Search Results

Tremendous amount of useful information can be extracted from the cylinder pressure signal for engine combustion control. However, the physical cylinder pressure sensors are undesirably expensive and their health need to be monitored for fault diagnostic purpose as well. This paper presents the results of the development of a virtual cylinder pressure sensor (VCPS) with individual variable-oriented independent estimators. Two neural network-based independent cylinder pressure related variable estimators were developed and verified at steady state. The results show that these models can predict the variables correctly compared with the extracted variables from the measured physical cylinder pressure sensor signal. Good generalization capabilities of the developed models are observed in the sense that the models work well not only for the training data set but also for the new inputs that they have never been exposed to before.

In-cylinder ion sensing through sparkplug electrodes can be used to determine in-cylinder A/F ratio by using a modified production coil-on-plug ignition system having ion sensing capability. The in-cylinder ionization can be characterized by the height of the peak, location of the peak from ignition command and area under the ionization signal curve. The effects of A/F ratio on the in-cylinder ionization can be isolated from other affecting factors by conducting tests on a constant volume combustion device in which the initial pressure and temperature can be well controlled. This results in a parabolic correlation of the ionization characteristics with the mixture equivalence ratio. Additionally the ionization characteristics show strong dependence on engine load and speed. Equivalence ratio characteristics during engine cranking and warm up are investigated, and a method for on-line calibration of ionization detection is discussed.