Microwave link precipitation particle identification method based on multi-scale permutation entropy

• Main Authors: TU JIE, CAO HUI, ZHANG YUSONG, ZHOU BAOHONG, YANG TAO, SHI PENGFEI, LIU SHUAI, YE WENJIE
• Format: Patent
• Language: Chinese; English
• Published: 19.01.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a microwave link precipitation particle identification method based on multi-scale permutation entropy. The method comprises the following steps: acquiring multi-environment microwave link attenuation data and dividing the data according to the type of precipitation particles; performing multi-scale coarse graining on the attenuated signal data, and performing multi-scale permutation entropy calculation after result sequence reconstruction and probability calculation; calculating the average attenuation rate of each section of attenuation signal time sequence, and constructing an average attenuation rate-scale-permutation entropy three-dimensional data set; unifying the data size, dividing a training set and a test set, and training the constructed 2D-CNN network; and inputting microwave link data, and identifying precipitation particles by using the multi-scale permutation entropy and the trained network model. According to the method, the microwave signal time sequence can be subject