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 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 knocking sensor (18) detecting vibration of an engine body (1) and a pressure sensor (19) detecting a pressure of a combustion chamber (5) are provided. A value representing the knocking strength is acquired from output values of the pressure sensor (19). Weights of a neural network are learned using a value representing the vibration of the engine body (1) detected by the knocking sensor (18) as an input value of the neural network and using the acquired value representing the knocking strength as training data. The value representing the knocking strength is estimated from the output values of the knocking sensor (18) by using the learned neural network.

A method is proposed for regulating a fill level of an exhaust component storage of a catalyst (26) of an internal combustion engine (10), wherein the regulating of the fill level is done by using a system model (100), comprising a catalyst model (102), and wherein uncertainties of measured or model variables influencing the regulating of the fill level are corrected by an adaptation, which is based on signals of an exhaust gas probe (34) arranged at the outlet side of the catalyst (26). The method is characterized in that the adaptation takes multiple pathways (200, 210, 220), wherein signals from different signal regions (260, 280, 300) of the exhaust gas probe (34) situated at the outlet side are processed on different pathways. An independent claim is addressed to a controller designed to carry out the method.

The air-fuel ratio feedback control section updates an air-fuel ratio feedback correction value. The air-fuel ratio learning control section performs, in each of learning regions, learning of an air-fuel ratio learning value. If the air-fuel ratio feedback correction value converges to a value less than or equal to a specified value, the air-fuel ratio learning control section determines that learning of the air-fuel ratio learning value in the learning region has been completed. If it has not yet been determined that learning of the air-fuel ratio learning value has been completed in any of the learning regions, the air-fuel ratio learning control section collectively updates the air-fuel ratio learning values of all the learning regions at the time of updating the air-fuel ratio learning value through learning in any of the learning regions.

A control device of an internal combustion engine includes: a parameter value acquiring part acquiring values of input parameters; a computing part utilizing a model using a neural network to calculate a value of an output parameter, and a control part controlling operation of the engine. The model outputs the value of the output parameter from an output layer node if the values of the input parameters are input to the input layer nodes. When an abnormality occurs at values of part of the input parameters among the input parameters, the computing part uses the corrected model to calculate the value of the output parameter, the corrected model being provided by correcting the model so that a value changing in accordance with a value of an abnormal input parameter is not input from a input layer node corresponding to the abnormal input parameter to a hidden layer node.

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 method and a device are provided for controlling an internal combustion engine, a knock sensor being provided for acquiring combustion signals of the internal combustion engine. Devices are also provided that, during running operation of the internal combustion engine, select operating ranges of the internal combustion engine that are suitable for a determination of fuel quality, and carry out a determination of the fuel quality in these ranges on the basis of signals of the knock sensor.

A first intake air amount an engine is calculated based on a detected value of an intake air flow rate of an air flowmeter. A second intake air amount is calculated based on any one of a detected value of an intake pipe pressure and a throttle opening degree instead of the detected value of the intake air flow rate. When it is determined that the intake pulsation is not large, a difference amount of the second intake air amount from the first intake air amount is calculated. A corrected second intake air amount, which is a sum of the second intake air amount and the difference amount, is set as an intake air amount calculated value when it is determined that the intake pulsation is large.

A control device of an internal combustion engine can respond to the variation of the flow reduction rate attributable to the difference in a clogging condition, and which can detect a deposit accumulation amount even if no idle condition is provided like HEV, etc. In a control device of an internal combustion engine, a map correction section determines a correction amount in accordance with an approximate line result based on an air amount at a predetermined opening degree at which the measurement of the air amount by an air flow meter is sufficiently performed with the exception of a first predetermined opening degree in the case where the measurement of the air amount by the air flow meter has not been performed sufficiently in the first predetermined opening degree in a current operation cycle.