Immunity-Based Aircraft Failure Detection and Identification Using an Integrated Hierarchical Multi-Self Strategy

Abstract

This paper presents the development and application of an integrated artificial immune system-based scheme for the detection and identification of a wide variety of aircraft sensor, actuator, propulsion, and structural failures/damages. The proposed approach is based on a hierarchical multi-self strategy where different self configurations are selected for the identification of specific abnormal conditions. Data collected using a motion-based flight simulator was used to define the self for a sub-region of the flight envelope. The aircraft model represents a supersonic fighter, including model-following adaptive control laws based on non-linear dynamic inversion and artificial neural network augmentation. The proposed detection scheme achieves low false alarm rates and high detection and identification rates for the four categories of failures considered.