期刊文献+

基于遗传神经网络废气分析的汽车故障诊断方法研究

Studies on the Automotive Diagnosis Method-the Generic-NN Based Exhaust Gas Analysis
下载PDF
导出
摘要 设计了神经网络诊断系统,并用于融合分析废气含量、发动机转速、氧传感器信号及某些工作状态信息诊断汽车故障。设计方法为应用遗传算法的复制、交换、变异过程代替BP网络的反向传播过程,并对遗传算法进行改进研究。实践证明,这种基于遗传神经网络方法的故障诊断系统具有收敛速度快、推广性能强的特点,提高了汽车故障诊断系统的效率和准确性。 A neural network diagllosis system is designed to integrate and analyze contents of exhaust gas,engine speed.oxygen sensor signal and some work status information and then to diagnose automotive failures.Its design method is to substitute the copy,interchange and variatiou processes of the generie algorithm for the reverse propagation process of the BP network.and improvement of the generic algorithm is also studied.It is proved that the generic-NN based failure diagnosis system converges fast and is easy to be used widely,and it improves efficiency and precision of automotive diagnosis system.
作者 张蕾 董恩国
出处 《汽车技术》 北大核心 2005年第9期36-38,共3页 Automobile Technology
关键词 排放 神经网络 故障 诊断 Emission,Neural network,Failure,Diagnosis
  • 相关文献

参考文献3

  • 1陈家瑞.汽车构造[M].北京:人民交通出版社,2000..
  • 2倪远平,李一民,周建华,杨剑.自适应遗传神经算法及故障识别[J].计算机工程与应用,2003,39(35):63-65. 被引量:5
  • 3Hush D R, Home B G. Progress in Supervised Neural Networks. IEEE Trans on Signal Processing Magazine, 2000 ( 1 ): 8~39

二级参考文献4

  • 1[1]Holland J H.Adaptation in natural and artificial systems[M].The University of Michigan Press, 1975
  • 2[2]Rudolph G.Convergence Analysis of Canonical Genetic Algorithms[J].IEEE Trans on Neural Networks, 1999; 5 ( 1 ): 96~101
  • 3[3]Hush D R,Horne B G.Progress in supervised neural networks[J].IEEE Trans on Signal Processing Magazine,2000-01:8~39
  • 4[4]Maniezzo V.Genetic evolution of the topology and weight distribution of neural network[J].IEEE Trans on Neural Network, 1999;5( 1 ):39~53

共引文献18

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部