中文摘要：

基于人工的神经网络(ANN ) ，模型被建议改进轨道预言的精确的一个新卫星轨道预言方法。以便避免修改动态模型的困难，使用 ANN 模型听说变化轨道预言错误，然后 ANN 的预言结果被尝试模型被用来基于动态模型补偿预言的轨道形成期末考试预言的轨道。实验结果证明轨道预言错误基于 ANN 模型是不到那基于动态模型，和为不同卫星和不同时间的改进效果是不同的。预言 8 的改进的最大的率， 15， 30 ? d 是分别地 80 ?% ， 77.77 ?% ， 85 ?% 。轨道预言错误控制技术基于背重叠弧的方法比较在它被 ANN 补偿以后，向前被带避免预言的轨道的精确是甚至更坏的风险模型。失败的现象基本上基于这种技术被消除，并且失败的率从 30 被减少 ?% ～ 5 ?% 。这种技术能保证 ANN 模型的设计申请能实现。

英文摘要：

A new satellite orbit prediction method based on artificial neural network （ANN） model is proposed to improve the precision of orbit prediction. In order to avoid the difficulty of amending the dynamical model, it is attempted to use ANN model to learn the variation of orbit prediction error, and then the prediction result of ANN model is used to compensate the predicted orbit based on dynamic model to form a final predicted orbit. The experiment results showed that the orbit prediction error based on ANN model was less than that based on dynamical model, and the ent satellites and different improvement effects for differtime were different. The maximum rates of improvement of predicting 8, 15, 30 d were respectively 80 %, 77.77 %, 85 %. The orbit prediction error control technique based on the method of back overlap arc compare was brought forward to avoid the risk that the precision of predicted orbit is even worse after it is compensated by ANN model. The phenomena of failure were basically eliminated based on this technique, and the rate of failure was reduced from 30 % to 5 %. This technique could ensure that the engineering application of ANN model could come true.