Open AccessTransformer Fault Diagnosis Based on RapidMiner and Modified ELM Algorithm
Author(s) -
Ji-you Zhong,
Jin-xiao Wei,
Xiaorong Wu,
Hao Tang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1585/1/012030
Subject(s) - extreme learning machine , particle swarm optimization , transformer , support vector machine , computer science , algorithm , artificial intelligence , pattern recognition (psychology) , engineering , artificial neural network , electrical engineering , voltage
For transformer fault diagnosis, the three ratio method lacks of encoding, and artificial intelligence methods lack of anti-interference ability.Thus, a new method of transformer fault diagnosis based on RapidMiner and modified particle swarm optimization Extreme Learning Machine (RM-MPSO-ELM) is proposed. Firstly, RapidMiner picks out the most relevant input variables of the transformer fault. then, using the modified particle swarm algorithm to optimize the parameters for Extreme Learning Machine. Finally, using the ELM to identify the potential of transformer fault, the diagnostic performance of IEC three ratio method, support vector machine (SVM) method and different combinations of ELM algorithm are also compared. The results show that the proposed method achieves higher diagnosis precision.