• 전자공학회논문지 IE
• /
• v.48 no.2
• /
• pp.19-25
• /
• 2011

This paper presented neural network modeling method using vehicle data to predict fuel consumption. To acquire data for training and testing the proposed neural network, medium-class gasoline vehicle drove at downtown and parameters measured include speed, engine rpm, throttle position sensor (TPS), and mass air flow (MAF) as input data, and fuel consumption as target data from OBD-II port. Multi layer perception network was used for nonlinear mapping between the input and the output data. It was observed that the neural network model can predict the vehicle quite well with mean squared error was $1.306{\times}10^{-6}$ for the fuel consumption.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.11
• /
• pp.58-63
• /
• 2020

The fuel injection amount and timing along with the ignition timing for the gasoline engine of a racing car were adjusted using an electronic control unit (ECU), and the engine performance was evaluated through an acceleration test. The fuel map for the fuel injection amount and ignition map for the ignition timing were derived. Using the transient throttle control, the air-fuel ratio could be maintained at a constant value even in the case of a sudden throttle operation. In the flat shift, ignition blocking was more effective than fuel blocking. In a 75 m acceleration test, the required duration without and with ECU control was 4.47 s and 3.99 s, respectively. Notably, the acceleration could be improved by approximately 10.7% when the ECU control was implemented.