Fault diagnosis of an internal combustion engine is proposed herein by means of vibration analysis and a comparative analysis of normal operation and induced misfire scenarios. In order to validate previous works on misfire with pure gasoline, measurements also included tests performed with ethanol-gasoline fuel blends. According to results, changes in the fuel mix seem to have little impact on the performance and behaviour of the engine. And additionally, the particular frequency components that allowed differentiation between normal and faulty conditions were also present on all the fuel blends tested. Fast Fourier Transform was applied to obtain the frequency domain of the signal as a previous step to the subsequent identification process based on statistical characteristics extraction. A fuel blend classification method based on the analysis of the vibration signals of the engine was studied using envelope, Spike Energy and Peak Value techniques. Differentiation was possible with the extraction of the statistical features of the Peak Value spectrum of the longitudinal acceleration with a specific filter selection.