摘要
机器算法应用于电气设备故障预警及诊断已愈来愈广泛。因其能够有效预防设备故障进一步恶化对电网造成严重损伤进而产生不可挽回的后果,所以对于电力系统稳定运行的维护有着显著的作用。目前,应用于该领域的机器算法主要有:误差反向传播(error back propagation, BP)神经网络、支持向量机(support vector machine,SVM)、深度学习[包括:递归神经网络(recurrent neural network,RNN)、卷积神经网络(convolution neural network,CNN)、深度信念网络(deep belief network,DBN)]等。首先,对机器算法的发展及基本理念进行了概述;其次,介绍了各种机器算法的基本原理及在其电气设备故障预警及诊断中的应用;最后,对深度学习在故障预警及诊断中的发展趋势进行了展望。
Machine algorithm has been widely applied for early warning and diagnosis of electrical equipment fault, which can effectively prevent equipment damage and extended damage to the power grid and cause irreparable consequences. Therefore, it has a significant effect on the maintenance of stable operation of the power system. At present, the main machine algorithms include back propagation(BP) neural network, support vector machine(SVM), and deep learning [including: recurrent neural network(RNN), convolution neural network(CNN), deep belief network(DBN)]. Firstly, the development and basic concepts of machine algorithms are outlined. Second, the basic principles of various machine algorithms and their applications in early warning and diagnosis of electrical equipment failure are introduced. Finally, the future development of deep learning in fault warning and diagnosis is prospected.
作者
李俊卿
陈雅婷
李斯璇
LI Jun-qing;CHEN Ya-ting;LI Si-xuan(School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,China)
出处
《科学技术与工程》
北大核心
2020年第9期3370-3377,共8页
Science Technology and Engineering
关键词
机器算法
电气设备
故障预警及诊断
深度学习
发展趋势
machine algorithm
electrical equipment
fault warning and diagnosis
deep learning
development trend