# US 2025/0094678 A1 · Single loop hybrid search for designing fire fighting flow capacity

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

- Number: US 2025/0094678 A1
- Document ID: US20250094678A1
- Status: Published application
- Kind: A1
- Application number: 18/886,906
- Filed: 2024-09-16
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Autodesk, Inc.
- Applicants: Autodesk, Inc.
- Inventors: Felipe Hernandez Cruz
- Web page: https://patentgrep.com/patent/US20250094678A1

## CPC

- G06F 30/28: using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06F 2113/08: Fluids
- G06F 2113/14: Pipes
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method and system provide the ability to determine a hydrant fire flow. Inputs are obtained A critical element is identified. Based on a physical-based heuristic, a new hydrant fire flow guess is determined. The search direction is evaluated and used to maintain/override (using a heuristic method) the fire flow guess. The new guess is assigned as a hydrant demand. Network pressure and flow values are updated. The constraints are evaluated. The guess is reduced if at least one constraint has been violated and increased of all constraints have been satisfied. The new guess is evaluated for convergence and if not converged, the process repeats.

## Claims

### Claim 1

A computer-implemented method for determining a hydrant fire flow, comprising:
(a) obtaining inputs comprising:
(i) a water network model;
(ii) a fire hydrant identification for a fire hydrant of interest;
(iii) a list of junctions with a minimum pressure threshold to satisfy and a minimum pressure threshold value, wherein the minimum pressure threshold comprises a first constraint in a set of constraints;
(iv) a list of pipes with a maximum velocity threshold to satisfy and a maximum velocity threshold value, wherein the maximum velocity threshold comprises a second constraint in the set of constraints;
(v) hydraulic results for base conditions for the fire hydrant of interest; and
(vi) parameter values required to determine the hydrant fire flow;
(b) identifying a critical element of the water network model;
(c) determining, based on a physical-based heuristic on the critical element, a new hydrant fire flow guess;
(d) determining whether the new hydrant fire flow guess is in an adequate search direction and:
(i) maintaining the new hydrant fire flow guess when the new hydrant fire flow guess is in an adequate search direction; and
(ii) overriding the new hydrant fire flow guess when the new hydrant fire flow guess is not in an adequate search direction, wherein the overriding utilizes a heuristic method;
(e) assigning the new hydrant fire flow guess as a hydrant demand of the fire hydrant of interest;
(f) updating a network pressure value and a network flow value;
(g) evaluating whether the set of constraints has been satisfied;
(h) reducing the new hydrant fire flow guess if at least one constraint in the set of constraints has been violated;
(i) increasing the new hydrant fire flow guess if all of the constraints in the set of constraints have been satisfied;
(j) evaluating the new hydrant fire flow guess for convergence; and
(k) breaking if there is convergence and returning to step (b) if convergence has not resulted.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the base conditions comprise:
a static demand comprising a normal water flow demand for normal water operations;
a user-defined fire demand comprising an emergency demand a user estimates will occur during a fire emergency; and
an available fire demand comprising a maximum flow that can be extracted from the fire hydrant without lowering its pressure below a given value.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the critical element is identified by prioritizing:
violated constraints in the set of constraints; and
a relative pressure distance to the minimum pressure threshold value; and
a relative velocity distance to the maximum velocity threshold value.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the determining the new hydrant fire flow guess based on a physical-based heuristic comprises:
determining a predefined number of prior hydrant fire flow guesses and prior values from the critical element;
adjusting a quadratic polynomial to the predefined number of values with the new hydrant fire flow guess as a dependent value;
solving the quadratic polynomial to determine the new hydrant fire flow guess, wherein when a quadratic value solution is equal to the minimum pressure threshold value, the quadratic value solution is determined as the new hydrant fire flow guess; and
returning the new hydrant fire flow guess.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining the adequate search direction based on whether the first constraint or the second constraint in the set of constraints has been violated, wherein:
the adequate search direction provides for a reduced flow when the first constraint or the second constraint is violated; and
the adequate search direction provides for an increased flow when the first constraint and the second constraint are satisfied.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein the heuristic method comprises:
determining an old change as a difference between two prior hydrant fire flow guesses;
determining a new guess change as a difference between a prior hydrant fire flow guess and the new hydrant fire flow guess;
determining if the new flow guess change is proportional to the old change;
increasing the new hydrant fire flow guess change and overriding the new hydrant fire flow guess based on the increase if in a same direction; and
decreasing the new hydrant fire flow guess change and overriding the new hydrant fire flow guess based on the decrease if in an opposite direction.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the network pressure value and network flow value are updated using head and flow estimation steps of a hydraulic analysis.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein there is convergence when:
global gradient algorithm (GGA) stopping criteria have been met;
all constraints in the set of constraints have been satisfied; and
the new hydrant fire flow guess is within a threshold distance of a prior hydrant fire flow guess from a last iteration.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein:
the hydrant fire flow is performed for each hydrant in a single loop that simultaneously solves for the hydrant fire flow and hydraulic conditions present when the hydrant fire flow occurs.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
repeating steps (a)-(k) for all fire hydrants in the water network model;
updating a physical manifestation of the water network model based on the new hydrant fire flow guesses.

### Claim 11

A computer-implemented system for determining a hydrant fire flow, comprising:
(a) a computer having a memory;
(b) a processor executing on the computer;
(c) the memory storing a set of instructions, wherein the set of instructions, when executed by the processor cause the processor to perform operations comprising:
(i) obtaining inputs comprising:
(1) a water network model;
(2) a fire hydrant identification for a fire hydrant of interest;
(3) a list of junctions with a minimum pressure threshold to satisfy and a minimum pressure threshold value, wherein the minimum pressure threshold comprises a first constraint in a set of constraints;
(4) a list of pipes with a maximum velocity threshold to satisfy and a maximum velocity threshold value, wherein the maximum velocity threshold comprises a second constraint in the set of constraints;
(5) hydraulic results for base conditions for the fire hydrant of interest; and
(6) parameter values required to determine the hydrant fire flow;
(ii) identifying a critical element of the water network model;
(iii) determining, based on a physical-based heuristic on the critical element, a new hydrant fire flow guess;
(iv) determining whether the new hydrant fire flow guess is in an adequate search direction and:
(1) maintaining the new hydrant fire flow guess when the new hydrant fire flow guess is in an adequate search direction; and
(2) overriding the new hydrant fire flow guess when the new hydrant fire flow guess is not in an adequate search direction, wherein the overriding utilizes a heuristic method;
(v) assigning the new hydrant fire flow guess as a hydrant demand of the fire hydrant of interest;
(vi) updating a network pressure value and a network flow value;
(vii) evaluating whether the set of constraints has been satisfied;
(viii) reducing the new hydrant fire flow guess if at least one constraint in the set of constraints has been violated;
(ix) increasing the new hydrant fire flow guess if all of the constraints in the set of constraints have been satisfied;
(x) evaluating the new hydrant fire flow guess for convergence; and
(xi) breaking if there is convergence and returning to step (ii) if convergence has not resulted.

### Claim 12 (depends on 11)

The computer-implemented system of claim 11, wherein the base conditions comprise:
a static demand comprising a normal water flow demand for normal water operations;
a user-defined fire demand comprising an emergency demand a user estimates will occur during a fire emergency; and
an available fire demand comprising a maximum flow that can be extracted from the fire hydrant without lowering its pressure below a given value.

### Claim 13 (depends on 11)

The computer-implemented system of claim 11, wherein the critical element is identified by prioritizing:
violated constraints in the set of constraints; and
a relative pressure distance to the minimum pressure threshold value; and
a relative velocity distance to the maximum velocity threshold value.

### Claim 14 (depends on 11)

The computer-implemented system of claim 11, wherein the determining the new hydrant fire flow guess based on a physical-based heuristic comprises:
determining a predefined number of prior hydrant fire flow guesses and prior values from the critical element;
adjusting a quadratic polynomial to the predefined number of values with the new hydrant fire flow guess as a dependent value;
solving the quadratic polynomial to determine the new hydrant fire flow guess, wherein when a quadratic value solution is equal to the minimum pressure threshold value, the quadratic value solution is determined as the new hydrant fire flow guess; and
returning the new hydrant fire flow guess.

### Claim 15 (depends on 11)

The computer-implemented system of claim 11, further comprising:
determining the adequate search direction based on whether the first constraint or the second constraint in the set of constraints has been violated, wherein:
the adequate search direction provides for a reduced flow when the first constraint or the second constraint is violated; and
the adequate search direction provides for an increased flow when the first constraint and the second constraint are satisfied.

### Claim 16 (depends on 15)

The computer-implemented system of claim 15, wherein the heuristic method comprises:
determining an old change as a difference between two prior hydrant fire flow guesses;
determining a new guess change as a difference between a prior hydrant fire flow guess and the new hydrant fire flow guess;
determining if the new flow guess change is proportional to the old change;
increasing the new hydrant fire flow guess change and overriding the new hydrant fire flow guess based on the increase if in a same direction; and
decreasing the new hydrant fire flow guess change and overriding the new hydrant fire flow guess based on the decrease if in an opposite direction.

### Claim 17 (depends on 11)

The computer-implemented system of claim 11, wherein the network pressure value and network flow value are updated using head and flow estimation steps of a hydraulic analysis.

### Claim 18 (depends on 11)

The computer-implemented system of claim 11, wherein there is convergence when:
global gradient algorithm (GGA) stopping criteria have been met;
all constraints in the set of constraints have been satisfied; and
the new hydrant fire flow guess is within a threshold distance of a prior hydrant fire flow guess from a last iteration.

### Claim 19 (depends on 11)

The computer-implemented system of claim 11, wherein:
the hydrant fire flow is performed for each hydrant in a single loop that simultaneously solves for the hydrant fire flow and hydraulic conditions present when the hydrant fire flow occurs.

### Claim 20 (depends on 11)

The computer-implemented system of claim 11, further comprising:
repeating steps (i)-(xi) for all fire hydrants in the water network model;
updating a physical manifestation of the water network model based on the new hydrant fire flow guesses.
