基于BP神经网络的发动机故障诊断研究

Study of Engine Fault Diagnosis Based on BP Neural Network

汽车发动机故障占整车的百分之四十以上,所以研究故障诊断系统实现对发动机故障的准确、快速诊断对整个汽车行业具有重要的意义。针对目前国内电控发动机故障诊断所存在的问题,BP网络能够很好地运用于发动机的故障诊断,利用发动机故障诊断的专家经验做出故障-原因样本训练集训练BP网络(BP网络的函数逼近的运用),再把故障数值输入到已经训练好的神经网络实现故障的诊断(BP网络分类的运用)。

Electronic-controlled engine,has high failure rate,which is accounted for more than forty percent of the vehicle,so it has the vital significance to the fault diagnosis system to realize accuracy and rapid diagnosis of engine failure of the whole automobile industry.This paper is in view of the present domestic problems existing in fault diagnosis of electronically controlled engines,the BP network can be well applied to the fault diagnosis of engine,using engine fault diagnosis expert experience to make sample training to set training BP network reason（the use of function approximation of BP network）,then the fault number can be input to neural network which has been trained to realize fault diagnosis（the use of BP network classification）.