论文部分内容阅读
提出了一种减聚类径向基函数自适应神经网络(RBF)的压滤机液压系统故障诊断方法。在RBF中采用了一种减聚类的学习算法来确定径向基函数的相应参数,并借助梯度下降法(LMS)求解网络的权值,学习步长根据训练误差自适应调节。试验结果显示,该方法可以有效提高故障诊断的精度和效率。
A fault diagnosis method of filter press hydraulic system based on RBF radial basis function adaptive neural network (RBF) is proposed. In the RBF, a learning algorithm of reducing clustering is adopted to determine the corresponding parameters of the radial basis function. The weight of the network is calculated by the gradient descent method (LMS), and the learning step is adaptively adjusted according to the training error. The experimental results show that this method can effectively improve the accuracy and efficiency of fault diagnosis.