改进的BP神经网络在局域网故障诊断中的应用

Application of an Improved BP Neural Network in Local Area Network Fault Diagnosis

现有的网络故障诊断方法存在诸多的不足,为了能够实现准确有效快速地排除网络故障,将人工神经网络的方法应用到对局域网的故障诊断中。先对传统的BP人工神经网络进行了分析,针对其收敛速度慢,存在局部极小值的缺点提出了一种改进后的BP人工神将网络。并先后将传统的以及改进后的两种BP神经网络应用到局域网的故障诊断中。仿真测试结果表明改进后的BP神经网络方法相比传统的BP神经网络方法确实能够更有效快速地完成对局域网的故障诊断,具有一定的应用价值。

The methods of existing network fault diagnosis have many deficiencies. In order to exclude the fault of network accurately and effectively, in this paper, artificial neural network method is applied in fault diagnosis on the LAN. An improved BP neural network is proposed for the purpose of overcoming the slow convergence and existence of local minimum in conventional BP neural network. Both the conventional and the improved BP neural network are applied in the LAN fault diagnosis respectively. The result of the simulation shows that the improved BP neural net- work is more fast and effective than the conventional BP neural network in the task of fault diagnosis, thus, this new method has practicability.