An Improved Neural Network Algorithm and its Application in Fault Diagnosis

2013 ◽  
Vol 765-767 ◽  
pp. 2355-2358
Author(s):  
Tai Shan Yan ◽  
Guan Qi Guo ◽  
Wu Li ◽  
Wei He
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Power Transformer ◽  
Convergence Speed ◽  
Bp Algorithm ◽  
Network Algorithms ◽  
Convergence Error ◽  
Neural Network Algorithm ◽  
Transformer Fault ◽  
Improved Bp Algorithm

Aiming at BP neural network algorithms limitation such as falling into local minimum easily and low convergence speed, an improved BP algorithm with two times adaptive adjust of training parameters (TA-BP algorithm) was proposed. Besides the adaptive adjust of training rate and momentum factor, this algorithm can gain appropriate permitted convergence error by adaptive adjust in the course of training. TA-BP algorithm was applied in fault diagnosis of power transformer. A fault diagnosis model for power transformer was founded based on neural network. The illustrational results show that this algorithm is better than traditional BP algorithm in both convergence speed and precision. We can realize a fast and accurate diagnosis for power transformer fault by this algorithm.

New Methold on Power Transformer Fault Diagnosis

2012 ◽  
Vol 217-219 ◽  
pp. 2623-2628
Author(s):  
Nan Lan Wang ◽  
Ming Shan Cai
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Fault Diagnosis ◽  
Power Transformer ◽  
Wavelet Neural Network ◽  
Bp Algorithm ◽  
Oil Analysis ◽  
Wavelet Network ◽  
Dissolved Gas ◽  
Transformer Fault

This paper improves the simple genetic algorithm and combines genetic algorithm with BP algorithm to the wavelet neural network in the power transformer fault diagnosis by dissolved gas-in-oil analysis, Simulation result shows the problem was solved that wavelet network settles into local small extremum so easily that the network surging will increase and the network will not be convergent if the initialization is unreasonable, and overcomes the shortcoming that the speed is too slow if use genetic algorithm to train neural network independently.

Fault Diagnosis Analysis of Power Transformer Based on PSO-BP Algorithm

2012 ◽  
Vol 466-467 ◽  
pp. 789-793
Author(s):  
Hui Qin Sun ◽  
Zhi Hong Xue ◽  
Ke Jun Sun ◽  
Su Zhi Wang ◽  
Yun Du
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Search Algorithm ◽  
Power Transformer ◽  
Network Models ◽  
Pso Algorithm ◽  
Bp Algorithm ◽  
Neural Network Models ◽  
Bp Network ◽  
Transformer Fault

BP neural network is currently the most widely used of neural network models in practical application in transformer fault diagnosis. BP algorithm is a local search algorithm which is easy to make the network into the local minimum values. Network training results are poor. It discusses PSO-BP algorithm which combines the particle swarm optimization (PSO) algorithm with the BP algorithm in this paper. It uses PSO algorithm to optimize the BP network’s weights and threshold. It is used in power transformer fault diagnosis. Experimental data results show that PSO-BP network fault diagnosis accuracy is higher than BP algorithm.

Improved PSO-BP neural network for power transformer fault diagnosis

2010 ◽  
Vol 30 (3) ◽  
pp. 783-785 ◽  
Author(s):  
Zhong-yang XIONG ◽  
Qing-bo YANG ◽  
Yu-fang ZHANG
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Power Transformer ◽  
Transformer Fault ◽  
Improved Pso

Research on BP Neural Network Algorithm Based on Quasi-Newton Method

2014 ◽  
Vol 686 ◽  
pp. 388-394 ◽  
Author(s):  
Pei Xin Lu
Keyword(s):  
Neural Network ◽  
Empirical Analysis ◽  
Newton Method ◽  
Bp Neural Network ◽  
Bp Algorithm ◽  
Newton Methods ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Quasi Newton ◽  
Improved Bp Algorithm

With more and more researches about improving BP algorithm, there are more improvement methods. The paper researches two improvement algorithms based on quasi-Newton method, DFP algorithm and L-BFGS algorithm. After fully analyzing the features of quasi-Newton methods, the paper improves BP neural network algorithm. And the adjustment is made for the problems in the improvement process. The paper makes empirical analysis and proves the effectiveness of BP neural network algorithm based on quasi-Newton method. The improved algorithms are compared with the traditional BP algorithm, which indicates that the improved BP algorithm is better.

Multi-Level Fault Diagnosis of Power Transformer Based on Fusion Technology

2013 ◽  
Vol 860-863 ◽  
pp. 1925-1928
Author(s):  
Zhi Bin Li ◽  
Qi Ben Li
Keyword(s):  
Fault Diagnosis ◽  
Power Transformer ◽  
Complex Structure ◽  
Transformer Oil ◽  
Fusion Technology ◽  
Fault Type ◽  
Neural Network Algorithm ◽  
Multi Level ◽  
Transformer Fault ◽  
Source Of Information

Traditional transformer fault diagnosis based on single source of information has significant limitation in identification of transformer fault type because of power transformers complex structure and changeable operating environment. So fusion technology is introduced into the fault diagnosis of power transformer. This method divides the progress of transformer fault diagnosis into two fusion levels. The first level is to ascertain whether it is overheated or discharged by content of gases dissolved in transformer oil. The second level is to ascertain the location or cause of the fault by electric data. The intelligence algorithms which are used in these two levels are both the improved BP neural network algorithm. Finally, the effectiveness is validated by the result of practical fault diagnosis examples.

Sign in / Sign up

Export Citation Format

Share Document