# US 2019/0376715 A1 · Ventilation system with automatic flow balancing derived from a neural network and methods of use

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

- Number: US 2019/0376715 A1
- Document ID: US20190376715A1
- Status: Published application
- Kind: A1
- Application number: 16/438,066
- Filed: 2019-06-11
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Broan-NuTone LLC
- Applicants: Broan-Nutone LLC
- Inventors: Simon Blanchard
- Web page: https://patentgrep.com/patent/US20190376715A1

## CPC

- F24F 11/63: Electronic processing
- F24F 11/0001: {for ventilation (F24F11/30 takes precedence)}
- F24F 11/77: by controlling the speed of ventilators
- F24F 12/001: {with heat-exchange between supplied and exhausted air}
- F24F 12/006: {using an air-to-air heat exchanger (F24F12/002 takes precedence)}
- Y02B 30/56: Heat recovery units
- Y02B 30/70: Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
- F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02)
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS

## Abstract

A ventilation system with automatic flow balancing derived from a neural network to consistently achieve a desired flow rate for inlet flow and/or outlet flow in various operating environments to optimize system performance. The system includes a ventilation device that includes an exhaust blower assembly with a blower motor and a control circuit having a mathematical equation that determines an estimated exhaust blower flow based upon select inputs. The ventilation device also includes a supply blower assembly with a blower motor and control circuit having a mathematical equation that determines an estimated supply blower flow based upon select inputs. When the estimated exhaust blower flow is different than an exhaust flow set point, the exhaust control circuit selectively alters power supplied to the exhaust motor. When the estimated supply blower flow is different than a supply flow set point, the supply control circuit selectively alters power supplied to the supply motor.

## Claims

### Claim 1

A ventilation system with automatic flow balancing derived from a neural network, the ventilation system comprising:
a ventilation device lacking a pressure sensor, the ventilation device including:
an exhaust blower assembly includes an exhaust blower motor and an exhaust control circuit, said exhaust control circuit having an exhaust mathematical equation that determines an estimated exhaust blower air flow for the exhaust blower assembly based upon the following inputs: (i) exhaust air path parameters derived from the use of a neural network, (ii) exhaust blower motor speed, and (iii) exhaust blower motor current;
a supply blower assembly includes a supply blower motor and a supply control circuit, said supply control circuit having a supply mathematical equation that determines an estimated supply blower air flow for the supply blower assembly based upon the following inputs: (i) supply air path parameters derived from the use of a neural network, (ii) supply blower motor speed, and (iii) supply blower motor current;
wherein when the estimated exhaust blower air flow is different than an exhaust air flow set point, the exhaust control circuit being configured to selectively alter power supplied to the exhaust blower motor in order to make the estimated exhaust blower air flow equal to the exhaust air flow set point; and
wherein when the estimated supply blower air flow is different than a supply air flow set point, the supply control circuit being configured to selectively alter power supplied to the supply blower motor in order to make the estimated supply blower air flow equal to the supply air flow set point.

### Claim 2 (depends on 1)

The ventilation system of claim 1, wherein the ventilation device is either a heat recovery ventilator or an energy recovery ventilator.

### Claim 3 (depends on 1)

The ventilation system of claim 1, wherein the exhaust and supply air path parameters are determined at a first location and the ventilation device is configured to be installed at a second location, said second location is different from the first location.

### Claim 4 (depends on 1)

The ventilation system of claim 1, wherein (i) the exhaust air path parameters are outputs of the neural network that is trained using an exhaust blower map, and (ii) the supply air path parameters are outputs of the neural network that is trained using a supply blower map.

### Claim 5 (depends on 4)

The ventilation system of claim 4, wherein in a test environment, (i) the exhaust blower map is generated from exhaust measured values recorded at various operating points of the exhaust blower assembly, and (ii) the supply blower map is generated from supply measured values recorded at various operating points of the supply blower assembly.

### Claim 6 (depends on 5)

The ventilation system of claim 5, wherein the exhaust measured values include: (i) current of the exhaust blower motor, (ii) speed of the exhaust blower motor, and (iii) exhaust air flow generated by the exhaust blower motor.

### Claim 7 (depends on 6)

The ventilation system of claim 6, wherein the supply measured values include: (i) current of the supply blower motor, (ii) speed of the supply blower motor, and (iii) supply air flow generated by the supply blower motor.

### Claim 8 (depends on 7)

The ventilation system of claim 7, wherein the estimated exhaust blower air flow is within 5% of the measured exhaust air flow generated by the exhaust blower motor and the estimated supply blower air flow is within 5% of the measured supply air flow generated by the blower motor.

### Claim 9 (depends on 1)

The ventilation system of claim 1, wherein the estimated exhaust blower air flow is calculated using the following exhaust mathematical equation Flow(X)=Sig(Sig(Sig(X·W1+B1)·W2+B2), where:
the exhaust air path parameters are W1-W3 and B1-B3,
X is an input matrix, which includes the speed of the exhaust blower motor in RPMs and the current of the exhaust blower motor in Amps, and
Sig is an activation function, which is
Sig

(
z
)
=
2
1
+
e
-
2


z
+
1.

### Claim 10 (depends on 9)

The ventilation system of claim 9, wherein the exhaust air path parameters W1-W3 and B1-B3 are:
W
1
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
12
⋯
w
62
]


B
1
=
[
b
1
⋯
b
6
]
W
2
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
16
⋯
w
66
]


B
2
=
[
b
1
⋯
b
6
]
W
3
=
[
w
1
⋮
w
6
]


B
3
=
[
b


1
]

### Claim 11 (depends on 1)

The ventilation system of claim 1, wherein the estimated supply blower air flow is calculated using the following exhaust mathematical equation Flow(X)=Sig(Sig(Sig(X·W1+B1)·W2+B2), where:
the supply air path parameters are W1-W3 and B1-B3,
X is an input matrix, which includes the speed of the supply blower motor in RPMs and the current of the supply blower motor in Amps, and
Sig is an activation function, which is
Sig

(
z
)
=
2
1
+
e
-
2


z
+
1.

### Claim 12 (depends on 11)

The ventilation system of claim 11, wherein the supply air path parameters W1-W3 and B1-B3 are:
W
1
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
12
⋯
w
62
]


B
1
=
[
b
1
⋯
b
6
]
W
2
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
16
⋯
w
66
]


B
2
=
[
b
1
⋯
b
6
]
W
3
=
[
w
1
⋮
w
6
]


B
3
=
[
b


1
]

### Claim 13 (depends on 1)

The ventilation system of claim 1, wherein the supply and exhaust air flow set points are specified by a system user via a controller.

### Claim 14

A ventilation system with automatic flow balancing derived from a neural network, the ventilation system comprising:
a ventilation device lacking a pressure sensor, but including:
a first blower assembly including a blower motor and a control circuit, said control circuit having a first mathematical equation;
wherein the first mathematical equation determines an estimated blower air flow for the first blower assembly based upon the following inputs: (i) air path parameters of the blower motor that are derived from the use of a neural network, (ii) blower motor speed, and (iii) blower motor current;
wherein when the estimated blower air flow is different than an air flow set point determined by a user of the ventilation system, the control circuit being configured to selectively alter power supplied to the blower motor in order to make the estimated blower air flow equal to the air flow set point.

### Claim 15 (depends on 14)

The ventilation system of claim 14, wherein the ventilation device is an air exchanger.

### Claim 16 (depends on 14)

The ventilation system of claim 14, wherein the ventilation device is selected from a group of ventilation devices consisting of: (i) heat recovery ventilator, (ii) energy recovery ventilator, (iii) range hood, (iv) bathroom exhaust fan, and (v) supply fan.

### Claim 17 (depends on 14)

The ventilation system of claim 14, wherein the air path parameters of the blower motor are determined at a first location and the ventilation device is configured to be installed at a second location, said second location is different from the first location.

### Claim 18 (depends on 14)

The ventilation system of claim 14, wherein the air path parameters of the blower motor are outputs of the neural network that is trained using a blower map of the blower motor.

### Claim 19 (depends on 18)

The ventilation system of claim 18, wherein in a test environment, the blower map of the blower motor is generated from measured values recorded at various operating points of the first blower assembly.

### Claim 20 (depends on 19)

The ventilation system of claim 19, wherein the measured values include: (i) current of the blower motor, (ii) speed of the blower motor, and (iii) air flow generated by the blower motor.

### Claim 21 (depends on 19)

The ventilation system of claim 19, wherein the estimated blower air flow is within 5% of the measured air flow generated by the blower motor.

### Claim 22 (depends on 14)

The ventilation system of claim 14, wherein the estimated blower air flow is calculated using the following first mathematical equation Flow(X)=Sig(Sig(Sig(X·W1+B1)·W2+B2), where:
the air path parameters are W1-W3 and B1-B3,
X is an input matrix, which includes the speed of the blower motor in RPMs and the current of the blower motor in Amps, and
Sig is an activation function, which is
Sig

(
z
)
=
2
1
+
e
-
2


z
+
1.

### Claim 23 (depends on 22)

The ventilation system of claim 22, wherein the air path parameters W1-W3 and B1-B3 are:
W
1
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
12
⋯
w
62
]


B
1
=
[
b
1
⋯
b
6
]
W
2
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
16
⋯
w
66
]


B
2
=
[
b
1
⋯
b
6
]
W
3
=
[
w
1
⋮
w
6
]


B
3
=
[
b


1
]

### Claim 24 (depends on 14)

The ventilation system of claim 14, wherein the first blower assembly is an exhaust blower assembly and the air path parameters of the blower motor are exhaust air path parameters, and wherein the ventilation device further includes:
a second blower assembly is a supply blower assembly having a supply blower motor and a supply control circuit, said supply control circuit having a second mathematical equation;
wherein the second mathematical equation determines an estimated supply blower air flow for the supply blower assembly based upon the following inputs: (i) supply air path parameters derived from the use of a supply neural network, (ii) supply blower motor speed, and (iii) supply blower motor current;
wherein when the estimated supply blower air flow is different than an supply air flow set point, the supply control circuit being configured to selectively alter power supplied to the supply blower motor in order to make the estimated supply blower air flow equal to the supply air flow set point.

### Claim 25 (depends on 24)

The ventilation system of claim 24, wherein the ventilation device is either a heat recovery ventilator or an energy recovery ventilator.

### Claim 26 (depends on 24)

The ventilation system of claim 24, wherein the supply air path parameters are determined at a first location and the ventilation device is configured to be installed at a second location, said second location is different from the first location.

### Claim 27 (depends on 24)

The ventilation system of claim 24, wherein the supply air path parameters are outputs the supply neural network that is trained using a supply blower map.

### Claim 28 (depends on 27)

The ventilation system of claim 27, wherein the supply blower map is generated based up measured values recorded at various operating points for the supply blower assembly.

### Claim 29 (depends on 28)

The ventilation system of claim 28, wherein in a test environment the measured values include: (i) current of the supply blower motor, (ii) speed of the supply blower motor, (iii) air flow generated by the supply blower motor.

### Claim 30 (depends on 29)

The ventilation system of claim 29, wherein the estimated supply blower air flow is within 5% of the measured supply air flow generated by the supply blower motor.

### Claim 31 (depends on 29)

The ventilation system of claim 29, wherein the exhaust air path parameters are outputs of the neural network that is trained using an exhaust blower map generated from measured values recorded at various operating points of the first blower assembly, said measured values include: (i) current of the blower motor, (ii) speed of the blower motor, and (iii) air flow generated by the blower motor; and
wherein the estimated blower air flow is within 5% of the measured air flow generated by the blower motor and the estimated supply blower air flow is within 5% of the measured supply air flow generated by the supply blower motor.

### Claim 32 (depends on 14)

The ventilation system of claim 14, wherein the estimated supply blower air flow is calculated using the equation Flow(X)=Sig(Sig(Sig(X·W1+B1)·W2+B2), where:
the supply air path parameters are W1-W3 and B1-B3,
X is an input matrix, which includes the speed of the supply blower motor in RPMs and the current of the supply blower motor in Amps, and
Sig is an activation function, which is
Sig

(
z
)
=
2
1
+
e
-
2


z
+
1.

### Claim 33 (depends on 32)

The ventilation system of claim 32, wherein the supply air path parameters W1-W3 and B1-B3:
W
1
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
12
⋯
w
62
]


B
1
=
[
b
1
⋯
b
6
]
W
2
=
[
w
11
⋯
w
61
⋮
⋱
⋮
w
16
⋯
w
66
]


B
2
=
[
b
1
⋯
b
6
]
W
3
=
[
w
1
⋮
w
6
]


B
3
=
[
b


1
]

### Claim 34 (depends on 14)

The ventilation system of claim 14, wherein the air flow set point is specified by a system user via a controller.
