A method of continuously variable valve duration (CVVD) location learning may include when a controller determines necessity of position learning for short duration and long duration of a CVVD system, performing conditional application re-learning control in which the position learning is performed in a situation in which validity determination of system environment condition for CVVD hardware and validity determination of vehicle environment condition for engine operation information of an engine are satisfied.

An apparatus for calculating a maximum output torque of an engine of a hybrid electric vehicle includes a torque deviation calculating unit configured to calculate a torque deviation by using a currently output engine torque and an engine command torque, an engine output change learning unit configured to learn the torque deviation when a torque deviation learning start condition of the hybrid electric vehicle is satisfied, and an engine part load maximum torque calculating unit configured to calculate an engine part load maximum output torque based on the learned torque deviation so as to control an output of the engine.

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.

Power system optimization is disclosed. An example power system described herein may include an engine control module that receives measurements associated with sensors, identifies settings associated with control devices, determines that a first set of parameters associated with the one or more control devices is to be optimized according to a first optimization process, iteratively performs the first optimization process until the first set of parameters are optimized, determines that a second set of parameters associated with the one or more control devices are to be optimized according to a second optimization process, iteratively performs the second optimization process until the second set of parameters are optimized, and, after the second set of parameters are optimized according to the second optimization process, configures one of the control devices to operate using an optimized value for the control device determined using the second optimization process.

An internal combustion engine controller for an internal combustion engine comprising a memory and a processor. The memory is configured to store a plurality of control maps, each control map defining a hypersurface of actuator setpoints for controlling an actuator of the internal combustion engine based on a plurality of input variables to the internal combustion engine controller. The processor comprises a map updating module, a parameter updating module and an engine setpoint module. The map updating module is configured to calculate an optimised hypersurface for at least one of the control maps based on a performance objective function of the internal combustion engine, sensor data from the internal combustion engine, and the plurality of input variables, wherein the performance objective function includes parameters. The parameter updating module is configured to update a parameter of the performance objective function upon determining a change in an operating condition of the internal combustion engine. The parameters comprise one or both of: engine parameters associated with an engine model; and cost parameters associated with a cost function. The map updating module is further configured to update the hypersurface of the control map based on the optimised hypersurface. The engine setpoint module is configured to output a control signal to each actuator based on a location on the hypersurface of the respective control map defined by the plurality of input variables.

During rapid warm-up operation, a CPU executes full lift injection processing, in which a nozzle needle reaches a maximum lift amount, in an intake stroke of each cylinder of a four-cylinder internal combustion engine, and then executes partial lift injection processing, in which the nozzle needle does not reach the maximum lift amount, in a compression stroke. On the other hand, during learning of injection characteristics of partial lift injection processing, the CPU executes full lift injection processing after executing partial lift injection processing, both of which are executed within a predetermined period in an intake stroke. The CPU learns the injection characteristics based on an inflection point in the temporal change of the induced electromotive force in a coil following the end of the partial lift injection processing.

A method for controlling a gas turbine engine having a constrained model based control (CMBC) system. The method including obtaining information about a current and previous states of the engine, updating model data information in the CMBC and a parameter estimation system based on the obtained information, and identifying trends in the data based on the information. The method also includes diagnosing the engine, based on the identified trends, determining at least one of a new constraint, objective, initial condition, model characteristic, prediction horizon, and control horizon for the control system based on the diagnosing step if the diagnosing step identified a fault condition, and adapting the CMBC system based on the at least one new constraint, objective, initial condition, model characteristic, prediction and control horizon. The method further includes generating at least on control command based on the adapting and commanding an actuator based on the control command.

A method and apparatus for compensates for oxygen sensor aging determines a correction of by measuring oxygen content above a specified threshold value and measuring current flowing through the sensor over time.

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.

A control apparatus for an internal combustion engine includes an exhaust gas sensor that has a sensor element and a heater for electrically heating the sensor element, a sensor circuit that detects the electric current generated by the exhaust gas sensor, a controller configured to: carry out starting processing to start the internal combustion engine, learn a value of the output of the sensor circuit when the starting processing is carried out by the controller, and control a temperature of the sensor element by using the heater, and controls the temperature of the sensor element to less than the predetermined temperature until the learning of the output value of the sensor circuit by the controller is completed after the starting processing is carried out by the controller.