China Mechanical Engineering ›› 2013, Vol. 24 ›› Issue (11): 1521-1524,1530.

Previous Articles     Next Articles

Research on Vehicle Driving Situation Identification (Part Ⅱ)——Based on Fuzzy-neural Network

Tian Yi1,2,3;Zhang Xin2;Zhang Xin2;Zhang Liang2   

  1. 1.The Academy of Armored Forces Engineering,Beijing,100072
    2.Beijing Jiaotong University,Beijing,100044
    3.Railway Management Bureau of JSLC,Jiuquan,Gansu,732750
  • Online:2013-06-10 Published:2013-06-04
  • Supported by:
     
    The National Key Technology R&D Program(No. 2011BAG04B00);
    Natural Science Foundation of Beijing(No. 4122062)

汽车运行状态识别方法研究(二)——基于模糊神经网络的识别方法

田毅1,2,3;张欣2;张昕2;张良2   

  1. 1.装甲兵工程学院,北京,100072
    2.北京交通大学,北京,100044
    3.酒泉卫星发射中心铁路管理处,酒泉,732750
  • 基金资助:
    “十二五”国家科技支撑计划资助项目 (2011BAG04B00);北京市自然科学基金资助项目(4122062);北京理工大学电动车辆国家工程实验室开放基金资助项目(2012-NELEV-03);北京交通大学基本科研业务费资助项目(M12JB00070) 
    The National Key Technology R&D Program(No. 2011BAG04B00);
    Natural Science Foundation of Beijing(No. 4122062)

Abstract:

By using the best subset of the vehicle driving pattern, a vehicle driving situation identification model was created herein, which was based on the fuzzy-neural network. Identifying vehicle driving cycle on the urban way and highway of the Beijing, Shanghai, Guangzhou and Wuhan,the results are: except the accuracy of Beijing urban way is as 82.67%, the accuracy of other vehicle driving cycles is as 100%; and the accuracy of Beijing urban way and highway on-road driving situation is as 89.08%.

Key words: driving situation identification, driving pattern parameter, fuzzy-neural network

摘要:

采用汽车运行状态特征参数的最优子集建立了一个基于模糊神经网络的汽车运行状态识别模型。对北京、上海、广州、武汉的主干道和快速路运行工况进行了识别,计算结果为:除对北京市主干道运行工况的识别准确度为82.67%外,对其余运行工况的识别准确度都为100%;对北京市主干道和快速路汽车实际运行车速的识别准确度为89.08%。

关键词: 运行状态识别, 运行状态特征参数;模糊神经网络

CLC Number: