In the automotive factory, various types of engines are assembled and dispatched. An engine fault not only damages the engine itself but also causes a break in the automobile system. Engine fault diagnosis can produce significant cost saving by scheduling preventive maintenance and preventing extensive downtime periods caused by extensive failure. Therefore, this paper presents a novel diagnosis method based on the extension theory and applies it in the fault diagnosis of engine malfunction by means of exhaust back pressure, the thickness of exhaust, the temperature of engine emissions and engine vibrations. This paper uses the matter-element method and extended correlation functions to construct the fault diagnosis model. The proposed method has been tested on practical diagnostic records and compared with the multilayer neural networks (MNN) and k-means classification methods. The test results show that the proposed method is suitable for detecting vibration fault of automotive engines, and is efficient in dealing with noise in the data. ICIC International
