Indoor environment model creation device

• US 10,353,355 B2
• Filed: 10/28/2015
• Issued: 07/16/2019
• Est. Priority Date: 05/18/2015
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Sawada, Masae, Motodani, Mio, Nakajima, Osamu, Yamamoto, Takaya
• Primary Examiner(s): Wathen, Brian W
• Assistant Examiner(s): Shafayet, Mohammed
• Application Number:
  US15/565,528
• Publication Number:
  US 20180088544A1
• Time in Patent Office: 1,357 Days
• Field of Search: 700300
• CPC Class Codes: F24F 11/0008 for air-humidification F24F11/30 takes precedence
• CPC Class Codes: F24F 11/89 Arrangement or mounting of control or safety devices
• CPC Class Codes: F24F 2110/70 Carbon dioxide
• CPC Class Codes: F24F 2120/10 Occupancy
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 2219/2614 HVAC, heating, ventillation, climate control
• CPC Class Codes: G05D 23/1932 to control the temperature of a plurality of spaces
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass
• CPC Class Codes: Y02P 90/84 Greenhouse gas [GHG] management systems

Abstract

An indoor environment model creation device is configured to create an indoor environment model of an indoor space in which air-conditioning equipment configured to condition air, an indoor humidity sensor configured to measure an indoor humidity of the indoor space, and a CO₂ sensor configured to measure a CO₂ concentration in the indoor space are installed. The indoor environment model includes a plurality of physics models in which heat, moisture, and CO₂ concentration parameters are included. The indoor environment model creation device includes: a data storage unit configured to store operation data of the air-conditioning equipment in a learning target period as learning-use input data, and store measurement data measured by the CO₂ sensor and the humidity sensor; and a model parameter learning unit configured to comprehensively learn the plurality of physics models with use of the learning-use input data and the measurement data, which are stored in the data storage unit.

Claims

1. An indoor environment model creation device configured to create an indoor environment model of an indoor space in which air-conditioning equipment, a CO₂ sensor, and a humidity sensor are installed, the air-conditioning equipment being configured to condition air, the CO₂ sensor being configured to measure a CO₂ concentration in the indoor space, the humidity sensor being configured to measure an indoor humidity of the indoor space,

the indoor environment model comprising a physics model including a heat parameter, a physics model including a moisture parameter, and a physics model including a CO₂ concentration parameter,

the indoor environment model creation device comprising:

a memory configured to store operation data of the air-conditioning equipment in a learning target period as learning-use input data, and store measurement data measured by the CO₂ sensor and the humidity sensor; and

processing circuitry configured to comprehensively learn a plurality of physics models with use of the learning-use input data and the measurement data stored in the memory,

wherein the processing circuitry is configured to simultaneously solve a physics model comprising a parameter that is included in common in all of the plurality of physics models and the heat parameter, a physics model comprising a parameter that is common to all of the plurality of physics models and the moisture parameter, and a physics model comprising a parameter that is common to all of the plurality of physics models and the CO₂ concentration parameter, and to perform convergence calculation, to thereby concurrently determine all parameters that are included in all of the plurality of physics models, and learn the physics models.

2. The indoor environment model creation device of claim 1, wherein the plurality of physics models comprise a heat conduction equation, a mass transfer equation about moisture, and a mass transfer equation about the CO₂ concentration.

3. The indoor environment model creation device of claim 2, wherein the plurality of physics models comprise an indoor temperature model expressed by the heat conduction equation, an indoor humidity model expressed by the mass transfer equation about moisture, and a CO₂ concentration model expressed by the mass transfer equation about the CO₂ concentration.

4. The indoor environment model creation device of claim 1,

wherein the plurality of physics models comprise parameters common to one another, and

wherein the processing circuitry is configured to comprehensively learn the common parameters.

5. The indoor environment model creation device of claim 1,

wherein the plurality of physics models comprise parameters classified into design parameters, which represent design elements of the air-conditioning equipment and the indoor space, and operation parameters, which comprise an occupancy parameter about an occupancy ratio, and

wherein the processing circuitry is further configured to

concurrently learn the design parameters in the plurality of physics models, while changing values of the design parameters, with the operation parameters in the plurality of physics models set to fixed values, and

concurrently learn the operation parameters in the plurality of physics models, while changing values of the operation parameters, with the design parameters in the plurality of physics models set to fixed values.

6. The indoor environment model creation device of claim 5, wherein the processing circuitry is configured to learn the indoor environment model only from the operation data and the measurement data.

7. An indoor environment model creation device configured to create an indoor environment model of an indoor space in which air-conditioning equipment, a CO₂ sensor, and a humidity sensor are installed, the air-conditioning equipment being configured to condition air, the CO₂ sensor being configured to measure a CO₂ concentration in the indoor space, the humidity sensor being configured to measure an indoor humidity of the indoor space,

the indoor environment model comprising a physics model including a heat parameter, a physics model including a moisture parameter, and a physics model including a CO₂ concentration parameter,

the indoor environment model creation device comprising:

a memory configured to store operation data of the air-conditioning equipment in a learning target period as learning-use input data, and store measurement data measured by the CO₂ sensor and the humidity sensor; and

a processing circuitry configured to comprehensively learn a plurality of physics models with use of the learning-use input data and the measurement data stored in the memory,

wherein the plurality of physics models consist of a physics model comprising a parameter that is included in common in all of the plurality of physics models and the heat parameter, a physics model comprising a parameter that is common to all of the plurality of physics models and the moisture parameter, and a physics model comprising a parameter that is common to all of the plurality of physics models and the CO₂ concentration parameter, and

wherein the processing circuitry is configured to first select some of the plurality of physics models as a learning target, and learn the parameter that is included in common in all of the plurality of physics models and a parameter that is uniquely included in a target physics model, and, in learning of the remaining physics models, the processing circuitry is configured to set thus first learned value as a value of a parameter common to all physics models and learn, for each of the remaining physics models, only a parameter uniquely included in each of the remaining physics models.

8. The indoor environment model creation device of claim 7, wherein the processing circuitry is configured to learn, in three or more stages, a parameter common to all of the plurality of physics models, and a parameter uniquely included in each of the plurality of physics models.

9. A method, implemented by an indoor environment model creation device configured to create an indoor environment model of an indoor space in which air-conditioning equipment, a CO₂ sensor, and a humidity sensor are installed, the air-conditioning equipment being configured to condition air, the CO₂ sensor being configured to measure a CO₂ concentration in the indoor space, the humidity sensor being configured to measure an indoor humidity of the indoor space,

the indoor environment model comprising a physics model including a heat parameter, a physics model including a moisture parameter, and a physics model including a CO₂ concentration parameter,

the method comprising:

storing, at a memory, operation data of the air-conditioning equipment in a learning target period as learning-use input data, and storing measurement data measured by the CO₂ sensor and the humidity sensor; and

comprehensively learn a plurality of physics models with use of the learning-use input data and the measurement data stored in the memory,

wherein the method includes simultaneously solving a physics model comprising a parameter that is included in common in all of the plurality of physics models and the heat parameter, a physics model comprising a parameter that is common to all of the plurality of physics models and the moisture parameter, and a physics model comprising a parameter that is common to all of the plurality of physics models and the CO₂ concentration parameter, and performing convergence calculation, to thereby concurrently determine all parameters that are included in all of the plurality of physics models, and learn the physics models.