CAJ | 학술논문

针对空间遥感任务中,光电探测器配载的斯特林制冷机制冷时长的预测问题,提出了一种使用自回归积分滑动平均模型( ARIMA)与人工神经网络( ANN)模型相结合的预测方法. 该方法采用时间序列的经典模型,将时间序列分解为趋势项与波动项的加和,采用ARIMA和ANN模型分别进行趋势项预测和波动项预测,并根据斯特林制冷机的间歇性工作模式特点对ARIMA模型进行改进. 最后,通过在真实数据上与其他方法的对比实验,验证了本文提出方法的有效性.
침대공간요감임무중,광전탐측기배재적사특림제랭궤제랭시장적예측문제,제출료일충사용자회귀적분활동평균모형( ARIMA)여인공신경망락( ANN)모형상결합적예측방법. 해방법채용시간서렬적경전모형,장시간서렬분해위추세항여파동항적가화,채용ARIMA화ANN모형분별진행추세항예측화파동항예측,병근거사특림제랭궤적간헐성공작모식특점대ARIMA모형진행개진. 최후,통과재진실수거상여기타방법적대비실험,험증료본문제출방법적유효성.
A new method combining autoregressive integrated moving average ( ARIMA) model and artificial neural network ( ANN) model is presented for the duration prediction of the Stirling cryocooler applied in space remote sensing missions. The stirling cryocooler is equipped with electrophotonic detector. A classic model based on time series is used to decompose the time series into trend item and oscillation item. For prediction, ARIMA model is used to predict the trend item and ANN model is used to predict the oscillation item, while ARIMA model is im-proved based on the intermittent working mode of the Stirling cryocooler. Finally, the validity of this method is veri-fied by applying to the real data and comparing the results with other methods.