US 11,898,800 B2
Flame analytics system
David Kucera, Bilovice nad Svitavou (CZ); Curtis Taylor, Paradise Valley, AZ (US); Jonathan McDonald, Shakopee, MN (US); Gregory Stewart, North Vancouver (CA); and Wyatt Culler, Berne, IN (US)
Assigned to HONEYWELL INTERNATIONAL INC., Charlotte, NC (US)
Filed by Honeywell International Inc., Morris Plains, NJ (US)
Filed on Oct. 28, 2019, as Appl. No. 16/665,572.
Claims priority of provisional application 62/755,297, filed on Nov. 2, 2018.
Prior Publication US 2020/0141653 A1, May 7, 2020
Int. Cl. F23N 5/24 (2006.01); F27D 21/04 (2006.01); G06N 20/00 (2019.01); G06N 5/02 (2023.01); G06N 5/04 (2023.01); F23N 5/16 (2006.01); G06F 16/21 (2019.01); F27D 21/00 (2006.01); F27D 21/02 (2006.01)
CPC F27D 21/04 (2013.01) [F23N 5/16 (2013.01); F23N 5/242 (2013.01); G06F 16/219 (2019.01); G06N 5/02 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); F23N 2223/04 (2020.01); F23N 2223/08 (2020.01); F23N 2223/36 (2020.01); F23N 2223/48 (2020.01); F23N 2229/00 (2020.01); F23N 2241/04 (2020.01); F23N 2900/05006 (2013.01); F27D 2021/0057 (2013.01); F27D 2021/026 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A flame analytics system comprising:
a burner;
one or more sensors at or about the burner, wherein the one or more sensors include two or more video sensors having 2D views at different angles of a flame in the burner and wherein the 2D views are reconstructed into 3D views for observation of the flame to distinguish individual flames from one another in a multi-burner appliance and/or to distinguish a flame from its background;
a historical database connected to the one or more sensors;
a model training module connected to the historical database; and
a runtime algorithm module connected to the one or more sensors and the model training module; and
wherein the runtime algorithm compares realtime data from the one or more sensors and the historical data from the model training module in accordance with a machine learning algorithm.