# US 2021/0080914 A1 · Predictive modelling and control for water resource infrastructure

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0080914 A1
- Document ID: US20210080914A1
- Status: Published application
- Kind: A1
- Application number: 16/620,421
- Filed: 2018-06-08
- Published: 2021-03-18
- Earliest claimed: 2017-06-09
- Assignees: Autodesk, Inc.
- Applicants: Emagin Clean Technologies Inc.
- Inventors: Thouheed Abdul GAFFOOR; Megh SUTHAR; Yousra Hazem Khalil Helmy MOHAMED
- Web page: https://patentgrep.com/patent/US20210080914A1

## CPC

- G05B 13/048: {using a predictor}
- G05B 13/0265: {the criterion being a learning criterion}
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- E03B 7/02: Public or like main pipe systems
- E03B 7/075: {Arrangement of devices for control of pressure or flow rate}
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- E03B: INSTALLATIONS OR METHODS FOR OBTAINING, COLLECTING, OR DISTRIBUTING WATER (drilling wells, obtaining fluids in general from wells E21B; pipe-line systems in general F17D)

## Abstract

A control mechanism scheduler for a water resource infrastructure receives operating data and disturbance data, the operating data describing infrastructure components of the water resource infrastructure, the disturbance data comprising a disturbance signal describing a disturbance expected to disturb the water resource infrastructure. The control mechanism scheduler generates classes for disturbance signals, generates simulations of the water resource infrastructure, and generates schedules of setpoints for control mechanisms actuable to control the infrastructure components of the water resource infrastructure in accordance with approaching a predetermined objective.

## Claims

### Claim 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 disturbance data comprising a disturbance signal describing 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 signal to generate a unique class corresponding to the disturbance signal;
generate a simulation of the water resource infrastructure based on the disturbance signal and on the operating data;
generate 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; and
associate the schedule of setpoints with the class and store the schedule of setpoints in the memory storage unit.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
application of the pattern recognition algorithm includes decomposing the disturbance signal into lower dimensions for clustering;
the pattern recognition algorithm comprises clustering; and
the class corresponds to a unique data cluster of disturbance signals.

### Claim 3 (depends on 1)

The system of claim 1, wherein generation of the schedule of setpoints includes:
generating interim simulations of the water resource infrastructure;
generating interim schedules of setpoints in accordance with approaching the predetermined objective; and
iterating the generation of the interim schedules and generation of the interim simulations until a predetermined objective is reached within a predetermined threshold.

### Claim 4 (depends on 3)

The system of claim 3, wherein:
the pattern recognition algorithm comprises clustering;
the class corresponds to a unique data cluster of the disturbance signal; and
iteration of the generation of the interim schedules and the generation of the interim simulations repeats for a plurality of centroids of the unique data clusters.

### Claim 5 (depends on 1)

The system of claim 1, wherein the simulation of the water resource infrastructure is generated by a hierarchical learning model.

### Claim 6 (depends on 5)

The system of claim 5, wherein the hierarchical learning model has a recursive hierarchical layered design comprising a plurality of regression estimators, each of the regression estimators describing an infrastructure component of the water resource infrastructure and being recursively interconnected in a directed graph.

### Claim 7 (depends on 1)

The system of claim 1, wherein at least some of the disturbance variables are expected to impact water demand in the water resource infrastructure.

### Claim 8 (depends on 7)

The system of claim 7, wherein at least some of the disturbance variables expected to impact water demand are organized into a daily or hourly time series.

### Claim 9 (depends on 1)

The system of claim 1, wherein the operating data is received from a monitoring system, the monitoring system comprising a supervisory control and data acquisition (SCADA) system monitoring the water resource infrastructure.

### Claim 10

A system for generating a schedule of setpoints of control mechanisms 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 disturbance data comprising disturbance variables;
a memory storage unit; and
a processor in communication with the communication interface and the memory storage unit, the processor configured to:
generate a predicted disturbance signal based on the disturbance variables;
attempt to classify the predicted disturbance signal into a predetermined class of disturbance signals recognized to represent a disturbance expected to disturb the water resource infrastructure, the predetermined class of disturbance signals having a corresponding predetermined schedule of setpoints for control mechanisms actuable to control the infrastructure components stored in the memory storage unit; and
where classification of the predicted disturbance signal is successful:
retrieve the predetermined schedule of setpoints; and
output the predetermined schedule of setpoints.

### Claim 11 (depends on 10)

The system of claim 10, wherein the processor is further configured to, where classification of the predicted disturbance signal is unsuccessful:
apply a pattern recognition algorithm to the disturbance data to generate a new class for the disturbance data;
generate a new schedule of setpoints for control mechanisms to achieve a predetermined objective; and
associate the new schedule of setpoints with the new class and store the new schedule of setpoints in the memory storage unit.

### Claim 12 (depends on 10)

The system of claim 10, wherein:
the class corresponds to a class of clusters generated by clustering historical disturbance variables into predetermined classes of disturbance signals; and
retrieval of the predetermined schedule of setpoints includes running the disturbance data through a cluster mapping engine to select the class of clusters.

### Claim 13 (depends on 10)

The system of claim 10, wherein the simulation of the water resource infrastructure is generated by a hierarchical learning model.

### Claim 14 (depends on 13)

The system of claim 13, wherein the hierarchical learning model has a recursive hierarchical layered design comprising a plurality of regression estimators, each of the regression estimators describing operating parameters of infrastructure components of the water resource infrastructure and being recursively interconnected in a directed graph.
