-
美国战略与预算评估中心(CSBA)先后制定了3份电磁频谱做作战领域的重要报告[4-5]和MOSAIC战[6],企图重新稳固其在电磁谱战领域的优势地位,而获取电磁频谱优势的关键是对电磁目标信号的分析与处理。
现在和未来的战争都是在对复杂的电磁环境进行战场的态势感知与认知分析的前提下,利用先进的海、陆、空、天作战集群进行的。这些作战集群依托于通信、数据链等无线手段将天基、空基、海基和陆基通信、雷达、导航定位设备、武器系统、作战平台、后勤保障系统链接起来,建立完善的预警探测、指挥控制、情报传输、干扰保护和火力交战网络、后勤保障网络,有效提高单机、单舰和各个单一的武器系统或平台的联合态势感知、火力打击和协同控制与优化的能力。这些使信息系统支撑下的体系作战效能得到显著增强的前提是信息系统具有强大的认知信号处理与分析能力。但是在现代和未来的战场中,电磁频谱设备或终端具有网络化、捷变性、多功能、自适应、频段覆盖范围宽、种类复杂多样和使用环境复杂多变等特性,给认知电磁频谱战系统的信号分析与处理带来巨大挑战;同时,随着人工智能在认知电子战中的广泛应用,特别是深度学习算法在电磁态势感知、信号的智能分析与处理方面发挥着越来越重要的作用,但其不可解释性在军事应用中具有明显的局限性,给指挥员的参考和指导作用有限;基于电磁目标的知识库和知识图谱系统需要适应开集信号处理,即如何通过有效的认知信号分析与处理架构来进行未知目标的检测、辨识与分析,知识库如何通过信号处理与分析算法来达到知识库的自增长,如何通过知识库和知识图谱进行电磁态势的预测与目标行为的推理等也是认知电子中的关键技术和亟待解决的难题[7-8]。
因此,目前认知电子战学界迫切需要建立合理的信号分析与处理架构来有效解决上述限制带来的不利影响。面对复杂电磁环境中的上述问题,本文展开基于人工智能的复杂电磁环境下目标信号分析与处理架构的研究,拟期给出合理、高效的认知电磁目标信号分析与处理架构,为电子战系统的信号分析与处理给出合理的统一解决方案,为高效、可靠实现认知OODA环路提供技术支撑,为认知电子战系统在复杂电磁环境下的电磁目标信号处理与分析提供解决问题的思路。
Research on Cognitive Processing Architecture and Application of Electromagnetic Signal in Complex Environment
-
摘要: 针对现代电磁频谱设备或终端具有网络化、捷变性、多功能、自适应、种类复杂多样和使用环境复杂多变等特性给认知电磁频谱战系统的信号分析与处理带来的巨大挑战的问题,提出了一种结合人工智能、适合复杂电磁环境下电磁目标信号认知处理与分析的架构。在该架构下电磁目标信号分析与处理被分为目标信号参数估计、目标信号类型分类、辐射源个体识别和目标信号的特征建库与知识图谱[
1 -3 ]的构建等4个层次,可以很好适应闭集和开集电磁目标信号的分析与处理;此外,在此架构下提出了未知辐射源辨识、跨模态辐射源智能识别和电磁辐射源的个体识别的算法框架,在实测数据集上的验证实验表明,该算法在闭集和开集电磁信号分析中有效可行。-
关键词:
- 电磁频谱战 /
- 认知处理架构 /
- 电磁目标知识图谱与推理 /
- 辐射源个体识别
Abstract: In view of the challenges that the modern electromagnetic spectrum equipment or terminals has such characteristics as network, agility, multi-function, adaptive, complex variety of types and working in complex environments, etc., in this paper, main research is focused on the structure of electromagnetic signal processing and analysis in complex electromagnetic environments. A new architecture is proposed, which combines artificial intelligence and is suitable for cognitive processing and analysis of electromagnetic signals in complex electromagnetic environments. In this framework, electromagnetic signal analysis and processing are divided into four levels: signal parameter estimation, signal type classification, radiation source identification, signal feature database and knowledge map construction[1 -3 ], The framework can be used to analyze and process closed electromagnetic signal set and open electromagnetic signal set; In addition, the identification of unknown emitter, the intelligent identification of cross-modal emitter and the individual identification of electromagnetic emitter are proposed in this framework. The verification test on the measured data set shows that these algorithms are effective and feasible in closed set and open set electromagnetic signal analysis. -
[1] MO C, WANG Y, JIA Y, et al. Survey on temporal knowledge graph[C]//The 2021 IEEE 6th International Conference on Data Science in Cyberspace. Shenzhen: IEEE, 2021: 294-300. [2] HU H, CHEN Y. Progress and analysis of multimodal knowledge graphs[C]//The 2022 7th International Conference on Intelligent Computing and Signal Processing. Xi’an: IEEE, 2022: 1097-1101. [3] 马昂, 于艳华, 杨胜利, 等. 基于强化学习的知识图谱综述[J]. 计算机研究与发展, 2022, 59(8): 1694-1722. MA A, YU Y H, YANG S L, et al. Survey of knowledge graph based on reinforcement learning[J]. Journal of Computer Research and Development, 2022, 59(8): 1694-1722. [4] CLARK B, MCNAMARA W M, WALTON T A. Winning the invisible war: gaining an enduring U. S. advantage in the electromagnetic spectrum[EB/OL]. (2019-11-21). https://csbaonline.org/research/publications/winning-the-invisible-war-gaining-an-enduring-u.s-advantage-in-the-electromagnetic-spectrum. [5] 骆超, 段洪涛, 吴曦. 电磁频谱战中的无线电监测—《电波制胜: 重拾美国在电磁频谱领域霸主地位》报告启示[J]. 中国无线电, 2016, 16(3): 58-59. LUO C, DUAN H T, WU X. Radio monitoring in electromagnetic spectrum warfare-inspiration from the report “Winning by Radio: Regaining U. S. Dominance in the Electromagnetic Spectrum”[J]. China Radio, 2016, 16(3): 58-59. [6] CLARK B, PATTERN D, SCHRAMM H. MOSAIC warfare exploiting artifical intelligence and autonomous system to implement descision-centric operation[EB/OL]. (2020-02-11). https://csbaonline.org/uploads/documents/Mosaic_Warfare_Web.pdf. [7] 夏爱军, 张旭昕, 李高云. 复杂电磁环境对体系作战能力生成影响分析初探[J]. 电子信息对抗技术, 2017, 32(3): 23-27. doi: 10.3969/j.issn.1674-2230.2017.03.006 XIA A J, ZHANG X X, LI G Y. Preliminary impact on the generation capacity under complicated electromagnetic environment[J]. Electronic Information Warfare Technology, 2017, 32(3): 23-27. doi: 10.3969/j.issn.1674-2230.2017.03.006 [8] 李高云, 旷生玉, 江果, 等. 智能化电子战装备发展路径探讨[J]. 中国电子科学研究院学报, 2022, 17(1): 7-11. LI G Y, KUANG S Y, JIANG G, et al. Development path 0f intelligent electronic warfare equipment[J]. Journal of China Academy of Electronics and Information Technology, 2022, 17(1): 7-11. [9] AHMED A M, EISSA O, SEZGIN A. Deep autoencoders for doa estimation of coherent sources using imperfect antenna array[C]//The 2020 3rd International Workshop on Mobile Terahertz Systems. Essen: IEEE, 2020: 1-5. [10] ZHANG W, LI J, DING C Z, et al. Small sample identification for specific emitter based on adversarial embedded network[C]//The 2021 International Conference on Image and Graphics. Wuhan: IEEE, 2020: 27-28. [11] 李润东, 李立忠, 李少谦, 等. 基于稀疏滤波神经网络的智能调制识别[J]. 电子科技大学学报, 2019, 48(2): 161-167. LI R D, LI L Z, LI S Q, et al. Intelligent modulation recognition based on neural networks with sparse filtering[J]. Journal of University of Electronic Science and Technology of China, 2019, 48(2): 161-167. [12] 唐泽宇, 邹小虎, 李鹏飞, 等. 基于迁移学习的小样本 OFDM目标增强识别方法[J]. 上海交通大学学报, 2022, 56(12): 1666-1674. TANG Z Y, ZOU X H, LI P F, et al. A few-shots OFDM target augmented identification method based on transfer learning[J]. Journal of Shanghai Jiaotong University, 2022, 56(12): 1666-1674. [13] 蒋季宏, 方宇轩, 张伟, 等. 小样本情景下基于特征融合的辐射源个体识别[J]. 电子信息对抗技术, 2022, 37(3): 20-25. JIANG J H, FANG Y X, ZHANG W, et al. Specific emitter identification based on feature fusion in few-shot scene[J]. Electronic Information Warfare Technology, 2022, 37(3): 20-25. [14] 陈维高, 朱卫纲, 唐晓婧, 等. 不完整数据集的MFR辐射源识别方法研究[J]. 电子科技大学学报, 2019, 48(1): 39-45. CHEN W G, ZHU W G, TANG X J, et al. Research on MFR emitter identification method for incomplete data[J]. Journal of University of Electronic Science and Technology of China, 2019, 48(1): 39-45. [15] 汤鹏, 徐以涛, 李京华, 等. 非合作辐射源识别技术发展动态分析[J]. 数据采集与处理, 2020, 35(6): 1033-1048. TANG P, XU Y T, LI J H, et al. Analysis of development of non-cooperative emitter identification technology[J]. Journal of Data Acquisition & Processing, 2020, 35(6): 1033-1048. [16] 张谦, 王吉, 唐泽宇, 等. 基于深度学习的通信电台个体识别技术[J]. 电子信息对抗技术, 2021, 36(2): 36-40. ZHANG Q, WANG J, TANG Z Y, et al. Individual identification technique of communication transmitters based on deep learning[J]. Electronic Information Warfare Technology, 2021, 36(2): 36-40. [17] 费华莲. 人工智能在电子战领域的应用[J]. 飞航导弹, 2020, 20(4): 41-45. FEI H L. Application of artificial intelligence in the field of electronic warfare[J]. Aerospace Technology, 2020, 20(4): 41-45. [18] ZONG L, XU C, YUAN H L, et al. A RF fingerprint recognition method based on deeply convolutional neural network[C]//The 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference. Chongqing: IEEE, 2020: 1778-1781. [19] GU H, WANG Y, GUI G, et al. Radio frequency fingerprinting driven drone identification based on complex-valued CNN[C]//The 13th EAI International Conference on Mobile Multimedia Communications. Harbin: IEEE, 2020: 27-28. [20] 利强, 张伟, 金秋园, 等. 基于知识原型网络的小样本多功能雷达工作模式识别[J]. 电子学报, 2022, 50(6): 1344-1350. LI Q, ZHANG W, JIN Q Y, et al. Multi-function radar working mode recognition with few samples based on knowledge embedded prototype network[J]. Acta Electronica Sinica, 2022, 50(6): 1344-1350. [21] 王天池, 俞璐. 迁移学习及其在通信辐射源个体识别中的应用[J]. 通信技术, 2022, 55(3): 265-273. WANG T C, YU L. Transfer learning and its application in communication emitter identification[J]. Communications Technology, 2022, 55(3): 265-273. [22] PENG Y G, ZHANG Y F, CHEN C X, et al. Radar emitter identification based on co-clustering and transfer learning[C]//The 2021 IEEE 16th Conference on Industrial Electronics and Applications. Chengdu: IEEE, 2021: 1685-1690. [23] 张伟, 王沙飞, 林静然, 等. 基于孪生网络的电磁目标跨模式识别算法[J]. 电子学报, 2022, 50(6): 1281-1290. ZHANG W, WANG S F, LIN J R, et al. Cross-modal recognition algorithm of electromagnetic targets via siamese network[J]. Acta Electronica Sinica, 2022, 50(6): 1281-1290. [24] ZHONG Y, ZHANG L, PU W. Multimodal deep learning model for specific emitter identification[C]//The 2021 IEEE 6th International Conference on Signal and Image Processing. Nanjing: IEEE, 2021: 857-860. [25] KONG F X, LI Q, SHAO H Z. Jamming strategy generation for hidden communication modes via graph convolution networks[C]//The 2021 International Conference on Acoustics, Speech and Signal Processing. Toronto: IEEE, 2021: 4960-4964. [26] 邢文革, 桂佑林, 顾万里. 多传感器系统误差特性匹配的动态估计与补偿算法[J]. 电子科技大学学报, 2021, 50(2): 186-192. XING W G, GUI Y L, GU W L. A dynamic estimation and compensation algorithm for matching the error characteristics of multi-sensor system[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(2): 186-192.