Integrated Framework for Artificial Immunity-Based Aircraft Failure Detection, Identification, and Evaluation

Abstract

This paper presents a novel conceptual framework for an integrated set of methodologies for the detection, identification, and evaluation of a wide variety of failures of aircraft subsystems based on the artificial immune system paradigm. The detection represents the capability to declare that a failure within any of the aircraft subsystems has occurred. The identification process determines which element has failed. The evaluation of the failure addresses three aspects: the type of the failure, its magnitude, and the reassessment of the generalized flight envelope. Failure detection, identification, and evaluation schemes are included using the bioimmune system metaphor combined with other artificial intelligence techniques. The immunity-based fault detection operates in a similar manner as does the immune system when it distinguishes between entities that belong to the organism and entities that do not. The proposed approach directly addresses the complexity and multidimensionality of aircraft dynamic response in the context of abnormal conditions and provides the adequate tools to solve the failure detection problem in an integrated and comprehensive manner. A multiself failure detection and identification scheme is presented for actuator, sensor, engine, and structural failures/damages, which was developed and tested using a motion-based flight simulator. The scheme achieves excellent detection rates and a low number of false alarms and demonstrates the effectiveness of the proposed framework.