Artificial immune system (AIS) is one of the critical research frontiers in artificial intelligence. The detector is the core problem of AIS, and the generation, evolution, and detection of the detector determine the application effect of the algorithm. In this paper, an AIS-based multi-level fault diagnosis technique with hyper-shell T cell and hypercube B cell detectors is proposed. According to different engineering requirements, the concept of multi-level fault diagnosis is proposed and a multi-task cascade AIS architecture of multi-level fault diagnosis is established. Hyper-shell T cells are used to detect the existence of fault and then determine the severity of damage. Meanwhile, hypercube B cells can identify the categories of failures. Investigations on the Paderborn University bearing data set demonstrate the effectiveness.

multi-level fault diagnosis, artificial immune system, hyper-shell T cell, hypercube B cell