基于集成模糊神经网络的柴油机故障诊断

Fault Diagnosis of Diesel Engine Based on Integrated Fuzzy Neural Network

柴油机是一个极为复杂的系统。在柴油机运行时,若发生故障,故障产生的原因以及故障发生的部位,大多数是模糊不清的。为研究柴油机故障部位以及故障程度,本文提出一种基于集成模糊神经网络的柴油机故障诊断方法,利用神经网络的对故障特征的提取能力以及模糊算法的推理能力,将诊断问题分解成若干个子问题到多个模糊神经网络上,进行独立训练,最后通过集成实现故障诊断。结果表明,证明该方法可以诊断柴油机故障以及故障的程度。

A diesel engine is an extremely complex system.When a diesel engine is running,if a fault occurs,the cause of the fault and the location of the fault are mostly ambiguous.In order to study the fault location and the degree of fault of the diesel engine,this paper proposes a diesel engine fault diagnosis method based on integrated fuzzy neural network.Using the neural network’s ability to extract fault features and the reasoning ability of the fuzzy algorithm,the diagnostic problem is decomposed into several sub problems Independent training is performed on multiple fuzzy neural networks,and finally fault diagnosis is achieved through integration.The results show that the method can be used to diagnose diesel engine faults and the degree of faults.