变分模态分解结合深度迁移学习诊断机械故障

针对机械故障振动信号在变工况条件下的特征提取与智能诊断问题，该研究提出了一种将变分模态分解（Variational Mode Decomposition，VMD）的优化算法与深度迁移学习（Deep Transfer Learning，DTL）模型相结合的故障诊断方法。首先，通过多种群差分进化（Multiple Population Differential Evolution，MPDE）算法和包络熵适应度函数来优化VMD，以解决VMD中本征模态函数分解个数k和惩罚因子α难以自适应确定的问题，再将VMD分解后的本征模态函数根据平均峭度准则进行重构，重构信号经过连续小波变换后获取信号时频特征。然后在深度残差网络（Deep Residual Network，ResNet）的基础上，将ResNet网络与迁移学习（Transfer Learning，TL）模型进行结合，采用边缘分布自适应方法缩小机械故障信号源域数据集与目标域数据集之间的差异，构建出适合于变工况条件下的机械故障诊断深度迁移学习模型。最后，在4个不同工况条件下的滚动轴承试验数据集中，将所提出的MPDE-VMD+DTL的故障诊断方法与传统BP神经网络、ResNet卷积神经网络和迁移成分分析进行对比。结果表明，该研究的MPDE-VMD+DTL方法诊断精度达到84.36%，BP、ResNet和迁移成分分析方法的诊断精度分别为23.60%、71.63%和19.68%，均低于该研究方法。MPDE-VMD +DTL方法实现了在不同工况下的端到端机械故障智能诊断，同时具有较好的泛化能力和鲁棒性。

Mechanical fault diagnosis based on variational mode decomposition combined with deep transfer learning

Abstract: In practice, mechanical equipments usually working with the variable speed and load, and the vibration signal of the equipments is nonlinear and nonstationary. The traditional fault diagnosis methods are prone to misdiagnosis or missed diagnosis. In order to solve the problem of feature extraction and intelligent diagnosis of mechanical fault vibration signal under variable working conditions, a fault diagnosis method combining optimized Variational Mode Decomposition (VMD) and Deep Transfer Learning(DTL) was proposed in this paper. First, Multiple Population Differential Evolution (MPDE) algorithm and envelope entropy fitness function were used to optimize VMD to solve the problem that the decomposition number k and penalty factor α were difficult to be determined adaptively. Second, the intrinsic mode functions of VMD decomposition were reconstructed according to the average kurtosis criterion. Continuous wavelet transform was used to process the reconstructed signal, and the time-frequency characteristics of the reconstructed signal were obtained. Third, combining the Residual Network (ResNet) with Transfer Learning (TL) model, the edge distribution adaptive method was used to reduce the difference between the source domain data set and the target domain data set of mechanical fault signal, and a deep transfer learning model for mechanical fault diagnosis under variable working conditions was constructed. Finally, the MPDE-VMD+DTL method was compared with the traditional BP neural network, ResNet convolution neural network and transfer component analysis (TCA) in different rolling bearing experimental datasets which contained CWRU, XJTU-SY, IMS and MCVN dataset. The results showed that the accuracy of fault diagnosis of MPDE-VMD+DTL method was 84.36%, and that of the BP neural network, ResNet and TCA were 23.60%, 71.63% and 19.68% respectively. MPDE-VMD+DTL method realized the end-to-end mechanical fault intelligent diagnosis under different working conditions, and had good generalization ability and robustness.