When the vibration signals of the rolling bearings contain strong interference noise, the spectrum division of the vibration signals is seriously disturbed by the noise. e traditional empirical wavelet transform (EWT) decomposes signals into a large number of components, and it is difficult to select suitable components that contain fault information. In order to address the problems above, in this paper, we proposed the improved empirical wavelet transform (IEWT) method. e simulation experiment proved that IEWT can solve the problem of a large number of EWT components and separate the impact component effectively which contains bearing fault information from noise. e IEWT method is combined with the support vector machine (SVM) to diagnosis the fault of the rolling bearings. e permutation entropy (PE) is used to construct feature vectors for its strong induction ability of dynamic changes of nonstationary and nonlinear signals. e crucial parameter penalty factor C and kernel parameter g of SVM are optimized by quantum genetic algorithm (QGA). Compared with traditional EWT and variational mode decomposition (VMD) methods, the effectiveness and advantages of this method are demonstrated in this study. e classification prediction ability of SVM is also better than that of K-nearest neighbor (KNN) and extreme learning machine (ELM).
Remaining useful life (RUL) prediction of key components is an important influencing factor in making accurate maintenance decisions for mechanical systems. With the rapid development of deep learning (DL) techniques, the research on RUL prediction based on the data-driven model is increasingly widespread. Compared with the conventional convolution neural networks (CNNs), the multi-scale CNNs can extract different-scale feature information, which exhibits a better performance in the RUL prediction. However, the existing multi-scale CNNs employ multiple convolution kernels with different sizes to construct the network framework. There are two main shortcomings of this approach: (1) the convolution operation based on multiple size convolution kernels requires enormous computation and has a low operational efficiency, which severely restricts its application in practical engineering. (2) The convolutional layer with a large size convolution kernel needs a mass of weight parameters, leading to a dramatic increase in the network training time and making it prone to overfitting in the case of small datasets. To address the above issues, a multi-scale dilated convolution network (MsDCN) is proposed for RUL prediction in this article. The MsDCN adopts a new multi-scale dilation convolution fusion unit (MsDCFU), in which the multi-scale network framework is composed of convolution operations with different dilated factors. This effectively expands the range of receptive field (RF) for the convolution kernel without an additional computational burden. Moreover, the MsDCFU employs the depthwise separable convolution (DSC) to further improve the operational efficiency of the prognostics model. Finally, the proposed method was validated with the accelerated degradation test data of rolling element bearings (REBs). The experimental results demonstrate that the proposed MSDCN has a higher RUL prediction accuracy compared to some typical CNNs and better operational efficiency than the existing multi-scale CNNs based on different convolution kernel sizes.
Using the magnetorheological (MR) damper model, this paper derives a semiactive suspension model for a high-speed railway vehicle, and a new evaluating method is proposed to analyze the effect of two kinds of time delay existing in control systems on vehicle dynamic performance. The railway vehicle is modeled by a 50 degree-of-freedom (DOF) system which considers the full 6 DOF of each wheelset, bogie, car body, and the pitch angle of each axle box. Several control strategies, sky-hook (SH), acceleration-driven damping (ADD), and mixed SH-ADD, are considered in the semiactive suspension system. To evaluate the effect of these semiactive controls and the different kinds of time delay on the lateral ride index of a high-speed railway vehicle, a 3D surface in a rectangular coordinate system is described. The cross curve between the 3D surface and a horizontal plane which represents the performance of passive suspension is projected on the X-Y plane, and the area enclosed by the contour line, X-axis, and Y-axis can be used to evaluate the performance of semiactive controls. The results show that the new method is convenient to evaluate the performance of semiactive control strategies visually when there is more than one kind of time delay.
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.