US 12,254,389 B2
Controller for controlling a technical system, and method for configuring the controller
Siegmund Düll, Munich (DE); Kai Heesche, Munich (DE); Volkmar Sterzing, Neubiberg (DE); and Marc Christian Weber, Munich (DE)
Assigned to Siemens Aktiengesellschaft, Munich (DE)
Appl. No. 17/254,926
Filed by Siemens Aktiengesellschaft, Munich (DE)
PCT Filed Jun. 26, 2019, PCT No. PCT/EP2019/067036
§ 371(c)(1), (2) Date Dec. 22, 2020,
PCT Pub. No. WO2020/002447, PCT Pub. Date Jan. 2, 2020.
Claims priority of application No. 18180156 (EP), filed on Jun. 27, 2018.
Prior Publication US 2021/0256428 A1, Aug. 19, 2021
Int. Cl. G06N 20/10 (2019.01); G05B 13/02 (2006.01); G06N 3/08 (2023.01)
CPC G06N 20/10 (2019.01) [G05B 13/0265 (2013.01); G06N 3/08 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for configuring a control device for a technical system by a machine learning method, wherein
a) a temporal sequence of training data for the machine learning method is captured, wherein the training data comprise state data specifying states of the technical system and control action data specifying control actions of the technical system,
b) a temporal sequence of the control action data is specifically extracted from the training data,
c) the sequence of the control action data is checked for a change over time, and detection of a change over time results in a time window that comprises the change over time of the control action data being ascertained,
d) the training data situated within the time window that comprises the change over time of the control action data are extracted on a time-window-specific basis to provide extracted time-window-specific training data that is a filtered subset of the temporal sequence of training data, and
e) the control device is trained, on the basis of the extracted time-window-specific training data, by the machine learning method and thus configured to control the technical system, and
wherein training data situated outside the time window that comprises the change over time of the control action data are suppressed, rejected, and/or given a lower weighting during the training of the control device.