US 11,815,863 B2
Predictive modeling and control for water resource infrastructure
Thouheed Abdul Gaffoor, Mississauga (CA); Megh Suthar, Toronto (CA); and Yousra Hazem Khalil Helmy Mohamed, Mississauga (CA)
Assigned to AUTODESK, INC., San Francisco, CA (US)
Filed by Autodesk, Inc., San Francisco, CA (US)
Filed on Feb. 21, 2023, as Appl. No. 18/171,971.
Application 18/171,971 is a continuation of application No. 16/620,421, granted, now 11,586,163, previously published as PCT/IB2018/054166, filed on Jun. 8, 2018.
Claims priority of provisional application 62/517,514, filed on Jun. 9, 2017.
Prior Publication US 2023/0205150 A1, Jun. 29, 2023
Int. Cl. G05B 13/04 (2006.01); G06N 20/00 (2019.01); G05B 13/02 (2006.01); G06N 5/04 (2023.01); E03B 7/02 (2006.01); E03B 7/07 (2006.01)
CPC G05B 13/048 (2013.01) [G05B 13/0265 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); E03B 7/02 (2013.01); E03B 7/075 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for training a control mechanism scheduler of a water resource infrastructure, the system comprising:
a communication interface configured to receive operating data and disturbance data, the operating data describing infrastructure components of the water resource infrastructure, the operating data comprising state variables describing a state of the infrastructure components and control variables describing control mechanisms for modifying actuable infrastructure components, the disturbance data comprising one or more disturbance signals received from a disturbance data provider that describes a disturbance expected to disturb the water resource infrastructure;
a memory storage unit; and
a processor in communication with the communication interface and the memory storage unit, the processor configured to:
apply a pattern recognition algorithm to disturbance variables of the disturbance signals to generate one or more unique classes for the disturbance signals, wherein the unique classes correspond to one or more patterns recognized in the disturbance signals;
generate a simulation of the water resource infrastructure based on the disturbance signals and on the operating data;
automatically generate, for each of the one or more unique classes, a schedule of setpoints for control mechanisms actuable to control the infrastructure components of the water resource infrastructure based on the simulation, generation of the schedule of setpoints being in accordance with approaching a predetermined objective, wherein the generation is in real-time;
store each schedule of setpoints in the memory storage unit and label each schedule of setpoints to correspond with an associated unique class of the one or more unique classes;
receive new disturbance signals;
classify the new disturbance signals into a first unique class of the one or more unique classes for which the schedule of setpoints has already been generated;
retrieve the schedule of setpoints associated with the first unique class; and
controlling the infrastructure components based on the retrieved schedule of setpoints.