RELIABILITY ANALYSIS OF WIND-RESISTANCE OF STANDING SEAM ROOF SYSTEM BASED ON ACTIVE LEARNING KRIGING MODEL

Due to the characteristics of lightweight and flexibility, the standing seam roof system is prone to wind damage under strong wind. In order to reduce the occurrence of wind damage, it is crucial to analyze the wind resistance reliability of a standing seam roof system. In this regard, an analysis method of wind resistance reliability is proposed for a standing seam roof system, based on the Monte Carlo method (AK-MCS) of the active learning Kriging model. The mechanical model of a standing seam roof system is established to analyze its failure form and to derive the limit state function corresponding to its failure criterion; By combining the AK-MCS method with the limit state function, the wind resistance reliability analysis method of a standing seam roof system is proposed. The wind resistance reliability of a standing seam roof system in a typical practical project is analyzed. The analysis results show that: the proposed method can balance accuracy and efficiency, and compared with the Monte Carlo method based on Latin Hypercube Sampling (LHS-MCS), the relative error result of the calculated reliability index is 3.74%, and the calculation cost is 25.1% of the LHS-MCS method; the reliability index β of a standing seam roof system calculated by the recommended method is 2.7703, which is lower than the reliability index required by the specification. Therefore, it is recommended to take corresponding strengthening measures at the seam between the support and roof panels.