Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network
Hypersonic Glide Vehicles (HGVs) are advanced aircraft that can achieve extremely high speeds (generally over 5 Mach) and maneuverability within the Earth's atmosphere. HGV trajectory prediction is crucial for effective defense planning and interception strategies. In recent years, HGV trajecto...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-04-01
|
| Series: | Defence Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214914724002563 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850150767770468352 |
|---|---|
| author | Yuepeng Cai Xuebin Zhuang |
| author_facet | Yuepeng Cai Xuebin Zhuang |
| author_sort | Yuepeng Cai |
| collection | DOAJ |
| description | Hypersonic Glide Vehicles (HGVs) are advanced aircraft that can achieve extremely high speeds (generally over 5 Mach) and maneuverability within the Earth's atmosphere. HGV trajectory prediction is crucial for effective defense planning and interception strategies. In recent years, HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency. However, it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models. To solve this problem, we propose a new deep learning framework (FECA-LSMN) for efficient HGV trajectory prediction. The model first uses a Frequency Enhanced Channel Attention (FECA) module to facilitate the fusion of different HGV trajectory features, and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network (LSMN) based on simple MLP-based structures to extract long/short-term HGV trajectory features for accurate trajectory prediction. Also, we employ a new data normalization method called reversible instance normalization (RevIN) to enhance the prediction accuracy and training stability of the network. Compared to other popular trajectory prediction models based on LSTM, GRU and Transformer, our FECA-LSMN model achieves leading or comparable performance in terms of RMSE, MAE and MAPE metrics while demonstrating notably faster computation time. The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network. The RevIN data normalization technique outperforms traditional min-max normalization as well. |
| format | Article |
| id | doaj-art-c833199f7d9e4d54b1813d5f5ea78bc8 |
| institution | OA Journals |
| issn | 2214-9147 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Defence Technology |
| spelling | doaj-art-c833199f7d9e4d54b1813d5f5ea78bc82025-08-20T02:26:27ZengKeAi Communications Co., Ltd.Defence Technology2214-91472025-04-014619921210.1016/j.dt.2024.11.001Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP networkYuepeng Cai0Xuebin Zhuang1School of Systems Science and Engineering, Sun Yat-Sen University, Guangzhou 510006, ChinaCorresponding author.; School of Systems Science and Engineering, Sun Yat-Sen University, Guangzhou 510006, ChinaHypersonic Glide Vehicles (HGVs) are advanced aircraft that can achieve extremely high speeds (generally over 5 Mach) and maneuverability within the Earth's atmosphere. HGV trajectory prediction is crucial for effective defense planning and interception strategies. In recent years, HGV trajectory prediction methods based on deep learning have the great potential to significantly enhance prediction accuracy and efficiency. However, it's still challenging to strike a balance between improving prediction performance and reducing computation costs of the deep learning trajectory prediction models. To solve this problem, we propose a new deep learning framework (FECA-LSMN) for efficient HGV trajectory prediction. The model first uses a Frequency Enhanced Channel Attention (FECA) module to facilitate the fusion of different HGV trajectory features, and then subsequently employs a Light Sampling-oriented Multi-Layer Perceptron Network (LSMN) based on simple MLP-based structures to extract long/short-term HGV trajectory features for accurate trajectory prediction. Also, we employ a new data normalization method called reversible instance normalization (RevIN) to enhance the prediction accuracy and training stability of the network. Compared to other popular trajectory prediction models based on LSTM, GRU and Transformer, our FECA-LSMN model achieves leading or comparable performance in terms of RMSE, MAE and MAPE metrics while demonstrating notably faster computation time. The ablation experiments show that the incorporation of the FECA module significantly improves the prediction performance of the network. The RevIN data normalization technique outperforms traditional min-max normalization as well.http://www.sciencedirect.com/science/article/pii/S2214914724002563Hypersonic glide vehicleTrajectory predictionFrequency enhanced channel attentionLight sampling-oriented MLP network |
| spellingShingle | Yuepeng Cai Xuebin Zhuang Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network Defence Technology Hypersonic glide vehicle Trajectory prediction Frequency enhanced channel attention Light sampling-oriented MLP network |
| title | Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network |
| title_full | Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network |
| title_fullStr | Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network |
| title_full_unstemmed | Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network |
| title_short | Hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling-oriented MLP network |
| title_sort | hypersonic glide vehicle trajectory prediction based on frequency enhanced channel attention and light sampling oriented mlp network |
| topic | Hypersonic glide vehicle Trajectory prediction Frequency enhanced channel attention Light sampling-oriented MLP network |
| url | http://www.sciencedirect.com/science/article/pii/S2214914724002563 |
| work_keys_str_mv | AT yuepengcai hypersonicglidevehicletrajectorypredictionbasedonfrequencyenhancedchannelattentionandlightsamplingorientedmlpnetwork AT xuebinzhuang hypersonicglidevehicletrajectorypredictionbasedonfrequencyenhancedchannelattentionandlightsamplingorientedmlpnetwork |