWangZK. A generalized scalarization method for evolutionary multi-objective optimization. Assoc Adv Artif Intell2023; 37(10): 12518–12525.
36.
TianYChengRZhangXY, et al. PlatEMO: a matlab platform for evolutionary multi-objective optimization. IEEE Comput Intell Mag2017; 12(4): 73–87.
37.
DebKJainH. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, Part I: Solving problems with box constraints. IEEE Trans Evol Comput2013; 18(4): 577–601.
38.
AnnibaleP. An adaptive evolutionary algorithm based on non-euclidean geometry for many-objective optimization. In: Genetic and Evolutionary Computation Conference (GECCO' 19), 13–17 July 2019, Prague, Czech Republic., 2019, pp. 595–603.
39.
ZhangXYTianYJinYC. A knee point driven evolutionary algorithm for many-objective optimization. IEEE Trans Evol Comput2015; 19(6): 761–776.
40.
JiaoRWZengSYLiCH, et al. Handling constrained many-objective optimization problems via problem transformation. IEEE Trans Cybern2021; 51(10): 4834–4847.
41.
ZhangQFLiH. MOEA/D: a multiobjective evolutionary algorithm based on decomposition. IEEE Trans Evol Comput2007; 11(6): 712–731.
42.
LiKDebKZhangQ, et al. An evolutionary many-objective optimization algorithm based on dominance and decomposition. IEEE Trans Evol Comput2015; 19(5): 694–716.
43.
WangZKZhangQFZhouAM, et al. Adaptive replacement strategies for MOEA/D. IEEE Trans Cybern2016; 46(2): 474–486.
44.
IshibuchiHImadaRMasuyamaN, et al. Comparison of hypervolume, IGD and IGD+ from the viewpoint of optimal distributions of solutions. In: DebKGoodmanECoello CoelloCA (eds) Evolutionary multi-criterion optimization. 2019, pp. 332–345. East Lansing, MI: Springer Cham.
45.
XuGYFengZMGuoEK, et al. Multi-objective optimization of hydraulic shovel using evolutionary algorithm. Autom Constr2022; 142: 104486.
46.
WolpertDHMacreadyWG. No free lunch theorems for optimization. IEEE Trans Evol Comput1997; 1(1): 67–82.
47.
JoyceTHerrmannJM. A review of no free lunch theorems, and their implications for metaheuristic optimization. In: YangX-S (ed.) Nature-inspired algorithms and applied optimization. 2018, pp. 27–51. Springer Cham. https://doi.org/10.1007/978-3-319-67669-2_2
48.
AbouhawwashM. KKT proximity measure versus augmented achievement scalarization function. Int J Comput Appl2018; 182(24): 1–7.
