Method for ascertaining a NO.SUB.x .concentration and a NH.SUB.3 .slip downstream from an SCR catalytic converter

Abstract

A method is provided for ascertaining a NO.sub.x concentration and an NH.sub.3 slip downstream from an SCR catalytic converter of an internal combustion engine of a vehicle. State variables of an internal combustion engine as first input variables and an updated NH.sub.3 fill level of the SCR catalytic converter as a second input variable cooperate with at least one machine learning algorithm or at least one stochastic model. The at least one machine learning algorithm or at least one stochastic model calculates the NO.sub.x concentration and the NH.sub.3 slip downstream from the SCR catalytic converter as a function of the first input variables and the second input variables and output the same as output variables.

Claims

1. A method for ascertaining a NO.sub.x concentration and an NH.sub.3 slip downstream from an SCR catalytic converter of an internal combustion engine of a vehicle, the method comprising the following steps: using, by a processor, state variables of an internal combustion engine as first input variables and an updated NH.sub.3 fill level of the SCR catalytic converter as a second input variable, for at least one machine learning algorithm or at least one stochastic model; and calculating, by the processor via the at least one machine learning algorithm or at least one stochastic model, the NO.sub.x concentration and the NH.sub.3 slip downstream from the SCR catalytic converter as a function of the first input variables and the second input variable; outputting, by the processor via the at least one machine learning algorithm or the at least one stochastic model, the calculated NO.sub.x concentration and the calculated NH.sub.3 slip downstream, as calculated output variables corresponding to an output NO.sub.x concentration and an output NH.sub.3 slip, wherein the output NO.sub.x concentration, the output NH.sub.3 slip, and an output NH.sub.3 oxidation, in addition to an instantaneous NH.sub.3 metering for the SCR catalytic converter, are input variables; performing a stoichiometric calculation of the updated NH.sub.3 fill level based on the input variables; and performing, by the processor, at least one of: controlling, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model a predictive control of an exhaust aftertreatment of the internal combustion engine or a predictive control of a drive system of the vehicle, or establishing, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model, an exceedance of emission variables or one of outputting a corresponding warning message or initiating a corresponding error response.

2. The method as recited in claim 1, wherein the method runs repeatedly for sequential time increments.

3. The method as recited in claim 2, wherein the at least one machine learning algorithm or the at least one stochastic model calculates the NH.sub.3 oxidation in the SCR catalytic converter as a function of the first input variables and the second input variable and outputs the calculated NH.sub.3 oxidation as an output variable.

4. The method as recited in claim 3, wherein the calculated, updated NH.sub.3 fill level is output and is used by the at least one machine learning algorithm or the at least one stochastic model in a next time increment as the updated NH.sub.3 fill level and as the second input variable for the calculation and output of the NO.sub.x concentration, the NH.sub.3 slip, and the NH.sub.3 oxidation downstream from the SCR catalytic converter.

5. The method as recited in claim 4, wherein, in a first time increment, an initial value is selected or estimated for the updated NH.sub.3 fill level as a function of the operating state of the internal combustion engine.

6. The method as recited in claim 4, wherein in a first time increment, an initial NH.sub.3 fill level of zero is selected for the updated NH.sub.3 fill level.

7. The method as recited in claim 4, wherein a stored initial value is selected for the updated NH.sub.3 fill level.

8. The method as recited in claim 4, wherein chemical reactions taking place in the SCR catalytic converter are taken into account in the stoichiometric calculation, the chemical reactions including a reduction of nitrogen oxides to nitrogen, an NH.sub.3 oxidation, and the NH.sub.3 slip.

9. The method as recited in claim 8, wherein balancing equations are used for the stoichiometric calculation.

10. The method as recited in claim 1, wherein the first input variables include at least one of: exhaust gas temperature, and/or exhaust gas pressure, and/or exhaust gas mass flow, and/or NO.sub.x concentration upstream from the SCR catalytic converter, and/or NO/NO.sub.x ratio, and/or space velocity of exhaust gas.

11. The method as recited in claim 1, wherein the calculating takes place in the vehicle during driving operation in real-time.

12. The method as recited in claim 11, wherein the calculating takes place in a processing unit of a control unit of the vehicle.

13. The method as recited in claim 12, wherein the processing unit is supported in the calculations of the at least one machine learning algorithm or the at least one stochastic model by an optimized hardware unit.

14. The method as recited in claim 11, wherein as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model, monitoring or a correction of corresponding sensor output variables takes place.

15. The method as recited in claim 1, wherein the at least one machine learning algorithm is configured as an artificial neural network.

16. The method as recited in claim 15, wherein the at least one machine learning algorithm configured as a convolutional neural network, or a recurrent neural network, or a long short-term memory.

17. The method as recited in claim 1, wherein the at least one stochastic model includes a Gaussian process model, or a sparse Gaussian process, or a Student-t process.

18. A non-transitory storage medium on which is stored a computer program for ascertaining a NO.sub.x concentration and an NH.sub.3 slip downstream from an SCR catalytic converter of an internal combustion engine of a vehicle, the computer program, when executed by a computer, causing the computer to perform the following steps: using, by a processor of the computer, state variables of an internal combustion engine as first input variables and an updated NH.sub.3 fill level of the SCR catalytic converter as a second input variable, for at least one machine learning algorithm or at least one stochastic model; and calculating, by the processor via the at least one machine learning algorithm or at least one stochastic model, the NO.sub.x concentration and the NH.sub.3 slip downstream from the SCR catalytic converter as a function of the first input variables and the second input variable; outputting, by the processor via the at least one machine learning algorithm or the at least one stochastic model, the calculated NO.sub.x concentration and the calculated NH.sub.3 slip downstream, as calculated output variables corresponding to an output NO.sub.x concentration and an output NH.sub.3 slip, wherein the output NO.sub.x concentration, the output NH.sub.3 slip, and an output NH.sub.3 oxidation, in addition to an instantaneous NH.sub.3 metering for the SCR catalytic converter, are input variables; performing a stoichiometric calculation of the updated NH.sub.3 fill level based on the input variables; and performing, by the processor, at least one of: controlling, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model a predictive control of an exhaust aftertreatment of the internal combustion engine or a predictive control of a drive system of the vehicle, or establishing, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model, an exceedance of emission variables or one of outputting a corresponding warning message or initiating a corresponding error response.

19. A vehicle control unit configured to for ascertaining a NO.sub.x concentration and an NH.sub.3 slip downstream from an SCR catalytic converter of an internal combustion engine of a vehicle, the control unit configured to: use, by a processor of the control unit, state variables of an internal combustion engine as first input variables and an updated NH.sub.3 fill level of the SCR catalytic converter as a second input variable, for at least one machine learning algorithm or at least one stochastic model; and calculate, by the processor via the at least one machine learning algorithm or at least one stochastic model, the NO.sub.x concentration and the NH.sub.3 slip downstream from the SCR catalytic converter as a function of the first input variables and the second input variable; and output, by the processor via at least one machine learning algorithm or the at least one stochastic model, the calculated NO.sub.x concentration and the calculated NH.sub.3 slip downstream, as calculated output variables corresponding to an output NO.sub.x concentration and an output NH.sub.3 slip, wherein the output NO.sub.x concentration, the output NH.sub.3 slip, and an output NH.sub.3 oxidation, in addition to an instantaneous NH.sub.3 metering for the SCR catalytic converter, are input variables performing a stoichiometric calculation of the updated NH.sub.3 fill level based on the input variables; and performing, by the processor, at least one of: controlling, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model a predictive control of an exhaust aftertreatment of the internal combustion engine or a predictive control of a drive system of the vehicle, or establishing, as a function of the calculated output variables of the at least one machine learning algorithm or the at least one stochastic model, an exceedance of emission variables or one of outputting a corresponding warning message or initiating a corresponding error response.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) The present invention is described in greater detail below with reference to the figures and by way of exemplary embodiments.

(2) FIG. 1 shows a schematic detail of the exhaust gas system of an exemplary diesel engine.

(3) FIG. 2 schematically shows an exemplary method sequence to ascertain a NO.sub.x concentration and an NH.sub.3 slip downstream from an SCR catalytic converter.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

(4) It is important for controlling engines and their exhaust aftertreatment during operation and for developing internal combustion engines with improved exhaust aftertreatment to have precise and highly up-to-date information available about the effectiveness of the exhaust aftertreatment components used. This is often challenging in the SCR catalytic converter; above all due to the availability and the responding behavior of the sensors for operating variables, such as nitrogen oxide concentration or NH.sub.3 slip. If an SCR catalytic converter functions in certain operating situations worse than intended, this may have significant effects on the emission behavior of the engine; however, under certain circumstances, it may not be discovered or may be discovered only after long delays.

(5) FIG. 1 schematically shows a detail of the exhaust gas system of an exemplary diesel engine. An engine detail 1 with a combustion chamber is here schematically shown as the beginning of the exhaust gas system. After combustion, the exhaust gas flows through a diesel oxidation catalytic converter 2. A temperature sensor and a lambda sensor are situated between engine detail 1 and diesel oxidation catalytic converter 2. An SCR catalytic converter 3 follows in the exhaust gas system downstream from diesel oxidation catalytic converter 2. A temperature sensor and a NO.sub.x sensor are situated between diesel oxidation catalytic converter 2 and SCR catalytic converter 3. A particle sensor (PM) and a NO.sub.x sensor are situated downstream from the SCR catalytic converter.

(6) FIG. 2 schematically shows an exemplary sequence of the described method. Block 20 represents the modeling of the SCR catalytic converter to calculate the output variables of NO.sub.x concentration after the SCR catalytic converter and NH.sub.3 slip of the SCR catalytic converter with the aid of at least one machine learning algorithm or at least one stochastic model. By way of example, exhaust gas temperature 202, NO.sub.x concentration upstream from the SCR catalytic converter 203, NO/NO.sub.2 ratio 204 and space velocity of exhaust gas 205 are shown as input variables. In addition, in an initial step before a first calculation of the dynamic modeling, an input value 201 is selected or estimated, which represents the fill level of the SCR catalytic converter with NH.sub.3. Since this value is generally not available by sensors, it must be ascertained or estimated from present or past operating variables or states. In certain operating states, e.g., at the beginning of an operation, an estimation of the fill level, e.g., to zero, may also be appropriate and sufficiently precise. The NH.sub.3 fill level may also be available by storing in a non-volatile memory after the end of the trip for the beginning of the new trip, and thus the model is correctly initiated in a new driving cycle. The at least one machine algorithm or at least one stochastic model 20 provides an instantaneous output value 207 for the NO.sub.x concentration after or downstream from the SCR catalytic converter, which may be stored as value 21, and an instantaneous output value 208 for the NH.sub.3 slip of the SCR catalytic converter, which may be stored as value 22, and an instantaneous output value 209 for the NH.sub.3 oxidation in the catalytic converter, which may be stored as value 23. The values are here preferably calculated for an up-to-date time increment. Stored values 21, 22, or 23 may be used as values 210, 220 or 230 for other calculations in the vehicle, for example, for controlling the exhaust aftertreatment or other vehicle variables, or for diagnoses. They additionally preferably cooperate as input values 301, 302, or 303, shown as block 30, with the calculation of the updated NH.sub.3 fill level based on stoichiometry and mass balance or the balance of the amount of substances. In addition, the instantaneous (carried out in the present time increment) NH.sub.3 metering 304 for the SCR catalytic converter is utilized for the calculation of the updated NH.sub.3 fill level. A stoichiometric calculation, which takes into account the chemical reaction occurring in the SCR catalytic converter, in particular the desirable reduction of nitrogen oxides to nitrogen, the undesirable NH.sub.3 oxidation, and the NH.sub.3 slip, is here carried out in calculation block 30. For this purpose, balance equations are used.

(7) The calculated, updated NH.sub.3 fill level cooperates in turn, in addition to other input variables 202 through 205 and instead of initial value 201, with calculation block 20 for the next time increment. The method is carried out iteratively for other time increments.

(8) Artificial neural networks, such as convolutional neural networks, in particular with non-linear, exogenic inputs, may be used for calculation block 20. Alternatively, Gaussian processes such as sparse Gaussian process models, e.g., with constant deviation, are also suitable.