Abstract:
Using machine learning for misfire detection in a Dynamic firing level modulation controlled internal combustion engine is described. A neural network is used to calculate expected crank acceleration from various inputs, including the dynamically defined cylinder skip fire sequence. The output of the neural network is then compared to a signal indicative of the measured crank acceleration. Based the comparison, a prediction is made if a misfire has occurred or not. In alternative embodiment, the neural network is expanded to include the measured crank acceleration as an additional input. With the latter embodiment, the neural network is arranged to directly predict misfire events.
Abstract:
Various methods and arrangements for determining a combustion control parameter for a working chamber in an engine are described. In one aspect, an engine controller includes a firing counter that stores a firing history for the working chamber. A combustion control module is used to determine a combustion control parameter, which is used to help manage combustion in the working chamber. The combustion control parameter is determined based at least in part on the firing history.
Abstract:
The described embodiments relate generally to skip fire control of internal combustion engines and particularly to mechanisms for determining a desired operational firing fraction. In some embodiments, a firing fraction determining unit is arranged to determine a firing fraction suitable for delivering a requested engine output. The firing fraction determining unit may utilize data structures such as lookup tables in the determination of the desired firing fraction. In one aspect the desired engine output and one or more operational power train parameters such as current engine speed, are used as indices to a lookup table used to select a desired firing fraction. In other embodiments, additional indices to the data structure may include any one of: transmission gear; manifold absolute pressure (MAP); manifold air temperature; a parameter indicative of mass air charge (MAC); cam position; cylinder torque output; maximum permissible manifold pressure; vehicle speed; and barometric pressure.
Abstract:
The described embodiments relate generally to skip fire control of internal combustion engines and particularly to mechanisms for determining a desired operational firing fraction. In some embodiments, a firing fraction determining unit is arranged to determine a firing fraction suitable for delivering a requested engine output. The firing fraction determining unit may utilize data structures such as lookup tables in the determination of the desired firing fraction. In one aspect the desired engine output and one or more operational power train parameters such as current engine speed, are used as indices to a lookup table used to select a desired firing fraction. In other embodiments, additional indices to the data structure may include any one of: transmission gear; manifold absolute pressure (MAP); manifold air temperature; a parameter indicative of mass air charge (MAC); cam position; cylinder torque output; maximum permissible manifold pressure; vehicle speed; and barometric pressure.