An atomic clock error prediction model training method and device

Abstract

The invention provides an atomic clock error prediction model training method and device, and relates to the field of atomic clock data processing. The atomic clock error prediction model training method comprises the steps of acquiring clock error data in a preset time period, wherein the clock error data comprise a training set and a test set; Substituting the clock error data in the training set, kernel function parameters and regularization parameters into a to-be-trained clock error prediction model to obtain a clock error prediction result, the to-be-trained clock error prediction modelbeing constructed and obtained by a kernel function selected based on a least square support vector machine algorithm; Obtaining an optimized kernel function parameter and an optimized regularizationparameter according to the clock error prediction result; And according to the optimization kernel function parameter and the optimization regularization parameter, training to obtain an optimizationclock error prediction model. According to the method, the clock error prediction model is constructed by using the least square support vector machine-based algorithm, so that a more accurate clock error prediction result is obtained.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method and device for training an atomic clock error prediction model. Background technique [0002] With the continuous rapid development of science and technology, navigation, positioning, measurement and astronomy all require time and frequency standards with higher stability and accuracy. As a time-frequency standard, the atomic time scale represents a country's technological level and is also the core embodiment of a country's competitiveness. Atomic clock error prediction is a key link in atomic clock time scale and atomic clock control. The accuracy of atomic clock error prediction directly affects the quality of atomic time scale and the control ability of atomic clock. Therefore, the influence of clock error prediction on atomic time scale is very important. [0003] At present, in order to build China's atomic time scale system, the Timekeeping Laboratory of ...

AI Technical Summary

Problems solved by technology

[0004] However, the prediction accuracy of the atomic clock error prediction method used in the prior art is low

Images