BP-Neural-Network-Based Aging Degree Estimation of Power Transformer Using Acoustic Signal

In this paper, an aging degree estimation method using acoustic signals is proposed based on a BP neural network. Twenty-eight transformers are taken as research objects. The transformer's internal noise mechanism is analyzed, and the acoustic signals of the high- and low-voltage sidewalls are collected and screened. The BP neural network is used to predict the transformer age in real-time. Comparing the predicted results with their actual operation time provides a sufficient basis for determining the degree of transformer aging and the need for an overhaul. After network training and data testing, the error between the predicted value and the actual value reaches the least. The proposed estimation method can play an innovative role in the process of transformer fault monitoring.

[1]  Gehao Sheng,et al.  Prediction Method for Power Transformer Running State Based on LSTM_DBN Network , 2018, Energies.

[2]  Xiaohong Huang,et al.  The efficiency analysis of the statistical feature in network traffic identification based on BP neural network , 2013, 2013 5th IEEE International Conference on Broadband Network & Multimedia Technology.

[3]  Fenghua Wang,et al.  Fault Diagnosis of On-Load Tap-Changer in Converter Transformer Based on Time–Frequency Vibration Analysis , 2016, IEEE Transactions on Industrial Electronics.

[4]  Kaixing Hong,et al.  Transformer winding fault detection by vibration analysis methods , 2016 .

[5]  Li Zhang,et al.  Analysis of Winding Vibration Characteristics of Power Transformers Based on the Finite-Element Method , 2018, Energies.

[6]  Chao Zhang,et al.  Noise analysis of UHV power transformer and research on active noise reduction system , 2017, 2017 20th International Conference on Electrical Machines and Systems (ICEMS).

[7]  Ma Qixiao,et al.  Research on the winding and iron core operation state of transformer based on the vibration acoustic fingerprint , 2016, 2016 International Conference on Condition Monitoring and Diagnosis (CMD).

[8]  Shutao Zhao,et al.  Intelligence Expert System of Transformer Running State Diagnosis Based on Acoustic Signal Analyzing , 2009, 2009 Second International Symposium on Knowledge Acquisition and Modeling.

[9]  Jiang Long,et al.  Research on Transformer Fault Diagnosis Based on BP Neural Network Improved by Association Rules , 2019, 2019 2nd International Conference on Electrical Materials and Power Equipment (ICEMPE).

[10]  Tetsuro Matsui,et al.  Development of remaining life assessment for oil-immersed transformer using structured neural networks , 2009, 2009 ICCAS-SICE.

[11]  Mehdi Bagheri,et al.  Real-time dry-type transformer aging evaluation , 2017, 2017 International Symposium on Electrical Insulating Materials (ISEIM).

[12]  Hai Huang,et al.  A vibration measurement system for health monitoring of power transformers , 2016 .

[13]  Gehao Sheng,et al.  Power Transformer Operating State Prediction Method Based on an LSTM Network , 2018 .

[14]  H. O. Gupta,et al.  Life estimation of distribution transformers considering axial fatigue in loose winding conductors , 2011 .

[15]  Ling Li,et al.  Diagnosis of DC Bias in Power Transformers Using Vibration Feature Extraction and a Pattern Recognition Method , 2018 .

[16]  F. Muzi,et al.  Vibro-acoustic techniques to diagnose power transformers , 2004, IEEE Transactions on Power Delivery.

[17]  Juan Carlos Burgos,et al.  Winding deformations detection in power transformers by tank vibrations monitoring , 2005 .

[18]  Guoqiang Liu,et al.  Measurement and analysis of UHV transformer noise with sound intensity and vibration method , 2017, 2017 20th International Conference on Electrical Machines and Systems (ICEMS).

[19]  Zhiguang Cheng,et al.  Study on Vibration of Iron Core of Transformer and Reactor Based on Maxwell Stress and Anisotropic Magnetostriction , 2019, IEEE Transactions on Magnetics.