基于模糊神经网络的车用发动机智能故障诊断系统  

FNN-based Intelligent Fault Diagnosis System for Vehicle Engine

作　　者：李国勇[1] 杨庆佛[2] 

机构地区：[1]太原理工大学信息工程学院,山西省太原市030024 [2]太原理工大学机械工程学院,山西省太原市030024

出　　处：《系统仿真学报》2007年第5期1034-1037,共4页Journal of System Simulation

基　　金：山西省青年科技研究基金项目(20011017)

摘　　要：针对车用发动机故障多,且具有模糊性和复杂性的特点,提出了一种基于模糊神经网络的车用发动机故障诊断专家系统。该设计结合了神经网络、模糊逻辑以及专家系统的优点,在利用神经网络对电控汽油机进行故障诊断的基础上,引入模糊逻辑的概念,采用模糊隶属函数来描述这些故障的程度,系统推理速度快,容错能力强。并运用MATLAB的图形用户界面(GUI)功能,设计了一种全新的人机交互界面,增加系统的易操作性,方便用户使用,更新系统简单直观。According to the fuzziness and complexity of a variety of vehicle engine malfunctions, a kind of FNN-based intelligent fault diagnosis system was put forward. The system has the characteristic of fast inference speed, strong fault-tolerance ability by combine the advantages of the neural networks, fuzzy logic and expert system. Fuzzy logic concept was injected on the basis that neural network makes fault diagnosis to electronic control gasoline engine and applying fuzzy membership functions to depict the fault extent. By applying GUI function of MATLAB, a new man-machine interaction interface was designed. It has a great improvement in convenient operation, facilitates to use and is simply and intuitively updated.

关 键 词：车用发动机 故障诊断 模糊神经网络 专家系统 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP206.3[自动化与计算机技术—控制科学与工程]