US 12,140,100 B2
Controlling an internal combustion engine using an operating parameter map derived from a trainable model
Julius Pfrommer, Karlsruhe (DE); Janina Stompe, Karlsruhe (DE); and Johannes Sailer, Karlsruhe (DE)
Assigned to Fraunhofer-Gesellschaft zur förderung der angewandten Forschung e.V., Munich (DE)
Appl. No. 18/252,104
Filed by FRAUNHOFER-GESELLSCHAFT ZUR FÖRDERUNG DER ANGEWANDTEN FORSCHUNG E.V., Munich (DE)
PCT Filed Nov. 9, 2021, PCT No. PCT/EP2021/081088
§ 371(c)(1), (2) Date May 8, 2023,
PCT Pub. No. WO2022/101187, PCT Pub. Date May 19, 2022.
Claims priority of application No. 10 2020 129 903.6 (DE), filed on Nov. 12, 2020.
Prior Publication US 2024/0003308 A1, Jan. 4, 2024
Int. Cl. F02D 41/14 (2006.01); F02D 41/24 (2006.01)
CPC F02D 41/1406 (2013.01) [F02D 41/2451 (2013.01); F02D 41/2487 (2013.01); F02D 2041/1437 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An engine control system comprising an engine control unit for an internal combustion engine of a vehicle and a learning unit, wherein the learning unit is integrated into the engine control unit or wherein the learning unit is an external learning unit, wherein
the control unit is designed to set one or more operating parameters of the internal combustion engine based on a predefined multidimensional operating parameter map which is stored in the control unit and specifies respective operating parameter values for various operating states of the internal combustion engine,
wherein the control unit is designed to transmit an operating parameter history, which comprises operating parameter values set for the internal combustion engine in its operating history, to a learning unit, and to receive operating parameter map update data from the learning unit and to update the stored operating parameter map by the operating parameter map update data; and wherein
a simulation model of the internal combustion engine and a target function for evaluating the behavior of the internal combustion engine is stored in the learning unit, wherein the simulation model is trainable by a learning algorithm stored in the learning unit, and the learning unit is designed
(i) to update the simulation model based on the transmitted operating parameter history and the stored target function by utilizing the learning algorithm;
(ii) to generate the operating parameter map update data by the updated simulation model; or
(iii) to provide the operating parameter map update data to the control unit for updating the operating parameter map stored in the control unit.