Long-short-term memory correction forecasting method and device for icing thickness of fan blade

Abstract

The embodiment of the invention provides a long-short-term memory correction forecasting method for the icing thickness of a fan blade. The method comprises the following steps: determining a to-be-forecasted area in which freezing rain icing numerical forecasting needs to be carried out; dividing an area to be forecasted into equidistant grids; initial field data and boundary condition data for carrying out freezing rain icing numerical value prediction are obtained, the initial field data are data on each grid point at the moment when an index value prediction mode starts integration, and the initial field data and the boundary condition data consistent with grids of a to-be-predicted area are input into a numerical value mode; obtaining a first freezing rain icing value of the fan blade in the to-be-forecasted area at a future preset time point; inputting the first freezing rain icing value into a long-short term memory neural network; and obtaining a second freezing rain icing value obtained by correcting the first freezing rain icing value by the long and short term memory neural network, and determining the second freezing rain icing value as the freezing rain icing value of the fan blade in the to-be-forecasted area at the future preset time point.

Description

technical field [0001] The present application relates to the field of power grid scheduling, and in particular to a long-short-term memory correction and forecasting method, device, storage medium and processor for the ice thickness of wind turbine blades. Background technique [0002] With the development of wind power generation technology, wind farms are located in mountainous areas with high altitudes, which makes freezing rain and icing of wind turbines occur frequently. However, in the prior art, a method of predicting wind and rain weather is usually adopted according to the weather forecast, but this method cannot accurately predict the icing condition of the fan blades. SUMMARY OF THE INVENTION [0003] The purpose of the embodiments of the present application is to provide a long-short-term memory correction prediction method, device, storage medium and processor for the ice-covered thickness of a fan blade. [0004] In order to achieve the above purpose, a fir...

AI Technical Summary

Problems solved by technology

However, in the prior art, the method of predicting wind and rain according to the weather forecast is usually adopted, but this method cannot accurately predict the icing situation of the fan blades

Images