US 11,982,997 B2
Real-time operation of an industrial facility using a machine learning based self-adaptive system
Yogesha Aralakuppe Ramegowda, Bengaluru (IN); Pachipulusu Lingesh Sumanth, Bengaluru (IN); Srikanth Olety Subramanya, Bengaluru (IN); Parag Ravindra Rao, Bengaluru (IN); and Koyalkar Raman Kishore, Bengaluru (IN)
Assigned to Honeywell International Inc., Charlotte, NC (US)
Filed by HONEYWELL INTERNATIONAL, INC., Morris Planes, NJ (US)
Filed on Sep. 28, 2019, as Appl. No. 16/586,920.
Prior Publication US 2021/0096547 A1, Apr. 1, 2021
Int. Cl. G05B 19/41 (2006.01); G05B 13/02 (2006.01); G05B 19/418 (2006.01); G06Q 10/0631 (2023.01)
CPC G05B 19/41865 (2013.01) [G05B 13/0265 (2013.01); G06Q 10/0631 (2013.01); G05B 2219/33034 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for improving real-time operation of at least one terminal station in an industrial facility using a machine learning-based self-adaptive system, the method comprising:
(a) obtaining, from the at least one terminal station, data comprising real-time operations data that relates to sensor data from a sensor data aggregation node of the at least one terminal station and historical data stored in a local database or at a cloud-storage, the data relating to at least one input parameter of the at least one terminal station;
(b) inputting the at least one input parameter to a machine learning configurable module of the machine learning-based self-adaptive system;
(c) analyzing the at least one input parameter by the machine learning configurable module using dynamic machine learning models and algorithms to identify at least one pattern to each of the at least one input parameter,
wherein the machine learning configurable module is configured to allocate bays of the at least one terminal station using a bay allocation module of the machine learning-based self-adaptive system,
wherein the dynamic machine learning models and algorithms comprise at least one of a supervised learning classification or regression algorithms, and
wherein the supervised learning classification or regression algorithms predict failure of at least one of equipment or asset in the industrial facility;
(d) recognizing the at least one pattern from the data provided by the sensor data aggregation node and providing training to the machine learning models and algorithms based on the at least one pattern;
(e) evaluating the at least one pattern against the real-time operations data obtained from the at least one terminal station;
(f) predicting at least one output parameter based on the at least one input parameter and the at least one pattern against the real-time operations;
(g) providing actionable insights using at least one module including the bay allocation module, a maintenance module and a notification module of the machine learning configurable module;
(h) sending the actionable insights to the sensor data aggregation node of the at least one terminal station;
(i) adjusting the at least one output parameter of the real-time operations data using the actionable insights; and
(j) modifying, using the bay allocation module, the bays allocation based on the adjustment of the at least one output parameter.