【摘要】 为了能在有噪声干扰的复杂环境下提取出滚动轴承振动信号的故障特征,提出了一种基于粒子群优化神经网络的轴承故障特征频率的提取方法。首先对采集的振动信号进行降噪处理;其次,进行特征提取与约简;最后,采用群体智能算法——粒子群算法优化BP神经网络初始权值和阈值,构建二者结合的模型来预测滚动轴承剩余有效寿命,并结合试验平台的实验数据对该模型进行验证。实验结果表明:该方法能够很好的降低提取振动信号时由于噪音产生的影响,滚动轴承剩余的预测更加准确。更多还原

【Abstract】 In order to extract the fault characteristics of rolling bearing vibration signal in the complex environment with noise interference, a method of extracting the fault characteristic frequency of rolling bearing based on particle swarm optimization neural network is proposed. The acquisition of vibration signal and white noise and feature extraction and reduction, finally using the algorithm of swarm intelligence, particle swarm algorithm to optimize initial weights and threshold, the BP neural network to build a combination of model to predict remaining useful life of rolling bearing and combining the test platform of experimental data to validate the model. The experimental results show that the method can effectively reduce the influence of noise when extracting vibration signals, and the prediction of rolling bearing residual is more accurate.更多还原