Battlefield information is generally incomplete, uncertain, or deceptive. To realize enemy intention recognition in an uncertain and incomplete air combat information environment, a novel intention recognition method is proposed. After repairing the missing state data of an enemy fighter, the gated recurrent unit (GRU) network, supplemented by the highest frequency method (HFM), is used to predict the future state of enemy fighter. An intention decision tree is constructed to extract the intention classification rules from the incomplete a priori knowledge, where the decision support degree of attributes is introduced to determine the node-splitting sequence according to the information entropy of partitioning (IEP). Subsequently, the enemy fighter intention is recognized based on the established intention decision tree and the predicted state data. Furthermore, a target maneuver tendency function is proposed to screen out the possible deceptive attack intention. The one-to-one air combat simulation shows that the proposed method has advantages in both accuracy and efficiency of state prediction and intention recognition, and is suitable for enemy fighter intention recognition in small air combat situations.
As the core process of case-based reasoning (CBR), case retrieval is the foundation for CBR success, and the quality of case retrieval depends on the case similarity measure. We improved the CBR system for aeroengine fault diagnosis by embedding the attitudinal Choquet integral (ACI) and 2-order additive measure to consider attribute interactions and decision makers’ attitudes. The enhanced case retrieval method can not only integrate the local similarity, attribute importance, and interaction between attributes, but also incorporate the attitude of the decision maker, thus producing more comprehensive and reasonable global similarity and high-quality recommendations. An experimental study of aeroengine fault diagnosis and comparisons with other similarity aggregation methods were performed to demonstrate the effectiveness of the proposed method.
Battlefield information is generally incomplete, uncertain, or deceptive. To realize the real-time recognition of an enemy’s intention, we developed a novel intelligent intention recognition method in uncertain and incomplete air combat information environments. A gated recurrent unit network complemented by the highest-frequency method was used to predict the enemy state with missing state data repaired. An intention decision tree was constructed to extract intention classification rules from incomplete prior knowledge, where the decision support degree was introduced to determine the node-splitting sequence according to the information entropy of partitioning. Subsequently, the enemy’s intention was recognized based on the established intention decision tree and state prediction data. Furthermore, a target maneuver tendency function was proposed to screen out possible deceptive attack intentions. Simulation studies show that the proposed method had advantages in both the accuracy and efficiency of state prediction and intention recognition; thus, it is suitable for real-time intention prediction in small-scale air battlefields.