An improved windowed time synchronous averaging method based on genetic algorithm

This paper proposes an improved windowed time synchronous averaging (TSA) method based on genetic algorithm in the implement of signal separation of planetary gearbox. The method of TSA with a full-range window is reviewed to demonstrate the cause of the distortion of the extracted signals. To eliminate the distortion, extracted signals need to be revised, a data-driven genetic algorithm is used to solve the correction coefficients. To validate the effectiveness of the proposed method, two case studies of an analytical signal from simulation and a signal collected from a planetary gearbox test rig are performed. The results of the experiments prove that the extracted signals with correction are more accurate when the proposed method is applied.