基于深度学习的电气控制系统故障诊断与容错技术
Fault Diagnosis and Fault Tolerance Technology of Electrical Control System Based on Deep Learning
张翠翠 1刘竹1
作者信息
- 1. 四川职业技术学院,四川遂宁 629000
- 折叠
摘要
提出了一种结合深度学习的电气系统故障诊断与容错方法.首先,该方法利用稀疏自编码器学习电气控制系统的行为特征,然后借助双向长短期记忆网络对学习的特征进行建模,以预测系统的当前状态并进行故障诊断,一旦检测到故障,将自动启动相应的容错流程.模拟实验的结果充分表明了该方法的有效性和实用性.
Abstract
This paper proposes a fault diagnosis and fault tolerance method for electrical systems that combines deep learning.Firstly,this method utilizes sparse autoencoders to learn the behavioral characteristics of electrical control systems,and then models the learned features using a bidirectional long short-term memory network to predict the current state of the system and perform fault diagnosis.Once a fault is detected,the corresponding fault tolerance process will be automatically initiated.The results of the simulation experiment fully demonstrate the effectiveness and practicality of this method.
关键词
深度学习/故障诊断/容错技术Key words
deep learning/fault diagnosis/fault tolerance technology引用本文复制引用
出版年
2024
NETL
NSTL
万方数据