With the rapid development of smart manufacturing, data-driven deep learning (DL) methods are widely used for bearing fault diagnosis. Aiming at the problem of model training crashes when data are imbalanced and the difficulty of traditional signal analysis methods in effectively extracting fault features, this paper proposes an intelligent fault diagnosis method of rolling bearings based on Gramian Angular Difference Field (GADF) and Improved Dual Attention Residual Network (IDARN). The original vibration signals are encoded as 2D-GADF feature images for network input; the residual structures will incorporate dual attention mechanism to enhance the integration ability of the features, while the group normalization (GN) method is introduced to overcome the bias caused by data discrepancies; and then the model is trained to complete the classification of faults. In order to verify the superiority of the proposed method, the data obtained from Case Western Reserve University (CWRU) bearing data and bearing fault experimental equipment were compared with other popular DL methods, and the proposed model performed optimally. The method eventually achieved an average identification accuracy of 99.2% and 97.9% on two different types of datasets, respectively.

This paper develops an improved dynamic reliability model for compressor rotor system, defined as a “unconventional active system” here. First, regarding to the variety of system-component connections, system specific reliability modeling technique is presented, in which the stress and strength are both nonnegative stochastic processes. The new model fully considers the load characteristics of rotor blades, and inherently embodied the effect of the statistical dependence between the failures of the rotor blades. Then, calculated by the new model, the relationship between reliability and time, and that between the hazard rate and time, for a compressor rotor system are discussed, respectively. Comparing to the traditional series system reliability model, the new system reliability model developed in this paper has higher accuracy for compressor rotor system, since the traditional models neglect the difference between compressor rotor system and traditional active system. Moreover, in order to master the cruise characteristics of the aero-plane during reliability analysis of its compressor rotor blade set, a flight cruise is separated into several stages based on the value of Mach number and its change rate, and a subsection solution method is innovatively proposed accordingly. At the end of the paper, a certain cruise of fighter plane is analyzed to verify the accuracy of the new method. The results show that, as to a flight cruise with different stages, the new method is basically reasonable to most of the load histories, especially for the situation with impact loads existing.

As a surface peening technique, shot peening introduces residual compressive stresses to the surface of the part, which effectively increases the fatigue life of the structure and material. However, when structures are subjected to alternating loads, this can lead to stress relaxation on the material surface, weakening the effectiveness of the shot peening process. In addition, reasonable shot peening parameters are essential. In this paper, the effects of shot peening pressure and shot coverage on the fatigue life of materials during shot peening were investigated, followed by fatigue tests on 20CrMnTi specimens using a high-frequency fatigue testing machine to study the effects of shot peening and re-shot peening on the fatigue life of shot-peened materials after different load cycles. The results show that a reasonable shot peening pressure and coverage rate can significantly improve the fatigue life of the material, while a shot peening pressure higher than 0.4 MPa will reduce the fatigue life of the material 20CrMnTi. Coverage rates of 100% and 200% can both improve the fatigue life of the material, while a 200% coverage rate has a better strengthening effect. Re-shot peening removes the residual compressive stress relaxation on the surface of the material caused by cyclic loading and improves the fatigue life of the material. The maximum value of the residual compressive stress on the surface of the test material after shot peening is 443 MPa, and after a certain number of fatigue loads, the residual compressive stress on the surface is reduced to 203 MPa, which is subjected to secondary shot peening, and the residual compressive stress is restored to 415 MPa, and the fatigue life is significantly increased. When the second shot peening time is taken as 25% of the fatigue life of the initial shot blasting of the material, the shot peening effect is better.

Bearing preload significantly affects the running performance of a shaft-bearing system including the fatigue life, wear, and stiffness. Due to the mounting error, the bearing rings are often angularly misaligned. The effects of the combined bearing preload and angular misalignment on the fatigue life of ball bearings and a shaft-bearing system are analyzed in this paper. The contact force distribution of angular contact ball bearings in the shaft-bearing system is investigated based on the system model. The system model includes the bearing model, and the shaft model is verified by comparing with the manufacturer’s manual and the results from other theoretical models, with the difference between the results from the present bearing model and manufacturer manual within 3%. The global optimization method is used to replace the Newton–Raphson algorithm to solve the ball elements’ displacements and friction coefficients, which improves the computation efficiency of the system model. The fatigue life of each bearing is evaluated with the consideration of the two preload methods and two angular misalignment cases. The fatigue life results show that the system life at the optimal angular misalignment is more than 1.5 times that without angular misalignment at the low preload value, and this ratio decreases as the preload value increases. The optimal angular misalignment of both the shaft-bearing system and the misaligned bearing is not always consistent, which depends on the preload value and bearing life. Both the constant-displacement preload and constant-force preload do not cause a significant difference in the highest system life. The different misaligned bearings can lead to different highest system lives as the preload value is low.