Variative Forecast of the Technical Condition of Wind Power Plant Equipment

To minimize the risk of erroneous managerial decisions due to incorrect forecasts, a comprehensive approach using several forecasting methods, each of which is based on a unique mathematical apparatus, is considered. A method for predicting the quantitative assessment of the technical condition of a wind power plant is proposed based on the combined use of ANFIS, an adaptive neural-fuzzy inference system, and LSTM, a network with long short-term memory. It provides a variative forecast of the technical condition of the equipment of a wind power plant. Comparing data in the case in which one of the systems makes an incorrect forecast makes it possible to enhance the accuracy of forecasting a quantitative assessment of the technical condition.