Provided is an exhaust gas purification apparatus having a control device that monitors the transition of a detection value of each of an upstream NOx sensor and a downstream NOx sensor, and when the NOx purification rate of the SCR catalyst falls to a value of a first threshold or lower, generates an abnormality detection signal indicating that an over storage state has occurred in an SCR catalyst if the amount of change in the detection value of the upstream NOx sensor per unit time is at least a second threshold and the amount of change in the detection value of the downstream NOx sensor per unit time is at most a third threshold.

A catalyst deterioration detection device is provided to detect deterioration of a catalyst provided in an exhaust passage of an internal combustion engine. The catalyst deterioration detection device includes a storage device and processing circuitry. The storage device stores map data specifying a mapping that uses time series data of an excess amount variable in a first predetermined period and time series data of a downstream detection variable in a second predetermined period as inputs to output a deterioration level variable. The processing circuitry executes an acquisition process that acquires data, a deterioration level variable calculation process that calculates a deterioration level variable of the catalyst based on an output of the mapping using the data acquired by the acquisition process as an input. The map data includes data that is learned through machine learning.

A radio frequency sensor system comprising a housing defining a resonant cavity. Radio frequency probe(s) in the cavity transmit and/or receive radio frequency signals. A radio frequency control unit is in communication with the radio frequency probe(s) for determining one or more states of the radio frequency sensor system based on changes in the characteristics of the radio frequency signals. A machine learning system is in communication with the radio frequency control unit for identifying and developing transfer functions and calibrations based on the changes in the characteristics of the radio frequency signals and determining the one or more states of the radio frequency sensor system.

To keep medium purification efficiency at a high level and prevent deterioration of emission performance. An aspect of the present invention includes: a downstream equivalence ratio calculation unit that calculates a catalyst downstream exhaust gas equivalence ratio by using a catalyst statistical model that receives at least a detection value of an air-fuel ratio sensor on an upstream side of a catalyst and outputs a catalyst downstream exhaust gas equivalence ratio; an oxygen output calculation unit that calculates an output value of an oxygen sensor by using an oxygen sensor statistical model that receives the catalyst downstream exhaust gas equivalence ratio and outputs an output value of the oxygen sensor on the downstream side of the catalyst; a downstream equivalence ratio correction unit that corrects the catalyst downstream exhaust gas equivalence ratio calculated by the downstream equivalence ratio calculation unit based on a calculation result of the oxygen output calculation unit and the detection value of the oxygen sensor; and an air-fuel ratio control unit that controls an air-fuel ratio of an air-fuel mixture of an internal combustion engine based on the corrected catalyst downstream exhaust gas equivalence ratio and air-fuel ratio target value.

Methods and systems are provided for an exhaust system. In one example, a method may include determining presence of a zone flow based on a comparison of a first exhaust sensor and a second exhaust sensor. The presence or absence of the zone flow may determine a rate at which an air-fuel ratio is adjusted.

In an approach to reduce nitrous oxide emissions using predictive urea dosing control, a route is determined. A set of target coverage fractions of ammonia is determined over a set of steps for the route, where the coverage fraction of ammonia is a ratio of stored ammonia to a maximum storage capacity of ammonia in a selective catalytic reduction (SCR) device. An actual coverage fraction of ammonia is determined for each step of the route. The actual coverage fraction of ammonia is compared to the target coverage fraction of ammonia for each step. The urea injection rate is adjusted based on a cost function.

An urea injection control system for an internal combustion engine, specifically adapted to apply a scheme for decreasing a NOx level downstream of a selective catalytic reduction catalyst of an ICE related exhaust gas aftertreatment system. The present disclosure also relates to a corresponding computer implemented method and a computer program product.

A method for reducing deposits related to a reduction agent (RA) in a portion of an exhaust aftertreatment system (EAS) of an internal combustion engine (ICE) and comprising an injector for injecting the RA into said EAS, said portion located downstream of said injector, as seen in an intended direction of flow of exhaust gas in said EAS, said method comprising: identifying for said ICE, a future operating sequence (FOS) comprising a first temporal portion (t.sub.1) and a second temporal portion (t.sub.2) subsequent to t.sub.1, confirming that said FOS is suitable for reducing deposits and that said ICE operates in accordance with said FOS, in response to said confirming being affirmative, injecting a first dosage (d.sub.1) of RA into said EAS during at least a part of said t.sub.1 and injecting a second dosage (d.sub.2) of RA smaller than d.sub.1 into said EAS during at least a part of t.sub.2.

A catalyst deterioration detection device is provided to detect deterioration of a catalyst provided in an exhaust passage of an internal combustion engine. The catalyst deterioration detection device includes a storage device and processing circuitry. The storage device stores map data specifying a mapping that uses time series data of an excess amount variable in a first predetermined period and time series data of a downstream detection variable in a second predetermined period as inputs to output a deterioration level variable. The processing circuitry executes an acquisition process that acquires data, a deterioration level variable calculation process that calculates a deterioration level variable of the catalyst based on an output of the mapping using the data acquired by the acquisition process as an input. The map data includes data that is learned through machine learning.

A method for timing of a regeneration process of an exhaust gas system of a vehicle engine includes collecting, during operation of the vehicle, data on an exhaust gas regeneration capability as a function of time, establishing, from the collected data, a statistical probability function for the exhaust gas regeneration capability as a function of time, and identifying, from the probability function, one or several time periods that statistically are suitable and/or unsuitable for carrying out a regeneration process. A method for regeneration of an exhaust gas system of a vehicle engine is also provided.