为了有效监控飞机的健康，针对飞机服役过程中所受的复杂载荷条件，提出了基于飞参数据的结构关键部位载荷孪生技术。首先基于相邻值填补、一维/多维数据异常检测、小波包分解和贝叶斯阈值去噪等方法完成光纤传感器数据优化治理；其次，基于数据挖掘手段和线性回归法，建立了结构关键部位应变特征及相关参数提取方法；最后针对影响飞机结构关键部位应变的相关飞参和特征，采用XGBoost模型训练相关飞参和特征到关键部位应变的映射关系，构建了飞参-应变的高精度孪生映射模型。高精度孪生映射预测模型以飞参和传感器数据作为原始输入，平均预测精度达到0.95以上，能够高效准确对飞机结构健康状态进行监测。

In order to effectively monitor the health of the aircraft, the twinning technology of key parts of the structure based on the flying parameters is proposed in view of the complex load conditions during the service of the aircraft. Firstly, fiber optic sensor data optimization governance was completed based on methods such as adjacent value filling, one-dimensional/multi-dimensional data anomaly detection, wavelet packet decomposition and Bayesian threshold denoising. Secondly, based on data mining method and linear regression method, the key strain feature extraction method and relat-ed parameter extraction method are established. Finally, regarding the relevant flight parameters and features that affect the strain of key parts of the aircraft structure, XGBoost model is used to train the mapping relationship between the rele-vant flight parameters and features and the strain of key parts, and a high precision twin mapping model of the flight pa-rameters and strain is constructed. The high precision twin mapping model uses the flight parameters and sensor data as the original input, and the average prediction accuracy is above 0.95, which can effectively and accurately monitor the healthy state of aircraft structure.