基于TCN模型的航空器四维航迹预测

打开文本图片集

中图分类号：TN919-34；TP18 文献标识码：A 文章编号：1004-373X（2025）17-0001-06

引用格式：，，，等.基于TCN模型的航空器四维航迹预测[J].现代电子技术，2025，48（17）：1-6.

Abstract：Inviewof thelowaccuracyofaircraftfour-dimensional trajectoryprediction，anaircraftfour-dimensional trajectorypredictionmodelwhichoptimizestemporalconvolutionalnetwork（TCN）bygeneticalgorithm（GA）isproposed.The modelaims tocapturethetemporalfeaturesof trajectorydataandthecontinuityinspace，achieving acuratepredictionsof the aireraft'sthree-dimensionalspatialpositionsandcorespondingtimeinthefuture.Thegeneticalgorith（GA）isusedtooptiize hyperparametersof the TCNmodelsuchasthenumberofconvolutionalfiltersandbatch size，so thatthe model prediction accuracyandperformanceareenhanced.ThemodelisrainedandtestedbytheactualADS-B（automaticdependentsurveilancebroadcast）data.TheexperimentalresultsshowthatthepredictionperformanceoftheTCNmodeloptimizedbyGAisbettrthan thatofthecomparisonmodels，anditsmeanabsolutepercentage erorisreducedby66.84%incomparison withtheLSTMmodel and 16.24% in comparisonwith the TCN model.The predictionaccuracyof the proposed model is higher thanthatof the other comparison models. The effectiveness of the proposed algorithm is verified.

Keywords：aircraft; four-dimensional trajectory prediction; TCN; LSTM; GA;ADS-B

0 引言

随着航空运输业的蓬勃发展，航线网络规模逐步扩大，航空交通密度不断增加，空域资源日趋紧张。（剩余7977字）