An Investigation on Engine Condition Monitoring Based on EEMD and Morphological Fractal Dimension

摘要

In respect to the nonlinear and low signal-to-noise ratio characteristics of the vibration signals measured from diesel engine, This paper conducts an investigation on diesel engine condition monitoring based on ensemble empirical mode decomposition (EEMD) and morphological fractal dimension. Firstly, the vibration signal is decomposed into a set of intrinsic mode functions (IMFs) by EEMD, and get the fault information of the characteristic IMF. Then the morphological fractal dimension of IMFs which contain diesel engine fault characteristic information is computed and as it for the characteristic parameters to identifying the diesel engine working states and fault types. The analysis of vibration signals measured from diesel engine at different states that are normal and exhaust valve leakage have been done. Results show that it can reflect nonlinear characteristics of vibration signals measured from diesel engine and monitor working condition of diesel engine accurately.