Planetary gearbox is a key transmission apparatus used to change speed and torque. Planetary gear is one of the most failure-prone components in planetary gearbox. Due to the complexity of the working environment, the collected vibration signals contain a lot of noise and interferences. The fault characteristic frequencies are usually submerged or even lost. Thus, the feature extraction of the vibration signal is beneficial to the subsequent fault diagnosis. As a fault identification approach that has been increasingly popular in the field of fault diagnosis, deep learning requires a large number of samples to train the model. Insufficient samples lead to low diagnostic accuracy for deep learning models. This paper proposes a novel fault diagnosis approach for planetary gears based on intrinsic feature extraction and deep transfer learning. The original vibration signals are decomposed into a series of band-limited intrinsic mode functions (BLIMFs) by variational mode decomposition (VMD). BLIMF with the most apparent fault characteristics is selected to generate two-dimensional time-frequency maps by continuous wavelet transform (CWT). The preprocessed time-frequency maps are adopted as the input of the pretrained VGG16 model. The bottom layers are frozen, and the top layers are fine-tuned to achieve the fault diagnosis of planetary gears. The applications to planetary gear datasets verify the superiority of the proposed method.
It is very important to detect fault and extract fault features of mechanical systems at an early stage, because the above two steps promise normal operation of mechanical systems. However, they are also very challenging. In this context, this article has put forward improved particle swarm optimization-based adaptive multiresolution dynamic mode decomposition of rolling bearing (IPSO-AMDMD). Multiresolution dynamic mode decomposition (MRDMD) is used to decompose signals of rolling bearing at the early stage, multiscale fuzzy entropy (MFE) is employed to divide low-rank components and sparse components. In order to make up for the shortcomings of the above two methods, namely truncated rank of MRDMD and inaccurate selection in threshold of MFE, this paper has proposed a new fitness function, which is called synthetic envelope kurtosis characteristic energy difference ratio, and adopted the improved particle swarm optimization algorithm (IPSO) to select the optimal parameters adaptively. With these two steps, signals can be decomposed perfectly. Finally, reconstructed signals, which are obtained through the combination of signals from each layer according to a certain weight, go through DMD again, thus getting the final recovered signal. Through simulation experiment and in-field experiment, it has proved that IPSO-AMDMD is viable and sound in accurately extracting features from fault signals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.