A method to reduce NOx breakthrough and NH3 slip is provided when the SCR system is increasing in temperature and/or increasing exhaust gas mass flow. The method includes the steps of monitoring states of parameters of the exhaust gas upstream of an SCR catalyst where the states of parameters include at least one of the inlet temperature or the exhaust gas mass flow; identifying one of a temperature increase or an increased exhaust gas mass flow at the SCR inlet; identifying a new lower ammonia set-point or storage concentration for the SCR; and identifying the rate of NH3 consumption. The method further includes the step of determining an “intervening phase” a small dosage of DEF is continued during the intervening phase.

Systems and methods for simulating gas flow dynamics of a real hydrogen fuel cell system using a computer, wherein the real hydrogen fuel cell system includes a gas container volume network having gas container volumes interconnected by gas transport lines. The method includes defining volume element and flow channel classes, defining a plurality of volume instances and a plurality of flow channel instances, for each flow channel instance, creating a first interconnection representation that defines a source container volume and a destination container volume for the flow channel instance, wherein the first interconnection representation mimics a portion of the gas container volume network of the real hydrogen fuel cell system, and simulating, using the first interconnection representation, a thermodynamic state for each of the volume instances, the thermodynamic state representing thermodynamic parameter(s) in each container volume of the gas container volume network of the real hydrogen fuel cell system.

The disclosure relates to a self-adaptive oil spraying control system and method for a biodiesel engine. The control system includes an exhaust pipe, a gas sensor, a control module and an oil sprayer, wherein the exhaust pipe is connected to the oil sprayer, the gas sensor is mounted in the exhaust pipe, and the gas sensor and the oil sprayer are connected to the control module respectively. According to the control method, a main spray advance angle of the engine is subjected to closed-loop control directly through comparison between an idling steady state NO.sub.x emission signal and an idling steady state NO.sub.x emission value of pure diesel when the engine uses the biodiesel, so that emission of NO.sub.x in the exhaust is reduced. Compared with the prior art, the disclosure has the advantages of no need of detecting a biodiesel ratio, high efficiency, good effect and the like.

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.

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.

Systems and methods for simulating gas flow dynamics of a real hydrogen fuel cell system using a computer, wherein the real hydrogen fuel cell system includes a gas container volume network having gas container volumes interconnected by gas transport lines. The method includes defining volume element and flow channel classes, defining a plurality of volume instances and a plurality of flow channel instances, for each flow channel instance, creating a first interconnection representation that defines a source container volume and a destination container volume for the flow channel instance, wherein the first interconnection representation mimics a portion of the gas container volume network of the real hydrogen fuel cell system, and simulating, using the first interconnection representation, a thermodynamic state for each of the volume instances, the thermodynamic state representing thermodynamic parameter(s) in each container volume of the gas container volume network of the real hydrogen fuel cell system.

A management device 100 includes: a data acquisition unit 122 configured to acquire cumulative data for each parameter related to stress acting on a DOC 33 configured to purify exhaust gas of an engine and an exhaust gas temperature of the exhaust gas raised for purification; a damage degree identification unit 123 configured to identify a degree of damage to the DOC 33 based on the acquired cumulative data; a relationship identification unit 124 configured to identify a relational expression indicating a relationship between the identified degree of damage and the exhaust gas temperature; an target information acquisition unit 125 configured to acquire an exhaust gas temperature of exhaust gas raised for purification performed by the DOC 33; and a diagnosis unit 126 configured to estimate a degree of damage to the DOC 33 based on the acquired exhaust gas temperature and the identified relational expression.

A computer-implemented method for determining whether a reductant (e.g. urea) injector is clogged is provided. The method includes receiving data indicative of an injector duty cycle and a pump duty cycle. Using a trained machine learning module, at least a first value is calculated, indicative of a probability of the injector being clogged. The method further includes providing, based on the first value, an indication of whether the reductant injector is clogged. A device for providing the indication using the method, a computer program, a reductant injector system, and e.g. a combustion engine including such a reductant injector system are also provided.

A method of generating vehicle control data includes: storing, with a storage device, relationship prescription data; operating, with an execution device, an operable portion of an internal combustion engine; acquiring, with the execution device, a detection value from a sensor that detects the state of the vehicle; calculating, with the execution device, a reward; and updating, with the execution device, the relationship prescription data using update mapping determined in advance, the update mapping using the state of the vehicle based on the detection value, an operation amount used to operate the operable portion, and the reward corresponding to the operation as arguments, and returning the relationship prescription data which have been updated such that an expected profit for the reward calculated when the operable portion is operated in accordance with the relationship prescription data increases.

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.