An engine system includes an air handling and fuel system whose states are managed by a reference managing unit. The engine system has a plurality of sensors whose sensor signals at least partially define a current state of the engine system. The reference managing unit includes a controller which controls the air handling and fuel system of the engine system as well as a processing unit coupled to the sensors and the controller. The processing unit includes an agent which learns a policy function that is trained to process the current state, determines air handling references and fuel system references by using the policy function after receiving the current state as an input, and outputs the air handling references and fuel system references to the controller. Then, the agent receives a next state and a reward value from the processing unit and updates the policy function using a policy evaluation algorithm and a policy improvement algorithm based on the received reward value. Subsequently, the controller controls the air handling and fuel system of the engine in response to receiving the air handling references and the fuel system references.

A controller includes a P/L learning unit that performs P/L learning, a purge learning unit that performs purge learning, an air-fuel ratio learning unit that performs air-fuel ratio learning, and a storage unit that stores learning result. When the learning result of each learning process is not stored in the storage unit at the time of engine start, the P/L learning unit learns an injection characteristic of an in-cylinder injection valve through the P/L learning process whenever the in-cylinder injection valve performs the P/L injection and interrupts the P/L learning process before the P/L learning process is completed. The purge learning unit performs the purge learning process, and the air-fuel ratio learning unit starts the air-fuel ratio learning process provided that the P/L learning process is interrupted. The P/L learning unit then resumes the P/L learning process provided that the purge learning process is completed.

Provided is a control device of a hybrid vehicle powered by an internal-combustion engine and a motor, wherein a catalyst that purifies exhaust gas is located in an exhaust passage of the internal-combustion engine, and the control device comprises: a learning unit configured to, during operation of the internal-combustion engine, learn a parameter for controlling a rotation speed of the internal-combustion engine so that a rotation speed of the internal-combustion engine during idling operation is equal to a target rotation speed; and a controller configured to stop the internal-combustion engine when a state where a correction amount of the parameter to cause the rotation speed during idling operation to be equal to the target rotation speed is equal to or greater than a predetermined value continues for equal to or greater than a predetermined time period, the correction amount being obtained by learning by the learning unit.

Various methods and systems are provided for calibrating one or more exhaust valves. In one example, a system comprises an exhaust valve configured to control flow of exhaust gas exiting an engine and a controller configured to calibrate the exhaust valve by commanding the exhaust valve to a fully closed position with a first driving current and measuring a first position of the exhaust valve at the first driving current, commanding the exhaust valve to a fully open position with a second driving current and measuring a second position of the exhaust valve at the second driving current, and generating a map based on a linear function determined from the first driving current, the second driving current, the measured first position, and the measured second position. The controller is further configured to adjust a position of the exhaust valve based on the map.

The present disclosure provides a method for learning emergency injection correction of an injector for preventing misfire. A misfire rate in a multi-stage injection mode is monitored, and it is controlled to be forcibly switched to a single injection mode when the misfire rate by the monitoring is equal to or greater than a specific value, such that injector injection correction learning is performed according to a learning entry condition. Accordingly, it is possible to reduce the deviation between cylinders by the sufficient injection amount deviation correction learning, thereby preventing misfire of the injector.

An exhaust-gas purification system and method controls an internal combustion engine having at least one cylinder-piston unit operating in a overrun (drag) mode in which piston motion is induced by motion of an output shaft of a drive output unit associated with the internal combustion engine. A control device controls, for each of cylinder-piston unit, an intake fluid, an exhaust valve and fuel injection to heat an exhaust emission control device by deactivating fuel injection, passing the substantially fuel-free intake fluid into the cylinder, compressing and thereby heating the fluid in the cylinder, and passing the heated outlet fluid to the exhaust emission control device. The control device may control the amount of heating based on measurement and/or use of a temperature model of the exhaust emission control device.

A method for operating an internal combustion engine with multiple cylinders. Each cylinder of the internal combustion engine includes at least one fuel injector, and each fuel injector is activated for opening and closing via a solenoid valve of the respective fuel injector. Structure-borne sound waves emitted by the fuel injectors and/or accelerations caused by the fuel injectors are detected by measurement. The structure-borne sound waves detected by measurement and/or the accelerations detected by measurement are evaluated, and based on the evaluation, characteristics of the fuel injectors are automatically determined.

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.

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 method for adapting a characteristic curve of a nitrogen oxide sensor of a combustion engine with exhaust gas recirculation having the first nitrogen oxide sensor upstream of an SCR catalytic converter and a second nitrogen oxide sensor downstream of the SCR catalytic converter includes determining that a particle filter is in a regeneration phase, increasing the exhaust gas recirculation rate, interrupting the supply of urea by a urea injection device, acquiring first nitrogen oxide values from signals generated by the first nitrogen oxide sensor, determining that the first nitrogen oxide values are within a first nitrogen oxide interval, acquiring values from second nitrogen oxide signals generated by the second nitrogen oxide sensor, and determining that the second nitrogen oxide values are within a second nitrogen oxide interval, and adapting the characteristic curve of the first nitrogen oxide sensor by the second nitrogen oxide values.