A control device mounted in a vehicle in which at least one controlled part is controlled based on an output parameter obtained by inputting input parameters to a learned model using a neural network, provided with a parked period predicting part predicting future parked periods of the vehicle and a learning plan preparing part preparing a learning plan for performing relearning of the learned model during the future parked periods based on results of prediction of the future parked periods.

An internal combustion engine (1), with an engine regulating device (3) and an exhaust gas aftertreatment device (16) with an SCR catalytic converter (4) for the reduction of at least one NO.sub.x component, and with a catalytic converter regulating device (6), wherein the engine regulating device (3) is prescribed a target value for an NO.sub.x mean value of the NO.sub.x component of the exhaust gases, which mean value results at an outlet point (7) of the exhaust gas aftertreatment device (16) in relation to a predefinable time period, and the engine regulating device (3) is configured at least in one operating mode to continuously calculate an NO.sub.x reference value for the catalytic converter regulating device (6) with consideration of No.sub.x components which have already been emitted and the predefined target value, which reference value is selected in such a way that the predefined target value results at the outlet point of the exhaust gas aftertreatment device (16) at the end of the predefinable time period when the calculated NO.sub.x reference value of the catalytic converter regulating device (6) is fed as NO.sub.x setpoint value to the regulating means.

Various embodiments include methods for determining the efficiency of an SCR catalytic converter in a system including a nitrogen oxide sensor, and a metering device for a reducing agent arranged in an exhaust-gas duct, and an exhaust recirculation line with a recirculation valve disposed downstream of the SCR catalytic converter and feeding an intake region of the engine. The methods comprise: setting or identifying a quasi-steady-state operating state and an associated recirculation rate; adding a first quantity of reducing agent using the metering device; measuring a resulting first nitrogen oxide value using the sensor; adding a further predefined quantity, different from the first quantity; measuring the resulting nitrogen oxide values using the sensor; and determining the efficiency of the SCR catalytic converter based at least in part on the associated exhaust-gas recirculation rate and the measured nitrogen oxide values.

A spark ignited internal combustion engine is controlled in response to a self-learned TOB reference. The self-learned TOB reference is based on a difference between a learned TOB offset and a desired or target TOB, and a sensed TOB. The learned TOB offset at a given operating condition, such as charge pressure, can be found by interpolating between the learned charge pressure breakpoints in a TOB learning algorithm. The TOB learning algorithm can include using a filtered charge pressure value to indicate the engine load at which the TOB is learned. An index determination is made with a look up table with charge pressure as an input and an array index of learned charge pressure and learned TOB offset as outputs.

A fuel combustion apparatus 2 according to the present invention includes: a combustion cylinder 4; a fuel feed unit 6 that introduces a swirling flow of an air-fuel mixture into the combustion cylinder; an ignition unit 10 including an igniter 32 located in the combustion cylinder 4; an ion detection unit 12 including a detector 40 located in the combustion cylinder 4; and a control unit 14 that adjusts a mixing ratio of the fuel based on a detection result obtained by the ion detection unit 12. Preferably, the fuel is ammonia. Preferably, the detector 40 is located in the vicinity of the igniter 32.

A system and method of integrating an engine having dynamic skip fire control with an exhaust gas recirculation system in a turbocharged internal combustion engine is described. An engine control system determines an appropriate firing pattern based at least in part on a desired exhaust gas recirculation flow rate. Signals from sensors in the intake manifold and exhaust system may also be used as part of a feedback loop to determine a desired exhaust gas recirculation flow rate.

Methods and systems are provided for increasing EGR delivered to an engine. In one example, a method may include determining an EVO timing set point and an external EGR setpoint in parallel, based on an inverse model. The EVO timing may be adjusted based on a combination of the EVO timing setpoint and an EGR cylinder balancing feedback loop, thereby varying internal EGR to the engine to supplement external EGR.

Various methods and systems are provided for controlling emissions. In one example, a controller is configured to respond to one or more of intake manifold air temperature (MAT), intake air flow rate, or a sensed or estimated intake oxygen fraction by changing an exhaust gas recirculation (EGR) amount to maintain particulate matter (PM) and NOx within a range, and then further adjusting the EGR amount based on NOx sensor feedback.

System for controlling an engine provided with an exhaust gas post-treatment system of the selective catalysis type, including a closed-loop control of NO.sub.x before the gas post-treatment system, according to the following steps: ⋅ a unit for determining a NO.sub.x setpoint in dependence on the rotational speed and the torque setpoint of the engine, ⋅ a unit for determining a NO value, and ⋅ a cascade control unit which is able to determine a setpoint for admitted oxygen and a correction of the supercharging pressure destined for unit for controlling the air loop of the engine as well as a correction of the injection pressure and a correction of the advance of the main injection in dependence on a NO.sub.x difference, between a NOx emission setpoint or corrected emission setpoint and a determined value of the quantity of NO.sub.x.

The disclosure relates to a self-adaptive oil spraying control system and method for a biodiesel engine. The control system includes an exhaust pipe, a gas sensor, a control module and an oil sprayer, wherein the exhaust pipe is connected to the oil sprayer, the gas sensor is mounted in the exhaust pipe, and the gas sensor and the oil sprayer are connected to the control module respectively. According to the control method, a main spray advance angle of the engine is subjected to closed-loop control directly through comparison between an idling steady state NO.sub.x emission signal and an idling steady state NO.sub.x emission value of pure diesel when the engine uses the biodiesel, so that emission of NO.sub.x in the exhaust is reduced. Compared with the prior art, the disclosure has the advantages of no need of detecting a biodiesel ratio, high efficiency, good effect and the like.