US 12,443,154 B2
Feature extraction integration with control programs
Jordan C. Reynolds, Austin, TX (US); John J. Hagerbaumer, Mequon, WI (US); Troy W. Mahr, Pleasant Prairie, WI (US); Thomas K. Jacobsen, Wake Forest, NC (US); and Giancarlo Scaturchio, Pisa (IT)
Assigned to Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed by Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed on Mar. 18, 2022, as Appl. No. 17/698,498.
Prior Publication US 2023/0297041 A1, Sep. 21, 2023
Int. Cl. G05B 13/04 (2006.01); G05B 13/02 (2006.01)
CPC G05B 13/041 (2013.01) [G05B 13/0265 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system to train a machine learning model for implementation in an industrial automation environment, the system comprising:
a memory that stores executable components; and
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a design component configured to receive a data set that comprises a control program that is configured for implementation by a Programmable Logic Controller (PLC);
a machine learning interface component configured to process the data set, calculate derivative values based on the data set, identify types for individual ones of the derivative values, rank the derivative values based on their types, and weight the derivative values based on their ranks;
the machine learning interface component further configured to generate feature vectors that comprise the weighted derivative values and supply the feature vectors to the machine learning model to train the machine learning model; and
the design component further configured to receive a machine learning training output generated by processing the feature vectors.