Wind power plant fan echo filtering method

• Main Authors: HU YIPENG, LEI XIANMEI, ZHU XIALIANG, WANG HONGDONG, ZHOU HU
• Format: Patent
• Language: Chinese; English
• Published: 07.05.2024
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The invention discloses a wind power plant fan echo filtering method, which comprises the following steps of: 1, performing speed dimension FFT (Fast Fourier Transform) on a radar echo signal, and replacing a frequency spectrum at a speed zero by using an average noise floor so as to eliminate radar echoes of a fan tower column; 2, using a probabilistic neural network (PNN) algorithm, inputting the frequency spectrum image of the fan blade tip as a training sample into a PNN model for training, and inputting a test frequency spectrum image set into the model after the model is trained; and according to the identification result output by the PNN model and the coordinate of the returned fan blade tip frequency spectrum position, using the average noise floor to replace the fan blade tip frequency spectrum so as to eliminate the echo interference of the fan blade tip in the spectrogram. According to the method, only the echo information of the radar is needed, the neural network structure is simple, the calcula