{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:10:19Z","timestamp":1785402619455,"version":"3.56.0"},"reference-count":34,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 62471483"],"award-info":[{"award-number":["Grant No. 62471483"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["Grant No. 62471483"],"award-info":[{"award-number":["Grant No. 62471483"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Yantai Double-Hundred Plan for High-End Talent Introduction and Cultivation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Complex flight maneuver recognition (FMR) underpins intelligent flight training, including training assessment, pilot skill profiling, and flight safety monitoring. Existing FMR methods typically require large labeled datasets, generalize poorly across aircraft, and provide limited decision transparency. We propose TableManeuver, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs. The method updates no base LLM parameters and uses a small labeled training set only as a retrieval library; it is therefore not a zero-shot setting. TableManeuver first converts flight parameter sequences into tabular text that preserves temporal indices and channel semantics, reducing the mismatch between numerical time series and the textual semantic space of LLMs. It then combines domain knowledge, neighborhood sample references, and task decomposition prompts in a retrieval-augmented reasoning architecture that guides explicit step-by-step inference. We evaluate the method on a flight dataset collected from human pilots on a high-fidelity flight simulation platform. Without base LLM parameter updates, TableManeuver achieves 96.2% precision, 96.8% recall, and a 96.5% F1 score, exceeding the strongest supervised baseline by 3.5 percentage points in F1. In cross-aircraft evaluation, the F1 score decreases by only 1.4 percentage points, which is substantially smaller than the degradation observed for deep learning baselines. Retrieval-only baselines that transfer neighbor labels without LLM inference perform markedly worse, indicating that the performance gains are not explained by neighbor label transfer alone. TableManeuver combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.<\/jats:p>","DOI":"10.3390\/e28080850","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T08:09:42Z","timestamp":1785398982000},"page":"850","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Recognition of Complex Flight Maneuvers via Retrieval-Augmented Large Language Models"],"prefix":"10.3390","volume":"28","author":[{"given":"Liqiang","family":"Ren","sequence":"first","affiliation":[{"name":"Institute of Information Fusion, Naval Aviation University, Yantai 264001, China"},{"name":"National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing, Yantai 264001, China"},{"name":"Key Laboratory of Sea-Air Information Perception and Processing Technology of Shandong Provincial, Yantai 264001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese People\u2019s Liberation Army Unit 92728, Shanghai 200436, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlong","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Information Fusion, Naval Aviation University, Yantai 264001, China"},{"name":"National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing, Yantai 264001, China"},{"name":"Key Laboratory of Sea-Air Information Perception and Processing Technology of Shandong Provincial, Yantai 264001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Information Fusion, Naval Aviation University, Yantai 264001, China"},{"name":"National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing, Yantai 264001, China"},{"name":"Key Laboratory of Sea-Air Information Perception and Processing Technology of Shandong Provincial, Yantai 264001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongdong","family":"Wan","sequence":"additional","affiliation":[{"name":"Institute of Information Fusion, Naval Aviation University, Yantai 264001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3934\/era.2023005","article-title":"Deep learning for Flight Maneuver Recognition: A survey","volume":"31","author":"Lu","year":"2023","journal-title":"Electron. Res. Arch."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"14","DOI":"10.62762\/CJIF.2024.344084","article-title":"Quantitative Evaluation Method for Anomaly Levels of Complex Flight Maneuver Based on Multi-sensor Data","volume":"2","author":"Ren","year":"2025","journal-title":"Chin. J. Inf. Fusion"},{"key":"ref_3","first-page":"23","article-title":"Establishment of avion inflight maneuver action recognizing knowledge base","volume":"22","author":"Ni","year":"2005","journal-title":"Comput. Simul."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.cja.2014.12.026","article-title":"Identification and standardization of maneuvers based upon operational flight data","volume":"28","author":"Wang","year":"2015","journal-title":"Chin. J. Aeronaut."},{"key":"ref_5","first-page":"1267","article-title":"Recognition of fighter maneuver in automatic flight training evaluation","volume":"46","author":"Meng","year":"2020","journal-title":"J. Beijing Univ. Aeronaut. Astronaut."},{"key":"ref_6","first-page":"74","article-title":"Research on complex motion recognition method based on basic flying motion","volume":"38","author":"Wang","year":"2018","journal-title":"Ship Electron. Eng."},{"key":"ref_7","unstructured":"Gui, C., Zhang, L., Bai, Y., Shi, G., Duan, Y., Du, J., Wang, X., and Zhang, Y. (2019, January 24\u201325). Recognition of flight operation action based on expert system inference engine. Proceedings of the 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China."},{"key":"ref_8","first-page":"84","article-title":"Aircraft flight motion recognition based on Fuzzy Support Vector Machine","volume":"26","author":"Yang","year":"2005","journal-title":"Acta Aeronaut. Astronaut. Sin."},{"key":"ref_9","first-page":"161","article-title":"Flight action recognition method based on Bayesian network","volume":"53","author":"Shen","year":"2017","journal-title":"Comput. Eng. Appl."},{"key":"ref_10","first-page":"347","article-title":"Flight maneuver recognition based on differential thinking and convolutional neural network","volume":"16","author":"Fang","year":"2021","journal-title":"J. China Acad. Electron. Inf. Technol."},{"key":"ref_11","first-page":"3932","article-title":"Automatic assessment method of pilot flight training quality based on maneuver action type recognition","volume":"45","author":"Zhu","year":"2023","journal-title":"Syst. Eng. Electron."},{"key":"ref_12","first-page":"539","article-title":"Flight maneuver recognition method and simulation based on recurrent neural network","volume":"15","author":"Zhou","year":"2020","journal-title":"J. China Acad. Electron. Inf. Technol."},{"key":"ref_13","first-page":"89","article-title":"Flight action recognition method based on focused attention mechanism","volume":"30","author":"Li","year":"2023","journal-title":"Electron. Opt. Control"},{"key":"ref_14","first-page":"737","article-title":"Symbolic flight action recognition based on neural network","volume":"44","author":"Fang","year":"2022","journal-title":"Syst. Eng. Electron."},{"key":"ref_15","unstructured":"Ren, L.Q., Wang, H.P., Pan, X.L., Wang, B., and Tang, T.T. (2025). Complex maneuver action recognition method based on wavelet time-frequency map and lightweight CNN-Transformer hybrid neural network. J. Beijing Univ. Aeronaut. Astronaut., Online."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patrec.2024.11.005","article-title":"FM-detector: End-to-end flight maneuver recognition method based on flight data","volume":"187","author":"Wang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"ref_17","first-page":"3094","article-title":"A review of research on time series classification based on deep learning","volume":"46","author":"Ren","year":"2024","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, Q., Qin, L., Liu, J., Peng, D., Guan, J., Wang, P., Hu, M., Zhou, Y., Gao, T., and Che, W. (2025). Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. arXiv.","DOI":"10.1007\/s11432-025-4665-8"},{"key":"ref_19","unstructured":"Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., and Gao, J. (2024). Large language models: A survey. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tao, X., Pan, T., Cheng, M., Luo, Y., Liu, Q., and Chen, E. (2024). Hierarchical multimodal LLMs with semantic space alignment for enhanced time series classification. arXiv.","DOI":"10.1145\/3785505"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"19622","DOI":"10.52202\/075280-0861","article-title":"Large language models are zero-shot time series forecasters","volume":"36","author":"Gruver","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_22","first-page":"1","article-title":"Scientific large language models: A survey on biological & chemical domains","volume":"57","author":"Zhang","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhao, Z., Wang, J., Kamarthi, H., and Prakash, B.A. (2024). LSTPrompt: Large language models as zero-shot time series forecasters by long-short-term prompting. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.466"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6851","DOI":"10.1109\/TKDE.2023.3342137","article-title":"PromptCast: A new prompt-based learning paradigm for time series forecasting","volume":"36","author":"Xue","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_25","unstructured":"Jin, M., Pan, S., Li, Y.-F., Ma, L., Zhang, J.Y., Chu, Z., Wang, S., Shi, X., Chen, P.-Y., and Wen, Q. (2023). Time-LLM: Time series forecasting by reprogramming large language models. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cheng, M.Y., Chen, Y., Liu, Q., Liu, Z., Luo, Y., and Chen, E. (2024). Advancing time series classification with multimodal language modeling. arXiv.","DOI":"10.1145\/3701551.3703499"},{"key":"ref_27","unstructured":"Jiang, Y., Pan, Z., Zhang, X., Garg, S., Schneider, A., Nevmyvaka, Y., and Song, D. (2024). Empowering time series analysis with large language models: A survey. arXiv."},{"key":"ref_28","unstructured":"Jin, M., Zhang, Y., Chen, W., Zhang, K., Liang, Y., Yang, B., Wang, J., Pan, S., and Wen, Q. (2024, January 21\u201327). Position: What can large language models tell us about time series analysis. Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_29","unstructured":"Cheng, M.Y., Tao, X.Y., Liu, Q., Zhang, H., Chen, Y.H., and Lei, C.Y. (2024). Learning transferable time series classifier with cross-domain pre-training from language model. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"43322","DOI":"10.52202\/075280-1877","article-title":"One fits all: Power general time series analysis by pretrained LM","volume":"36","author":"Zhou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wang, J., Cheng, M., and Liu, Q. (2025). Can slow-thinking LLMs reason over time? Empirical studies in time series forecasting. arXiv.","DOI":"10.1145\/3773966.3777931"},{"key":"ref_32","unstructured":"Fang, X., Xu, W., Tan, F.A., Zhang, J., Hu, Z., Qi, Y., Nickleach, S., Socolinsky, D., Sengamedu, S., and Faloutsos, C. (2024). Large language models (LLMs) on tabular data: Prediction, generation, and understanding\u2014A survey. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"106527","DOI":"10.1016\/j.asoc.2020.106527","article-title":"A flight maneuver recognition method based on multi-strategy affine canonical time warping","volume":"95","author":"Wei","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"ref_34","unstructured":"Doshi-Velez, F., and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/8\/850\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T08:14:56Z","timestamp":1785399296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/8\/850"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["e28080850"],"URL":"https:\/\/doi.org\/10.3390\/e28080850","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]}}}