In the conditions of short-range air combat operations, one of the important issues is the timely identification of air targets. In the course of solving this issue, an algorithm for identifying the type of air targets was developed, which will allow making a timely decision to determine the effective type of weapon to be used against the detected target. To ensure the stability and reliability of the developed algorithm, it is necessary to adapt it under conditions of uncertainty and noisy data. To operate successfully in such conditions, the algorithm must be able to dynamically adjust to changes in the air situation, including the use of electronic interference by the enemy, target maneuvering, and inaccurate measurement of target parameters. Traditional approaches are often ineffective due to their limited flexibility and low noise immunity.

The proposed approach uses a combination of the Kalman filter and fuzzy logic to ensure the adaptability of the algorithm in dynamic conditions. The Kalman filter effectively reduces the influence of noise on measurements, allowing for more accurate data on target parameters, and fuzzy logic provides flexibility and the ability to make decisions in conditions of incomplete or fuzzy information. This combined approach allows the algorithm to work efficiently even in complex and unstable conditions, increasing the accuracy of airborne target identification.