Gear fault diagnosis has been a vital technology to enhance the reliability and reduce the maintenance cost of gear systems. Tooth spalling is one of the most destructive surface failure models of the gear faults. Revealing the dynamic characteristics of a gear system with spalling fault and extracting the fault feature are the premise and basis for effective fault diagnosis. Previous studies have mainly concentrated on the spalling damage on a single gear tooth, but the spalling distributed over double teeth which usually occurs in practical engineering problems is rarely reported. To remedy this deficiency, this paper constructs a new dynamical model of a gear system with double-teeth spalling fault and validates this model with various experimental tests. The dynamic characteristics of gear systems are obtained by considering the excitations induced by the number of spalling teeth, the relative position of two faulty teeth, and the rotational speed. The method based on the Variational Mode Decomposition (VMD) and the Fast Kurtogram (FK) is proposed to extract the features of the double-teeth spalling fault. First, the raw signal is decomposed into a set of Intrinsic Mode Functions (IMFs) by applying the VMD, and the IMFs with strong correlation are summed as a reconstructed signal. The reconstructed signal is then filtered by an optimal band-pass filter based on the FK. Combined with envelope spectrum analysis, the feature extraction ability of the proposed method is compared with that of the original FK method and the method based on the Empirical Mode Decomposition and the FK, respectively. The results indicate that the proposed dynamic model and fault feature extraction method can provide a theoretical basis for spalling defect diagnosis of gear systems.
In this paper, the dynamics of a mechanical exciter and three cylindrical rollers (CRs) with the non-identical friction coefficients interacting through a rigid platform is considered. Sufficient conditions for the existence and stability of synchronous solutions in the coupled system are derived by using the average method of modified small parameters and Routh-Hurwitz principle. The obtained theoretical results are illustrated and analysed based on numerical calculations. In the analysis, the numerical results are presented for simple one-parameter variation, as well as for a group of varied parameters, when the influence of the coupling structure’s parameters on synchronization and stability is studied. An appropriate selection of the key parameters will eventually lead to desired synchronization performance. Finally, the theoretical and numerical results are supported by computer simulations. The stable synchronized states can be observed in the simulations even when there are unavoidably small differences in the three friction coefficients. If we mismatch the friction coefficients of the CRs, they are seen to synchronize with a constant phase difference. The key feature of the proposed coupled system is the dynamic coupling torque, which serves as the vehicle for transferring energy from an induction motor to three CRs without the direct driving sources and the synchronization controller for maintaining the originally synchronous and stable states against the disturbance in the simulations.
In recent advances, deep learning-based methods have been broadly applied in fault diagnosis, while most existing studies assume that source domain and target domain data follow the same distribution. As differences in operating conditions lead to the deterioration of diagnosis performance, domain adaptation technology has been introduced to bridge the distribution gap. However, most existing approaches generally assume that source domain labels are available under all health conditions during training, which is incompatible with the actual industrial situation. To this end, this paper proposes a semi-supervised adversarial transfer networks for cross-domain intelligent fault diagnosis of rolling bearings. Firstly, the Gramian Angular Field method is introduced to convert time domain vibration signals into images. Secondly, a semi-supervised learning-based label generating module is designed to generate artificial labels for unlabeled images. Finally, the dynamic adversarial transfer network is proposed to extract the domain-invariant features of all signal images and provide reliable diagnosis results. Two case studies were conducted on public rolling bearing datasets to evaluate the diagnostic performance. An experiment under variable operating conditions and an experiment with different numbers of source domain labels were carried out to verify the generalization and robustness of the proposed approach, respectively. Experiment results demonstrate that the proposed method can achieve high diagnosis accuracy when dealing with cross-domain tasks with deficient source domain labels, which may be more feasible in engineering applications than conventional methodologies.
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.