Data-Based Windstorm Type Identification Algorithm and Extreme Wind Speed Prediction

Abstract

The extreme wind speed estimation method, which is critical for designing wind load calculation for building structures, should consider windstorm climate types for mixed climates. However, it is very difficult to obtain windstorm climate types from meteorological data records, therefore, it restricts the application of extreme wind speed estimation in mixed climates. This paper first proposes a windstorm type identification algorithm based on a numerical pattern recognition method that utilizes feature extraction and generalization. Subsequently, three sets of model experiments are conducted using data from three meteorological stations on the southeast coast of China from 1990 to 2016, and the prediction of a single station model and a regional model is discussed. The prediction performances of six machine learning algorithms under different experiments are compared. Based on classification results, the extreme wind speeds calculated based on mixed windstorm types are compared with those obtained from conventional methods, and the effects on structural design for different return periods are analyzed.