In order to reduce the impact of transmission line icing accidents on the safe production of the power grid, the power grid operation and maintenance department guides the deicing and melting work of the power grid by estimating the thickness of the line icing. This paper proposes to predict the ice thickness based on the entropy weight method and BP neural network learning method. First, the entropy weight method is used to select the main influencing factors of line icing. Then a BP neural network prediction model of ice coating is constructed with weather and terrain as input and ice thickness as output. Finally, performance evaluation is performed using artificial ice observation data. The goodness of fit between the test data and the artificial ice observation data is 0.76805. The error is 5.33mm, which is far lower than 6.51 mm compared with the stepwise regression model. This verifies the validity of the model and has certain significance for the research on transmission line icing prediction.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com