The introduction of inexpensive cylinder pressure sensors provides new opportunities for precise engine control. This paper presents a control strategy of spark advance and air-fuel ratio based upon cylinder pressure for spark ignition engines. In order to extend the cylinder pressure based engine control to a wide range of engine speeds, the appropriate choice of control parameters is important as well as essential.
For this control scheme, peak pressure and its location for each cylinder during every engine cycle are the major parameters for controlling the air-fuel ratio and spark timing. However, the conventional method requires the measurement of cylinder pressure at every crank angle degree to determine the peak pressure and its location. In this study, the peak pressure and its location were estimated, using a multi-layer feedforward neural network, which needs only five cylinder pressure samples at -40°, -20°, 0°, 20°, and 40° after TDC.
The neural network plays an important role in mitigating the A/D conversion load of an electronic controller by increasing the sampling interval from 1°crank angle (CA) to 20°CA. The estimated location of the peak pressure can be regarded as a good index for combustion phasing, and can also be used as an MBT control parameter. The peak pressure reflects the air-fuel ratio from rich mixture to lean mixture near the lean misfire limit, and can be used as an air-fuel ratio control parameter as well.
The feasibility of this methodology was closely examined through steady and transient engine operations to control spark advance and air-fuel ratio. Moreover, a commercial two-liter four-cylinder engine was employed in this experiment. The experimental results revealed a favorable agreement between the real MBT and target air-fuel ratio.