CAJ | 학술논문

建立双机协同被动探测的任务模型，运用模糊理论对问题状态空间进行泛化，针对不同的探测阶段给出了目标转移函数的不同形式，通过合理定义动作空间和奖励函数将问题描述为Markov决策过程。给出了双机协同被动雷达探测的模糊Q学习算法，并对算法进行仿真，仿真结果表明，该方法能够有效控制双机的飞行路径，实现对机动及非机动目标的有效探测。
건립쌍궤협동피동탐측적임무모형，운용모호이론대문제상태공간진행범화，침대불동적탐측계단급출료목표전이함수적불동형식，통과합리정의동작공간화장려함수장문제묘술위Markov결책과정。급출료쌍궤협동피동뢰체탐측적모호Q학습산법，병대산법진행방진，방진결과표명，해방법능구유효공제쌍궤적비행로경，실현대궤동급비궤동목표적유효탐측。
Based on the partition of the radiation area of the target's active radar,the task model of the dual-aircraft is set up .By using fuzzy theory to make a generalization to the problem's state space,providing different transition functions according to different detecting stages,and properly defining the action space and reward function,the problem is formulated as a Markov Decision Process ( MDP) .Details of the fuzzy Q learning are presented .Simulation studies indicate that the proposed algorithm can provide adaptive strategies for the dual-aircraft to control their flight paths for non-maneuvering or maneuvering target detection .