# US 11,112,138 B2 · Air-conditioning control method and air-conditioning control device

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

- Number: US 11,112,138 B2
- Document ID: US11112138B2
- Status: Granted
- Kind: B2
- Application number: 16/212,159
- Filed: 2018-12-06
- Published: 2019-06-13
- Granted: 2021-09-07
- Earliest claimed: 2017-12-08
- Assignees: Panasonic Intellectual Property Management Co., Ltd.
- Applicants: Panasonic Intellectual Property Management Co., Ltd.
- Inventors: Taiji Sasaki; Hiroko Sugimoto; Minghao Ni
- Web page: https://patentgrep.com/patent/US11112138B2

## CPC

- F24F 11/38: Failure diagnosis
- F24F 11/0008: {for air-humidification (F24F11/30 takes precedence)}
- F24F 11/56: Remote control
- F24F 11/65: for selecting an operating mode
- G05B 13/0265: {the criterion being a learning criterion}
- G05B 13/048: {using a predictor}
- F24F 2110/10: Temperature
- F24F 2110/12: of the outside air
- F24F 2110/20: Humidity
- F24F 2110/64: Airborne particle content
- F24F 2120/12: Position of occupants
- F24F 2130/10: Weather information or forecasts
- F25B 2700/02: Humidity
- F25B 2700/2104: of an indoor room or compartment
- 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)
- 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)
- F25B: REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS

## Abstract

An air-conditioning control method includes: acquiring a first sensor value measured by a first sensor device provided at a different position within an identical space to a second sensor device at a first frequency; acquiring a second sensor value measured by the second sensor device at a second frequency, wherein the second frequency is higher than the first frequency; generating a first sensor predicted value from the second sensor value based on a correlation between the first sensor value and the second sensor value in a period in which the second sensor value is acquired and the first sensor value is not acquired; and determining an operation of an air-conditioning apparatus based on the first sensor predicted value.

## Claims

### Claim 1

An air-conditioning control method comprising:
periodically acquiring, by a processor and from a first sensor device at a predetermined communication frequency, a first sensor value transmitted by the first sensor device at the predetermined communication frequency, the first sensor device being provided at a different position than a second sensor device within a same space, the first sensor device including a memory that stores the measured first sensor value before transmitting to the processor;
periodically acquiring, by the processor and from the second sensor device at a predetermined measuring frequency, a second sensor value that is measured the predetermined measuring frequency, wherein the second predetermined measuring frequency is higher than the predetermined communication frequency;
determining, by the processor, whether or not the first sensor value is acquired from the first sensor device;
in response to determining that the first sensor value is acquired, performing machine learning of a prediction model by the processor based on a correlation between the first sensor value and the second sensor value;
determining, by the processor, whether or not the second sensor value is acquired;
in response to determining that the second sensor value is acquired, generating a first sensor predicted value from the second sensor value by the processor using the prediction model in a period in which the second sensor value is acquired and the first sensor value is not acquired;
determining, by the processor, an operation of an air-conditioning apparatus based on the first sensor predicted value; and
controlling, by the processor, the air-conditioning apparatus based on the determined operation,
wherein the air-conditioning control method further comprises changing the first predetermined communication frequency by using the first sensor predicted value and the first sensor value, and
the processor periodically acquires, from the first sensor device at the changed predetermined communication frequency, the first sensor value transmitted by the first sensor device at the changed predetermined communication frequency,
wherein the first sensor device measures the first sensor value at the predetermined measuring frequency, and stores in the memory of the first sensor device, such that a plurality of first sensor values are stored in the memory of the first sensor device before transmitting to the processor at the predetermined communication frequency,
in each of the periodically acquiring at the predetermined communication frequency, the processor acquires, from the first sensor device, a number of first sensor values among the plurality of first sensor values stored in the memory of the first sensor device, wherein the number of the first sensor values acquired includes at least two first sensor values,
the processor changes a number of first sensor values to acquire in a subsequent acquiring of the periodically acquiring of the first sensor value, by using the first sensor predicted value and a number of first sensor values acquired in a current acquiring, and
in the subsequent acquiring of the periodically acquiring at the predetermined communication frequency, the processor acquires, from the first sensor device, the changed number of first sensor values transmitted by the first sensor device.

### Claim 2 (depends on 1)

The air-conditioning control method according to claim 1, wherein
the first sensor value, the second sensor value, and the first sensor predicted value include at least one of a temperature, humidity, and a quantity of particulate matter.

### Claim 3 (depends on 1)

The air-conditioning control method according to claim 1, wherein
the changing of the predetermined communication frequency includes changing the predetermined communication frequency based on a difference between the first sensor value measured at a time in a past and the first sensor predicted value generated from the second sensor value acquired at the same time as when the first sensor value was measured in the past.

### Claim 4 (depends on 1)

The air-conditioning control method according to claim 1, wherein
the machine learning of the prediction model is performed further based on the first sensor predicted value.

### Claim 5 (depends on 1)

The air-conditioning control method according to claim 1, wherein
the prediction model includes a plurality of the prediction models learned by learning methods different from each other, and
the air-conditioning control method further comprises determining each of the prediction models to use from the plurality of prediction models by using the first sensor predicted value and the first sensor value.

### Claim 6 (depends on 1)

The air-conditioning control method according to claim 1, further comprising
detecting an abnormality of the first sensor device by using the first sensor predicted value and the first sensor value.

### Claim 7 (depends on 1)

The air-conditioning control method according to claim 1, further comprising
correcting the first sensor predicted value by using a difference between the first sensor value in a past and the first sensor predicted value generated from the second sensor value acquired in the past.

### Claim 8 (depends on 1)

The air-conditioning control method according to claim 1, further comprising
acquiring an operating state of the air-conditioning apparatus,
wherein the correlation includes a correlation among the first sensor value, the second sensor value, and the operating state of the air-conditioning apparatus.

### Claim 9 (depends on 1)

The air-conditioning control method according to claim 1, further comprising
acquiring weather information indicating a weather condition outside a space in which the first sensor device and the second sensor device are installed,
wherein the first sensor device and the second sensor device are installed at different positions in the same space, and
the correlation includes a correlation among the first sensor value, the second sensor value, and the weather information.

### Claim 10

An air-conditioning control device comprising:
a memory that stores instructions; and
a processor, when executing the instructions stored in the memory, that performs operations including:
periodically acquiring, from a first sensor device at a predetermined communication frequency, a first sensor value transmitted by the first sensor device at the predetermined communication frequency, the first sensor device being provided at a different position than a second sensor device in a same space, the first sensor device including a memory that stores the measured first sensor value before transmitting to the processor;
periodically acquiring, from the second sensor device at a predetermined measuring frequency, a second sensor value that is measured at the predetermined measuring frequency, wherein the predetermined measuring frequency is higher than the predetermined communication frequency;
determining whether or not the first sensor value is acquired from the first sensor device;
in response to determining that the first sensor value is acquired, performing machine learning of a prediction model based on a correlation between the first sensor value and the second sensor value;
determining whether or not the second sensor value is acquired;
in response to determining that the second sensor value is acquired, generating a first sensor predicted value from the second sensor value by using the prediction model in a period in which the second sensor value is acquired and the first sensor value is not acquired;
determining an operation of an air-conditioning apparatus based on the first sensor predicted value; and
controlling the air-conditioning apparatus based on the determined operation,
wherein the processor further changes the predetermined communication frequency by using the first sensor predicted value and the first sensor value, and
the processor periodically acquires, from the first sensor device at the changed predetermined communication frequency, the first sensor value transmitted by the first sensor device at the changed predetermined communication frequency,
wherein the first sensor device measures the first sensor value at the predetermined measuring frequency, and stores in the memory of the first sensor device, such that a plurality of first sensor values are stored in the memory of the first sensor device before transmitting to the processor at the predetermined communication frequency,
in each of the periodically acquiring at the predetermined communication frequency, the processor acquires, from the first sensor device, a number of first sensor values among the plurality of first sensor values stored in the memory of the first sensor device, wherein the number of the first sensor values acquired includes at least two first sensor values,
the processor changes a number of first sensor values to acquire in a subsequent acquiring of the periodically acquiring of the first sensor value, by using the first sensor predicted value and a number of first sensor values acquired in a current acquiring, and
in the subsequent acquiring of the periodically acquiring at the predetermined communication frequency, the processor acquires, from the first sensor device, the changed number of first sensor values transmitted by the first sensor device.

### Claim 11 (depends on 1)

The air-conditioning control method according to claim 1, further comprising:
acquiring an operating state of the air-conditioning apparatus and weather information outside a space in which the first sensor device and the second sensor device are installed; and
determining whether or not the operating state of the air-conditioning apparatus and the weather information are acquired;
wherein in response to determining that the second sensor value, the operating state and the weather information are acquired, the first sensor predicted value is generated from the second sensor value by using the prediction model based on a correlation between the first sensor value, the second sensor value, the operating state and the weather information.

### Claim 12 (depends on 1)

The air-conditioning control method according to claim 1, further comprising:
in response to determining that the first sensor value is acquired from the first sensor device,
storing, by the processor, the acquired first sensor value into a storage; and
setting, by the processor, a learning flag as true,
wherein, the machine learning of the prediction model is performed, in a case where the learning flag is set as true.

### Claim 13 (depends on 1)

The air-conditioning control method according to claim 1, further comprising:
in response to determining that the second sensor value is acquired,
storing, by the processor, the acquired second sensor value into a storage; and
setting, by the processor, a prediction flag as true,
wherein, the first sensor predicted value is generated, in a case where the prediction flag is set as true.

### Claim 14 (depends on 1)

The air-conditioning control method according to claim 1, further comprising calculating a difference between the first sensor predicted value and the first sensor value,
wherein the processor changes the predetermined communication frequency when the calculated difference is greater than a predetermined threshold value, and
the processor periodically acquires, from the first sensor device at the changed predetermined communication frequency, the first sensor value transmitted by the first sensor device at the changed predetermined communication frequency.
