Date of Award


Document Type

Open Access Master's Thesis

Degree Name

Master of Science in Mechanical Engineering (MS)

Administrative Home Department

Department of Mechanical Engineering-Engineering Mechanics

Advisor 1

Jeffrey D. Naber

Advisor 2

Jason R. Blough

Committee Member 1

Mahdi Shahbakhti


Shifting consumer mindsets and evolving government norms are forcing automotive manufacturers the world over to improve vehicle performance and also reduce greenhouse gas emissions. A critical aspect of achieving future fuel economy and emission targets is improved powertrain control and diagnostics.

This study focuses on using a sensor fusion based approach to improving control and diagnostics in a gasoline engine. A four cylinder turbocharged engine was instrumented with a suite of sensors including ion sensors, exhaust pressure sensors, crank position sensors and accelerometers. The diagnostic potential of these sensors was studied in detail. The ability of these sensors to detect knock, misfires and also correlate with pressure and combustion metrics was also evaluated.

Lastly a neural network based approach to combine individual sensor signal information was developed. The neural network was used to estimate mean effective pressure and location of fifty percent mass fraction fuel burn. Additionally, the influence of various neural network architectures was studied.

Results showed that under pseudo transient conditions a recursive neural network could use information from the low cost sensors to estimate mean effective pressure within an error of 0.1bar and combustion phasing within 2.5 crank-angle degrees.