US 12,106,224 B2
Method and assistance system for assisting the planning of automation systems
Thomas Runkler, Munich (DE); Jürgen Baus, Eggenstein-Leopoldshafen (DE); and Michael Rock, Landau (DE)
Assigned to Siemens Aktiengesellschaft, Munich (DE)
Filed by Siemens Aktiengesellschaft, Munich (DE)
Filed on May 28, 2019, as Appl. No. 16/423,755.
Claims priority of application No. 18174558 (EP), filed on May 28, 2018.
Prior Publication US 2019/0362239 A1, Nov. 28, 2019
Int. Cl. G06N 3/088 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/088 (2013.01) [G06N 3/04 (2013.01)] 26 Claims
OG exemplary drawing
 
1. An assistance system which assists in planning layouts and configurations of automation systems prior to operation of said automation systems, comprising:
a computer having a processor and memory;
a configuration database comprising configuration datasets of automation systems, a respective configuration dataset in each case comprising configuration data of a predefined automation system;
a vectorizer for structuring and adjusting configuration datasets, the vectorizer converting the configuration datasets of the configuration database into vectorized configuration datasets comprising at least one of (i) normalization of data and/or values; (ii) creation of a numerical representation of data, (iii) chaining of ordered data sequences and/or of related data from various sources, (iv) formation of values that describe or combine data and (v) conversion of time series into the frequency domain and/or conversion of frequency series into the time domain;
an artificial intelligence (AI) component for processing the vectorized configuration datasets utilizing artificial intelligence;
wherein the processing of the vectorized configuration datasets by the AI component comprises utilizing a neural network having a deep learning architecture during planning of the layouts and configurations of the automation systems via the assistance system prior to operation of said automation systems.