Active Diverse Learning Neural Network Ensemble Approach for Power Transformer Fault Diagnosis

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.

Download Full-text

Study on Fault Diagnosis of Power Transformer with Reduction Method of Attribute Significance

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1049-1050.665 ◽

2014 ◽

Vol 1049-1050 ◽

pp. 665-668

Author(s):

Hong Li Lv

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Rough Sets ◽

Power Transformer ◽

Reduction Algorithm ◽

Rough Sets Theory ◽

Fault Diagnosis System ◽

Transformer Fault ◽

Sets Theory ◽

Quality Diagnosis

This paper studies the power transformer fault quality diagnosis using rough sets theory and neural network. It is rough sets reduction as the pre-unit of neural network based on reduction algorithm with the attribute significance. The paper describes the reduction algorithm and implementation method detailed. Through the training and testing results with practical data, it is proved that the reduction algorithm with the attribute significance can make the number of input samples shorter, the training speed faster and the diagnostic accuracy higher. The algorithm is feasible and effective for applying to the fault diagnosis system of power transformer.

Download Full-text

Power transformer fault diagnosis based on dissolved gas analysis by artificial neural network

2012 First International Conference on Renewable Energies and Vehicular Technology ◽

10.1109/revet.2012.6195276 ◽

2012 ◽

Cited By ~ 17

Author(s):

Souahlia Seifeddine ◽

Bacha Khmais ◽

Chaari Abdelkader

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Fault Diagnosis ◽

Power Transformer ◽

Gas Analysis ◽

Dissolved Gas ◽

Dissolved Gas Analysis ◽

Artificial Neural ◽

Transformer Fault

Download Full-text

New Methold on Power Transformer Fault Diagnosis

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.217-219.2623 ◽

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.

Download Full-text