Optimized Selection Method of Air Combat Course of Action under Stochastic Uncertainty

Abstract

Aiming at the design problem of aviation swarm combat course of action (COA), considering the influence of stochastic parameters in the causal relationship model and optimization problem model, according to the dynamic influence net (DIN) theory, stochastic simulation technique, feedforward neural network (FNN) function approximation technique and multi-objective artificial fish school algorithm (MOAFSA), this paper proposed a COA optimized method based on DIN and multi-objective stochastic chance constraint optimization for aviation swarm combat. First, on the basis of establishing the overall framework of the model and defining the elements of causal relationship modeling, the static and dynamic causal relationship modeling and optimization problem modeling were carried out respectively. Second, the probability propagation mechanism of DIN was established, which mainly included two aspects, i.e., the overall process and the specific algorithm. Then, input and output data were generated based on stochastic simulation. According to these data, FNN was adopted for function approximation, and MOAFSA was adopted for iterative optimization. Finally, the rationality of the model, and the effectiveness and superiority of the algorithm were verified through multiple sets of simulation cases.

Keywords

Stochastic uncertainty / aviation swarm / stochastic simulation / course of action / feedforward neural network / multi-objective artificial fish school algorithm

References

[1] Alaeddine H, Jihene M. Deep residual network in network. Computational Intelligence and Neuroscience, 2021, 6659083: 1-9.

[2] Askari Q, Younas I. Political optimizer based feedforward neural network for classification and function approximation. Neural Processing Letters, 2021, 53: 429-458.

[3] Chen C, Du Z J, Liang X X, Shi J M, Zhang H. Modeling and solution based on stochastic games for development of COA under uncertainty. Journal of Systems Engineering and Electronics, 2019, 30(2): 288-296.

[4] Chen C, Kong D F, Du Z J, Ran L. Modeling and solution of COA development based on timed influence net and game theory. Applied Mathematical Modelling, 2014, 38(21–22): 5269-5278.

[5] Chen X L, Cao L, Shen C. Research on course of action planning based on deep inverse reinforcement learning. National Defense Technology, 2019, 40(4): 55-61.

[6] Chen Z J, Wu P Y, Li B M. A strong law of large numbers for non-additive probabilities. International Journal of Approximate Reasoning, 2013, 54: 365-377.

[7] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.

[8] Fu CX, Jiang J, Yang K W (2015). Advanced timed influence nets with random time delay for weapon system-of-systems combat networks. International Conference on Automation, Mechanical Control and Computational Engineering. Ji’nan, China, April 24–26, 2015.

[9] Göztepe, Kerim and Ejder, Ahmet and Çalıkoğlu, Evren (2011). Course of action (COA) selection for special operations using fuzzy multi-criteria decision making technique. 2nd International Fuzzy Systems Symposium. Ankara, Turkey, November 17–18, 2011.

[10] Haider S, Levis A H. Modeling time-varying uncertain situations using dynamic influence nets. International Journal of Approximate Reasoning, 2008, 49: 488-502.

[11] He H. Research on Network Modeling and Optimization Method for Course of Action Planning Generation, 2019, China: National University of Defense Technology

[12] Huang Y M, Ge B F, Zhao B, Yang K W (2020). Course of action generation using graph model for conflict resolution. IEEE 15th International Conference of System of Systems Engineering. Budapest, Hungary, Jun 2–4, 2020.

[13] Kazakos PP, Zaidi AK (2008). An algorithm for activation timed influence nets. Proceedings of the 9th IEEE International Conference on Information Reuse and Integration. Las Vegas, Nevada, USA, July 13–15, 2008.

[14] Li ZW, Liu F, Yang WJ, Peng SH, Zhou J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 6999-7019.

[15] Levis A H (2019). On narrative modeling and assessment for strategic change. Proceedings of the 33rd European Conference on Modeling and Simulation. Caserta, Italy, June 11–14, 2019.

[16] Monroe C C. Optimizing Military Planner’s Course of Action Decision-making, 2019, USA: Georgia Institute of Technology

[17] Qi C, Wang D, Avila H M, Zhao P, Wang H W. Hierarchical task network planning with resources and temporal constraints. Knowledge-Based Systems, 2017, 133: 17-32.

[18] Staff U S Joint Operation Planning: Joint Publication 5-0, 2020, USA: DC: Department of Defense

[19] Sun J B, Huang J, Chang L L, Jiang J, Tan Y J. BRBcast: A new approach to belief rule-based system parameter learning via extended causal strength logic. Information Sciences, 2018, 444: 51-71.

[20] Sun J B, You Y Q, Ge B F, Tan Y J, Yang K W. Optimization framework and applications of training multistate influence nets. Applied Intelligence, 2022, 52: 1477-1492.

[21] Trivedi V, Varshney P, Ramteke M. A simplified multi-objective particle swarm optimization algorithm. Swarm Intelligence, 2020, 14: 83-116.

[22] Tu HY, Levchuk YN, Pattipati KR. Robust action strategies to induce desired effects. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 2004, 34(5): 664-680.

[23] Wan L J, Li W, Dai J B, Huang A Q. The modeling and solution of course of action generation based on IN-DEA. Journal of Physics: Conference Series, 2017, 10(3): 1-9.

[24] Wan L J, Li W, Huang AQ (2017). The modeling frame and generation flow of combat course of action. Proceedings of the 5th International Conference on Frontiers and Manufacturing Science and Measuring Technology. Taiyuan, China, June 24–25, 2017.

[25] Wan L J, Zhong Y, Li W. COA optimized selection method of aviation swarm based on DINs and DABC. IEEE Access, 2020, 8: 65116-65126.

[26] Wang X H, Zhang Y, Wang L Z, Lu D W, Zeng G Q. Robustness evaluation method for unmanned aerial vehicle swarms based on complex network theory. Chinese J Aeronaut, 2020, 33(1): 352-364.

[27] Yu Y, Si X S, Hu CH, Zhang J X. A review of recurrent neural networks: LSTM cells and networkarchitectures. Neural Computation, 2019, 31(7): 1235-1270.

[28] Yuan M H, Li Y D, Zhang L Z, Pei F Q. Research on intelligent workshop resource scheduling method based on improved NSGA-II algorithm. Robotics and Computer-Integrated Manufacturing, 2021, 71: 102141.

[29] Zhang J Y, Yao P Y, Yang D S, Wang X, Zhou X X. Approach to organizational course of actions selection based on DINs and PSO. Systems Engineering–Theory & Practice, 2011, 31(10): 1985-1993.

[30] Zhang Q R, Zhang M, Chen T H, Sun Z F, Ma Y Z, Yu B. Recent advances in convolutional neural network acceleration. Neurocomputing, 2019, 323(5): 37-51.

[31] Zhong Y, Wan L J, Zhang J Y. Optimized selection method for air combat course of action with interval uncertainty. Acta Aeronautica et Astronautica Sinica, 2021, 42(2): 324282

[32] Zhou Y M, Zhao H R, Chen J F, Jia Y H. A novel mission planning method for UAVs’ course of action. Computer Communications, 2020, 152(4): 345-356.

[33] Zhu Y G, Zhang X Y, Zhang Y L, Zhang X H. Influence nets based course of action optimization under combinational constraints. Computer Simulation, 2017, 34(7): 22-26.