Vibration reliability analysis for aeroengine compressor blade based on support vector machine respo

• 作 者: GAO Hai-feng BAI Guang-chen
• 机 构: School of Energy and Power Engineering, Beijing University of Aeronautics and Astronautics, Beijing
• 出 处: 中南大学学报（英文版）
• 发表日期: 2015年5期
• 关键词: vibration reliability analysis compressor blade support vector machine response

To ameliorate reliability analysis efficiency for aeroengine components, such as compressor blade, support vector machine response surface method (SRSM) is proposed. SRSM integrates the advantages of support vector machine (SVM) and traditional response surface method (RSM), and utilizes experimental samples to construct a suitable response surface function (RSF) to replace the complicated and abstract finite element model. Moreover, the randomness of material parameters, structural dimension and operating condition are considered during extracting data so that the response surface function is more agreeable to the practical model. The results indicate that based on the same experimental data, SRSM has come closer than RSM reliability to approximating Monte Carlo method (MCM); while SRSM (17.296 s) needs far less running time than MCM (10958 s) and RSM (9840 s). Therefore, under the same simulation conditions, SRSM has the largest analysis efficiency, and can be considered a feasible and valid method to analyze structural reliability.