汽车运行状态识别方法研究（一）——特征参数选择

中国机械工程 ›› 2013, Vol. 24 ›› Issue (09): 1258-1263.

汽车运行状态识别方法研究（一）——特征参数选择

田毅1,2,3;张欣2;张昕2;张良2

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

出版日期:2013-05-10 发布日期:2013-05-16
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）

Research on Vehicle Driving Situation Identification(Part Ⅰ)——Driving Pattern Selection

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

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:2013-05-10 Published:2013-05-16
Supported by:
The National Key Technology R&D Program（No.2011BAG04B00）;
Natural Science Foundation of Beijing（No. 4122062）

摘要/Abstract

摘要：

提出了一种将自适应遗传算法和浮动搜索算法相结合的混合搜索算法。首先通过自适应遗传算法对汽车运行状态特征参数之间的边界进行搜索，再依据获得的边界得出汽车运行状态特征参数全集特征;然后以浮动搜索算法对全集进行搜索，进而选择出汽车运行状态特征参数最优子集。在混合搜索算法中，浮动搜索的起始点采用个体间遗传的方式，使其始终保持最优，最大程度避免无效搜索，缩短搜索时间。通过计算得到了由8个参数组成的汽车运行状态特征参数最优子集。

关键词: 混合搜索算法, 浮动搜索, 自适应遗传算法, 最优子集

Abstract:

A hybrid search algorithm was built herein, which combined effectively the genetic algorithm and the floating search algorithm. This hybrid search algorithm firstly searched the boundary among driving pattern parameters through adaptive genetic algorithm and got the universal set of vehicle driving patterns; then the best subset was selected by using the floating search algorithm. In the hybrid search algorithm, the start point of floating selection algorithm was the best, which was chosen from each cycle of genetic algorithm calculation. So most of the invalid searches can be avoided and the searching time decreased, too. A best driving pattern subset is obtained which includes eight parameters.

Key words: hybrid search algorithm, floating search algorithm, adaptive genetic algorithm, best subset

中图分类号:

U469.74

田毅1, 2, 3, 张欣2, 张昕2, 张良2. 汽车运行状态识别方法研究（一）——特征参数选择[J]. 中国机械工程, 2013, 24(09): 1258-1263.

TIAN Yi-1, 2, 3, ZHANG Xin-2, ZHANG Cuan-2, ZHANG Liang-2. Research on Vehicle Driving Situation Identification(Part Ⅰ)——Driving Pattern Selection[J]. China Mechanical Engineering, 2013, 24(09): 1258-1263.

参考文献

[1]Lin C, Jeon S, Peng H, et al. Driving Pattern Recognition for Control of Hybrid Electric Trucks[J]. Vehicle System Dynamics, 2004, 42(1/2): 41-57.
[2]Langari R, Won J S. Intelligent Energy Management Agent for a Parallel Hybrid Vehicle—Part I: System Architecture and Design of the Driving Situation Identification Process[C]//IEEE Transaxtions on Vehicular Technology. USA: IEEE, 2005: 925-935.
[3]罗玉涛，胡红斐，沈继军. 混合动力电动汽车行驶工况分析与识别[J]. 华南理工大学学报（自然科学版），2007，35(6)：8-13.
Luo Yutao,Hu Hongfei,Shen Jijun. Analysis and Recognition of Running Cycles of Hybrid Electric Vehicle[J]. Journal of South China University of Technology (Natural Science Edition)，2007，35(6)：8-13.
[4]周楠，王庆年，曾小华. 基于工况识别的HEV自适应能量管理算法[J].湖南大学学报（自然科学版），2009，36(9)：37-41.
Zhou Nan，Wang Qingnian，Zeng Xiaohua. Adaptive HEV Energy Managemen Algorithms Based on Drive-cycle Recognition[J]. Journal of Hunan University(Natural Sciences), 2009，36(9)：37-41.
[5]Zhang Liang, Zhang Xin, Tian Yi, et al.Intelligent Energy Management for Parallel HEV Based on Driving Cycle Identification using SVM[C]//The Institution of Engineering and Technology, Proceedings of the 2009 International Workshop on Information Security and Application.Oulu: IWISA, 2009: 457-460.
[6]田毅，张欣, 张昕,等. 基于神经网络工况识别的HEV模糊控制策略[J]. 控制理论与应用, 2011，28(3)：363-369.
Tian Yi, Zhang Xin, Zhang Xin,et al. HEV Fuzzy Control Strategy Based on the Neural Network Identification of Driving Cycle[J]. Control Theory & Applications, 2011，28(3)：363-369.
[7]Ericsson E. Independent Driving Pattern Factors and Their Influence on Fuel-use and Exhaust Emission Factors[J]. Transportation Research Part D, 2001, 6(4)：325-345.
[8]魏志成.基于遗传算法的鲁棒数字图像水印研究[D].天津：天津大学, 2007.
[9]曾喻江. 基于遗传算法的卫星星座设计[D]. 武汉：华中科技大学， 2007.
[10]Somol P, Pudil P, Novovicova J,et al. Adaptive Floating Search Methods in Feature Selection[J]. Pattern Recognition Letters, 1999,20(3):1157-1163.
[11]Songyot N, David P C. An Improvement on Floating Search Algorithms for Feature Subset Selection[J]. Pattern Recognition,2009,42(4):1932-1940.