The subject matter of the present invention relates to trained machine-learning models (300), methods (200, 400) and apparatuses (500) allowing a future resonant frequency of a catalyst for selective reduction of nitrogen oxides (SCR) to be predicted, the resonant frequency being representative of a concentration of a reducing agent within the SCR. The SCR forms part of a system for after-treatment of a flow of exhaust gases of an internal combustion engine with which a motor vehicle is provided. The general principle of the invention is based on the observation of correlations between the resonant frequency of an SCR and the concentration of ammonia present within the SCR. This observation led the inventor to envision using machine learning to create a trained machine-learning model in order to predict the resonant frequency of an SCR. In the invention, the trained machine-learning model is a so-called predictive model in which significant correlations are discovered in a set of past observations and in which it is sought to generalize these correlations to cases that have not yet been observed.

The invention relates to a method for starting an internal combustion engine, the exhaust gas system of which is equipped with an electrically heatable lambda sensor and a catalytic converter with an oxygen reservoir. The combination of method steps according to the invention allows the internal combustion engine to be started with an optimal raw emission reduction directly after a cold start and an optimal pollutant conversion in the warm-up phase. The invention likewise relates to a motor vehicle with an internal combustion engine comprising an exhaust gas system having an electrically heatable lambda sensor and a catalytic converter with an oxygen reservoir, and comprising a controller, wherein the controller is designed to carry out the method according to the invention.

An in-vehicle controller includes processing circuitry. The processing circuitry stops injection of fuel under a preset fuel cutoff condition including a lockup clutch being in an engagement state. A request for raising heating performance of a heater core is a heater actuation request, and an amount of particulate matter deposited on a filter is a deposition amount. The processing circuitry controls the lockup clutch in a disengagement state when a heater actuation request is generated and the deposition amount is less than a preset deposition amount threshold. The processing circuitry controls the lockup clutch in the engagement state when the heater actuation request is generated and the deposition amount is greater than or equal to the preset deposition amount threshold.

The present invention is a method of determining emissions of vehicle pollutants using an on-board measurement system with a sensor (CAP) and a computer system including a generic model (MOD GEN) of the vehicle. The method is based on the use of the measurements and of the model for determining the amount of pollutants.

Systems and apparatuses include a circuit structured to receive information indicative of a catalyst health, receive information from a sensor array indicative of a catalyst activity, determine a catalyst health management criteria has been met based on the information, determine a catalyst age based on the information indicative of the catalyst activity and the catalyst health management criteria being met, compare the determined catalyst age to a predetermined age threshold, and provide a notification when the determined catalyst age exceeds the predetermined age threshold.

A misfire detection device for an internal combustion engine includes processing circuitry. The internal combustion engine includes a selective reduction type catalyst configured to remove NOx from an exhaust gas, an addition valve arranged upstream of the catalyst to add a reducing agent into the exhaust gas, and a NOx concentration sensor arranged downstream of the catalyst to detect a downstream concentration, that is, a NOx concentration in the exhaust gas downstream of the catalyst. The processing circuitry is configured to execute an addition process adding the reducing agent into the exhaust gas with operation of the addition valve and a determination process determining that a misfire has occurred in the internal combustion engine when a detection value of the downstream concentration is decreased on condition that the addition process is being executed.

A non-transitory computer-readable medium having a NOx sensor purification instructions for a NOx sensor causes: an on-vehicle electronic computer mounted in the vehicle, when it comes to a predetermined purification time, to execute a start procedure to send a start command to perform a purification control to the control unit; and control unit, in response to the start command, to execute a purification procedure to perform the purification control which causes the current flowing in the reference pump cell from the reference pump current to be a purification pump current, which is set to a current value larger than the reference pump current.

A catalyst temperature estimation device that estimates a temperature of a catalyst provided in an exhaust passage of an internal combustion engine includes a storage device and processing circuitry. The storage device stores mapping data that specifies a mapping that uses multiple input variables to output an estimation value of the temperature of the catalyst. The multiple input variables include at least one variable of an ambient temperature variable or an excess amount variable. The multiple input variables further include a fluid energy variable, which is a state variable related to energy of fluid flowing into the catalyst, and a previous cycle value of the estimation value of the temperature of the catalyst. The processing circuitry is configured to execute an acquisition process, a temperature calculation process, and an operation process. The mapping data includes data that is learned through machine learning.

A method for the quality assurance of exhaust gas behavior in a motor vehicle, particularly in a hybrid vehicle, includes monitoring an on-board-diagnosis function; providing a journey counter a diagnosis counter, and a nominal diagnosis frequency value; incrementing the journey counter following the beginning of a driving cycle; generating an actual diagnosis frequency value using a combination of the diagnosis counter and the drive counter; and establishing a difference between the nominal diagnosis frequency value and the actual diagnosis frequency value. If the difference falls short of a threshold: a control method is selected, which is designed to successfully complete a currently running OBD of the OBD function and to initiate and complete a non-running OBD. Following the completion of the OBD of the OBD function, the diagnosis counter is incremented and the motor control restored to an original motor control.

An aftertreatment system comprises a housing defining an internal volume. A filter is disposed in the housing and configured to remove particulate matter included in the exhaust gas. A delta pressure sensor configured to measure an inlet apparent pressure value upstream of the filter. An ambient pressure sensor separate from the delta pressure sensor is configured to measure an ambient pressure value of an ambient environment in which the aftertreatment system is located. A controller is configured to receive the inlet apparent pressure value, receive the ambient pressure value from the ambient pressure sensor, determine a relative inlet exhaust pressure value based upon the inlet apparent pressure value and the ambient pressure value, and adjust an exhaust flow rate of the exhaust gas based at least on the relative inlet exhaust pressure value.