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 SystemBased on Deep Learning

作　　者：张翠翠 刘竹[1] ZHANG Cuicui;LIU Zhu(Sichuan Vocational and Tchnical College,Suining,Sichuan 629000,China)

机构地区：[1]四川职业技术学院,四川遂宁629000

出　　处：《自动化应用》2024年第8期35-37,共3页Automation Application

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。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 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]