To address the complex challenge of identifying the contact state between a shaft and a hole and to improve the efficiency of robotic shaft-hole assembly tasks, a robotic shaft-hole assembly method based on variable admittance control is proposed. In this method, admittance control serves as the foundational force controller for shaft-hole assembly. On this basis, the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm from deep reinforcement learning is utilized to optimize the parameters of the admittance controller. Additionally, a nonlinear reward function is designed, which not only prevents the assembly strategy from converging to local optima but also further accelerates the training speed of the assembly task. Experiments conducted with a collaborative robotic arm performing 15° inclined hole assembly demonstrated that the assembly efficiency of the variable admittance method was 9.6% higher than that of the fixed admittance parameter method, validating the feasibility and effectiveness of the proposed variable admittance shaft-hole assembly method.

Recently, hydroforming has paid dividends in composite forming due to its uniform pressure distribution, which helps in reducing the delamination defects. Considering the need to develop an appropriate criterion for evaluating the formability of FMLs, inspired by sheet metal forming and testing, the uniform pressure loading test was adopted to characterize the formability of semi-cured FMLs by forming limit curve ( FLC). In this paper, both theoretical analysis models considering and ignoring the tangential cohesive effect were established, and the stress expression of the critical zone was given. The results show that the tangential cohesive stress demonstrates a non-negligible influence on the FLC. A new form of comprehensive FLC was given by defining global equivalent strain and global strain ratio and analyzed by the finite element method. In addition, the numerical simulation model and the experimental parameters were verified. A simplified Hashin criterion was proposed and developed into the numerical simulation as a subroutine based on theoretical analysis. Parameters such as blank holder pressure, pressure rate, and temperature were considered both in experiments and simulation. Only fiber stretching damage was distinguished in the cross, single, and arc crack but no wrinkling. As predicted theoretically, a lower forming limit is expected when FMLs are subjected to greater tangential cohesive stress. Finally, with the help of numerical simulation, the influence of different boundary conditions on the comprehensive FLC was studied. Instead of a simple evaluation of FMLs, this comprehensive FLC could be used directly to optimize hydroforming processes in the engineering field.