基于车联网的汽车发动机远程故障诊断研究

Research on Remote Fault Diagnosis of Vehicle Engine based on Vehicle Interconnection

针对当前汽车发动机远程故障诊断需求,结合当前的智能算法与通信技术,提出一种基于车联网与改进神经网络的发动机故障诊断系统。为实现研究的目的,首先就当前车内网故障采集传输与故障诊断存在的问题,利用车联网对发动机故障采集进行搭建;其次,为更好地提取汽车发动机故障特征,采用小波去噪与神经网络结合的方式,通过小波去噪完成对故障特征的预处理,以提高故障特征提取的效果,然后利用神经网络算法完成对故障特征的识别,最后通过搭建试验平台,以火花塞点火产生的波形为例,对方案进行了试验验证,结果表明本试验方案的识别正确率高于传统的OBD识别方法。

In view of the current demand for remote fault diagnosis of automotive engines,combined with the current intelligent algorithm and communication technology,an engine fault diagnosis system based on vehicle network and improved neural network is proposed.In order to realize the purpose of this study,first of all,the problems existing in the fault acquisition,transmission and fault diagnosis of the current internal network fault are built,and the engine fault acquisition is built with the vehicle network.Secondly,in order to better extract the characteristics of the automobile engine fault,the wavelet denoising and neural network is used to accomplish the fault feature preprocessing,so as to improve the effect of fault feature extraction.Then the neural network algorithm is used to identify the fault features.Finally,the experimental platform is built and the waveform generated by spark plug ignition is used as an example to verify the above scheme.The results show that the recognition rate of the test scheme is higher than that of the traditional method of OBD recognition.