提出了一种通过符号化方法对授时系统时间偏差进行预测的方法。该方法利用矢量拟合来表达时间序列的走势形态，采用聚类算法对形态进行聚类，然后根据聚类结果得到符号序列，并用不完全抽取方法来抽取序列模式。预测时，可根据学习得到的模式集来对新序列做出预测分析。通过对授时系统误差数据的实验表明，该方法可以对时间偏差进行较好预测，并可对预测的数值进行校准，从而进一步提高授时精度。%A new method for time offset forecast based on symbolic sequences is presented. The method uses vector fitting to represent the forms of the trends of time series and applies cluster method to classify these forms. Then the symbolic sequences are obtained and the patterns of sequences are extracted by using half-baked patterns extracting algorithm. This method can also forecast new sequences based on the sets of patterns just learned. Experiments show that it gives good results to forecast time offset series and can align the values just predicted .So it can afford higher accuracy by this method.
展开▼
