一类反馈过程神经元网络模型及其学习算法

A Feedback Process Neuron Network Model and Its Learning Algorithm

提出了一种基于权函数基展开的反馈过程神经元网络模型．该模型为三层结构，由输入层、过程神经元隐层和过程神经元输出层组成．输入层完成系统时变过程信号的输入及隐层过程神经元输出信号向系统的反馈；过程神经元隐层用于完成输入信号的空间加权聚合和激励运算，同时将输出信号传输到输出层并加权反馈到输入层；输出层完成隐层输出信号的空间加权聚集和对时间的聚合运算以及系统输出．文中给出了学习算法，并以旋转机械故障自动诊断问题为例验证了模型和算法的有效性．

A feedback process neural network model based on weight function base ex-pansion is put forward.Structurally,this model has three layers,namely the input layer,process neuron hidden layer and process neuron output layer.The input layer completesinput of the time-varying process signal and feedback of output from the hidden layer to thesystem,the process neuron hidden layer is used to complete the space weight aggregationand incitation operation,at the same time the output signal is transferred to the outputlayer and fed back to the input layer after being weighted.The output layer completes spaceweight aggregation and time aggregation of output signal from the hidden layer and thesystem output.The learning algorithm is given in this paper.The effectiveness of the modeland algorithm is proved by automatic diagnoses of a rotating machine.