自然科学版 英文版
自然科学版 英文版
自然科学版 英文版

您目前所在的位置:首页 - 期刊简介 - 详细页面

中南大学学报(自然科学版)

Journal of Central South University

第41卷    第4期    总第194期    2010年8月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7207(2010)04-1398-07
基于神经网络的混凝土泵车发动机万有特性建模与工况优化
贺尚红,杨昀梓

(长沙理工大学 汽车与机械工程学院,湖南长沙,410114)

摘 要: 将底盘传动系纳入发动机动力系统,提出混凝土泵车发动机万有特性模型的现场测试方法。利用BP神经网络建立某型号混凝土泵车发动机的万有特性模型,并以此为依据对该型号混凝土泵车工况进行优化,获得4种工况下与液压系统最佳匹配的发动机转速。试验结果表明:利用BP神经网络建立的某型号混凝土泵车发动机万有特性模型最大相对误差仅为2.31%;建模方法简单、精度高,以该模型为依据优化后的发动机工况节油效果明显,最大可节油11.67%。

 

关键字: 混凝土泵车;万有特性模型;神经网络;工况优化

Modeling of universal characteristics and optimization of operating conditions of concrete pump truck based on neural network
HE Shang-hong, YANG Yun-zi

School of Automotive and Mechanical Engineering, Changsha University of Science & Technology,
Changsha 410114, China

Abstract:Combining the transmission system with engine, a new on-site test method of universal characteristics of power system for concrete pump was put forward. With BP artificial neural network, the model of universal characteristics of a concrete pump truck engine was established, and the optimal matched speed between engine and hydraulic system of a concrete pump truck was acquired in four different working conditions. The experimental results show that the maximum relative error of specific fuel consumption between expected value and measured value is about 2.31%. The neural network is a simple and accurate method for modeling universal characteristics of engine. The maximum percentage of fuel consumption saving is 11.67% under optimal operating conditions.

 

Key words: concrete pump truck; model of universal characteristics; neural network; optimization of operating conditions

中南大学学报(自然科学版)
  ISSN 1672-7207
CN 43-1426/N
ZDXZAC
中南大学学报(英文版)
  ISSN 2095-2899
CN 43-1516/TB
JCSTFT
版权所有:《中南大学学报(自然科学版、英文版)》编辑部
地 址:湖南省长沙市中南大学 邮编: 410083
电 话: 0731-88879765 传真: 0731-88877727
电子邮箱:zngdxb@csu.edu.cn 湘ICP备09001153号