基于GRNN-PSO的新型多端口盘式电机电磁结构优化

doi:10.13229/j.cnki.jdxbgxb.20240404

摘要/Abstract

摘要：

针对传统电机输出端口单一的问题，提出一种新型多端口盘式永磁电机（MDPMM）。首先，介绍了该电机结构及工作原理；其次，针对该电机环形弧线定子定位力对推力的影响，对定位力进行了分析计算。由于影响定位力的电磁结构参数较多，设计了一种广义回归神经网络（GRNN）来建立MDPMM快速计算模型，通过建立环形弧线定子区域有限元模型得到参数样本库作为GRNN输入参数，并与支持向量机（SVM）进行对比，验证了GRNN的优越性；以“不降低推力密度，推力的最小波动”为优化目标，采用粒子群优化（PSO）算法对环形弧线定子区域的各结构参数进行优化。最后，通过对比优化前后仿真分析验证了混合GRNN-PSO算法的有效性。

关键词: 多端口盘式电机, 推力波动, 广义回归神经网络, 粒子群优化

Abstract:

To address the issue of a single output port in traditional motors， a novel multi-port disc-type permanent magnet motor （MDPMM） was proposed. First， the structure and working principle of this motor is introduced. Second， the impact of the positioning force of the ring-arc stator on thrust was analyzed and calculated. Due to the numerous electromagnetic structural parameters affecting the positioning force， a generalized regression neural network （GRNN） was designd to establish a rapid calculation model for the MDPMM. By constructing a finite element model of the ring-arc stator region， a parameter sample library was obtained as input for the GRNN. The superiority of GRNN is verified by comparing it with support vector machines （SVM）. With the optimization objective of "no reduction of thrust density and minimum fluctuation of thrust" ， the particle swarm optimization（PSO）algorithm is used to optimize the structural parameters of the ring-arc stator region. Finally， the effectiveness of the hybrid GRNN-PSO algorithm is validated through comparative simulation analysis before and after optimization.

Key words: multi-port disk permanent magnet motor, thrust ripples, generalised regression neural network, particle swarm optimisation

中图分类号:

TM351

刘欣,樊溢国. 基于GRNN-PSO的新型多端口盘式电机电磁结构优化[J]. 吉林大学学报(工学版), 2025, 55(12): 3822-3830.

Xin LIU,Yi-guo FAN. Optimization of electromagnetic structure of new multi⁃port disk motor based on GRNN⁃PSO[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(12): 3822-3830.

图/表 18

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

表3

图10

图11

图12

图13

表4

图14

参考文献 19

[1]	孙晓东, 张瑶, 陈龙. 电动汽车永磁同步轮毂电机无差拍预测电压补偿控制[J]. 吉林大学学报:工学版, 2022, 52 (10): 2213-2224.
	Sun Xiao-dong, Zhang Yao, Chen Long. Deadbeat predictive voltage compensation control for permanent magnet synchronous hub motors of electric vehicles[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52 (10): 2213-2224.
[2]	魏东辉, 汪霭廷, 计京鸿, 等. 永磁直线同步电机自适应模糊分数阶滑模精密运动控制[J]. 吉林大学学报:工学版, 2021, 51(6): 2295-2303.
	Wei Dong-hui, Wang Ai-ting, Ji Jing-hong, et al. Adaptive fuzzy fractional⁃order sliding mode precise motion control of permanent magnet linear synchronous motor[J]. Journal of Jilin University(Engineering and Technology Edition), 2021,51(6):2295-2303.
[3]	刘欣, 郑晓林. 多端口空间永磁同步电机磁路模型及电磁特性[J]. 电机与控制学报, 2022, 26(11): 82-94.
	Liu Xin, Zheng Xiao-lin. Magnetic circuit model and electromagnetic characteristics of multiport spatial permanent magnet synchronous motor[J]. Electric Machines and Control, 2022, 26(11): 82-94.
[4]	Zhu Z Q, Li H Y, Deodhar R, et al. Recent developments and comparative study of magnetically geared machines[J]. CES Transactions on Electrical Machines and Systems, 2018, 2(1): 13-22.
[5]	刘晓, 卢萌, 林娉婷, 等. 双磁场调制磁齿轮电机磁场调制机理研究[J]. 电机与控制学报, 2022, 26(10): 34-40.
	Liu Xiao, Lu Meng, Lin Ping-ting, et al. Operation principle analysis of flux modulation in dual-flux-modulated magnetic gear machine[J]. Electric Machines and Control, 2022, 26(10): 34-40.
[6]	Nishanth F N U, Van Verdeghem J, Severson E L. A review of axial flux permanent magnet machine technology[J]. IEEE Transactions on Industry Applications, 2023, 59(4): 3920-3933.
[7]	Zhao J L, Quan X W, Sun X D, et al. Design of a novel axial flux rotor consequent-pole permanent magnet machine[J]. IEEE Transactions on Applied Superconductivity, 2020, 30(4): 1-6.
[8]	Liu X, Zhang Y T, Yang S, et al. Modeling and analysis of novel space disc planet motor with multi-port output[J]. IEEE Transactions on Energy Conversion, 2023, 38(2): 888-898.
[9]	Zhu X Y, Xiang Z X, Quan L, et al. Multimode optimization research on a multiport magnetic planetary gear permanent magnet machine for hybrid electric vehicles[J]. IEEE Transactions on Industrial Electronics, 2018, 65(11): 9035-9046.
[10]	Liu C Y, Gao H M, Xiong Y S, et al. Detent force reduction in permanent magnet linear synchronous motor base on magnetic field similarity method[J]. IEEE Access, 2019, 7: 57341-57348.
[11]	杨阳, 赵吉文, 宋俊材, 等. 基于深度神经网络模型的无铁心永磁同步直线电机结构优化研究[J]. 中国电机工程学报, 2019, 39(20): 6085-6094, 6189.
	Yang Yang, Zhao Ji-wen, Song Jun-cai, et al. Structural optimization of air-core permanent magnet synchronous linear motors based on deep neural network models[J]. Proceedings of the CSEE, 2019, 39(20): 6085-6094, 6189.
[12]	刘慧娟, 傅为农. 一种参数化网格剖分方法及其在电机优化设计中的应用[J]. 中国电机工程学报, 2012, 32(21): 125-130.
	Liu Hui-juan, Fu Wei-nong. A parameterized mesh generation and refinement method for finite element magnetic field computation and its application in optimal design of electric motors[J]. Proceedings of the CSEE, 2012, 2(21): 125-130.
[13]	Sun Y, Lang M X, Wang D Z, et al. A PSO-GRNN model for railway freight volume prediction: empirical study from China[J]. J Ind Eng Manag, 2014, 7(2): 413-433.
[14]	Luo Y C, Huang H Y, Chen B W, et al. Vector-controlled permanent magnet synchronous motor drive speed identification using general regression neural network[J]. Sensors and Materials, 2023, 35(5): 1587-1598.
[15]	Kumar A, Parkash C, Vashishtha G, et al. State-space modeling and novel entropy-based health indicator for dynamic degradation monitoring of rolling element bearing[J]. Reliability Engineering & System Safety, 2022, 221: No. 108356.
[16]	Bendu H, Deepak B B V L, Murugan S. Multi-objective optimization of ethanol fuelled HCCI engine performance using hybrid GRNN-PSO[J]. Applied Energy, 2017, 187: 601-611.
[17]	Specht D F. A general regression neural network[J].IEEE Transacyions Neural Networks,1991,2(6):568-576.
[18]	Bendu H, Bbvl D, Murugan S. Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol[J]. Energy Convers Manag, 2016, 122: 165-173.
[19]	Kennedy J, Eberhart R. Particle swarm optimization[C]∥Proceedings of ICNN'95-International Conference on Neural Networks,Perth, Australia, 1995: 1942-1948.

相关文章 15

[1]	徐辉,夏佳乐,马振耀,边德军,艾胜书. 基于自适应权重粒子群的污水提热系统优化策略[J]. 吉林大学学报(工学版), 2025, 55(9): 3049-3055.
[2]	李燕飞,吴加宁. 基于改进RBF神经网络的人体姿态局部特征识别算法[J]. 吉林大学学报(工学版), 2025, 55(5): 1749-1755.
[3]	金庆良,周鑫森,陈翼,吴承文. 基于群智能增强核极限学习机的创新人才预测模型[J]. 吉林大学学报(工学版), 2025, 55(5): 1763-1771.
[4]	郭祎,魏书威,姜涛. 基于区位势能和多源数据的城市客运交通规划算法[J]. 吉林大学学报(工学版), 2025, 55(4): 1328-1335.
[5]	张良力,马晓凤. 基于改进粒子群算法的新能源汽车充电站选址方法[J]. 吉林大学学报(工学版), 2024, 54(8): 2275-2281.
[6]	巩亚东,丁明祥,李响,田近民. TC4钛合金材料铣削加工分析及参数优化[J]. 吉林大学学报(工学版), 2024, 54(4): 917-925.
[7]	谭国金,孔庆雯,何昕,张攀,杨润超,朝阳军,杨忠. 基于动力特性和改进粒子群优化算法的桥梁冲刷深度识别[J]. 吉林大学学报(工学版), 2023, 53(6): 1592-1600.
[8]	张铮,朱齐丹,吕晓龙,樊星. 冗余机械臂运动学逆解的求解优化方法[J]. 吉林大学学报(工学版), 2023, 53(12): 3379-3387.
[9]	高金武,贾志桓,王向阳,邢浩. 基于PSO-LSTM的质子交换膜燃料电池退化趋势预测[J]. 吉林大学学报(工学版), 2022, 52(9): 2192-2202.
[10]	张冲,胡云峰,宫洵,孙耀. 燃料电池阴极流量无模型自适应滑模控制器设计[J]. 吉林大学学报(工学版), 2022, 52(9): 2085-2095.
[11]	秦静,郑德,裴毅强,吕永,苏庆鹏,王膺博. 基于PSO-GPR的发动机性能与排放预测方法[J]. 吉林大学学报(工学版), 2022, 52(7): 1489-1498.
[12]	朱思峰,赵明阳,柴争义. 边缘计算场景中基于粒子群优化算法的计算卸载[J]. 吉林大学学报(工学版), 2022, 52(11): 2698-2705.
[13]	于向军,槐元辉,李学飞,王德武,俞安. 基于克里金和粒子群算法的装载机铲掘轨迹规划[J]. 吉林大学学报(工学版), 2020, 50(2): 437-444.
[14]	金顺福,郄修尘,武海星,霍占强. 基于新型休眠模式的云虚拟机分簇调度策略及性能优化[J]. 吉林大学学报(工学版), 2020, 50(1): 237-246.
[15]	王宏志,姜方达,周明月. 基于遗传粒子群优化算法的认知无线电系统功率分配[J]. 吉林大学学报(工学版), 2019, 49(4): 1363-1368.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	最小值	最大值
辅助齿的齿厚D/mm	3	5
辅助齿的齿高H/mm	13	15
极距τ_p/mm	9.75	12
永磁体厚度h_m/mm	3	5
气隙高度δ/mm	0.5	1.5

参数	水平1	水平2	水平3
D/mm	3	4.5	5
H/mm	13	14	15
τ_p/mm	9.75	10.875	12
h_m/mm	3	4.5	5
δ/mm	0.5	1	1.5

序号	环形弧线定子设计参数					输出性能
序号	H/mm	D/mm	δ/mm	h_m/mm	τ_p/mm	F/N	γ/N
1	15	3	0.5	3	9.75	95.35	12.35
2	15	4.5	0.5	3	9.75	93.03	31.19
3	15	5	0.5	3	9.75	92.92	36.09
?	?	?	?	?	?	?	?
160	13	3	1.5	5	12	110.71	18.84
161	13	4.5	1.5	5	12	110.87	8.00
162	13	5	1.5	5	12	110.95	5.62

参数	优化前	GRNN-PSO优化后	RSM优化后
D/mm	5	4.87	3.92
H/mm	15	13.27	13.57
τ_p/mm	12	10.58	11.99
h_m/mm	5	3.37	3.91
δ/mm	0.5	0.93	0.77