To solve the problem that the China new-generation Doppler weather radar named CINRAD is easy to lose small shear in radial or tangential direction, a new alerting algorithm of low-level wind shear based on Fuzzy C-Means (FCM) was proposed for wind shear identification of front and tornado. In order to achieve high shear and low shear warning, the core idea of this algorithm was to use 8-neighborhood system, according to the wind speed divergence characteristics to identify varying degrees of shear. Firstly, the Total Variation (TV) model was used in radar velocity base data denoising while maintaining the details of the data. Secondly, the 8-neighborhood system was convoluted in turn with 4-direction template to obtain the omni directional velocity gradient. Then, in order to achieve different intensity of wind shear altering, the FCM algorithm was used to classify the gradient values into two categories. Using the measured data provided with the Wuhan Rainstorm Research Institute to test and verify, the small shear was identified. The results show that the algorithm to detect wind shear is superior to the wind shear recognition algorithm based on radial or tangential direction in terms of both position accuracy and edge recognition, which has important guiding significance to judgment of position and intensity and analysis of wind shear caused by different weather.

According to the shape features of wind shear images extracted by wavelet invariant moment based on cubic B-spline wavelet basis, an improved Genetic Algorithm (GA) was proposed to apply to the type recognition of microburst, low-level jet stream, side wind shear and tailwind-or-headwind shear. In the improved algorithm, the adaptive crossover probability only considered the number of generation and mutation probability just emphasized the fitness valve of individuals and group, so that it could control the evolution direction uniformly, and greatly maintain the population diversity simultaneously. Lastly, the best feature subset chosen by the improved genetic algorithm was fed into 3-nearest neighbor classifier to classify. The experimental results show that it has a good direction and be able to rapidly converge to the global optimal solution, and then steadily chooses the critical feature subset in order to obtain a better performance of wind shear recognition that the mean recognition rate can reach more than 97% at last.