一种基于迁移学习的遥测数据异常检测方法

为解决卫星遥测数据异常检测面临的数据不平衡且缺乏有标签样本的问题,提出一种基于一维卷积神经网络(1dCNN)迁移学习的异常检测方法.首先利用源域卫星的遥测数据对1dCNN进行预训练,使得模型的卷积层具有卫星状态特征的提取能力;然后将训练好的模型迁移到缺乏标签数据的目标域卫星中;利用目标域有标签样本对预训练模型进行微调,...

An Anomaly Detection Method of Telemetry Data by Means of Transfer Learning

In order to solve the problems of imbalanced data and lack of labeled samples faced by satellite telemetry data anomaly detection, a method of anomaly detection based on one dimensional convolutional neural network (1dCNN) transfer learning is proposed. Firstly, the source domain satellite data are used to pre train the 1dCNN to make the model’s convolutional layer have satellite state feature extraction capabilities; then the pre trained model is transferred to the target domain satellite lacking labeled data; finally, the labeled samples of the target domain are used to fine tune the pre trained model so as to achieve anomaly detection of the samples of the target domain test set. In order to make the 1dCNN adapt to the imbalance of satellite telemetry data samples, a cost sensitive training strategy is introduced. By establishing a dynamic loss function, the cs 1dCNN can improve the capacity of recognizing the abnormal samples. Experiments with the power subsystem data of two anonymous satellites verify the effectiveness and robustness of the proposed anomaly detection transfer method.