Search Results

Downsized gasoline engines, coupled with gasoline direct injection (GDI) and turbocharging, have provided an effective means to meet both emissions standards and customers’ drivability expectations. As a result, these engines have become more and more common in the passenger vehicle marketplace over the past 10 years. To maximize fuel economy, these engines are commonly calibrated to operate at low speeds and high engine loads – well into the traditional ‘knock-limited’ region. Advanced engine controls and GDI have effectively suppressed knock and allowed the engines to operate in this high efficiency region more often than was historically possible. Unfortunately, many of these downsized, boosted engines have experienced a different type of uncontrolled combustion. This combustion occurs when the engine is operating under high load and low speed conditions and has been named Low Speed Pre-Ignition (LSPI). LSPI has shown to be very damaging to engine hardware.

1Increasing adoption of downsized, boosted, spark-ignition engines has improved vehicle fuel economy, and continued improvement is desirable to reduce carbon emissions in the near-term. However, this strategy is limited by damaging preignition events which can cause hardware failure. Research to date has shed light on various contributing factors related to fuel and lubricant properties as well as calibration strategies, but the causal factors behind an individual preignition cycle remain elusive. If actionable precursors could be identified, mitigation through active control strategies would be possible. This paper uses artificial neural networks to search for identifiable precursors in the cylinder pressure data from a large real-world data set containing many preignition cycles. It is found that while follow-up preignition cycles in clusters can be readily predicted, the initial preignition cycle is not predictable based on features of the cylinder pressure.