摘要
对粗糙集的属性离散化和约简算法进行了研究,提出了一种基于粗糙集与神经网络相融合的故障诊断方法。首先提出一种优化NS断点集的方法用于离散化决策表,然后采用差别矩阵和差别函数直接求取最小属性约简集,最后采用神经网络对JZQ-250齿轮箱进行故障诊断,并比较了约简前后特征集的诊断结果,实验表明粗糙神经网络能够简化网络结构,有较强的容错和抗干扰能力,且迭代次数少,收敛速度快,诊断精度高,是一种有效的齿轮箱故障诊断方法。
A method of combining the rough sets and neural network based on the condition attributes discretiza- tion and reduction algorithm is proposed to fault diagnosis. Firstly the method for optimizing Naive Scaler breakpoint set is presented to discrete the decision table, and then the discernibility matrix and function are used to get the mini- mum attribute reduction set. Finally, the neural network is applied to fault diagnosis on JZQ - 250 gearbox, and com- paring the diagnosis results of the characteristic set before reduction with that after reduction, the experiments show that the rough - neural network can reduce the network structure, and has the powerful fault tolerance and anti - jam- ming capability with the feature of less iteration, faster convergence rate, higher diagnostic accuracy, which is an ef- fective method for the gearbox fault diagnosis.
出处
《机械传动》
CSCD
北大核心
2013年第10期134-139,共6页
Journal of Mechanical Transmission
基金
国家自然科学基金项目(51175480)
关键词
故障诊断
齿轮箱
粗糙集
神经网络
Fault diagnosis Gearbox Rough set Neural network
