Abstract:Wind is a critical parameter of meteorological observation, and the shadow effect has a significant effect on the wind speed and direction measured by the ultrasonic anemometer. In order to eliminate the measurement error caused by the shadow effect under different wind speed and temperature conditions, a shadow effect compensation method based on computational fluid dynamics (CFD) simulation and back propagation (BP) neural network data processing is proposed in combination with the measuring principle of the ultrasonic time difference method. Firstly, the CFD simulation software—Fluent is used to simulate the wind field of ultrasonic anemometer. The wind speed, wind direction and temperature sample data affected by the shadow effect are obtained, and then the performance of BP neural network algorithm in ultrasonic anemometer is studied and analyzed by using these samples to reduce the relative error. Finally, the accuracy of the shadow effect compensation method in this paper is validated by using the wind tunnel data of the ultrasonic anemometer. The results show that the accuracy of the wind measurement is significantly improved after correcting the shadow effect by the prediciton model based on CFD and BP neural network, which can meet the high precision measurement requirements of ultrasonic anemometer. The results of this study have a certain reference value for the development of high precision ultrasonic wind measurement instrument.