基于粗糙集的汽油机失火故障神经网络诊断

Gasoline Engine Misfire Fault Diagnosis Based on Rough Sets Theory and Neural Network

汽油机失火现象易导致汽车排放恶化和动力性下降,而失火现象复杂难以诊断,因此失火故障诊断已成为汽车诊断检测研究的热点问题。该文应用粗糙集,提出了一种利用汽油机排气中废气排放体积分数值和汽油机工况参数诊断汽油机失火故障的方法,对汽油机失火故障、废气排放成份及工况参数等之间的关系进行了属性简化,剔除了不必要的属性。在时代超人发动机上进行了有失火故障和无故障排气成分检测对比试验,利用试验数据和内燃机工况参数,建立了一种基于粗糙集和RBF神经网络的内燃机失火故障诊断模型。应用试验数据和MATLAB软件对模型进行学习训练,将训练好的神经网络模型应用于内燃机失火故障的诊断。结果表明,该模型能正确诊断内燃机失火故障,可以简化神经网络结构,减少神经网络的输入节点数,提高系统诊断效率。

Gasoline engine burning phenomenon is easy to cause the deterioration of vehicle emission and dynamic performance, and the fire is difficult to diagnose, so the diagnosis of fire has become a hot issue in the research of vehicle diagnosis and detection. A method for diagnosis of misfire fault in internal combustion engine based on exhaust density of HC, CO2, 02 and the engine＇s work parameters are presented in this paper. Rough sets theory is used to simplify attribute parameter reflecting exhaust emission and conditions of internal combustion engine and in which unnecessary properties are eliminated. The engine＇s work parameters, exhaust emission with misfire fault and without fault are tested by the experimentation of Super Engine. A diagnosis model which deseribing the relationship between the misfire degree and the internal combustion engine＇s exhaust emission and work parameters is established based on rough sets theory and RBF neural network. The model reduces the sample size, optimizes the neural network, increases the diagnosis correctness. The model is also trained by test data and MATLAB software. The model has been used to diagnose internal emnbustion engine misfire fault, the result illustrates that this model can diagnose the misfire correctly, simplify the structure of neural network, reduce input node number, improve the diagnosis efficiency.