Electric power facility site selection prediction method and system based on deep learning

Abstract

The invention relates to the technical field of wind power generation, in particular to an electric power facility site selection prediction method and system based on deep learning, and the method comprises the steps: 1, collecting map data information of an existing wind power plant and a later anemometer tower; 2, manually marking each wind power plant and each anemometer tower to obtain first label data; 3, constructing an FCNN neural network model and a first label data classification result; 4, labeling the classification result of the first label data again to obtain second label data; 5, constructing a CNN neural network model and a second label data classification result; and 6, predicting the optimal anemometer tower position information of the new wind power plant to obtain the predicted optimal anemometer tower position information, and storing the predicted optimal anemometer tower position information in the SQL database. According to the invention, when the later-stage anemometer tower is constructed in a new wind power plant, the optimal construction position information of the later-stage anemometer tower in the new wind power plant can be automatically predicted only by inputting the map data information of the wind power plant, and the purpose of reducing the labor cost and the time cost is achieved.

Description

【Technical field】 [0001] The present invention relates to the technical field of wind power generation, in particular to a method and system for location prediction of power facilities based on deep learning. 【Background technique】 [0002] In recent years, with the improvement of environmental protection awareness and the development of new energy technology, more and more manpower and material resources have been invested in the field of new energy. And a very important category in the new energy field is wind power generation. The proportion of wind power generation in the country has reached 5.23% of the total power generation, and the development speed is very fast. However, due to the existence of consumption problems, there is a higher demand for accurate power generation prediction and evaluation of wind farms. Wind resource detection, power generation post-evaluation and ultra-short-term power forecasting for wind farms that have been put into operation are importa...

AI Technical Summary

Problems solved by technology

Then the result of doing this is that due to the different professional standards and experience of each person, the screening results may be different. For this reason, manpower and time will be spent on on-site inspections, which will waste a lot of manpower and time. Meet the needs of the existing wind power development for the construction of wind measuring towers

Images