Immunity-based accommodation of aircraft subsystem failures

Abstract

PurposeThis paper aims to describe the design, development and flight-simulation testing of an artificial immune-system-based approach for accommodation of different aircraft sub-system failures/damages.Design/methodology/approachThe approach is based on building an artificial memory, which represents self- (nominal conditions) and non-self (abnormal conditions) within the artificial immune system paradigm. Self- and non-self are structured as a set of memory cells consisting of measurement strings, over pre-defined time windows. Each string is a set of features values at each sample time of the flight. The accommodation algorithm is based on the cell in the memory that is the most similar to the in-coming measurement. Once the best match is found, control commands corresponding to this match are extracted from the memory and used for control purposes.FindingsThe results demonstrate the possibility of extracting pilot compensatory commands from the self/non-self structure and capability of the artificial-immune-system-based scheme to accommodate an actuator malfunction, maintain control and complete the task.Research limitations/implicationsThis paper concentrates on investigation of the possibility of extracting compensatory pilot commands. This is a preliminary step toward a more comprehensive solution to the aircraft abnormal condition accommodation problem.Practical implicationsThe results demonstrate the effectiveness of the proposed approach using a motion-based flight simulator for actuator and sensor failures.Originality/valueThis research effort is focused on investigating the use of the artificial immune system paradigm for control purposes based on a novel methodology.