A complex vibration signal processing technique is applied to four-cylinder spark and compression ignition engines for the diagnosis of power faults inside the cylinders. This technique utilizes two-sided power spectra of complex vibration signals measured from engine blocks as the patterns for engine cylinder power faults. The two-sided power spectra feature that they give not only the frequency contents of complex signals but also the directivity of the engine block motion.
For the automatic detection / diagnosis of cylinder power faults, two pattern recognition methods are employed, correlation method and multilayer neural networks.
Experimental results show that the success rate for diagnosis of cylinder power faults using two-sided power spectra is higher than that using the conventional one-sided power spectra. The proposed technique is also tested to check the robustness to the sensor position and the engine rotational speed.