【摘要】 发动机出现故障的机率较高,一般占整车故障的40%左右。研究发动机故障诊断专家系统,可以及时、准确进行故障定位,提高工作效率。但是传统专家系统存在推理效率低、自学习能力差等缺点。本研究将模糊逻辑和传统神经网络相结合形成模糊神经网络,建立了模糊神经网络(FNN)故障诊断模型,并将该模型应用于发动机故障诊断,优势互补,提高了专家系统的推理效率和自学习能力,其性能高于传统的BP网络。更多还原

【Abstract】 Engines have a high chance of failure,usually accounting for about 40% of vehicle failures.This expert system for engine troubleshooting locates problems in a timely and accurate manner with a view to enhancing efficiency by improving the traditional expert system that features inefficient inference and poor self-learning capability.The fuzzy logic and traditional neural networks are combined to form fuzzy neural networks and establish a model of fuzzy neural network(FNN) of fault diagnosis.When applied to engine fault diagnosis,this model shows complementary advantages to effectively solve these problems,and works more effectively than the traditional BP network.更多还原