This paper proposes an efficient and noise-insensitive end-to-end lightweight deep learning method. The method synthesizes the characteristics of a frequency domain transform and a deep convolutional neural network. The former can extract multiscale information in vibration signal processing and the latter has a good classification performance, data-driven, and high transfer-learning ability. A vibration signal is decomposed into a pyramidal wavelet packet, and each sub-band coefficient is used as an input of a channel in the deep network. A deep residual convolutional network based on a separable convolution and concatenated rectified linear unit (CReLU) lightweight convolution technology is used for fault diagnosis. The proposed algorithm is compared with related deep learning algorithms using two bearing datasets produced by Case Western Reserve University (CWRU) and the Center for Intelligent Maintenance Systems (IMS), University of Cincinnati. Compared with the existing algorithms, the experimental results show that the comprehensive performance of the algorithm proposed in this paper is “small, light, and fast,” and satisfactory diagnostic results are obtained in the fault diagnosis of rotating machinery.

To improve the fault diagnosis performance for rotating machinery, an efficient, noise-resistant end-to-end deep learning (DL) algorithm is proposed based on the advantages of the wavelet packet transform in vibration signal processing (the capability to extract multiscale information and more spectral distribution features) and deep convolutional neural networks (good classification performance, data-driven design and high transfer-learning ability). First, a vibration signal is subjected to pyramid wavelet packet decomposition, and each sub-band coefficient is used as the input for each channel of a deep convolutional network (DCN). Then, based on the lightweight modeling requirements and techniques, a new DCN structure is designed for the fault diagnosis. The proposed algorithm is compared with the support vector machine algorithm and the published DL algorithms based on a bearing dataset produced by Case Western Reserve University. The experimental results show that the proposed algorithm is superior to the existing algorithms in terms of accuracy, memory space, computational complexity, noise resistance, and transfer performance, producing good results.

A kinematic model of the planetary roller screw mechanism (PRSM) is proposed, which accounts for the run-out errors of the screw, roller, nut, ring gear, and carrier, and the position errors of the nut and the pinhole in the carrier. The roller floating region, which contains all the possible positions of the roller inside the pinhole, is obtained by analyzing the axial clearances between mating thread surfaces and the radial clearance between the roller and carrier. The proposed model is based on the constraint that the set of roller floating region is not empty. Then, the additional rigid-body movement on the nut is derived and the path of motion transfer from the screw to the nut is obtained. According to the fundamental property of rigid-body kinematics, the axial velocity of the nut is derived and the transmission error of the PRSM is calculated. The proposed model is verified by comparing the calculated transmission error with experimental one. The results show that the transmission error of the PRSM with run-out and position errors is cyclic with a period corresponding to the rotation period of the screw and the magnitude of the transmission error can be much larger than the lead error of the screw. Besides, due to the run-out and position errors, the roller can move radially or transversally inside the pinhole of the carrier when the elements in the PRSM are regarded as rigid bodies.

In this article, 3D or three-dimensional finite element analysis is used to simulate and evaluate the load distribution characteristics of a planetary roller screw mechanism under thermo-mechanical coupling. The finite element model takes into account the installation modes of the planetary roller screw mechanism, which is verified by comparison with theoretical models for a certain load magnitude in four installation modes. In addition, the effects of the installation mode, load magnitude, and temperature condition on the load distribution are also systematically analyzed. The numerical results reveal a phenomenon of threads separating from the meshing, which indicates that the influence of thermo-mechanical coupling on the load distribution cannot be ignored. Furthermore, the influence of the installation mode on the screw–roller interface is larger than that on the nut–roller interface. Compared with the screw–roller interface, the temperature difference is one of the main conditions affecting the load distribution of the planetary roller screw mechanism and has a significant effect on the nut–roller interface. In addition, the influences of the screw rotational speed and the load magnitude on the load distribution on the screw–roller interface are larger than those on the nut–roller interface for the four installation modes.

The thermal behavior of the standard planetary roller screw mechanism needs to be investigated since the large amount of heat generated by the friction torque on multiple contact points during the transmission process. In this article, a simplified transmission system model of standard planetary roller screw mechanism is first established for the finite element analysis. Second, the friction torque of standard planetary roller screw mechanism is calculated and the boundary conditions of thermal analysis are deduced. Then, the transient thermal analysis of the standard planetary roller screw mechanism based on finite element method is conducted by considering the moving heat source and thus temperature field distribution at any time and the temperature rise curve at different positions of the standard planetary roller screw mechanism can be obtained. Finally, the correlation between the experimental data and the calculated values confirms the validity of the proposed thermal model for the transient thermal analysis.