A certain number of hole-like defects will occur in aluminum alloys under cyclic loading. The internal holes will reduce the strength of the material and cause stress concentration, which will aggravate the development of fatigue damage. A classification method of defect features based on X-ray CT damage data is proposed. The random hole distribution model is established through the linear congruence method and the region division method. The hole parameter is introduced as the intermediate variable of the 3D reconstruction model of internal defects. In the mesoscopic stage, the function relationship between the distribution of random holes and the fatigue life is established based on the coupling relationship between the number and proportion of pores and the fatigue life. In the macroscopic stage, the relationship between the random holes and the macroscopic crack growth life is established by taking the crack length as the damage variable. The crack propagation rate decreased with the increase in the number of holes. The prediction model of the whole life stage is established using the life function from microcrack initiation to macroscopic crack propagation. Finally, the validity of the whole stage fatigue life prediction model is demonstrated through the comparison and verification of experiments, which provides a certain engineering value for the life estimation of 6061-T6 aluminum alloy materials.

Remote sensing images have the characteristics of high complexity, being easily distorted, and having large-scale variations. Moreover, the motion of remote sensing targets usually has nonlinear features, and existing target tracking methods based on remote sensing data cannot accurately track remote sensing targets. And obtaining high-resolution images by optimizing algorithms will save a lot of costs. Aiming at the problem of large tracking errors in remote sensing target tracking by current tracking algorithms, this paper proposes a target tracking method combined with a super-resolution hybrid network. Firstly, this method utilizes the super-resolution reconstruction network to improve the resolution of remote sensing images. Then, the hybrid neural network is used to estimate the target motion after target detection. Finally, identity matching is completed through the Hungarian algorithm. The experimental results show that the tracking accuracy of this method is 67.8%, and the recognition identification F-measure (IDF1) value is 0.636. Its performance indicators are better than those of traditional target tracking algorithms, and it can meet the requirements for accurate tracking of remote sensing targets.