结构健康监测缺失数据的插补方法、电子设备及程序产品
By employing adversarial learning between a generative interpolation network and a discriminator, combined with a physical consistency loss term and a dilated temporal convolutional network, the problem of data recovery from multiple sensor synchronization loss in structural health monitoring was solved, achieving high-precision interpolation results.
CN122020004BActive Publication Date: 2026-07-17XIAMEN UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAMEN UNIV
- Filing Date
- 2026-04-08
- Publication Date
- 2026-07-17
Smart Images

Figure CN122020004B_ABST
Abstract
本公开提供了一种结构健康监测缺失数据的插补方法、电子设备及程序产品,涉及计算机技术领域。本公开的结构健康监测缺失数据的插补方法包括:获取针对目标结构的包含多个传感器通道的时间序列观测数据,并生成与时间序列观测数据对应的掩码矩阵;根据掩码矩阵,在时间序列观测数据中的数据缺失位置填充随机噪声,得到目标输入矩阵;将目标输入矩阵输入至生成式插补网络中,生成式插补网络包括生成器和判别器;对生成器和判别器进行对抗学习联合训练,得到目标数据插补模型,在对抗学习联合训练的过程中,其联合训练损失函数至少包括物理一致性损失项;以及根据目标数据插补模型,对待插补时间序列观测数据进行数据插补。
Need to check novelty before this filing date? Find Prior Art