# US 11,078,857 B2 · Calculation of exhaust emissions of a motor vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,078,857 B2 - Document ID: US11078857B2 - Status: Granted - Kind: B2 - Application number: 16/754,321 - Filed: 2018-10-09 - Published: 2020-07-30 - Granted: 2021-08-03 - Earliest claimed: 2017-10-16 - Assignees: Robert Bosch GmbH - Applicants: Robert Bosch GmbH - Inventors: Martin Schiegg; Heiner Markert; Stefan Angermaier - Web page: https://patentgrep.com/patent/US11078857B2 ## CPC - F02D 41/1444: {characterised by the characteristics of the combustion gases} - F02D 41/26: using computer, e.g. microprocessor - F01N 11/007: {the diagnostic devices measuring oxygen or air concentration downstream of the exhaust apparatus} - F02B 77/086: {Sensor arrangements in the exhaust, e.g. for temperature, misfire, air/fuel ratio, oxygen sensors} - F02D 41/1405: {Neural network control} - F02D 41/1439: {characterised by the position of the sensor} - F02D 41/1452: {the characteristics being a COx content or concentration} - F02D 41/1453: {the characteristics being a CO content or concentration} - F02D 41/1458: {with determination means using an estimation} - F02D 41/1462: {with determination means using an estimation} - F02D 41/1465: {with determination means using an estimation} - F02D 41/2429: {Methods of calibrating or learning} - F02D 41/28: Interface circuits - G01M 15/05: by combined monitoring of two or more different engine parameters - G01M 15/102: {by monitoring exhaust gases} - G05B 13/027: {using neural networks only} - G05B 13/029: {using neural networks and expert systems} - G06N 3/045: Combinations of networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0475: Generative networks - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 3/09: Supervised learning - G06N 3/094: Adversarial learning - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - F01N 11/00: Monitoring or diagnostic devices for exhaust-gas treatment apparatus - F01N 2900/0402: using adaptive learning - F02D 41/1401: {characterised by the control or regulation method (F02D41/1473, F02D41/1477 take precedence)} - F02D 2041/1433: {using a model or simulation of the system} - F02D 2041/1437: {Simulation} - F02D 2041/286: {comprising means for signal processing} - F02D: CONTROLLING COMBUSTION ENGINES (vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed B60K31/00; conjoint control of vehicle sub-units of different type or different function, road vehicle drive control systems for purposes other than the control of a single sub-unit B60W) - F01N: GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR MACHINES OR ENGINES IN GENERAL; GAS-FLOW SILENCERS OR EXHAUST APPARATUS FOR INTERNAL-COMBUSTION ENGINES (arrangements in connection with gas exhaust of propulsion units in vehicles B60K13/00; combustion-air intake silencers specially adapted for, or arranged on, internal-combustion engines F02M35/00; protecting against, or damping, noise in general G10K11/16) - F02B: INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL (gas-turbine plants F02C; hot-gas or combustion-product positive-displacement engine plants F02G) - G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for ascertaining emissions of a motor vehicle driven with the aid of an internal combustion engine in a practical driving operation. A machine learning system is trained to generate time curves of the operating variables with the aid of measured time curves of operating variables of the motor vehicle and/or of the internal combustion engine, and to then ascertain the emissions as a function of these generated time curves. ## Claims ### Claim 1 A computer-implemented method for ascertaining emissions of a motor vehicle driven using an internal combustion engine in a driving operation, the method comprising the following steps: training a machine learning system to generate time curves, of operating variables of the internal combustion engine and/or of the motor vehicle, using measured time curves of the operating variables of the internal combustion engine and/or of the motor vehicle; generating, by the machine learning system, the time curves of the operating variables; ascertaining the emissions as a function of the generated time curves generated by the machine learning system; and controlling the motor vehicle as a function of the ascertained emissions. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein the machine learning system includes a first part which initially transforms the measured time curves into first variables, each of which characterizes latent variables, a space of the latent variables having a reduced dimensionality as compared to a space of the measured time curves, and the machine learning system includes a second part which generates, as a function of the latent variables, second variables, each of which characterizes the generated time curves of the operating variables. ### Claim 3 (depends on 2) The method as recited in claim 2, wherein the first variables, which characterize the latent variables, are the latent variables themselves, and the second part includes a parameterized Gaussian process model parameterized by third parameters, and the third parameters and the latent variables are adapted during the training of the machine learning system in such a way that a marginal probability of a reconstruction of the measured time curves is maximized below these latent variables. ### Claim 4 (depends on 3) The method as recited in claim 3, wherein the first part includes a neural network parameterized by fourth parameters, and the adaptation of the latent variables occurs during the training by adapting the fourth parameters. ### Claim 5 (depends on 2) The method as recited in claim 2, wherein the first part and the second part of the machine learning system form an autoencoder. ### Claim 6 (depends on 2) The method as recited in claim 2, wherein the first part and the second part of the machine learning system form a variational autoencoder. ### Claim 7 (depends on 2) The method as recited in claim 2, wherein the first variables, which characterize the latent variable, are the latent variables themselves, and the first part ascertains the latent variables from the measured time curves using a sparse dictionary learning method, which variables represent coefficients of the measured time curves in a representation as a linear combination of the dictionary learned using this method. ### Claim 8 (depends on 1) The method as recited in claim 1, wherein latent variables are predefined and the machine learning system generates the time curves of the operating variables as a function of the predefined latent variables, and the emissions are then ascertained as a function of the generated time curves. ### Claim 9 (depends on 8) The method as recited in claim 8, wherein the latent variables are ascertained using a method of statistical test planning. ### Claim 10 (depends on 8) The method as recited in claim 8, wherein a probability density distribution of the latent variables resulting as a function of the measured time curves is ascertained and the predefined latent variables are drawn as a random sample from the estimated probability density distribution. ### Claim 11 (depends on 1) The method as recited in claim 1, wherein the machine learning system includes a first part to which either the measured time curves of the operating variables or time curves of the operating variables generated by a second part of the machine learning system are fed, the first part being trained during the training of the machine learning system to decide whether it is fed a measured time curve of the operating variables or a generated time curve of the operating variables, and the second part being trained during the training of the machine learning system to generate the time curves of the operating variables as a function of randomly selected input variables. ### Claim 12 (depends on 11) The method as recited in claim 11, wherein the second part is trained during the training of the machine learning system to generate the time curves of the operating variables as the function of the randomly selected input variables in such a way that the first part is able to only poorly decide whether it is fed the measured time curve or the generated time curve of the operating variables. ### Claim 13 (depends on 11) The method as recited in claim 11, wherein randomly selected input variables are predefined and the machine learning system generates the time curves of the operating variables as a function of the randomly selected input variables, and the emissions are then ascertained as a function of the generated time curves. ### Claim 14 (depends on 13) The method as recited in claim 13, wherein at least some of the randomly selected input variables are ascertained using a method of statistical test planning. ### Claim 15 A non-transitory machine-readable memory medium on which is stored a computer program for ascertaining emissions of a motor vehicle driven using an internal combustion engine in a driving operation, the computer program, when executed by a computer, causing the computer to perform the following steps: training a machine learning system to generate time curves, of operating variables of the internal combustion engine and/or of the motor vehicle, using measured time curves of the operating variables of the internal combustion engine and/or of the motor vehicle; generating, by the machine learning system, the time curves of the operating variables; ascertaining the emissions as a function of the generated time curves generated by the machine learning system; and controlling the motor vehicle as a function of the ascertained emissions. ### Claim 16 A computer configured to ascertain emissions of a motor vehicle driven using an internal combustion engine in a driving operation, the computer configured to: train a machine learning system to generate time curves, of operating variables of the internal combustion engine and/or of the motor vehicle, using measured time curves of the operating variables of the internal combustion engine and/or of the motor vehicle; generate, by the machine learning system, the time curves of the operating variables; ascertain the emissions as a function of the generated time curves generated by the machine learning system; and control the motor vehicle as a function of the ascertained emissions. ### Claim 17 (depends on 15) The non-transitory machine-readable memory medium as recited in claim 15, wherein: latent variables are predefined and the machine learning system generates the time curves of the operating variables as a function of the predefined latent variables, and the emissions are then ascertained as a function of the generated time curves; wherein a probability density distribution of the latent variables resulting as a function of the measured time curves is ascertained and the predefined latent variables are drawn as a random sample from the estimated probability density distribution. ### Claim 18 (depends on 16) The computer as recited in claim 16, wherein the machine learning system includes a first part to which either the measured time curves of the operating variables or time curves of the operating variables generated by a second part of the machine learning system are fed, the first part being trained during the training of the machine learning system to decide whether it is fed a measured time curve of the operating variables or a generated time curve of the operating variables, and the second part being trained during the training of the machine learning system to generate the time curves of the operating variables as a function of randomly selected input variables. ### Claim 19 (depends on 1) The method as recited in claim 1, wherein the operating variables include at least one of the following: (i) an accelerator pedal position of the motor vehicle, and/or (ii) a brake pedal position of the motor vehicle, and/or (iii) a position of a clutch of a transmission of the motor vehicle, and/or (iv) a gear of the transmission, and/or (v) a speed of the motor vehicle, and/or (vi) a driving resistance of the motor vehicle, and/or (vii) a tractive force of the internal combustion engine, and/or (viii) a tractive force of an electromotive drive, and/or (ix) a rotational speed of the internal combustion engine, and/or (x) an airmass intake per unit time of the internal combustion engine, and/or (xi) a pressure in an intake manifold of the internal combustion engine, and/or (xii) a quantity of a high-pressure EGR (exhaust gas recirculation), and/or (xiii) a quantity of a low-pressure EGR, and/or (xiv) a timing of a closing an inlet valve, and/or (xv) a timing of an opening of an outlet valve, and/or (xvi) a maximum valve lift of the inlet valve, and/or (xvii) a maximum valve lift of the outlet valve, and/or (xviii) a position of a system for changing a compression of the internal combustion engine, and/or (xix) a fuel quantity of injections of the internal combustion engine, and/or (xx) an injection timing of the injections, and/or (xxi) a pressure in a fuel high-pressure accumulator, and/or (xxii) a coolant temperature of the internal combustion engine, and/or (xxiii) a temperature in an intake system of the internal combustion engine. ### Claim 20 (depends on 15) The non-transitory machine-readable memory medium as recited in claim 15, wherein the operating variables include at least one of the following: (i) an accelerator pedal position of the motor vehicle, and/or (ii) a brake pedal position of the motor vehicle, and/or (iii) a position of a clutch of a transmission of the motor vehicle, and/or (iv) a gear of the transmission, and/or (v) a speed of the motor vehicle, and/or (vi) a driving resistance of the motor vehicle, and/or (vii) a tractive force of the internal combustion engine, and/or (viii) a tractive force of an electromotive drive, and/or (ix) a rotational speed of the internal combustion engine, and/or (x) an airmass intake per unit time of the internal combustion engine, and/or (xi) a pressure in an intake manifold of the internal combustion engine, and/or (xii) a quantity of a high-pressure EGR (exhaust gas recirculation), and/or (xiii) a quantity of a low-pressure EGR, and/or (xiv) a timing of a closing an inlet valve, and/or (xv) a timing of an opening of an outlet valve, and/or (xvi) a maximum valve lift of the inlet valve, and/or (xvii) a maximum valve lift of the outlet valve, and/or (xviii) a position of a system for changing a compression of the internal combustion engine, and/or (xix) a fuel quantity of injections of the internal combustion engine, and/or (xx) an injection timing of the injections, and/or (xxi) a pressure in a fuel high-pressure accumulator, and/or (xxii) a coolant temperature of the internal combustion engine, and/or (xxiii) a temperature in an intake system of the internal combustion engine. ### Claim 21 (depends on 16) The computer as recited in claim 16, wherein the operating variables include at least one of the following: (i) an accelerator pedal position of the motor vehicle, and/or (ii) a brake pedal position of the motor vehicle, and/or (iii) a position of a clutch of a transmission of the motor vehicle, and/or (iv) a gear of the transmission, and/or (v) a speed of the motor vehicle, and/or (vi) a driving resistance of the motor vehicle, and/or (vii) a tractive force of the internal combustion engine, and/or (viii) a tractive force of an electromotive drive, and/or (ix) a rotational speed of the internal combustion engine, and/or (x) an airmass intake per unit time of the internal combustion engine, and/or (xi) a pressure in an intake manifold of the internal combustion engine, and/or (xii) a quantity of a high-pressure EGR (exhaust gas recirculation), and/or (xiii) a quantity of a low-pressure EGR, and/or (xiv) a timing of a closing an inlet valve, and/or (xv) a timing of an opening of an outlet valve, and/or (xvi) a maximum valve lift of the inlet valve, and/or (xvii) a maximum valve lift of the outlet valve, and/or (xviii) a position of a system for changing a compression of the internal combustion engine, and/or (xix) a fuel quantity of injections of the internal combustion engine, and/or (xx) an injection timing of the injections, and/or (xxi) a pressure in a fuel high-pressure accumulator, and/or (xxii) a coolant temperature of the internal combustion engine, and/or (xxiii) a temperature in an intake system of the internal combustion engine.