Search Results

Signal processing incorporating Artificial Neural Networks (ANN) has been shown to be well suited for modeling engine-related performance indicators [ 1 , 2 , 3 ] that require multi-dimensional parametric calibration space. However, to obtain acceptable accuracy, traditional ANN implementation may require processing resources beyond the capability of current engine controllers. This paper explores the practicality of implementing an ANN-based algorithm performing real-time calculations of the volumetric efficiency (VE) for an engine with variable valve actuation (phasing and lift variation). This alternative approach was considered attractive since the additional degree of freedom introduced by variable lift would be cumbersome to add to the traditional multi-dimensional table-based representation of VE.

Recent advancements in the combustion control of new generation engines can benefit from real time, precise sensing of the cylinder pressure profile to facilitate successful combustion feedback. Currently, even laboratory-grade pressure sensors can deliver pressure traces with insufficient signal-to-noise quality due to electrical or combustion-induced signal interference. Consequently, for example, calculation of compression and expansion polytropic indices may require statistical averaging over several cycles to deliver required information. This lag in the resultant feedback may become a concern when the calculated combustion metric is used for feedback control, especially in the case of transients. The method described in this paper involves a special digital filter offering excellent performance which facilitates reduced-error calculation of individual polytropic indices.