基于奇异值分解的滚动轴承故障诊断的神经网络方法

径向基函数神经网络是一种三层前馈型神经网络,它具有较强的非线性函数逼近能力和分类能力.根据径向基函数神经网络的优点,在对滚动轴承振动信号故障特征分析的基础上,提出一种应用奇异值分解将高维相关变量转化为低维独立变量,并利用其特征值建立径向基函数神经网络的方法,同时将该网络用于对滚动轴承的故障诊断.理论和试验证明了该方法的有效性,且具有较高的故障分类精度.

Neural Networks Method of Bearing Fault Diagnosis Based on Singularity Value Decomposition

Radial basis function neural network is a type of three-layer feedforward network.It has many good properties, such as powerful ability for function approximation, classification and learning rapidly. In this paper, in the light of the merit of radial basis function neural network and on the basis of the feature analysis of vibration signal of rolling bearing, a new method of singularity value decomposition is presented.It can transform multidimensional correlated variable into low dimensional independent variable. Radial basis function neural network is established with the eigenvalue presenting from signal's singularity. Based on the theory of radial basis function neural network, fault diagnosis of rolling bearing is recognized correspondingly. Theory and experiment shows that the recognition of fault diagnosis of rolling bearing based on singularity value decomposition and radial basis function neural network theory is available and its precision is high.