Using machine learning for cylinder misfire detection in a dynamic firing level modulation controlled internal combustion engine is described. In a classification embodiment, cylinder misfires are differentiated from intentional skips based on a measured exhaust manifold pressure. In a regressive model embodiment, the measured exhaust manifold pressure is compared to a predicted exhaust manifold pressure generated by neural network in response to one or more inputs indicative of the operation of the vehicle. Based on the comparison, a prediction is made if a misfire has occurred or not. In yet other alternative embodiment, angular crank acceleration is used as well for misfire detection.

Using machine learning for cylinder misfire detection in a dynamic firing level modulation controlled internal combustion engine is described. In a classification embodiment, cylinder misfires are differentiated from intentional skips based on a measured exhaust manifold pressure. In a regressive model embodiment, the measured exhaust manifold pressure is compared to a predicted exhaust manifold pressure generated by neural network in response to one or more inputs indicative of the operation of the vehicle. Based on the comparison, a prediction is made if a misfire has occurred or not. In yet other alternative embodiment, angular crank acceleration is used as well for misfire detection.

A fuel formulation comprising a sugar and ammonia solution, wherein the sugar and ammonia are present in a combined amount of greater than 70 percent by weight of the fuel formulation, and wherein the sugar comprises fructose, glucose, sucrose or a combination thereof.

A fuel formulation comprising a sugar and ammonia solution, wherein the sugar and ammonia are present in a combined amount of greater than 70 percent by weight of the fuel formulation, and wherein the sugar comprises fructose, glucose, sucrose or a combination thereof.

Operating a direct-injection compression-ignition engine includes injecting early pilot shots of fuel, and controlling a cylinder temperature timing to combust the early pilot shots according to a combustion phasing that is based on the cylinder temperature timing. A main charge of the fuel is combusted based on the combustion of the early pilot shots. A combustion control unit is structured to command actuation of a fuel injector and a cylinder temperature controller to phase combustion of early pilot shots of the fuel, prior to a TDC position of a piston in an engine cycle. The cylinder temperature controller is a variable valve actuator or other apparatus controlling cylinder temperature in a manner decoupled from piston position.

Operating a direct-injection compression-ignition engine includes injecting early pilot shots of fuel, and controlling a cylinder temperature timing to combust the early pilot shots according to a combustion phasing that is based on the cylinder temperature timing. A main charge of the fuel is combusted based on the combustion of the early pilot shots. A combustion control unit is structured to command actuation of a fuel injector and a cylinder temperature controller to phase combustion of early pilot shots of the fuel, prior to a TDC position of a piston in an engine cycle. The cylinder temperature controller is a variable valve actuator or other apparatus controlling cylinder temperature in a manner decoupled from piston position.

Using machine learning for cylinder misfire detection in a dynamic firing level modulation controlled internal combustion engine is described. In a classification embodiment, cylinder misfires are differentiated from intentional skips based on a measured exhaust manifold pressure. In a regressive model embodiment, the measured exhaust manifold pressure is compared to a predicted exhaust manifold pressure generated by neural network in response to one or more inputs indicative of the operation of the vehicle. Based on the comparison, a prediction is made if a misfire has occurred or not. In yet other alternative embodiment, angular crank acceleration is used as well for misfire detection.

Using machine learning for cylinder misfire detection in a dynamic firing level modulation controlled internal combustion engine is described. In a classification embodiment, cylinder misfires are differentiated from intentional skips based on a measured exhaust manifold pressure. In a regressive model embodiment, the measured exhaust manifold pressure is compared to a predicted exhaust manifold pressure generated by neural network in response to one or more inputs indicative of the operation of the vehicle. Based on the comparison, a prediction is made if a misfire has occurred or not. In yet other alternative embodiment, angular crank acceleration is used as well for misfire detection.

An apparatus comprises a first circuit and a second circuit. The first circuit is structured to determine that a combustion cylinder is operating in a transition period between an exhaust stroke and an intake stroke of the combustion cylinder. The second circuit is structured to provide an injection command during the transition period to a fuel injector associated with the combustion cylinder, the injection command being to inject fuel into a combustion chamber of the combustion cylinder such that at least a portion of the fuel escapes from the combustion chamber through an exhaust port of the combustion cylinder.

An apparatus comprises a first circuit and a second circuit. The first circuit is structured to determine that a combustion cylinder is operating in a transition period between an exhaust stroke and an intake stroke of the combustion cylinder. The second circuit is structured to provide an injection command during the transition period to a fuel injector associated with the combustion cylinder, the injection command being to inject fuel into a combustion chamber of the combustion cylinder such that at least a portion of the fuel escapes from the combustion chamber through an exhaust port of the combustion cylinder.