Size-topology optimization design and modeling of a new gripper for precision manipulation robot
摘要
This study proposes a novel design and modeling framework for a compliant robotic gripper with high industrial relevance in precise manipulation robots. The gripper structure is optimized through stress-constrained topology optimization, while its mechanical behaviors are predicted through a physics-informed deep neural network. Two use cases are explored, including the jaw’s stroke prediction and the working frequency modeling under physical constraints. A multi-objective genetic algorithm identifies optimal design parameters, achieving a 4.71 mm stroke, 43.62 Hz frequency, 22.25 MPa stress, and a safety factor of 3.23. The entire stroke of the gripper is 6 mm. It was revealed that the stroke is amplified twice without an external displacement amplification mechanism. A 3D-printed prototype is tested; the results indicated that there is good alignment between predictions and experimental results. The results revealed that the gripper’s large stroke enables it to adapt to objects of varying sizes. The design and modeling synthesis method for the compliant robotic gripper highlights its potential for applications in industrial manipulation tasks on robotic arms.