In-flight Actuator Failure Detection and Identification for a Reduced Size UAV Using the Artificial Immune System Approach

This paper presents the preliminary development of an actuator failure detection and identification scheme using the artificial immune system technique. The scheme is tested using in-flight data from a reduced size remotely controlled research aircraft equipped with a jet engine. The immunity-based detection is, in principle, similar to the process of self/nonself discrimination, through which the natural immune system recognizes extraneous agents. The process of defining the identifiers and developing the detection and identification scheme is presented. A combined method using positive and negative selection strategy is used to generate detectors. Different sets of flight data are used to design and test the scheme. The evaluation of the scheme is performed in terms of detection rate, number of false alarms, and detection time for normal conditions and upset conditions including one stabilator or aileron locked at trim position. The proposed detection scheme achieves good detection performance for all flight conditions considered. This approach proves promising for coping with the multidimensional characteristics of integrated/comprehensive detection of aircraft sub-system failures.