Tight combination navigation fault detection method based on time sequence two-dimensional coding

The invention relates to a tightly integrated navigation fault detection method based on time series two-dimensional coding, and belongs to the technical field of integrated navigation, and the method comprises the following steps: carrying out time series two-dimensional coding on pseudo-range data in Kalman filtering innovation data of a single satellite under normal navigation of a GNSS/INS integrated navigation system to obtain a two-dimensional image; performing unsupervised training of the VAE-GAN deep neural network by using the two-dimensional image; the VAE-GAN deep neural network can detect the fault of a single satellite; and adopting the trained VAE-GAN deep neural network to detect a single satellite fault in the positioning process of the integrated navigation system. According to the invention, the sensitivity of the system to faults is improved, and the problem of sample imbalance in fault detection training is avoided. 本发明涉及一种基于时间序列二维编码的紧组合导航故障检测方法，属于组合导航技术领域，方法包括：对采集的GNSS/INS组合导航系统正常导航下单颗卫星的