Research on Decoupling of Fiber Bragg Grating Tactile Signal Based on Neural Network

• Published in: Journal of physics. Conference series Vol. 2617; no. 1; pp. 12006 - 12015
• Main Authors: Yan, Haitang, Jin, Rencai, Zhang, Jiaojiao, Qian, Yuandi, Qian, Muyun
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.10.2023
• Subjects: Back propagation networks; Bragg gratings; Computer simulation; Decoupling; Fiber Bragg grating; Finite element method; Flexible; Neural network; Neural networks; Physics; Tactile sensors (robotics); Three-dimensional force; Wearable technology
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2617/1/012006

Abstract For the purpose of resolving the nonlinear coupling problem of the three-dimensional force of the fiber Bragg grating tactile sensor applied to flexible wearable devices, we propose a method to decouple the three-dimensional force signal by applying the error back-propagation neural network and the radial-based neural network to simulation and experiment based on the mechanical finite element simulation of the sensing unit, using the fiber Bragg grating tactile sensor as the research object. The decoupling results of the neural network on the 3D force simulation data show that the radial-based neural network has higher decoupling accuracy than the error back-propagation neural network, and can better approximate the mapping relationship between the 3D force magnitude containing noise and the center wavelength drift of the FBG tactile sensor. The research results of this paper are of practical value for the research and promotion of the flexible haptic sensor for electronic skin.