ANFIS-based long-period fiber bragg grating curvature measuring method

Abstract

The invention discloses an ANFIS-based long-period fiber bragg grating curvature measurement method. The method comprises the following steps; step one, establishing a training sample set; step two, constructing an adaptive-network-based fuzzy inference system (ANFIS); and step three, measuring the curvature by using the long-period fiber bragg grating. The invention discloses a long-period fiberbragg grating curvature identification method which is used for measuring the curvature of a long-period fiber bragg grating sensor. The objective of the invention is to combine advantages of excellent learning, approximation and prediction capabilities of fuzzy logic and a neural network so as to improve the accuracy of the strain quantification of the fiber grating sensor of the long-period fiber; compared with an existing curvature measurement method of the long-period fiber bragg grating, the method has the advantages that the strain quantification accuracy is high, the learning period isshort, and the model universality is high. The method can be applied to other sensing applications only by slight modification.

Description

technical field [0001] The invention relates to the field of long-period fiber grating strain sensing, in particular to an ANFIS-based long-period fiber grating curvature measurement method. Background technique [0002] Long-period fiber grating strain sensors have the advantages of small size, light weight, anti-electromagnetic interference, high durability, and corrosion resistance, so they have attracted extensive attention from the engineering community. Its working principle is based on the resonance wavelength shift of the long-period fiber grating under the action of physical parameters such as curvature. It is therefore crucial to determine the relationship between the external parameters and the resonant wavelength with sufficient precision. [0003] The resonant wavelength and attenuation rate of the transmission spectrum of the LPFG vary with the bending curvature. During the bending process of the LPFG, the bending changes the mode field distribution of the co...

AI Technical Summary

Problems solved by technology

However, the curvature sensing characteristics of long-period fiber gratings are quite complicated. In actual curvature measurement, it is very difficult to reverse the curvature based on the existing resonance wavelength value. To solve this problem, an adaptive neuro-fuzzy system is used to detect the The curvature of the raster is predicted

Images