Identification of slip parameters based on fiber Bragg grating and neural network

This paper proposes a flexible sensor made of fiber Bragg gratings (FBGs) package that can effectively recognize the direction and velocity of relative sliding on its surface. The measurement principle and structural design of the sensor are introduced, and the sensor is analyzed by finite element simulation software to verify that the sensor can detect the shear deformation of relative sliding on its surface. On this basis, an experimental platform is built to test the relative sliding direction and velocity, the feature values are extracted after the initial signal is processed with noise reduction, and the recognition prediction is carried out by using back-propagation neural network (BPNN) and GA-BP neural network optimized by Genetic Algorithm (GA). The experimental results show that GA-BP neural network has better recognition accuracy, and the correlation coefficients R² in the recognition of the sliding direction and velocity parameters are 0.9851 and 0.9819, respectively, which are able to recognize the sliding sensation parameters effectively.