基于粗糙集的模糊神经网络在故障诊断中的应用

文章将粗糙集理论、模糊逻辑推理和神经网络等方法相结合,提出一种基于粗糙集的模糊神经网络理论的复杂机械的故障诊断方法。该方法应用模糊逻辑推理建立故障诊断决策表,采用粗糙集理论对故障样本数据属性约简,将获取的主要特征属性输入到神经网络中进行训练学习,然后把检测数据输入到诊断系统中进行检测。检测结果表明,该方法在船舶柴油机的故障诊断中是有效的。

Application of rough set based fuzzy neural network in fault diagnosis

Based on the methods of rough set theory,fuzzy logic reasoning and neural network,a fault diagnosis method for complex machinery using rough set based neural network theory is presented in this paper.This method uses the fuzzy logic reasoning to establish the decision table of fault diagnosis,and uses the rough set theory to reduce the attributes of the fault sample data.The main feature attributes obtained are inputted into the neural network for training,and then the test data are inputted into the diagnosis system for testing.The test results indicate that the presented method is effective in the fault diagnosis of marine diesel engine.