基于粗糙集理论的柴油机神经网络故障诊断研究

介绍了粗糙集理论的核心内容 ,给出了基于 kohonen神经网络的连续属性值离散化方法。应用粗糙集理论对反映柴油机运行工况的特征参数进行了属性简化 ,剔除了不必要的属性。研究了 RBF神经网络故障诊断模型及学习规则 ,给出了基于粗糙集理论的 RBF神经网络故障诊断原理和步骤。通过对柴油机供油系统柱塞磨损故障的自动分类和诊断 ,表明该系统能有效地减少神经网络的输入节点数 ,克服了神经网络规模过于庞大及分类识别速度慢等缺点。

The Research of Diesel Engine Fault Diagnosis with ANN Based on Rough Sets Theory

The core content of rough sets theory is introduced and the discrete method of continuous attribute value based on kohonen neural network is given.Rough sets theory is used to simplify attribute parameter reflecting operating conditions of diesel engine and in which unnecessary properties are eliminated.Fault diagnosis model and learning rule of RBF ANN is studied.Fault diagnosis principle and step of RBF ANN based on rough sets theory is given.Through automatic fault classification and diagnosis for plunger abrasion fault in fuel injection system of diesel engine,the example shows that this system reduces input node number and overcomes some shortcomings,such as neural network scale is too large and the rate of classification is slow.