Torsional system parameter identification of internal combustion engines under normal operation

For internal combustion engines, lumped-mass models of the crankshaft system are frequently used for torque estimation in control and diagnostic applications, such as cylinder balancing and misfire detection. Due to inherent model uncertainties and changing system dynamics it may be necessary to adapt the model parameters from time to time in order to preserve the required model accuracy. In this paper a frequency-domain method for on-line identification of the parameters describing the torsional dynamics of internal combustion engines is presented. In the proposed method, the engine is excited by adjusting the cylinder-wise injected fuel amounts, and the measured responses in torsional vibration frequency components are used for parameter estimation. As the fuel-injection adjustments can be determined in such a way that the net indicated torque is unaffected, the identification can be performed on-line without disturbing normal engine operation. The procedure can be applied to estimate the torsional stiffness and damping parameters of the flexible coupling connecting the engine and the load. In addition, the gains which describe how the cylinder-wise fuel injections affect the amplitudes of relevant torsional vibratory frequency components are obtained. The parameter identification method is successfully evaluated in full-scale engine tests on a 6.6 MW six-cylinder medium-speed common-rail diesel engine.