一种基于CNN的混叠光谱解调算法及FPGA实现

为了解决光纤布拉格光栅(FBG)传感网络的光谱信号混叠问题，基于现场可编程门阵列(FPGA)提出了一种利用卷积神经网络(CNN)模型的混叠光谱信号解调算法，并对其进行硬件实现与加速。通过对模型参数进行定点数量化，压缩网络模型的存储空间，提高FPGA中DSP资源的利用率；利用循环展开和数组重排等硬件优化方法，提高了系统实时性，确定了算法的并行计算方案。研究结果表明，在100 MHz的时钟下，测试集解调精度为1.19 pm,推理速度为每帧14.96μs,光谱解调速率为60 kHz,对于FBG混叠光谱信号解调具有较高的精度和速率。

CNN-based Overlapping Spectral Demodulation Algorithm and Its FPGA Implementation

To solve the spectral signal overlapping problem in fiber Bragg grating (FBG) sensing networks, this study proposes a spectral signal demodulation algorithm using a convolutional neural network model based on a field-programmable gate array (FPGA) and implements it in hardware for acceleration. The models parameters are quantized to a fixed-point representation, reducing the storage space of the model and enhancing the utilization of DSP resources in the FPGA. Hardware optimization techniques such as loop unrolling and array rearrangement are employed to improve real-time system performance, establishing a parallel computing scheme for the algorithm. The results indicate that under a clock frequency of 100MHz, the demodulation accuracy of the test set is 1.19pm at an inference speed of 14.96μs per frame and a spectral demodulation rate of 60kHz. The proposed algorithm exhibits high precision and speed in the demodulation of overlapped FBG spectral signals.