In this paper the independent component analysis (ICA) is applied to engine acoustic signals to identify the engine noise sources. The ICA decomposes the signals into a number of independent components (ICs) so the individual engine acoustic sources can be studied separately. The theoretical description of the characteristics of the diesel engine noise sources is introduced first. The predictive models indicate that the engine noise generation mechanisms follow the same principle as that of the ICA model. The relevant theory and properties of the ICA model are outlined next. A numerical example is presented to verify the separation efficiency of the ICA. The numerical example shows that the ICA can effectively separate the embedded low-level sources. A single set of microphone system is then used to measure the acoustic signals and a sequential ICA model is developed to work with the measurements. The continuous wavelet transform (CWT) is applied to represent the ICs in the time-frequency domain. The source separation results from the recorded acoustic signals are in accordance with theoretical predictions and engine design specifications.