论文信息 - The study of improved Fisher ratio for default diagnosis of power transformer

The study of improved Fisher ratio for default diagnosis of power transformer

Improved Fisher ratio method is presented in default diagnosis of power transformer based on dissolved gas analysis. Owing to the disadvantages of Fisher ratio method in RBF network structure optimization, authors put forward using improved Fisher ratio method to select the RBF centers, optimize the network structure. The results show that the neural structure is simplified strongly, the converged precision and class separability is improved, and this method is satisfied to diagnosis the default of power transformer.

[1] Y. M. Tu,et al. Transformer insulation diagnosis based on improved ANN analysis , 1997, Proceedings of 5th International Conference on Properties and Applications of Dielectric Materials.

[2] Rosalind W. Picard,et al. On the efficiency of the orthogonal least squares training method for radial basis function networks , 1996, IEEE Trans. Neural Networks.

[3] Mohammad Bagher Menhaj,et al. Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[4] P. J. Griffin,et al. A combined ANN and expert system tool for transformer fault diagnosis , 1998 .

[5] Lipo Wang,et al. Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[6] Shang-Liang Chen,et al. Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.