US 12,088,553 B2
Implementing device modifications based on machine learning processes performed within a secure deployment system
Rob A. Entzminger, Shawnee, KS (US); David C. Mazur, Mequon, WI (US); Nathaniel S. Sandler, Chagrin Falls, OH (US); Todd A. Wiese, Hubertus, WI (US); and Jonathan Alan Mills, Mayfield Heights, OH (US)
Assigned to Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed by Rockwell Automation Technologies, Inc., Mayfield Heights, OH (US)
Filed on Feb. 7, 2023, as Appl. No. 18/107,005.
Claims priority of provisional application 63/425,117, filed on Nov. 14, 2022.
Prior Publication US 2024/0160174 A1, May 16, 2024
Int. Cl. H04L 9/40 (2022.01); G05B 19/042 (2006.01); G05B 19/418 (2006.01); G06N 20/00 (2019.01); H04L 67/00 (2022.01)
CPC H04L 63/0209 (2013.01) [G05B 19/0423 (2013.01); G05B 19/4185 (2013.01); G06N 20/00 (2019.01); H04L 63/1425 (2013.01); H04L 67/34 (2013.01); G05B 2219/23317 (2013.01); G05B 2219/25205 (2013.01); H04L 63/20 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, via a secure deployment management (SDM) system, data associated with one or more operations of an industrial device from a secure deployment management (SDM) node associated with the industrial device, wherein the SDM node comprises a system-on-chip (SoC) component that is preregistered with the SDM system and the SoC component is integrated within the industrial device, wherein the SDM node corresponds to one of a plurality of SDM nodes authorized to communicate with the SDM system via a preprogrammed handshake protocol, and wherein the data is received via a secure communication channel between the SDM system and the SDM node after the secure communication channel is established by the SDM system with the SDM node and one or more security protocols;
receiving, via the SDM system, updated data associated with the one or more operations of the industrial device from the SDM node, wherein the updated data is acquired after the data, and wherein the SDM node is communicatively coupled with a machine learning system for sending and receiving data, wherein the machine learning system is configured to:
generate an updated machine learning model based on the updated data and a machine learning model representative of one or more expected outputs associated with the one or more operations of the industrial device, wherein the machine learning model is generated based on the data;
generate updated configuration data in response to one or more expected outputs of the updated machine learning model being outside one or more thresholds; and
send the updated configuration data to the SoC component of the SDM node;
receiving, via the SDM system, the updated configuration data from the SDM node via the secure communication channel; and
sending, via the SDM system, the updated configuration data to the industrial device after establishing the secure communication channel between the SDM system and the SDM node and verifying that the updated configuration data is associated with the industrial device, wherein the industrial device is configured to receive the updated configuration data from the SDM node without performing one or more security operations on the updated configuration data.