Reconstruction Technology of Flexible Structure Shape Based on FBG Sensor Array and Deep Learning Algorithm

A structural displacement field reconstruction method is proposed to aim at the problems of deformation monitoring and flexible plate-like structures in aerospace field. This combines deep neural network model cross-layer connection structure with fiber grating sensor network. paper first introduces principle strain detection sensor, studies mapping relationship between displacement, proposes a strain-displacement conversion based on an improved Then intelligent system built. By controlling stepping distance motor produce different deformations plate structure, information real are obtained high-density dial indicator array. Finally, prediction by training, under states realized. Experimental results show that mean absolute error measuring points this less than 0.032 mm. feasible theory practice can be applied vehicle structures.