US 12,353,506 B2
Future reliability prediction based on system operational and performance data modelling
Richard B. Jones, Georgetown, TX (US)
Assigned to The Hartford Steam Boiler Inspection and Insurance Company, Hartford, CT (US)
Filed by HARTFORD STEAM BOILER INSPECTION AND INSURANCE COMPANY, Hartford, CT (US)
Filed on Jan. 9, 2023, as Appl. No. 18/094,835.
Application 18/094,835 is a continuation of application No. 16/566,845, filed on Sep. 10, 2019, granted, now 11,550,874.
Application 16/566,845 is a continuation of application No. 14/684,358, filed on Apr. 11, 2015, granted, now 10,409,891, issued on Sep. 10, 2019.
Claims priority of provisional application 61/978,683, filed on Apr. 11, 2014.
Prior Publication US 2023/0169146 A1, Jun. 1, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/18 (2006.01); G06Q 10/0635 (2023.01); G06F 111/10 (2020.01)
CPC G06F 17/18 (2013.01) [G06Q 10/0635 (2013.01); G06F 2111/10 (2020.01); Y02P 90/845 (2015.11)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by at least one processor, operating data associated with a facility in real-time, wherein the operating data comprises one or more operating characteristics of a measurable system for the facility;
receiving, by the at least one processor, asset reliability data associated with the facility;
utilizing, by the at least one processor, one or more machine learning models to optimize performance of operation activities within the facility based on an identification of a target variable associated with the facility in comparison to the operating data and the asset reliability data;
generating, by the at least one processor, an operation standard associated with the facility to form a plurality of category values based on the target variable associated with the performance of the operation activities, wherein the plurality of category values categorize the operation data by a predetermined interval based on the operation data, the target variable and a result of the one or more machine learning models;
determining, by the at least one processor, an estimated future reliability of the facility based on the asset reliability data and the plurality of category values for subsequent updates associated with current data of the facility to form an updated estimated future reliability of the facility;
continually tracking, by the at least one processor, the plurality of category values associated with the target variable of the facility in real-time; and
causing to display, by the at least one processor, information regarding the estimated future reliability of the facility and/or information regarding the updated estimated future reliability of the facility.