Artificial neural networks for PIO events classification comparing different data collection procedures

This work evaluates the accuracy and reliability of PIO test classification using the PIO Rating Scale and proposes using an automatic tool for this evaluation based on test data to eliminate the subjectivity inherent to the application of rating scales. Two test procedures (discrete synthetic task and pitch capture) are executed in a flight simulator, using aircraft dynamic models with different PIO proneness and experienced flight test pilots. The results show a significant effect of subjectivity in pilot rating and various reliability for different test procedures. This data is used to build an artificial neural network (ANN) proposed to classify the executions using the PIO Rating Scale. The ANN presented low computational cost and 97.1% accuracy when using data extracted from the pitch capture test procedure.