In recent years, medium- and low-volume fraction silicon carbide particle-reinforced aluminum matrix composites (SiCp/Al) have increasingly become a key material in the aerospace industry. Force prediction and material removal mechanism analysis of milling SiCp/Al are necessary to improve the surface integrity of products. An orthogonal experiment of SiCp/2009Al with a volume fraction of 20% was carried out, and the effect of the milling parameters on milling force was studied with the input parameters of milling speed, feed rate, and milling depth. Thereby, the empirical force model of milling SiCp/2009Al is established by fitting the experiential data based on the multiple linear regression analysis methods. Moreover, the effects of the milling parameters on the force were analyzed. Finally, the material removal mechanism of milling SiCp/Al is analyzed based on dislocation theory. The analyzed results reveal that the removal mechanism of the SiCp/Al composites includes plastic deformation of the aluminum matrix, cutting of particles, fragmentation, and deboning. Based on dislocation theory and maximum undeformed thickness theory, the effect of cutting parameters on the form of material removal was analyzed, which serves as a guide for selecting appropriate machining parameters to obtain improved machining quality of SiCp/Al composites.

Although existing few-shot learning works yield promising results for in-domain queries, they still suffer from weak cross-domain generalization. Limited support data requires effective knowledge transfer, but domain-shift makes this harder. Towards this emerging challenge, researchers improved adaptation by introducing task-specific parameters, which are directly optimized and estimated for each task. However, adding a fixed number of additional parameters fails to consider the diverse domain shifts between target tasks and the source domain, limiting efficacy. In this paper, we first observe the dependence of task-specific parameter configuration on the target task. Abundant task-specific parameters may over-fit, and insufficient task-specific parameters may result in under-adaptation – but the optimal task-specific configuration varies for different test tasks. Based on these findings, we propose the Task-aware Adaptive Network (TA ² -Net), which is trained by reinforcement learning to adaptively estimate the optimal task-specific parameter configuration for each test task. It learns, for example, that tasks with significant domain-shift usually have a larger need for task-specific parameters for adaptation. We evaluate our model on Meta-dataset. Empirical results show that our model outperforms existing state-of-the-art methods. Our code is available at https://github.com/PRIS-CV/TA2-Net.

In this paper, a milling force prediction model considering the Taylor factor is established, and the Ti-6Al-4V milling force predicted by the model under different milling parameters is presented. In the study, the milling experiment of Ti-6Al-4V was carried out, the milling force was collected by the dynamometer, and the microstructure evolution of the milling surface before and after milling was observed by EBSD. Through the comparative analysis of the experimental results and the model prediction results, the reliability of the prediction model proposed in this study was verified, and the influences of the milling parameters on the milling force were further analyzed. Finally, based on the EBSD observation results, the effects of the milling parameters on the microstructure evolution of the milling surface were studied. The results show that both the tangential milling force and normal milling force increase with the increase in the milling depth and feed rate. Among the milling parameters selected in this study, the milling depth has the greatest influence on the milling force. The average errors of the tangential milling force and normal milling force predicted by the milling force model are less than 10%, indicating that the milling force prediction model established in this paper considering Taylor factor is suitable for the prediction of the Ti-6Al-4V milling force. With the change in the milling parameters, the grain structure, grain size, grain boundary distribution, phase distribution, and micro-texture of the material surface change to varying degrees, and the plastic deformation of the milling surface is largely coordinated by the slip.