Sensitivity Identification of Low-frequency Cantilever Fibre Bragg Grating Accelerometer

Abstract

Vibration response of low-frequency cantilever fibre Bragg grating (FBG) accelerometer produced by Euler–Bernoulli model (namely FBG-MM model) is found to be frequency-dependent, unsimilar to SDOF model. Therefore, the sensitivity of the cantilever FBG accelerometer could not be identified using polynomial or basic fitting methods. This paper presents the use of cascade-forward backpropagation neural network (CFB) to predict the sensitivity of the cantilever FBG accelerometer in a "black box", which refers to the behaviour of the deep neural network. The inputs of the network are maximum base accelerations and forcing frequencies, which was set between 20 and 90 Hz (below than the first fundamental frequency of the proposed FBG accelerometer), while the output is the wavelength shift. The validation results show that the wavelength shift predicted by the trained CFB demonstrates good agreement with the FBG-MM, with the input parameter within the range of that used in training process. In addition, results also show that the trained CFB would be invalid if the input parameter is out of the range of that used in training process. In real acceleration measurement, since the forcing frequency is unknown beforehand, the trained CFB must be re-trained by considering the maximum base accelerations are embedded with forcing frequencies.