English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In order to solve the problem that the (OS-ELM) is used in the fault diagnosis of the transformer, the genetic algorithm (Algorithm Genetic) is applied to the on-line extreme learning machine, and a new method of transformer fault diagnosis is proposed. In this method, the number of hidden layer neurons of the Block L, the data set size N, and the hidden layer activation function are selected by the Algorithm Genetic optimization algorithm. Through simulation test, the fault diagnosis of transformer is 99.56%, and the test time is 0.0024 s. Compared with the optimization, the diagnostic accuracy and the test time of the transformer fault are improved obviously. Introduction In the long run,the transformer will inevitably lead to failure, Using the historical data and current status data of transformer fault to analyze and identify the fault to eliminate potential failures and defects as soon as possible, has been the concern of researchers study. There were many traditional transformer fault diagnosis intelligent methods,for example, IEC recommended three ratio method, Rogers and Dornerburg method etc. But coding boundary is too absolute and coding need be artificially drawn in the traditional threshold detection means. There is some defects especially lack of encoding[1][2];At the same time, emerging intelligent methods such as BP neural network, SVM,Bayesian network and so on, are facing the main problems example high intensity human interference, learning speed slowly, poor learning extensibility and a large sample of demand etc[5].The existing DGA data cannot meet the demand of their training[3][6].When applied to the high response demanding online program, these emerging intelligent methods are often inefficient[4]. At present, the research of the online sequence extreme learning machine (OS-ELM) is used in the diagnosis of transformer fault[7], and the data are effectively avoided,However, the artificial choice of the online sequence of extreme learning machine parameters, resulting in the limit of learning machine training accuracy is not high enough. Genetic algorithm is proposed to optimize the fault diagnosis method of OS-ELM, and the parameters of the machine parameters are optimized by using genetic algorithm to optimize the parameters of OS-ELM[8][9].The feasibility and superiority of the proposed method is verified by the comparison of the training accuracy and training time. Introduction of OS-ELM Online sequence extreme learning machine (OS-ELM) is a single hidden layer forward neural network (SLFN) training algorithm which can be applied to some regression and classification tasks. The method adopts the way of partitioned matrix effectively to avoid the repeated training data and to a great extent improve the efficiency of learning. OS-ELM algorithm described as follows: 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2015) © 2015. The authors Published by Atlantis Press 892 Given training data set N,the hidden layer output function G(ai,bi,x) and the number of hidden layer nodes L. Step1 Initialization phase: choose the part of the data set { } 0 0 1 , N i i i N x t = = form the N,where N0≥L a)Randomly selected input weights ai and threshold of hidden layer node bi,i=1,...L; b)Calculate the output matrix In the hidden layer H0

Optimizing Online Sequential Extreme Learning Machine Parameters and Application to Transformer Fault Diagnosis