A prescribed air-fuel ratio feedback control region for performing feedback-control of air-fuel ratio has therein: a first region where fuel is injected, during one combustion cycle, only from a first fuel injection valve injecting fuel directly into a cylinder; and a second region where fuel is injected, during one combustion cycle, from both of the first fuel injection valve and a second fuel injection valve injecting fuel into an air-intake passage. A second region is configured such that an amount of fuel injected from the first fuel injection valve and an amount of fuel injected from the second fuel injection valve remain at a given constant ratio regardless of operating status. A diagnosis on the first and second fuel injection valves is performed by using a first air-fuel ratio learning value learned in the first region and a second air-fuel ratio learning value learned in the second region.

A control support device for supporting control of a vehicle using a learned model obtained by machine learning, includes: a data acquisition unit acquiring sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning; a learning unit generating a learned model by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit and is data including input parameters and an output parameter of the learned model; and a transmission unit Transmitting at least one of the generated learned model and an output parameter calculated by inputting sensor information of the vehicle, control of which is supported, to the generated learned model as an input parameter.

A device and method for controlling an internal combustion engine having a catalytic converter. At least one actuating variable for the internal combustion engine is determined as a function of a system model of the catalytic converter and/or the internal combustion engine. The system model, a setpoint variable for the control and/or the actuating variable is adapted. Information about a modeled residual oxygen content in the exhaust gas downstream from the catalytic converter is determined using the system model. Information about an acquired residual oxygen content in the exhaust gas at the output of the catalytic converter is acquired. The information about the modeled residual oxygen content is compared with the information about the acquired residual oxygen content. A measure for an adaptation requirement is determined as a function of the result of the comparison.

The controller includes a fuel amount control unit adjusting amount of fuel supplied to a cylinder through feedback control with an air-fuel ratio deviation as input, a target air-fuel ratio adjustment unit alternately repeating a lean period process and a rich period process, and a learning value correction unit updating a learning value to compensate for a steady deviation in an air-fuel ratio. If an absolute value of an oxygen amount deviation is less than a determination value, the learning value update unit updates a learning value only when one of the lean period process and the rich period process is switched to the other one. If the absolute value of the oxygen amount deviation is greater than or equal to the determination value, the learning value is updated both when one of the processes is switched to the other one and when the switching is reversed.

A method, computer program product and apparatus for the pilot control of a mixture preparation for an internal combustion engine are disclosed, which include determining a configuration of the internal combustion engine. The configuration is determined by a combination of discrete positions of a plurality of actuators which influence at least one operating parameter of the internal combustion engine. The method, computer program product and apparatus additionally determine a constant adaptation component of the mixture preparation which is fed back by an exhaust gas probe of the internal combustion engine, and store the constant adaptation component and the associated configuration in memory. The pilot control of the mixture preparation is performed with the constant adaptation component when the internal combustion engine is operated in the same configuration.

An imbalance detection device is provided. An obtainment process includes obtaining a rotation waveform variable based on a detection value of a sensor that detects a rotational behavior of a crankshaft, and an air-fuel ratio detection variable in each of a plurality of first intervals. A calculation process includes calculating an imbalance variable based on an output of a mapping having a value obtained by the obtainment process as an input. The imbalance variable indicates a degree of variations in an air-fuel ratio of the internal combustion engine. The rotation waveform variable indicates a difference between instantaneous speed variables that are variables corresponding to the rotational speed of the crankshaft in each of the second intervals.

Methods and systems are disclosed for operating an engine that includes a knock control system that may determine contributions of individual noise sources to an engine background noise level. The contributions of the individual noise sources may be the basis for establishing the presence or absence of knock in one or more engine cylinders. The contributions of individual noise sources may be determined when engine cylinders are deactivated.

The controller includes a fuel amount control unit adjusting amount of fuel supplied to a cylinder through feedback control with an air-fuel ratio deviation as input, a target air-fuel ratio adjustment unit alternately repeating a lean period process and a rich period process, and a learning value correction unit updating a learning value to compensate for a steady deviation in an air-fuel ratio. If an absolute value of an oxygen amount deviation is less than a determination value, the learning value update unit updates a learning value only when one of the lean period process and the rich period process is switched to the other one. If the absolute value of the oxygen amount deviation is greater than or equal to the determination value, the learning value is updated both when one of the processes is switched to the other one and when the switching is reversed.

A control device for an internal combustion engine executes an automatic stop control and automatic start-up control for an intermittent operation of the internal combustion engine. In the automatic start-up control, the control device is configured to commence a restart by starting fuel injection from a fuel-injection-start cylinder. In the automatic stop control, the control device is configured to: execute an air-fuel-ratio rich processing that controls an air-fuel ratio such that the air-fuel ratio becomes richer than the stoichiometric air-fuel ratio before a start of the fuel cut; execute a throttle closing processing that closes a throttle valve in synchronization with the fuel cut; and execute a throttle opening processing approaches the atmospheric air pressure before a cylinder destined to be the fuel-injection-start cylinder later completes the last intake stroke in the course of the engine stop after execution of the throttle closing processing.

A control support device for supporting control of a vehicle using a learned model obtained by machine learning, includes: a data acquisition unit acquiring sensor information, which is related to a state of an inside or an outside of a supplying vehicle that supplies parameters to be used for the machine learning; a learning unit generating a learned model by performing the machine learning using an input/output data set, which is the sensor information acquired by the data acquisition unit and is data including input parameters and an output parameter of the learned model; and a transmission unit Transmitting at least one of the generated learned model and an output parameter calculated by inputting sensor information of the vehicle, control of which is supported, to the generated learned model as an input parameter.