Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM

To solve the problem of low track prediction accuracy caused by the limitations of deep learning and the cumulative error generated by recursive prediction strategies, a short-term prediction algorithm for air target tracks based on residual correction CNN-BiLSTM was proposed. Firstly, a convolution...

Full description

Bibliographic Details
Main Author: WANG Shuo, WU Nan, HUANG Jie, WANG Jiantao
Format: Article
Language:zho
Published: Editorial Office of Command Control and Simulation 2024-02-01
Series:Zhihui kongzhi yu fangzhen
Subjects:
Online Access:https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1708501833680-1260337552.pdf
_version_ 1797301131997609984
author WANG Shuo, WU Nan, HUANG Jie, WANG Jiantao
author_facet WANG Shuo, WU Nan, HUANG Jie, WANG Jiantao
author_sort WANG Shuo, WU Nan, HUANG Jie, WANG Jiantao
collection DOAJ
description To solve the problem of low track prediction accuracy caused by the limitations of deep learning and the cumulative error generated by recursive prediction strategies, a short-term prediction algorithm for air target tracks based on residual correction CNN-BiLSTM was proposed. Firstly, a convolution module was introduced to extract potentially associated spatial location features from the track data, and a bidirectional long and short time memory network was used to extract temporal features from the track data, achieving real-time one-step prediction and multi-step advance prediction of air targets. Then, the integrated moving average autoregression was introduced as a residual correction model to model the residual generated by real-time one-step prediction, and the residual value of the hybrid neural network model for multi-step advanced prediction is calculated. Finally, the output results of the hybrid neural network model and the residual correction model are fused to obtain the final trajectory prediction value. Experiment results proved that the algorithm can significantly improve the accuracy of short-term prediction of airborne target tracks.
first_indexed 2024-03-07T23:18:00Z
format Article
id doaj.art-8780583d6d3a4e98a94fff1318f06015
institution Directory Open Access Journal
issn 1673-3819
language zho
last_indexed 2024-03-07T23:18:00Z
publishDate 2024-02-01
publisher Editorial Office of Command Control and Simulation
record_format Article
series Zhihui kongzhi yu fangzhen
spelling doaj.art-8780583d6d3a4e98a94fff1318f060152024-02-21T09:43:17ZzhoEditorial Office of Command Control and SimulationZhihui kongzhi yu fangzhen1673-38192024-02-01461556310.3969/j.issn.1673-3819.2024.01.007Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTMWANG Shuo, WU Nan, HUANG Jie, WANG Jiantao0University of Information Engineering, Zhengzhou 450001, ChinaTo solve the problem of low track prediction accuracy caused by the limitations of deep learning and the cumulative error generated by recursive prediction strategies, a short-term prediction algorithm for air target tracks based on residual correction CNN-BiLSTM was proposed. Firstly, a convolution module was introduced to extract potentially associated spatial location features from the track data, and a bidirectional long and short time memory network was used to extract temporal features from the track data, achieving real-time one-step prediction and multi-step advance prediction of air targets. Then, the integrated moving average autoregression was introduced as a residual correction model to model the residual generated by real-time one-step prediction, and the residual value of the hybrid neural network model for multi-step advanced prediction is calculated. Finally, the output results of the hybrid neural network model and the residual correction model are fused to obtain the final trajectory prediction value. Experiment results proved that the algorithm can significantly improve the accuracy of short-term prediction of airborne target tracks.https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1708501833680-1260337552.pdfresidual correction|cnn-bilstm|short-term prediction|arima
spellingShingle WANG Shuo, WU Nan, HUANG Jie, WANG Jiantao
Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
Zhihui kongzhi yu fangzhen
residual correction|cnn-bilstm|short-term prediction|arima
title Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
title_full Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
title_fullStr Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
title_full_unstemmed Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
title_short Short-term prediction algorithm of air target track based on residual correction CNN-BiLSTM
title_sort short term prediction algorithm of air target track based on residual correction cnn bilstm
topic residual correction|cnn-bilstm|short-term prediction|arima
url https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1708501833680-1260337552.pdf
work_keys_str_mv AT wangshuowunanhuangjiewangjiantao shorttermpredictionalgorithmofairtargettrackbasedonresidualcorrectioncnnbilstm