Search Results

In this, Part 1 of the paper, the sound generation of a diesel engine is modelled based upon the combustion process, and time-frequency analysis is used to reveal the underlying characteristics of the sound waves. Simulation shows that the frequency bandwidth of the generated acoustic signals is significantly widened around the engine's top dead centre (TDC) positions, with the energy concentrated predominantly at the firing frequency and its harmonics. As anticipated, the model predicts an increase in sound level with increasing engine load and speed, and the model-predicted noise generation is correlated with waveforms extracted from intrusively-monitored cylinder pressure. Real monitored data, taken in an ordinary engine test-bay environment and without special acoustic monitoring precautions, is shown to be highly contaminated due to adverse environmental acoustics and intrusive background noise.

In this paper, the focus is upon the condition monitoring implications of acoustic monitoring. Namely, its ability to detect, diagnose and locate incipient deterioration in a number of common failure modes. To improve the reliability of the condition monitoring procedures, the noise contaminated signals are conditioned based upon the results of speed and load dependency investigation of the identified low and high frequency regions of sound. High pass filtering is shown to eliminate much of the environmental dependency of the monitored signals, whilst retaining the pertinent condition indicating information content. Real fault testing shows that the location of different faults, their influences upon combustion, and the ability to distinguish between them can all be extracted from the shape of the contours in the Continuous Wavelet Transform (CWT).