机器算法在电气设备故障预警及诊断中的应用

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。

Application of Machine Algorithm in Early Warning and Diagnosis of Electrical Equipment Fault

The application of machine algorithms to the early warning and diagnosis of electrical equipment failures has become more and more extensive. Because it can effectively prevent equipment damage and further damage to the power grid and cause irreparable consequences, it has a significant effect on the maintenance of stable operation of the power system. At present, the main application of machine algorithms are: BP neural network, SVM, deep learning (including: RNN, CNN, DBN). This paper first gives an overview of the development and basic concepts of machine algorithms. Secondly, the basic principles of various machine algorithms and their applications in early warning and diagnosis of electrical equipment failure are introduced. Finally, this paper looks forward to the development trend of deep learning in fault warning and diagnosis.