采用代理模型的液力变矩器性能优化设计

王安麟; 赵一鸣; 李晓田; 曹国祥

doi:10.7652/xjtuxb202010001

您当前的位置：

首页 >

文章列表页 >

采用代理模型的液力变矩器性能优化设计

更新时间：2025-07-09

- 采用代理模型的液力变矩器性能优化设计
- An Optimi-ation Design for Performance of Hydraulic Torque Converters Based on Surrogate Model
- 西安交通大学学报 2020年54卷第10期页码：1-8
- 作者机构：
  
  同济大学机械与能源工程学院,上海,201804
- 作者简介：
- 基金信息：
  
  : 2020-01-02。作者简介: 王安麟(1954—),男,教授,博士生导师。基金项目: 国家重点研发计划资助项目(2018YFC0810203)
- DOI：10.7652/xjtuxb202010001
  中图分类号： TP249
- 网络首发：2020-10-10，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
王安麟, 赵一鸣, 李晓田, 等. 采用代理模型的液力变矩器性能优化设计[J]. 西安交通大学学报, 2020,54(10):1-8.

An Optimi-ation Design for Performance of Hydraulic Torque Converters Based on Surrogate Model[J]. 2020, 54(10): 1-8.
王安麟, 赵一鸣, 李晓田, 等. 采用代理模型的液力变矩器性能优化设计[J]. 西安交通大学学报, 2020,54(10):1-8. DOI： 10.7652/xjtuxb202010001.

An Optimi-ation Design for Performance of Hydraulic Torque Converters Based on Surrogate Model[J]. 2020, 54(10): 1-8. DOI： 10.7652/xjtuxb202010001.

摘要

为解决液力变矩器性能与叶片形态变量间的复杂映射问题

提高设计效率与精度

提出了采用代理模型取代三维流体计算方法

并结合寻优算法对液力变矩器的性能进行优化设计的方案。首先

在标定基于CFD仿真的液力变矩器性能响应结果前提下

利用正交设计方法

获得液力变矩器性能的大自由度仿真试验数据; 然后

分别设计响应面以及神经网络2种代理模型

获取变矩器叶片角变量与其性能的映射关系

比较分析其建模效率和精度; 最后

以某型号双涡轮液力变矩器启动变矩比及低速比区最高效率最大化为设计目标

分别通过2种代理模型应用NSGA-Ⅱ算法获取优化方案。仿真结果表明:在同一试验数据下

响应面模型的建模效率较高

神经网络模型的变量设计空间外延性较好; 采用神经网络模型优化得到的液力变矩器模型与依照出厂参数设计的液力变矩器模型相比

其启动变矩比及低速比区最高效率分别提高了14.27%和10.24%

与采用响应面模型优化得到的液力变矩器模型相比分别提高了4.36%和1.53%。

Abstract

An optimi-ation design for the performance of hydraulic torque converter(HTC)by using a surrogate model to replace the numerical calculation of 3D fluid field method and to combine with optimi-ation algorithm is carried out to solve the complex mapping problem between the performance of HTC and the morphological variable of blade

and to improve the design efficiency and accuracy. Firstly

it bases on the premise of calibrating the performance response of the HTC based on CFD simulation that an orthogonal design method is used to obtain simulation test data with large-degree-of-freedom for the performance of the HTC. Then

a response surface model and a neural network model are designed to construct the mapping relationship between the HTC's blade angles and their performance

and the modeling efficiency and accuracy are compared and analy-ed. Finally

a certain type of dual turbine torque converter is taken as a research object and its starting torque ratio and the maximum efficiency

关键词

Keywords

references

陈凯, 吴光强. 基于遗传算法的液力变矩器与发动机匹配的多目标优化 [J]. 汽车工程, 2014, 36(5): 532-536.

CHEN Kai, WU Guangqiang. Multi-objective optimization of matching hydraulic torque converter and engine based on genetic algorithm [J]. Automotive Engineering, 2014, 36(5): 532-536.

DONG Yu, KORIVI V, ATTIBELE P, et al. Torque converter CFD engineering: part I torque ratio and K factor improvement through stator modifications [C]∥SAE 2002 World Congress. New York, USA: SAE International, 2002: 20122815243456.

KIM G, JANG J. Effects of stator shapes on hydraulic performances of an automotive torque converter with a squashed torus [C]∥SAE 2002 World Congress. New York, USA: SAE International, 2002: 201228152434 59.

刘城, 潘鑫, 闫清东, 等. 基于DOE及RSM的液力变矩器叶片数对性能的影响及优化 [J]. 北京理工大学学报, 2012, 32(7): 689-693.

LIU Cheng, PAN Xin, YAN Qingdong, et al. Effect of blade number on performance of torque converter and its optimization based on DOE and response surface methodology [J]. Transactions of Beijing Institute of Technology, 2012, 32(7): 689-693.

李兴泉, 邓兆祥, 章竟成, 等. 基于响应面的液力变矩器叶片优化设计 [J]. 华南理工大学学报(自然科学版), 2011, 39(11): 149-154.

LI Xingquan, DENG Zhaoxiang, ZHANG Jingcheng, et al. Optimized design of blade of hydraulic torque converter based on response surface method [J]. Journal of South China University of Technology(Natural Science Edition), 2011, 39(11): 149-154.

韩克非, 吴光强, 王立军. 基于正交设计的泵轮叶栅关键参数对液力变矩器的性能影响优化分析 [J]. 中国电机工程学报, 2010, 30(35): 65-70.

HAN Kefei, WU Guangqiang, WANG Lijun. Performance optimization analysis of the effects of pump cascade key parameters on torque converter based on orthogonal design [J]. Proceedings of the CSEE, 2010, 30(35): 65-70.

王安麟, 孟庆华, 曹岩, 等. 液力变矩器的叶片数神经网络模型 [J]. 西安交通大学学报, 2015, 49(7): 11-16.

WANG Anlin, MENG Qinghua, CAO Yan, et al. Blade number neural networks model of hydraulic torque converter [J]. Journal of Xi'an Jiaotong University, 2015, 49(7): 11-16.

马文星. 液力传动理论与设计 [M]. 北京: 化学工业出版社, 2004: 41-105.

喻伯平, 李高华. 谢亮, 等. 基于代理模型的旋翼翼型动态失速优化设计 [J]. 浙江大学学报(工学版), 2020, 54(4): 833-842.

YU Boping, LI Gaohua, XIE Liang, et al. Dynamic stall optimization design of rotor airfoil based on surrogate model [J]. Journal of Zhejiang University(Engineering Science), 2020, 54(4): 833-842.

王钊, 俞建阳, 陈浮. 基于Kriging代理模型的DBD等离子体控制叶顶泄漏流动研究 [J]. 工程热物理学报, 2020, 41(3): 573-580.

WANG Zhao, YU Jianyang, CHEN Fu. Numerical investigation based on kriging surrogate model of tip leakage flow controlled by DBD plasma [J]. Journal of Engineering Thermophysics, 2020, 41(3): 573-580.

王艾伦, 刘乐, 刘庆亚. 基于Kriging代理模型的拉杆组合转子强度可靠性研究 [J]. 工程设计学报, 2019, 26(4): 433-440.

WANG Ailun, LIU Le, LIU Qingya. Research on strength reliability of pull rod combined rotor based on Kriging surrogate model [J]. Chinese Journal of Engineering Design, 2019, 26(4): 433-440.

郭广强, 张人会, 陈学炳, 等. 低比转速离心叶轮的POD代理模型优化方法 [J]. 华中科技大学学报(自然科学版), 2019, 47(7): 50-55.

GUO Guangqiang, ZHANG Renhui, CHEN Xuebing, et al. Optimization method for low specific speed centrifugal impeller based on POD surrogate model [J]. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2019, 47(7): 50-55.

张泽斌, 张鹏飞, 郭红, 等. Kriging序贯设计方法在滑动轴承优化中的应用 [J]. 哈尔滨工业大学学报, 2019, 51(7): 178-183.

ZHANG Zebin, ZHANG Pengfei, GUO Hong, et al. Implementation of Kriging model based sequential design on the optimization of sliding bearing [J]. Journal of Harbin Institute of Technology, 2019, 51(7): 178-183.

王安麟, 孟庆华, 韩继斌. 基于拉丁超立仿真试验设计的双涡轮变矩器性能分析 [J]. 中国工程机械学报, 2015, 13(4): 295-298.

WANG Anlin, MENG Qinghua, HAN Jibin. Dual-turbine torque converter performance analysis based on Latin hypercube simulation experiment design [J]. Chinese Journal of Construction Machinery, 2015, 13(4): 293-298.

王安麟, 杨智雄, 李文嘉. 基于主效应分析的变矩器叶片角变量空间优化 [J]. 华南理工大学学报(自然科学版), 2018, 46(2): 14-21.

WANG Anlin, YANG Zhixiong, LI Wenjia. Optimization research for variable space of torque converter based on main effect analysis of blade angles [J]. Journal of South China University of Technology(Natural Science Edition), 2018, 46(2): 14-21.

李飞. 代理模型预测研究及其在叶轮机械中的应用 [D]. 辽宁大连: 大连理工大学, 2014: 46-50.

窦毅芳, 刘飞, 张为华. 响应面建模方法的比较分析 [J]. 工程设计学报, 2007(5): 359-363.

DOU Yifang, LIU Fei, ZHANG Weihua. Comparative analysis of response surface modeling methods [J]. Chinese Journal of Engineering Design, 2007(5): 359-363.

李明军, 王均星, 王亚洲. 基于改进粒子群优化算法和极限学习机的混凝土坝变形预测 [J]. 天津大学学报, 2019, 52(11): 1136-1144.

LI Mingjun, WANG Junxing, WANG Yazhou. Deformation prediction of concrete dam based on improved particle swarm optimization algorithm and extreme learning machine [J]. Journal of Tianjin University, 2019, 52(11): 1136-1144.

王志明. Kolmogorov定理的一个变形 [J]. 数学杂志, 2008, 28(4): 393-398.

WANG Zhiming. A transformation to the Kolmogorov theorem [J]. Journal of Mathematics, 2008, 28(4): 393-398.

DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.

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

相变冷却换热器动态热响应降阶预测方法研究

采用动力学模态分解和长短期记忆网络的压缩空气储气装置流场动态预测方法

新能源汽车热管理系统协同优化策略

高超声速飞行器干扰补偿与解耦最优反步控制策略

面向强化装配界面接触热性能的导热特性异质化设计方法