Aiming at the problems of large error and poor stability of traditional wavelength demodulation of fiber Bragg grating sensor, a wavelength peak detection method of fiber Bragg grating sensor based on generalized regression neural network and improved particle swarm optimization algorithm is proposed. Through the improved particle swarm optimization algorithm, the smoothing factor of the generalized regression neural network is optimized to improve the accuracy of the central wavelength calculation of the generalized regression neural network. The performance of the proposed method at different central wavelengths is analyzed through experiments. The results show that the proposed method is more stable than the traditional method, and the demodulation error is smaller, the absolute deviation of the overall central wavelength is reduced by 35.90% and 24.24%, and the relative wavelength variation deviation is reduced by 20.00% and 13.04%.
