摘要
为了提高信息化系统故障诊断的精度,避免BP神经网络陷入局部最优并且提高收敛速度,提出一种麻雀搜索算法改进BP神经网络的信息化故障诊断模型。运用麻雀搜索算法优化选择BP神经网络的初始权值和阈值。与PSO-BPNN和GA-BPNN相比,SSA-BPNN进行信息化系统故障诊断具有更强的寻优能力和故障诊断精度,为信息化系统故障诊断提供了新的方法。
In order to improve the accuracy of information system fault diagnosis,avoiding BP neural network fall into local optimization and improve the rate of convergence,an information fault diagnosis model based on BP neural network improved by sparrow search algorithm is proposed.Sparrow search algorithm is applied to optimize the initial weights and thresholds of BP neural network.Compared with PSO-BPNN and GA-BPNN,SSA-BPNN has better optimization ability and fault diagnosis precision,providing a new method for fault diagnosis of information system.
作者
董贇
邓卓茗
DONG Yun;DENG Zhuoming(Guangxi Power Grid Limited Liability Company Information Center,Nanning 530023,China)
出处
《微型电脑应用》
2024年第1期220-223,共4页
Microcomputer Applications
关键词
神经网络
麻雀搜索算法
信息化系统
故障诊断
neural network
sparrow search algorithm
information system
fault diagnosis
