Development and Validation of a Model for Mechanical Efficiency in a Spark Ignition Engine

Paper #:
  • 1999-01-0905

Published:
  • 1999-03-01
Citation:
Arsie, I., Pianese, C., Rizzo, G., Flora, R. et al., "Development and Validation of a Model for Mechanical Efficiency in a Spark Ignition Engine," SAE Technical Paper 1999-01-0905, 1999, https://doi.org/10.4271/1999-01-0905.
Pages:
14
Abstract:
A set of models for the prediction of mechanical efficiency as function of the operating conditions for an automotive spark ignition engine is presented. The models are embedded in an integrated system of models with hierarchical structure for the analysis and the optimal design of engine control strategies. The validation analysis has been performed over a set of more than 400 steady-state operating conditions, where classical engine variables and pressure cycles were measured. Models with different functional structures have been tested; parameter values and indices of statistical significance have been determined via non-linear and step-wise regression techniques. The Neural Network approach (Multi Layer Perceptrons with Back-Propagation) has been also used to evaluate the feasibility of using such an approach for fast black-box modelization. The proposed regression models, characterized by a very limited computational demand, exhibit excellent performance over a large set of experimental data, with less than ten parameters but requiring a rather complex engine geometrical and operative description. On the other hand, the Neural Network model has been developed considering as independent variables only four measurable engine parameters and the training has been performed using a reduced set of experimental data. The results presented show a relevant precision improvement with respect the available models cited in literature. The different model structures developed are suitable for several uses, both for off-line and on-line applications.
Access
Now
SAE MOBILUS Subscriber? You may already have access.
Buy
Select
Price
List
Download
$27.00
Mail
$27.00
Members save up to 40% off list price.
Share
HTML for Linking to Page
Page URL

Related Items

Training / Education
2017-06-15
Training / Education
2018-03-26
Article
2017-03-13
Training / Education
2018-02-05