粒子群优化算法在齿轮箱振动信号去噪中的应用

 以振动频谱分析和粒子群优化算法为主要理论依据，以风力涡轮机齿轮箱为例，提出一种基于一维加速搜索算法和粒子群优化的齿轮箱振动信号去噪方法。利用一维加速搜索算法缩减搜索范围，应用粒子群优化算法提升优化效果，对切比雪夫带通滤波器和Morlet小波滤波器的设计参数进行优化，并对齿轮箱故障振动信号进行滤波处理。仿真实验结果表明，此方法能够实现快速有效滤波去噪，适用于齿轮箱实时故障诊断的研究，具有一定的理论研究价值和实践应用价值。

Application of Particle Swarm Optimization Algorithm to Denoising Vibration Signal of Gearbox

Taking the gearbox in wind turbine as an example, this paper introduces a method about denoising the vibration signal of gearbox based on the vibration spectrum analysis and particle swarm optimization algorithm. The particle swarm optimization algorithm can reduce the search space by using one dimension search, and improve the optimization result by simultaneously optimizing the design parameters of Chebyshev band pass filter and Morlet wavelet filter, eventually filtering out the fault vibration signal of the gearbox. Experimental results show that this method can effectively eliminate the external noise in the vibration signal, and that the hybrid algorithm can effectively reduce the search range of particle swarm optimization and improve the optimization result for the relevant parameter optimization of Chebyshev band-pass filter and Morlet wavelet filter. It is applicable to the real-time gearbox fault diagnosis research. Therefore, it has certain value for theoretical research and practical applications. This hybrid algorithm has good optimized performance and the optimization process is fast. The fault features are obvious in the denoised signal, and can be applied to the real-time fault diagnosis of gearbox in the future research.