Intelligent assembly correction system based on fiber Bragg grating sensing array

To address the challenge of identifying and compensating online for end-effector deviations caused by manufacturing errors, clamping errors, and contact uncertainties during assembly, this study proposes an intelligent assembly correction method based on fiber Bragg grating array sensing. In this method, fiber Bragg grating sensors are mounted on the outer sides of the four flexible fingers of the gripper to capture multidirectional surface wavelength responses during contact. A wavelength–position deviation mapping model is established, and inverse kinematics is employed to compute joint correction values for closed-loop pose adjustment of the end-effector. Finite element analysis indicates that the optimal sensor placement is approximately 35 mm from the finger base. The experimental results show that the four fiber Bragg grating sensors exhibit a force–wavelength sensitivity of approximately 50 pm/N, whereas the mean error, standard deviation, and maximum absolute error of position prediction were 0.01, 0.06, and 0.15 mm, respectively. The proposed system achieves a final assembly success rate of 93.3%. These results demonstrate that the proposed method provides a feasible solution for online sensing and closed-loop compensation in constrained assembly processes.