Abstract
In view of the low accuracy of transformer fault diagnosis with traditional method, a novel multi-input and multi-output polynomial neural network (PNN) is proposed and used for transformer fault diagnosis. Firstly, single output PNN I classification model is trained and constructed according to the five kinds of characteristic gas corresponding four fault types (high-energy discharge, low-energy discharge, superheat and normal state) sample data, the transformer states are divided into normal state and abnormal state, then a transformer fault diagnosis model based on multiple output PNN II is built to aim at the three fault types such as high-energy discharge, low-energy discharge and thermal heating. Simulation and test results show that accuracy can reach 100% by using the presented model, which has excellent anti-interference performance.
Similar content being viewed by others
References
Pandya, A.A., Parekh, B.R.: Interpretation of sweep frequency response analysis (SFRA) traces for the open circuit and short circuit winding fault damages of the power transformer. Int. J. Electr. Power Energy Syst. 62(11), 890–896 (2014)
Souahlia, S., Bacha, K., Chaari, A.: MLP neural network-based decision for power transformers fault diagnosis using an improved combination of Rogers and Doernenburg ratios DGA. Int. J. Electr. Power Energy Syst. 43(1), 1346–1353 (2012)
Sun, Y.J., Zhang, S., Miao, C.X., et al.: Improved BP neural network for transformer fault diagnosis. J. China Univ. Min. Technol. 17(1), 138–142 (2007)
Shao, K.: A novel method of transformer fault diagnosis based on extension theory and information fusion in wireless sensor networks. Energy Procedia 12(12), 669–678 (2011)
Han, H., Wang, H.J., Dong, X.C.: Transformer fault Diagnosis based on feature selection and parameter optimization. Energy Procedia 12(39), 662–668 (2011)
Zhang, Y.X., Bai, J., Zhang, S.P.: Fault diagnosis of power transformer based on immune particle swarm and BP neural network. J. Beihua Univ. (Nat. Sci.) 15(2), 269–273 (2014)
Fei, S.W., Miao, Y.B., Liu, C.L., et al.: Fault diagnosis of transformer based on particle swarm optimization-based support vector machine. High Volt. Eng. 35(3), 509–513 (2009)
Al-Janabi, S., Rawat, S., Patel, A., et al.: Design and evaluation of a hybrid system for detection and prediction of faults in electrical transformers. Int. J. Electr. Power Energy Syst. 67(67), 324–335 (2015)
Sheng, W.F., Xiao, B.Z.: Fault diagnosis of power transformer based on support vector machine with genetic algorithm. Expert Syst. Appl. 36(8), 11352–11357 (2009)
Mohamed, E.A., Abdelaziz, A.Y., Mostafa, A.S.: A neural network-based scheme for fault diagnosis of power transformers. Electr. Power Syst. Res. 75(1), 29–39 (2005)
Hung, C.P., Wang, M.H.: Diagnosis of incipient faults in power transformers using CMAC neural network approach. Electr. Power Syst. Res. 71(1), 235–244 (2004)
Yadaiah, N., Ravi, N.: Internal fault detection techniques for power transformers. Appl. Soft Comput. 11(8), 5259–5269 (2011)
Sun, H.C., Huang, Y.C., Huang, C.M.: Fault diagnosis of power transformers using computational intelligence: a review. Energy Procedia 14, 1226–1231 (2012)
Chen, A.P., Lin, C.C.: Fuzzy approaches for fault diagnosis of transformers. Fuzzy Sets Syst. 118(1), 139–151 (2001)
Abu-Siada, A., Hmood, S.: A new fuzzy logic approach to identify power transformer criticality using dissolved gas-in-oil analysis. Electr. Power Energy Syst. 67, 401–408 (2015)
Bacha, K., Souahlia, S., Gossa, M.: Power transformer fault diagnosis based on dissolved gas analysis by support vector machine. Electr. Power Syst. Res. 83(1), 73–79 (2012)
Ganyun, L.V., Cheng, H.Z., Zhai, H.B., et al.: Fault diagnosis of power transformer based on multi-layer SVM classifier. Electr. Power Syst. Res. 74(1), 1–7 (2005)
Zhang, J., Zou, A.J., Tong, T.S.: A neural network based on polynomial basis functions. 1995 Conference Paper. Establishment of Intelligent Automation Committee, vol. 1, pp. 287–292. Intelligent Automation Association of China, Beijing (1995)
Zhang, J., Zou, A.J., Tong, T.S.: A neural network based on polynomial basis functions. J. Hunan Univ. 44, 84–89 (1996)
Xiao, X.C., Jiang, X.H., Zhang, Y.N.: Implicit surface reconstruction from point cloud data based on generalized polynomials neural network. J. Comput. Appl. 29(8), 2043–2045, 2064 (2009)
Patra, J.C., Van den Bos, A.: Modeling of an intelligent pressure sensor using functional link artificial neural networks. ISA Trans. 39(1), 15–27 (2000)
Zou, A.J., Shen, H.Y.: Identifier based on Chebyshev neural network. Coal Mine Autom. 4, 10–11 (1998)
Akritas, P., Antoniou, I., Ivanov, V.V.: Identification and prediction of discrete chaotic maps applying a Chebyshev neural network. Chaos Solitons Fractals 11(1), 337–344 (2000)
Patra, J.C., Kot, A.C.: Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks. IEEE Trans. Syst. Man Cybern. B 32(4), 505–511 (2002)
Zou, A.J., Wu, W., Li, R.F., et al.: Construction of the encryption matrix based on Chebyshev chaotic neural networks. J. Electron. (China) 29, 248–253 (2012)
Zou, A.J., Shen, J.Z.: A neural network model structure study based on Fourier. Nat. Sci. J. Xiangtan Univ. 23(2), 23–26 (2001)
Zou, A.J., Luo, Y.X.: Modeling and stock prediction based on Legender neural networks. Comput. Simul. 22(11), 241–242, 246 (2005)
Zou, A.J., Zhang, Y.N., Xiao, X.C.: An asynchronous encryption algorithm based on Hermite chaotic neural networks. CAAI Trans. Intell. Syst. 4(5), 458–462 (2009)
Zhang, Y.N., Liu, J.R., Yin, Y.H., et al.: Weights and structure determination of multi-input Laguerre orthogonal polynomial feed-forward neural network. Comput. Sci. 39(12), 249–251, 277 (2012)
Dhahri, H., Alimi, A.M., Abraham, A.: Hierarchical multi-dimensional differential evolution for the design of beta basis function neural network. Neurocomputing 97(1), 131–140 (2012)
Li, C., Shi, D., Zou, Y.P.: A feedback neural network with weights of sinusoidal functions. Acta Phys. Sin. 61(7), 070701–070708 (2012)
Nan, D., Liu, L.J.: Relationship between basis-function neural networks and reproducing kernel function. J. Beijing Univ. Technol. 40(9), 1428–1431 (2014)
Xiao, X.C., Zhang, Y.N., Jiang, X.H., et al.: Approximation-performance and global-convergence analysis of basis-function feedforward neural network. Mod. Comput. 2, 4–8 (2009)
Zhang, Y.N., Liu, W., Yi, C., et al.: Weights immediate determination for feed-forward neural network with Legendre orthogonal basis function. J. Dalian Marit. Univ. 34(1), 32–36 (2008)
Zhang, Y.N., Li, W., Cai, B.H., et al.: A Chebyshev orthogonal basis neural network with direct weight determination. Comput. Simul. 26(1), 157–161 (2009)
Zhang, Y.N., Yang, Y.W., Xiao, X.C., et al.: Weights direct determination of a spline neural network. Syst. Eng. Electron. 31(38), 2685–2688 (2009)
Zhang, Y.N., Chen, Y.L., Jiang, X.H., et al.: Weights-directly-determined and structure-adaptively-tuned neural network based on Chebyshev basis functions. Comput. Sci. 36(6), 210–213 (2009)
Zhang, Y.N., Qu, L., Chen, J.W., et al.: Weights and structure determination method of multiple-input sigmoid activation function neural network. Appl. Res. Comput. 29(11), 4113–4116, 4151 (2012)
Zhang, Y.N., Lao, W.C., Yu, X.T., et al.: Weights and structure determination of two-input power-activation feed-forward neural network. Comput. Eng. Appl. 48(15), 102–106 (2012)
Xing, Y.K., Shi, Y., Mou, C.: Multivariate Chebyshev neural network and quick learning algorithm. Comput. Eng. Appl. 49(13), 36–39 (2013)
Tian, Q.C., Tian, M.X., Yang, X.F.: Weights-direct-determination for image restoration of basis function neural network. Comput. Eng. Appl. 49(8), 178–181 (2013)
Zhang, Y.N., Luo, F.H., Chen, J.H.: Weights and structure determination of 3-input Bernoulli polynomial neural net. Comput. Eng. Sci. 35(5), 142–148 (2013)
Yang, W.G.: Weights direct determination of triangular fuzzy feed-forward neural network. Acta Sci. Nat. Univ. Sunyatseni 2(2), 33–37 (2013)
Zou, A.J., Zhang, Y.N.: Basis Function Neural Network and Application, pp. 106–109. Sun Yat-sen University Press, Guangzhou (2009)
Acknowledgements
The authors would like to thank the National Natural Science Foundation of China (Nos. 61173036, 61272534), the “Climbing Plan” Special Fund Project of Guangdong Province (No. pdjh2017a0233) and the Science and Technology Project of Guangdong Province (No. 2016A010101028) for financial supports.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zou, A., Deng, R., Mei, Q. et al. Fault diagnosis of a transformer based on polynomial neural networks. Cluster Comput 22 (Suppl 4), 9941–9949 (2019). https://doi.org/10.1007/s10586-017-1020-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-017-1020-3