【摘要】 针对旋转机械早期故障信号微弱，富含大量噪声的问题，提出麻雀优化算法（SSA）和随机共振（SR）相结合的微弱信号提取方法。首先，对大参数信号进行变尺度处理，使其满足SR的要求；其次，以信噪比作为目标函数，运用SSA算法优化SR模型的结构参数，利用系统的SR实现微弱信号信噪比的提高；最后，通过仿真信号验证所提出方法的有效性，并将该方法应用于轴承内圈故障和轻度磨损钻头微弱信号的提取中。结果表明：提出的方法对微弱信号的提取性能优于传统的SR模型以及PSO-SR模型，有效提高了信号信噪比，实现了故障微弱信号的提取与增强。更多还原

【Abstract】 The early fault signal of rotating machinery is weak and includes a lot of noise, and is hardly to be extracted.To solve this problem, a weak signal extraction method combining Sparrow Search Algorithm(SSA) with Stochastic Resonance(SR) is proposed. Firstly, the large-parameter signal is scaled to meet the requirements of SR. Secondly, with the signal-to-noise ratio(SNR) as the objective function, the SSA algorithm is used to optimize the structural parameters of the SR model, and the system’s SR is used to raise the SNR of weak signals. Finally, the effectiveness of the proposed method is verified by signal simulation. The method is applied to the extraction of weak fault signals from bearing inner ring and lightly worn bits signals. The results show that the extraction performance of the proposed method for weak signals extraction is better than the traditional SR model and PSO-SR model. This method effectively raises the SNR and realizes the extraction and enhancement of faulty weak signals.更多还原