Open AccessApplication of improved GM (1, m) model for transformer faults prediction
Author(s) -
Guoping Chen,
Yujie Shi,
Haizhi She,
Yanjun Qin,
Xiaoyang Zhou,
Zhengdong Qi,
Wenke Guo
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/558/5/052033
Subject(s) - transformer , exponential function , sequence (biology) , algorithm , computer science , predictive modelling , mathematics , data mining , machine learning , engineering , voltage , mathematical analysis , biology , electrical engineering , genetics
The traditional GM (1, m) prediction model is improved, the original data sequence is transformed, and its data generation method is changed, so that the transformed data sequence has a more approximate exponential change property, which meets the gray model’s smoothness Requirements, to be able to predict fluctuation series. At the same time, in order to improve the prediction accuracy of the model, the model background value is optimized, so that the prediction accuracy of the model is greatly improved. The improved GM (1,7) prediction model is used to predict the volume fraction of various gas characteristics of the transformer. Compared with the traditional GM (1,1) and GM (1,7) prediction results, it has a good approximation to the original data sequence the effect shows the effectiveness of the model.