WIND LOAD PREDICTION OF LARGE-SPAN DRY COAL SHEDS BASED ON GRNN AND ITS APPLICATION

The distribution and fluctuation of wind load on large-span dry coal sheds are complicated. Wind load on typical shape of roofs can be sometimes determined based on the wind tunnel tests carried out on roofs of similar shape. To expand the application scope of the test data, Generalized Regression Neural Network (GRNN) is introduced. The prediction models on large-span dry coal are given, where the wind load is expressed by eight parameters: mean, RMS, skewness, kurtosis of wind pressure coefficients, three auto-spectral parameters (including descendent slope in high frequency range, peak reduced spectrum and reduced peak frequency) and coherence exponent for cross-spectra. Cross validation and trails are carried out to determine the parameter in the GRNN model. Further, the wind load prediction is applied on a dry coal shed shell. The wind-induced responses are calculated and compared with the results of wind tunnel tests, with extremely close result. Therefore, it can be concluded that GRNN is feasible in predicting wind load on roof structures.