面向微小振动故障诊断的匹配小波深度迁移学习

针对传统方法在微小振动故障诊断中存在的特征识别效率低和样本数量有限等问题，提出匹配小波深度模型迁移学习方法。首先利用Morse连续小波对一维故障信号进行匹配升维，捕捉微小变化，得到可视化强化特征图像；其次对深度迁移网络源域模型进行有效迁移，该模型具有高效的图像学习经验，可降低目标域训练样本数量；最后在模型迁移中根据有限数据进行流程的参数优化。实验证明，该方法泛化能力强，可对多工况下微小特征进行检测与定位，并有效减少对数据的依赖，能够极大提高运算速度和诊断精度。

Research on matched wavelet deep transfer learning for micro vibration fault diagnosis

This paper proposed a matching wavelet depth model transfer learning algorithm to solve the problems of low efficiency of feature identification and limited number of samples, which exist in traditional methods for small vibration fault diagnosis. Firstly, it used Morse continuous wavelets to capture small changes in a one-dimensional fault signal by matching and up-dimensioning the signal to obtain a visual enhanced feature image. Then, this algorithm effectively transfered the source domain model of the depth transfer network. This model had efficient image learning experience and could reduce the number of training samples in the target domain. Finally, it optimized the parameters of the process for this algorithm based on limited data in model transfer. The algorithm has proven to be highly generalizable, allowing the detection and localization of minute features in multiple operating conditions and effectively reducing the reliance on data, greatly improving the speed of computing and diagnostic accuracy.