The recognized hidden defects in a car engine is the most important work for a maintain engineer, so they can regulate the engines to be safe and improve the reliability of automobile systems. In this paper, we will present a novel defect recognized method based on the extension neural network type-3 (ENN-3) and apply this method in the defect fault recognition of a practical car engine. The proposed recognized method has been tested on the practical tested records of the Nissan CEFIRO 2.0 engine and also compared with other traditional classified methods. Experimental results are of great interest for the hidden defect recognition of car engines.
