Visual reconstruction of flexible structure based on fiber grating sensor array and extreme learning machine algorithm

A visual reconstruction method was proposed based on fiber Bragg grating (FBG) sensors and an intelligent algorithm, aiming to solve the problems of low accuracy and complex reconstruction process in conventional reconstruction methods of flexible structures. Firstly, the wavelength data containing structural strain information was captured by FBG sensors, together with deformation displacement information. Subsequently, a predicted model was built based on an extreme learning machine (ELM) and further optimized by the particle swarm optimization (PSO) algorithm. Different deformation patterns were tested on an aluminum alloy plate, indicating the ability of the predicted model to produce the deformation displacement for reconstruction. The experimental results show that the maximum error can be as low as 0.050 mm, which verifies that the proposed method is feasible and satisfied with the deformation monitoring of the spacecraft structure.