Automated Flight Maneuver Recognition for Intelligent Flight Simulator

The rapid growth in the number of aircrafts and pilots emphasizes the need for an AI-enabled training framework that can offer precise, automated examination of flight maneuvers, thereby optimizing the pilot’s training efficiency and minimizing iterations of the conduct of flight maneuvers thereby reducing the training time of the pilot for a flight. This paper introduces a novel hybrid methodology to intelligently detect manoeuvres performed during a flight using signal processing and machine learning techniques. A general framework is developed that can be used for all kinds of flight phases and aircraft types. The framework is implemented in a two-step approach. Firstly, Continuous Wavelet Transform (CWT) of the signals of interest for different manoeuvres are generated, to find the time at which a manoeuvre happens during a sortie. CWT looks at the energy levels in the transformed signal and uses smart thresholding technique to pick out only the parts with high energy, to extract real maneuvers. In the next step, these selected parts are recognised using a pre-trained machine learning model. The pre-trained machine learning model is developed using a supervised learning technique Random Forest to recognize different manuevers. Various statistical parameters such as mean, standard deviation, kurtosis, skewness, etc. of several flight parameters were used as the input features to train the Random Forest classifier. In the present work, the classifier is trained using several actual flight test data maneuvers, and is also supplemented with simulated maneuvers. The achieved gross accuracy for maneuver recognition is approximately 94%. This approach can be adopted for various aircraft programs for various range of flight maneuvers to aid pilots to reduce their training time in the simulator as well as actual flights.