基于BP及其优化神经网络的双电机多挡AMT挡位决策研究

任永强; 伍奇胜; 袁飚

doi:10.16578/j.issn.1004.2539.2020.01.007

您当前的位置：

首页 >

文章列表页 >

基于BP及其优化神经网络的双电机多挡AMT挡位决策研究

理论研究 | 更新时间：2022-11-10

- 基于BP及其优化神经网络的双电机多挡AMT挡位决策研究
- Research of Gear Position Decision of Dual Motor Multiple Speed AMT based on BP and Its Optimization Neural Network
- 机械传动 2020年44卷第1期页码：41-46
- 作者机构：
  
  1.合肥工业大学机械工程学院，安徽合肥 230009
- 作者简介：
  
  任永强（1968— ），男，浙江东阳人，博士，副教授，研究方向为精密测量，汽车成套自动化装备及测控研究。
  伍奇胜（1992— ），男，安徽无为县人，硕士研究生，研究方向为先进制造技术。
- 基金信息：
  
  安徽省科技重大专项(17030901062);贵州省教育厅自然科学基金（青年人才成长项目）（黔教合KY字[2018]319号,黔教合KY字[2017]249）
- DOI：10.16578/j.issn.1004.2539.2020.01.007
  中图分类号：
扫描看全文
任永强,伍奇胜,袁飚.基于BP及其优化神经网络的双电机多挡AMT挡位决策研究[J].机械传动,2020,44(01):41-46.

Ren Yongqiang Wu Qisheng Yuan Biao.Research of Gear Position Decision of Dual Motor Multiple Speed AMT based on BP and Its Optimization Neural Network[J].Journal of Mechanical Transmission,2020,44(01):41-46.
任永强,伍奇胜,袁飚.基于BP及其优化神经网络的双电机多挡AMT挡位决策研究[J].机械传动,2020,44(01):41-46. DOI： 10.16578/j.issn.1004.2539.2020.01.007.

Ren Yongqiang Wu Qisheng Yuan Biao.Research of Gear Position Decision of Dual Motor Multiple Speed AMT based on BP and Its Optimization Neural Network[J].Journal of Mechanical Transmission,2020,44(01):41-46. DOI： 10.16578/j.issn.1004.2539.2020.01.007.

摘要

针对传统BP神经网络挡位决策存在的不足，利用三参数换挡规律进行算法和参数优化，得到优化后的BP神经网络。以纯电动汽车双电机多挡AMT为对象，采集试验数据，构建优化前后的神经网络，进行训练和仿真分析。对训练过程的分析说明，优化后的神经网络具有更快的学习速度；对训练后相应模型的仿真分析说明，优化后的神经网络挡位决策模型具有更高的精度。经过优化后的参数可为相应的理论研究提供参考。

Abstract

By using the three-parameter shift law， the algorithm and parameter optimization are carried out to overcome the shortcomings of traditional BP neural network in optimized BP neural network of gear position decision， and then the optimized BP neural network is obtained. Taking the dual motor multiple speeds AMT of pure electric vehicle as the object， the experimental data are collected， the neural network before and after optimization is constructed， and then the training and simulation analysis are carried out. It can be concluded that the neural network has a faster learning speed by training the neural network. By analyzing the training process， it is concluded that the optimized neural network has faster learning speed， and the optimized neural network gear position decision model has higher accuracy through simulation analysis of the corresponding model after training， and the optimized parameters provide reference value for the corresponding theoretical research.

关键词

三参数双电机多挡 BP神经网络优化挡位决策

Keywords

Three-parameterDual motor multiple speedBP neural networkOptimizationGear position decision

references

牛炳.AMT换挡规律及其自适应性研究[D].上海:上海交通大学，2009：13-18.

NIU Bing.Reserch on shift schedule and its adaptability in automated mechanical transmission[D].Shanghai:Shanghai Jiaotong University，2009:13-18.

陈清洪，秦大同，叶心.AMT汽车动态模糊神经网络三参数换挡策略研究[J].汽车工程，2010，32（6）：505-509.

CHEN Qinghong，QIN Datong，YE Xin.A study on the three parameter shift schedule of AMT vehicle based on dynamic fuzzy neural network[J].Automotive Engineering，2010，32(6):505-509.

刘振军，胡建军，李光辉，等.模糊神经网络的自动变速汽车换挡规律分析[J].重庆大学学报，2009，32（8）：897-903.

LIU Zhenjun，HU Jianjun，LI Guanghui，et al.Analysis of shift schedule for the automatic transmission vehicle based on fuzzy neural network[J].Journal of Chongqing University，2009，32(8):897-903.

邓志巧.基于神经网络的混合动力汽车档位决策研究[D].合肥：合肥工业大学，2016：7-16.

DENG Zhiqiao.Research on gear position decision of hybrid electric vehicle based on neural network[D].Hefei:Heifei University of Technology，2016:7-16.

乔晟杰，孙良，王伟达，等.基于发动机神经网络模型的矿用车动态换挡规律研究[J].机械传动，2017，41（8）：48-52.

QIAO Shengjie，SUN Liang，WANG Weida，et al.Research of the dynamic shift schedule of mining track based on neural network engine model[J].Journal of Mechanical Transmission，2017，41(8):48-52.

戴群亮，赵丁选.基于BP神经网络优化算法的工程车辆挡位判断的训练及仿真[J].机械工程学报，2002，38（11）：124-127.

DAI Qunliang，ZHAO Dingxuan.Training and simulation on gear position decision for vehicle based on optimal algorithm of BP network[J].Chinese Journal of Mechanical Engineering，2002，38(11):124-127.

IAN G，YOSUHA B，AIRON C.Deep learning:adaptive computation and machine learning series[M].Cambridge:The MIT press，2016：105-106.

MAN Z，LEE K，WANG D H，et al.A new robust training algorithm for a class of single-hidden layer feedforward neural networks[J].Neurocomputing，2011，74（16）:2491-2501.

陈伟根，潘翀，云玉新，等.基于改进小波神经网络算法的电力变压器故障诊断方法[J].仪器仪表学报，2008，29（7）：1489-1493.

CHEN Weigen，PAN Chong，YUN Yuxin，et al.Fault diagnostic method for power transformer based on improved wavelet neural network algorithm[J].Chinese Journal of Scientific Instrument，2008，29(7):1489-1493.

HE K M，ZHANG X Y，REN S Q，et al.Delving deep into rectifiers:Surpassing human-level performance on image net classification[C]//2015 IEEE International Conference on Computer Vision，December7-13，2015，Santiago.New York:IEEE，2015:1026-1034.

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

暂无数据