An engine system includes an air handling control unit which controls a plurality of air handling actuators responsible for maintaining flow of air and exhaust gas within the engine system. The engine system has a plurality of sensors whose sensor signals at least partially define a current state of the engine system. The air handling control unit includes a controller which controls the air handling actuators 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 a control signal to send to the controller by using the policy function after receiving the current state as an input, and outputs the control signal 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 actuators in response to receiving the control signal. In one aspect of the embodiment, the control signal is a command signal for the air handling actuators.

Methods and systems are disclosed for operating an engine that includes a knock control system. The method and system may increase opportunities to learn one or more engine knock background noise levels via changing poppet valve timing and/or fuel injection timing. The method and system may also improve knock detection if knock sensor degradation is suspected.

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 operating a nitrogen oxide sensor of a vehicle having a first nitrogen oxide sensor, a second nitrogen oxide sensor and a catalytic converter, one of the first and second nitrogen oxide sensors being arranged upstream of the catalytic converter with respect to the exhaust gas flow direction, and the other of the first and second nitrogen oxide sensors being arranged downstream of the catalytic converter, includes: determining a first characteristic value of the first nitrogen oxide sensor; determining a second characteristic value of the second nitrogen oxide sensor determining a ratio of the first characteristic value to the second characteristic value; and adapting a sensor or measured value of the second nitrogen oxide sensor in accordance with the ratio of the first characteristic value to the second characteristic value.

A method for adaptation of a detected camshaft position of a camshaft in an internal combustion engine with: Detection of an ACTUAL gas signal in a gas space that is associated with the camshaft and is associated with a detected camshaft position; Processing of the gas signal to produce an ACTUAL gas criterion; Modeling of multiple simulated gas criteria, each of which is associated with a target camshaft position; Determination of a simulated gas criterion with the least deviation from the ACTUAL gas criterion; Determination of an ACTUAL camshaft position that corresponds to the simulated gas criterion with the least deviation from the ACTUAL gas criterion; Determination of a camshaft position correction value from the difference between the ACTUAL camshaft position determined and the detected camshaft position; Determination of corrected camshaft positions by correcting the detected camshaft positions with the camshaft position correction value.

A method and system for estimating air mass per cylinder of an internal combustion engine is provided. An output signal from a MAF sensor is digitally processed to provide an estimate air mass per cylinder (APC). The system includes the MAF sensor; a data acquisition unit configured to receive an output signal from the MAF sensor and produce a sampled signal having a sampling rate greater than one sample per firing event; a multiple band pass (MBP) filter configured to remove signal components caused by airflow pulsations and oscillations through the MAF sensor; an envelope detector configured to detect the lower and upper envelopes of the MBP filtered signal; a MAF estimator configured to estimate a mass airflow based on the detected lower and upper envelopes; a signal decimator; a low pass filter; and a APC converter to converted the low pass filtered signal into an estimated APC.

An apparatus includes a sensor module, an offset diagnostic module, and a notification module. The sensor module is in operative communication with a cylinder pressure sensor and structured to acquire cylinder pressure data from the cylinder pressure sensor indicative of an actual in-cylinder pressure of a cylinder of an engine. The offset diagnostic module is structured to interpret the cylinder pressure data to determine an offset of the cylinder pressure sensor based on a reference in-cylinder pressure and the actual in-cylinder pressure. The notification module is structured to provide an offset error notification responsive to the offset being greater than a threshold offset.

Methods and systems are provided for reducing errors in estimated fuel rail pressure incurred at the time of a scheduled injection event due to engine-driven cyclic fuel rail pressure changes. In one example, a pulse-width commanded during a scheduled injection event is determined as a function fuel rail pressure samples collected over a moving window that is customized for the corresponding fuel injector. In another example, the commanded pulse-width is determined as a function of an average fuel rail pressure sampled during a quiet zone of injector operation and predicted fuel rail pressure altering events occurring between the quiet zone and the scheduled injection event.

Methods and systems are provided for a battery supplying power to an exhaust oxygen sensor heater. In one example, a method may include estimating a power delivered to the heater during heating of the sensor and in response to a power delivered from a battery being lower than a threshold, adjusting a battery charging strategy prior to an immediately subsequent engine start.

An object is to reduce the influence of a hydrogen-ascribable difference between the measurement value of an oxygen sensor and the actual value. An exhaust system includes an oxygen sensor configured to measure the air-fuel ratio of exhaust gas provided in an exhaust passage of an internal combustion engine and including a diffusion rate limiting layer and a controller configured to correct the measurement value of the oxygen sensor in such a way as to increase the measurement value of the oxygen sensor by an amount of correction that is made larger when the responsivity of the oxygen sensor to changes in the air-fuel ratio of the internal combustion engine is high than when it is low in the same operation state of the internal combustion engine.