基于改进的BP神经网络的柴油发动机故障诊断  

Research of diesel engine fault diagnosis based on improved BP neural network

作　　者：巴寅亮[1,2] 王书提 谢鑫[1,2] 

机构地区：[1]新疆农业大学机械交通学院 [2]新疆农业工程装备创新设计重点实验室,乌鲁木齐830052

出　　处：《工业仪表与自动化装置》2015年第3期94-97,102,共5页Industrial Instrumentation & Automation

摘　　要：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GW2.8TC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。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.

关 键 词：柴油发动机 高压共轨 BP神经网络 LM算法 电控系统 故障诊断 

分 类 号：TK428[动力工程及工程热物理—动力机械及工程] TP183[自动化与计算机技术—控制理论与控制工程]