An engine controller, an engine control method, and a memory medium are provided. A second calculation process calculates an intake air amount without using a detected value of the intake air flow rate. A guard process sets a difference amount learning value as a learning reflected value when the difference amount learning value is less than or equal to an upper limit guard value and greater than or equal to a lower limit guard value. A calculation method switching process sets a sum of a second intake air amount and the learning reflected value as a calculated value of the intake air amount when it is determined that an intake air pulsation is great.

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 controller and a control method for a vehicle including an engine with a supercharger and an automatic transmission provided in a power transmission path between the engine and driving wheels are provided. The controller is configured to perform learning control of learning a command value associated with gear shifting of the automatic transmission. The controller is configured to limit a supercharging pressure of the supercharger when the automatic transmission is performing gear shifting to be equal to or less than a predetermined pressure until initial learning which is performed by the learning control unit in a predetermined period after the vehicle has been manufactured is completed.

A method for learning an opening time of an injector for an engine of a vehicle may include applying, by a controller, an injection start command to the injector supplying fuel to the engine; determining, by the controller, a fuel pressure change amount in a fuel rail supplying the fuel to the injector after the injection start command is applied; and learning, by the controller, an opening delay time of the injector based on the determined fuel pressure change amount.

In an evaporated fuel treatment apparatus including a bypass passage branching from an atmosphere passage and connected to a canister by detouring around at least one ii and a bypass valve to open and close the bypass passage, a controller holds the bypass valve in a closed state until an integrated purge flow rate reaches a predetermined value after start of purge control, the integrated purge flow rate being an integrated value of flow rate of purge gas flowing through a purge passage. When the integrated purge flow rate reaches the predetermined value, the controller turns the bypass valve to an open state.

A fuel injection control method of injecting fuel to a combustion chamber of an engine through an injector, the method may include pre-energizing to drive the injector during a predetermined pre-energizing time; and performing, by the controller, a main injection in which the injector is controlled by the controller to inject the fuel into the combustion chamber by a target injection amount, after the pre-energizing of the injector, wherein the pre-energizing magnetizes an injector coil of the injector in advance by applying the amount of current preventing the flow rate of the fuel from being generated by the pre-energizing, to the injector during the pre-energizing time.

A state detection system for an internal combustion engine includes: a memory configured to store mapping data, the mapping data being data that defines a detection mapping, the detection mapping being a mapping between an input and an output, the input being a first waveform variable and a second waveform variable and the output being a value of a combustion state variable, and the detection mapping including a joint operation of the first waveform variable and the second waveform variable based on a parameter learned by machine learning; and a processor configured to execute an acquisition process and a determination process. The acquisition process acquires a value of the first waveform variable. The determination process determines whether or not the internal combustion engine is in a predetermined operating state.

A storage device of a control system stores a trained neural network that is trained by using training data to which information as to whether there is an abnormality in an air flow meter is given as a true label. The trained neural network receives, as inputs, condition index values including the opening of a throttle valve and the engine speed, a load detected value calculated based on a detection signal of the air flow meter, a load estimated value estimated without using the detection signal of the air flow meter, and a change index value indicating the degree of change of the engine load. A CPU of the control system executes a diagnostic process to determine whether there is an abnormality in the air flow meter, using the neural network, which receives the condition index values, load detected value, load estimated value, and change index value as the inputs.

A storage device of a control system stores a trained neural network that is trained by using training data to which information as to whether there is an abnormality in an air flow meter is given as a true label. The trained neural network receives, as inputs, condition index values including the opening of a throttle valve and the engine speed, a load detected value calculated based on a detection signal of the air flow meter, a load estimated value estimated without using the detection signal of the air flow meter, and a change index value indicating the degree of change of the engine load. A CPU of the control system executes a diagnostic process to determine whether there is an abnormality in the air flow meter, using the neural network, which receives the condition index values, load detected value, load estimated value, and change index value as the inputs.

A controller and a control method for a vehicle including an engine with a supercharger and an automatic transmission provided in a power transmission path between the engine and driving wheels are provided. The controller is configured to perform learning control of learning a command value associated with gear shifting of the automatic transmission. The controller is configured to limit a supercharging pressure of the supercharger when the automatic transmission is performing gear shifting to be equal to or less than a predetermined pressure until initial learning which is performed by the learning control unit in a predetermined period after the vehicle has been manufactured is completed.