School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou 221116, China.
Faculty Mechanical, Maritime and Materials Engineering, Delft University of Technology, Delft 2628, The Netherlands.
Sensors (Basel). 2018 May 28;18(6):1735. doi: 10.3390/s18061735.
Poor working environment leads to frequent failures of planetary gear trains. However, complex structure and variable transmission make the vibration signal strongly non-linear and non-stationary, which brings big problems to fault diagnosis. A method of planetary gear fault diagnosis via feature image extraction based on multi central frequencies and vibration signal frequency spectrum is proposed. The original vibration signal is decomposed by variational mode decomposition (VMD), and four components with narrow bands and independent central frequencies are decomposed. In order to retain the feature spectrum of the original vibration signal as far as possible, the corresponding feature bands are intercepted from the frequency spectrum of original vibration signal based on the central frequency of each component. Then, the feature images of fault signals are constructed as the inputs of the convolution neural network (CNN), and the parameters of the neural network are optimized by sample training. Finally, the optimized CNN is used to identify fault signals. The overall fault recognition rate is up to 98.75%. Compared with the feature bands extracted directly from the component spectrums, the extraction method of the feature bands proposed in this paper needs fewer iterations under the same network structure. The method of planetary gear fault diagnosis proposed in this paper is effective.
较差的工作环境会导致行星齿轮传动频繁出现故障。然而，复杂的结构和多变的传动比使得振动信号呈现强烈的非线性和非平稳性，这给故障诊断带来了很大的问题。本文提出了一种基于多中心频率和振动信号频谱的特征图像提取的行星齿轮故障诊断方法。原始振动信号通过变分模态分解（VMD）进行分解，分解出四个具有窄带宽和独立中心频率的分量。为了尽可能保留原始振动信号的特征谱，根据各分量的中心频率，从原始振动信号的频谱中截取相应的特征频段。然后，将故障信号的特征图像作为卷积神经网络（CNN）的输入，通过样本训练优化神经网络的参数。最后，利用优化后的 CNN 对故障信号进行识别。总的故障识别率高达 98.75%。与直接从分量谱中提取的特征频段相比，本文提出的特征频段提取方法在相同的网络结构下需要更少的迭代次数。因此，本文提出的行星齿轮故障诊断方法是有效的。
