LAUSR

A Misfire event is an unwanted phenomenon that compromises the regular operation of the engine, increasing the pollution of emission gases and decreasing its efficiency. Therefore, smart systems that detect misfire ensure better engine operation and compliance with government environmental regulations. This paper presents a comparative study of two smart systems that use two different methodologies for misfire detection in a 2006 Ford Zetec-Rocam engine, which is a 4-stroke spark-ignition engine. The first methodology tested was vibration analysis, which consists of collecting vibration data from the engine block using a vibration acquisition system. After the acquisition stage, we extracted and selected the signal features using the fast Fourier transform (FFT) in order to recognize the fault patterns through the use of an artificial neural network (ANN), which presented an accuracy of 99.30%. The second methodology was the acoustic analysis of the engine sound. The data were collected by a sound acquisition system, and then the feature extraction and selection were done by using the same technique as we did in the vibration analysis. For this technique, the ANN developed presented an accuracy of 98.70%. Although the vibration analysis is slightly more accurate than the acoustic analysis for misfire diagnosis, the acoustic system has the advantage of not being necessary the physical contact between the data acquisition system and the engine. Therefore, both techniques may be applied with great accuracy, and the decision of using one approach or another will depend on the equipment availability and the user's specialty.