To improve the peak detection accuracy of Fiber Bragg Grating (FBG) sensors, a peak detection method for Fiber Bragg Grating based on Genetic Algorithm Optimized Generalized Regression Neural Network (GA-GRNN) is proposed. The genetic algorithm is employed to optimize the smoothing factor of the generalized regression neural network, enhancing its accuracy in calculating the central wavelength of FBGs. Consequently, the overall accuracy of the FBG peak detection system is significantly improved. Experimental results demonstrate a detection accuracy of 3.1 pm. This method offers high precision and resolution, enabling the detection of arbitrary FBG peaks within a short wavelength range.