Fiber Bragg gratings (FBGs) are among the most utilized fiber optic sensors due to their high sensitivity toward physical parameters, which makes them preferable for various sensing applications. In this theoretical research work, an apodized FBG is designed to eliminate the side lobes from the reflectivity spectrum for the sensitivity estimation of physical parameters including temperature, strain, and pressure. Bragg wavelength changes due to the effects of measurands as FBG works on the principle of Bragg wavelength shift. The sensitivity of the measurand is measured by analyzing the changes that occur in the Bragg wavelength due to the impact of measurands. A strong linearity has been obtained for the sensitivity measurement of temperature, strain, and pressure for the designed apodized FBG. The Support vector machine (SVM), a supervised machine learning (ML) model, is implemented with different kernel functions for the predictive analysis of physical parameters for the credibility of the designed apodized FBG sensor to achieve improved sensing outcomes, particularly to work in a hazardous environment in case of any adverse scenario of any physical parameter. The predictive analysis performance of the SVM with RBF (radial basis function) kernel is observed better compared to the PUK (Pearson VII universal kernel) kernel as indicated by the high R² value.

光纤布拉格光栅 (FBG) 因其对物理参数的高灵敏度而成为最常用的光纤传感器之一，这使得它们更适合各种传感应用。在这项理论研究工作中，设计了变迹光纤光栅来消除反射光谱中的旁瓣，以用于温度、应变和压力等物理参数的灵敏度估计。布拉格波长由于被测量的影响而发生变化，FBG 的工作原理是布拉格波长漂移。通过分析布拉格波长由于被测量的影响而发生的变化来测量被测量的灵敏度。所设计的变迹光纤光栅的温度、应变和压力的灵敏度测量具有很强的线性度。支持向量机 (SVM) 是一种监督机器学习 (ML) 模型，采用不同的核函数来实现，用于对物理参数进行预测分析，以保证所设计的变迹 FBG 传感器的可信度，从而实现改进的传感结果，特别是在任何物理参数出现任何不利情况时的危险环境。与 PUK（Pearson VII 通用核）核相比，具有 RBF（径向基函数）核的 SVM 的预测分析性能更好，如高R ²值所示。