军事知识服务平台
基于三次样条插值与BiLSTM的FBG形状重构方法
FBG Shape Reconstruction Method Based on Cubic Spline Interpolation and BiLSTM
摘要 针对光纤布拉格光栅(FBG)形状传感技术中因测点稀疏及Frenet积分法导致的误差累积严重、重构精度低等问题,文章提出一种基于三次样条插值与双向长短时记忆网络(BiLSTM)的端到端形状重构方法.该方法利用三次样条插值将稀疏的离散应变信号变为稠密的空间应变序列,以满足光纤变形的物理连续性约束;再通过BiLSTM模型构建光纤沿着轴向的应变传递特征与空间几何约束;实现从应变空间到三维坐标的直接映射.仿真与实验结果表明,该方法摒弃了传统几何重构的逐点推算过程,有效消除了累积误差,仿真结果的相对平均误差分别为 0.28%和 0.23%,末端误差分别为 0.271 9 mm和 0.463 9 mm,实验结果的相对平均误差分别为1.22%和1.03%,末端误差分别为7.10 mm和5.47 mm.
Abstract:
To address the issues of severe error accumulation and low reconstruction accuracy in fiber Bragg grating shape sensing technology caused by sparse measurement points and the Frenet-Serret integration method,this study proposes an end-to-end shape reconstruction method based on cubic spline interpolation and Bidirectional Long Short-Term Memory(BiLSTM).This method employs cubic spline interpolation to convert sparse discrete strain signals into dense spatial strain sequences,thereby satisfying the physical continuity constraints of optical fiber deformation.Subsequently,a BiLSTM model is used to capture the strain transfer characteristics along the fiber axis and the associated spatial geometric constraints,establishing a direct mapping from strain space to three-dimensional coordinates.Simulation and experimental results show that this method eliminates the point-by-point calculation process used in traditional geometric reconstruction,effectively eliminating cumulative errors.The average relative errors of the simulation results were 0.28%and 0.23%,and the endpoint errors were 0.271 9 mm and 0.463 9 mm,respectively.The average relative errors of the experimental results were 1.22%and 1.03%,and the endpoint errors were 7.10 mm and 5.47 mm,respectively.
刊 名 半导体光电 ISTICPKU
年,卷(期): 2026, 47(5)
分类号: TN911.6
机标分类号: TP391 O212 U469.79
在线出版日期: 2026年11月4日