CAJ | 학술논문

柴油发动机采用高压共轨燃油喷射技术，提高了柴油机的综合性能，但高压共轨柴油机电控系统比较复杂，增大了柴油机故障诊断的难度。该文介绍了BP神经网路及LM算法，并利用改进的BP神经网络对发动机电控系统故障进行诊断研究。以长城哈佛GW2.8 TC发动机为实验对象，让发动机在怠速状态下，对发动机进行故障设置，利用金德KT600故障诊断仪采集发动机的故障数据流，运用改进的BP神经网络建立诊断模型，诊断结果表明改进的BP神经网络的收敛速度快，运用改进的BP网络诊断柴油机电控系统故障是行之有效的。
시유발동궤채용고압공궤연유분사기술，제고료시유궤적종합성능，단고압공궤시유궤전공계통비교복잡，증대료시유궤고장진단적난도。해문개소료BP신경망로급LM산법，병이용개진적BP신경망락대발동궤전공계통고장진행진단연구。이장성합불GW2.8 TC발동궤위실험대상，양발동궤재태속상태하，대발동궤진행고장설치，이용금덕KT600고장진단의채집발동궤적고장수거류，운용개진적BP신경망락건립진단모형，진단결과표명개진적BP신경망락적수렴속도쾌，운용개진적BP망락진단시유궤전공계통고장시행지유효적。
Diesel engine with high pressure common rail fuel injection technology, improves the com-prehensive performance of diesel engine, but the high pressure common rail diesel engine electronic con-trolled system is more complex, increasing the difficulty of diesel engine fault diagnosis. This paper intro-duce the BP neural network and LM algorithm, and carry on the research on fault diagnosis of engine e-lectronic controlled system based on improved BP neural network. Taking the Great Wall Harvard GW 2. 8TC engine as the experimental object, keeping the engine at idle speed condition, setting up some fault assumption for the engine, collecting the failure data flow of the engine by kinder KT600 fault diag-nosis instrument, using improved BP neural network to establish diagnosis model. The diagnosis results show that the convergence rate of improved BP neural network is quickly, it is effective to diagnose elec-tronic controlled system fault of diesel engine by improved BP neural network.