Engine Fault Diagnosis Using Acoustic Signals

This work presents an experimental study to detecting the faults of engine using its noise. The noises produced by the engine and its accessory systems are numerous: whines, squeals, knock, rattles, and many other sounds. Faults diagnosis for Mitsubishis car engine model 2006 has been conducted and this diagnosis includes normal operating conditions for the engine (without malfunction) and for malfunctions situations at variable engine speed 1000,2000, 3000 and 4000 rpm respectively The engine data is acquired from a four cylinder one- petrol engine test bed under consideration at different operating states, and then simulated. Most of the conventional fault diagnosis techniques using sound emission and vibration signals are based on analyzing the signal amplitude in the time or frequency domain. For engine under fired and misfires spark the all the domain parameters (RMS amplitude, peak amplitude and energy) was processed using MATLAB software. It was found that fault detection and diagnosis for internal combustion engines is complicated by the presence of engine noise during normal operation. The average of amplitude found to be 450 x10(-3)m for normal engine working without any malfunction and 458x10(-3)m for misfire of one spark plug and for misfire of two spark plugs 457.8 x10(-3)m. In this study, some of the engine malfunction such as failure spark plug has been recorded, but we can generalize it to include all engine breakdown. Generally, sound emission signal serves as a promising alternative to the condition monitoring and fault diagnosis in rotating machinery when the vibration signal is not available. This research paper explores that automobiles could be major sources of noise pollution. Condition monitoring and fault diagnosis of IC engine through acoustic signal analysis is an established technique for detecting early stages of component degradation