CAJ | 학술논문

柴油发动机采用电控技术可以优化其动力性、改善燃油使用经济性和控制排放，同时也使得柴油发动机变得更加复杂，增加了故障诊断的难度性。提出了一种基于LVQ神经网络的故障诊断方法，介绍了LVQ神经网络和学习方法。以长城哈佛GW2.8TC柴油发动机电控系统为实验对象，利用金德KT600故障诊断仪采集柴油机的数据流，运用LVQ神经网络建立诊断模型，诊断结果表明利用LVQ神经网络进行故障诊断，效果比较好，具有一定的现实意义。
시유발동궤채용전공기술가이우화기동력성、개선연유사용경제성화공제배방，동시야사득시유발동궤변득경가복잡，증가료고장진단적난도성。제출료일충기우LVQ신경망락적고장진단방법，개소료LVQ신경망락화학습방법。이장성합불GW2.8TC시유발동궤전공계통위실험대상，이용금덕KT600고장진단의채집시유궤적수거류，운용LVQ신경망락건립진단모형，진단결과표명이용LVQ신경망락진행고장진단，효과비교호，구유일정적현실의의。
Diesel engine with electronic controlled technology can optimize the power performance, improve the using economy of fuel and curb emissions, but also making diesel engine become more and more complex, increasing the difficulty of fault diagnosis. Proposing a fault diagnosis method based on LVQ Neural Network, introducing LVQ Neural Network and its learning method, taking the electronic controlled system of Great Wall Harvard GW2.8TC diesel engine as the experimental object, collecting the data flow of the engine by kinder KT600 fault diagnosis instrument, using LVQ Neural Network to establish diagnosis model, the diagnosis results show that it is effective to use LVQ neural network to diagnose fault, and has a certain practical significance.