Health monitoring method of aero-engine based on immunology principles

In view of the problems such as complex modeling, large sample demands and discontinuous learning in recent health monitoring of aero-engine, a method based on immunology principles is proposed. Taking state symptoms as antigens, and detectors under different fault modes as antibodies, the normal and anomaly conditions are distinguished via negative selections. Memory antibodies that can identify the structures of antigens are generated via the clonal selection mechanism. The health condition of aero-engine is determined by the maximum fault membership. The proposed method was applied to monitor health state of aero-engine. The emulation result indicates that the method has the merits of high identification accuracy, and being fit for health monitoring of aero-engine with low demands on fault samples.