Artificial classification system of aging period based on insulation status of transformers

• Published in: 2009 International Conference on Machine Learning and Cybernetics Vol. 6; pp. 3310 - 3315
• Main Authors: Cheng-Chien Kuo, Horng-Lin Shieh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2009
• Subjects: Accelerated aging; Artificial Classification System; Artificial neural networks; Data mining; Degradation; Insulation aging; Insulation testing; Life estimation; Neural Network; Partial discharge; Partial discharges; Particle swarm optimization; Power transformer insulation; Signal processing; System testing; Transformer
• ISBN: 9781424437023; 1424437024
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2009.5212754

The classification system to identify the aging period of insulation status for cast-resin transformer through current impulse method of partial discharge is proposed in this paper. An effectively insulating classification technology plays an important role to enhance the system operating reliability. Since PD is a well know evidence of insulation degrading, a series of high voltage test with acceleration aging process to collect PD signals for classification system are conducted in the lab. Some selected statistical PD features instead of waveform are then extracted from these experimental PD signals as input data of the classification system. Also, an artificial neural network that combined particle swarm optimization is presented as the effectively classification tool. To demonstrate the effectiveness and feasibility of the proposed approach, the artificial classification system is applied on both noisy and noiseless circumstance with promising results.