Classification of mechanical conditions for HVCBs based on artificial immune network

The vibration features of high voltage circuit breakers (HVCBs) shift with the changes of their working conditions. The existing pattern recognition methods are lack of the ability to pursue this transition, which degrades the performance of the corresponding diagnostic systems. This paper introduces the mechanism of natural immune system and immune network theory, borrowing ideas from which, a self-learning method for diagnosing mechanical failures of HVCBs is presented on the basis of artificial immune network memory classifier (AINMC). Finally, this network is applied to classify vibration patterns of HVCBs. Comparison has been made between self-learning method and non self-learning method, and result shows that self-learning method can achieve more precise judgment of the mechanical condition of HVCBs.