IP Library Granted Patent US 12663785
Granted Patent B2
US 12663785 · App. 18/182,767 · Granted Jun 23, 2026

Apparatuses, computer-implemented methods, and computer program products for closed loop optimal planning and scheduling under uncertainty

Inventors: Jeffrey Glen Renfro (Deer Park, TX); Saadet Ulas Acikgoz (Northbrook, IL)
Assignee: Honeywell International Inc.
G05B19/41865G05B2219/32423G05B2219/34418G05B2219/49068
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12663785
App. No.
18/182,767
Granted
Jun 23, 2026
Kind
B2
Abstract

Embodiments of the present disclosure provide for improved optimized plan predictions. Such embodiments, utilize optimized model(s) that accounts for uncertainty in input data to the model. Some example embodiments, receive input data associated with one or more industrial plants. At least a portion of the input data may include uncertain input data. The noted example embodiments, generate uncertainty-based modification data, and apply the uncertainty-based modification data to the input data to generate updated input data. The noted example embodiments generate, based at least in part on applying the updated input data to an optimization model, predicted optimized plan. The predicted optimized plan comprises optimized plan data. Further, the noted example embodiments initiate the performance of one or more prediction-based actions based at least in part on the predicted optimized plan.

Claims (44)

1 . A computer-implemented method for generating an optimized plan with respect to a target comprising:

receiving, using one or more processors, input data associated with one or more industrial plants, wherein at least a portion of the input data comprises uncertain input data;

identifying, using the one or more processors, a set of uncertain input variables associated with the uncertain input data;

generating, using the one or more processors, a data distribution for each uncertain input variable in the set of uncertain input variables;

generating, using the one or more processors, uncertainty-based modification data based at least in part on sampling the data distribution for each uncertain input variable;

applying at least the uncertainty-based modification data to the input data to generate updated input data;

generating, using the one or more processors and based at least in part on applying the updated input data to an optimization model, predicted optimized plan comprising optimized plan data, wherein the generation of the predicted optimized plan based at least in part on applying the updated input data comprises for each sampled set of uncertain input variables, optimizing a control error minimization problem for each of one or more constraint priority groups associated with operation of the one or more industrial plants based at least in part on a priority order, wherein each constraint priority group is associated with a priority level; and

initiating, using the one or more processors, performance of one or more prediction-based actions based at least in part on the predicted optimized plan.

2 . The computer-implemented method of claim 1 , wherein generating the predicted optimized plan based at least in part on applying the input data comprises:

for each sampled set of uncertain input variables:

optimizing, using the one or more processors, a profit maximization problem, wherein the profit maximization problem comprises at least a decision variable cost measure.

3 . The computer-implemented method of claim 1 , wherein the optimization model embodies a non-linear model predictive control.

4 . The computer-implemented method of claim 1 , wherein the optimization model comprises at least a feedback mechanism configured to enable closed loop planning.

5 . The computer-implemented method of claim 1 , wherein initiating performance of one or more prediction-based actions comprises outputting at least a portion of the optimized plan to a user interface.

6 . The computer-implemented method of claim 1 , wherein initiating performance of one or more prediction-based action comprise causing automatic reconfiguration of operation of at least one physical component of the one or more industrial plants based at least in part on at least a portion of the optimized plan.

7 . An apparatus for generating an optimized plan with respect to a target, the apparatus comprising at least one processor and at least one non-transitory memory including computer-coded instructions thereon, the computer-coded instructions, with the at least one processor, cause the apparatus to:

receive input data associated with one or more industrial plants, wherein at least a portion of the input data comprises uncertain input data;

identify a set of uncertain input variables associated with the uncertain input data;

generate a data distribution for each uncertain input variable in the set of uncertain input variables;

generate uncertainty-based modification data based at least in part on sampling the data distribution for each uncertain input variable;

apply at least the uncertainty-based modification data to the input data to generate updated input data;

generate, based at least in part on applying the updated input data to an optimization model, predicted optimized plan comprising optimized plan data, wherein the generation of the predicted optimized plan based at least in part on applying the updated input data comprises for each sampled set of uncertain input variables, optimizing a control error minimization problem for each of one or more constraint priority groups associated with operation of the one or more industrial plants based at least in part on a priority order, wherein each constraint priority group is associated with a priority level; and

initiate performance of one or more prediction-based actions based at least in part on the predicted optimized plan.

8 . The apparatus of claim 7 , wherein the computer-coded instructions, with the at least one processor, cause the apparatus to generate the predicted optimized plan based at least in part on applying the input data comprises:

for each sampled set of uncertain input variables:

optimizing a profit maximization problem, wherein the profit maximization problem comprises at least a decision variable cost measure.

9 . The apparatus of claim 7 , wherein the optimization model embodies a non-linear model predictive control.

10 . The apparatus of claim 7 , wherein the optimization model comprises at least a feedback mechanism configured to enable closed loop planning.

11 . The apparatus of claim 7 , wherein the computer-coded instructions, with the at least one processor, cause the apparatus to initiate performance of one or more prediction-based actions comprises outputting at least a portion of the optimized plan to a user interface.

12 . The apparatus of claim 7 , wherein the computer-coded instructions, with the at least one processor, cause the apparatus to initiate performance of one or more prediction-based action comprise causing automatic reconfiguration of operation of at least one physical component of the one or more industrial plants based at least in part on at least a portion of the optimized plan.

13 . A computer program product generating an optimized plan with respect to a target, the computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, configures the computer program product for:

receiving input data associated with one or more industrial plants, wherein at least a portion of the input data comprises uncertain input data;

identifying, using the one or more processors, a set of uncertain input variables associated with the uncertain input data;

generating, using the one or more processors, a data distribution for each uncertain input variable in the set of uncertain input variables;

generating uncertainty-based modification data based at least in part on sampling the data distribution for each uncertain input variable;

applying at least the uncertainty-based modification data to the input data to generate updated input data;

generating, based at least in part on applying the updated input data to an optimization model, predicted optimized plan comprising optimized plan data, wherein the generation of the predicted optimized plan based at least in part on applying the updated input data comprises for each sampled set of uncertain input variables, optimizing a control error minimization problem for each of one or more constraint priority groups associated with operation of the one or more industrial plants based at least in part on a priority order, wherein each constraint priority group is associated with a priority level; and

initiating the performance of one or more prediction-based actions based at least in part on the predicted optimized plan.

14 . The computer program product of claim 13 , wherein generating the predicted optimized plan based at least in part on applying the input data comprises:

for each sampled set of uncertain input variables:

optimizing a profit maximization problem, wherein the profit maximization problem comprises at least a decision variable cost measure.

15 . The computer program product of claim 13 , wherein the optimization model embodies a non-linear model predictive control.

16 . The computer program product of claim 13 , wherein the optimization model comprises at least a feedback mechanism configured to enable closed loop planning.

17 . The computer program product of claim 13 , wherein initiating performance of one or more prediction-based actions comprises outputting at least a portion of the optimized plan to a user interface.