水下推进电机的自适应降阶热模型

李睿烨; 程鹏; 兰海

doi:10.15938/j.emc.2024.07.009

欢迎来到能源电力期刊网！

您当前的位置：

首页 >

文章列表页 >

水下推进电机的自适应降阶热模型

更新时间：2025-06-26

- 水下推进电机的自适应降阶热模型
- Self-adaptive reduced order thermal modeling of underwater propulsion motors
- 电机与控制学报 2024年28卷第7期页码：88-100
- 作者机构：
  
  哈尔滨工程大学智能科学与工程学院，黑龙江哈尔滨 150001
- 作者简介：
  
  作者简介：李睿烨（1994—），男，博士研究生，研究方向为大功率电机的电磁-热综合优化设计及方法研究；
  通信作者：程鹏
  兰海（1975—），男，博士，教授，博士生导师，研究方向为优化算法、微电网、船舶电力系统分析及控制理论。
- 基金信息：
  
  国家重点研发计划项目(2022YFC3103401)
- DOI：10.15938/j.emc.2024.07.009
  中图分类号： TM301.4
- 收稿：2023-09-06，
  
  纸质出版：2024-07
- 稿件说明：
移动端阅览
李睿烨, 程鹏, 兰海. 水下推进电机的自适应降阶热模型[J]. 电机与控制学报, 2024,28(7):88-100.

LI Ruiye, CHENG Peng, LAN Hai. Self-adaptive reduced order thermal modeling of underwater propulsion motors[J]. Electric Machines and Control, 2024, 28(7): 88-100.
李睿烨, 程鹏, 兰海. 水下推进电机的自适应降阶热模型[J]. 电机与控制学报, 2024,28(7):88-100. DOI： 10.15938/j.emc.2024.07.009.

LI Ruiye, CHENG Peng, LAN Hai. Self-adaptive reduced order thermal modeling of underwater propulsion motors[J]. Electric Machines and Control, 2024, 28(7): 88-100. DOI： 10.15938/j.emc.2024.07.009.

摘要

为了提升水下推进电机的综合性能，提出自适应降阶模型来分析电机的动态多模态热场域性能特性，解决现有算法在处理高维复杂问题时资源耗费大和易陷入局部最优的问题。在时域中模型采用“无方程”的非侵入式动态模态分解方法，从时间序列数据中提取主要动态模态，实现系统数据的降维和模态分解，精确描述系统行为和预测未来状态；在空间域中，结合基于改善期望的自适应策略和径向基函数进行参数化近似和降阶。通过评估设计空间中各候选点的预测不可信度，迭代提升模型质量，平衡空间全局探索与局部探究间的关系。多步骤协作建模框架能够从有限的大规模模拟数据集中进行精确的场域解预测。通过实验系统验证了模型在常规和异常状态下温度变化规律的有效性和可靠性，结果表现出高准确性和稳定性。

Abstract

To enhance the comprehensive performance of underwater propulsion motors，an adaptive reduced-order model was developed to analyze the dynamic multimodal thermal field performance characteristics. This approach addresses the issues of high resource consumption and local optimum traps encountered by existing algorithms in handling high-dimensional complex problems. In the time domain，an‘equation-free' non-intrusive dynamic mode decomposition method was employed to extract the primary dynamic modes from time series data，achieving dimensionality reduction and mode decomposition for precise system behavior description and future state prediction. In the spatial domain，a combination of an expectation-improvement-based adaptive strategy and radial basis functions was used for parametric approximation and order reduction. By evaluating the prediction uncertainty of each candidate point in the design space，the model quality was iteratively improved，balancing global exploration and local exploitation. This multi-step collaborative modeling framework enables accurate field solution predictions from limited large-scale simulation datasets. The model's effectiveness and reliability in predicting temperature variations under both normal and abnormal conditions were validated through experimental systems，demonstrating high accuracy and stability.

关键词

Keywords

references

刘利强,尹彦博,齐咏生,等.一种多模型融合的风电系统永磁同步发电机数字孪生建模方法[J].电机与控制学报,2023,27 (11):149.

LIU Liqiang, YIN Yanbo, QI Yongsheng, et al. Digital twin modeling method of wind power system permanent magnet synchronous generator based on multi modal fusion[J]. Electric Machines and Control,2023,27(11):149.

罗豪,成立,杨丽君,等.虚实融合的变压器内绝缘状态孪生方法[J/OL].电工技术学报:1-12[2024-06-01]. https://doi.org/10.19595/j.cnki.1000-6753.tces.231839.

LUO Hao, CHENG Li, YANG Lijun, et al.The state twinning method of transformer internal insulation by virtual-real fusion[J/OL].Transactions of China Electrotechnical Society:1-12[2024-06-01].https://doi.org/10.19595/j.cnki.1000-6753.tces.231839.

KOZIEL S, PIETRENKO D A. Recent advances in high frequency modeling by means of domain confinement and nested Kriging[J]. IEEE Access, 2020,8:189326.

SAMANIEGO E, ANITESCU C, GOSWAMI S, et al. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications[J]. Computer Methods in Applied Mechanics and Engineering, 2020, 362:112790.

HE J, KUSHWAHA S, PARK J, et al. Sequential deep operator networks (S-DeepoNet) for predicting full-field solutions under time-dependent loads[J]. Engineering Applications of Artificial Intelligence, 2024, 127:107258.

SALVADOR M, DEDE L, MANZONI A. Non intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networks[J]. Computers Mathematics with Applications, 2021, 104:1.

YU Jian, YAN Chao, JIANG Zhenghua, et al. Adaptive nonintrusive reduced order modeling for compressible flows[J]. Journal of Computational Physics, 2019, 397:108855.

OULGHELOU M, ALLERY C. Non intrusive method for parametric model order reduction using a bi-calibrated interpolation on the Grassmann manifold[J]. Journal of Computational Physics,2021, 426:109924.

PIETRENKO D A, KOZIEL S. Cost-efficient surrogate modeling of high-frequency structures using nested Kriging with automated adjustment of model domain lateral dimensions[J]. AEU-International Journal of Electronics and Communications, 2020, 121:153224.

SANCARLOS A, GHNATIOS C, DUVAL J L, et al. Fast computation of multi-parametric electromagnetic fields in synchronous machines by using PDG-based fully separated representations[J]. Energies, 2021, 14(5):1454.

MONTIER L, HENNERON T, CLENET S, et al. Proper generalized decomposition applied on a rotating electrical machine[J]. Proper Generalized Decomposition Applied on a Rotating Electrical Machine, 2018, 54(3):16.

BOSCAGLIA L, BOGLIETTI A, NATEGH S, et al. Numerically based reduced-order thermal modeling of traction motors[J]. IEEE Transactions on Industrial Application,2021,57(4):4118.

荆澜涛,董雪情,杨超,等.面向数字孪生应用的变压器温度场有限元降阶建模方法研究[J].高电压技术,2023,49 (6):2408.

JING Lantao, DONG Xueqing, YANG Chao, et al. Research on finite element reduced order modeling method of transformer temperature field for digital twin application[J]. High Voltage Engineering, 2023, 49(6):2408.

ZHANG Long, YU Chengguo, LIU Bingbin. Surrogate-based structural optimization design of large-scale rectangular pressure vessel using radial point interpolation method[J]. International Journal of Pressure Vessels and Piping, 2022,197:197.

MAO Jianxing, HU Dianyin, LI Da, et al. Novel adaptive surrogate model based on LRPIM for probabilistic analysis of turbine disc[J]. Aerospace Science and Technology, 2017,70:76.

SUNNY M R, MULANI B, SANYAL S, et al. An artificial neural network residual Kriging based surrogate model for shape and size optimization of a stiffened panel[C]//54th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference,April 8-11,2013,Boston, American. 2013:1-14.

CHAN C W, WANG N, CHA K C. Aparametric study of artificial neural network as a surrogate model for heel-toe running computation[J]. Journal of Biomechanics,2007,40(2):565.

PHOLDEE N, BUREERAT S, NUANTONG W. Kriging surrogate-based genetic algorithm optimization for blade design of a horizontal axis wind turbine[J]. Computer Modeling in Engineering & Sciences, 2021,126(1):261.

VERMA M, SINGH M, SREEJETH M. Integrated Taguchi method assisted polynomial meta modelling & genetic algorithm based optimisation of a surface inset permanent synchronous motor for performance improvement[J]. IET Electrical Systems in Transportation,2022,12(1):26.

TONG Wenming, WEI Haiyang, LI Shiqi, et al. A novel multiobjective optimization method for the optimization of interior permanent magnet synchronous machines[J]. IET Electric Power Applications,2021,15(3):359.

LI Ruiye, CHENG Peng, HONG Yingyi, et al. Design synchronous generator using Taguchi-based multi-objective optimization[J]. Energies,2020,13(13):3337.

VAPNIK V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks, 1999,10(5):988.

SACKS J, WELCH W J, MITCHELL T J, et al. Design and analysis of computer experiments[J]. Statistical Science, 1989, 4(4): 409.

丁舜年.大型电机的发热与冷却[M].北京:科学出版社,1992.

A. N.鲍里先科.电机中的空气动力学与热传递[M].北京:机械工业出版社,1985.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

新型结构高速无槽永磁同步电机研究