JP7372630B2 - Estimation device, estimation method and program - Google Patents

Description

The present invention relates to an estimation device, an estimation method, and a program.

Various methods have been proposed for estimating the heating and cooling capacity (hereinafter referred to as "air conditioning capacity") of an air conditioner (hereinafter referred to as "air conditioner"). For example, Patent Document 1 discloses an air conditioning capacity estimating device that estimates air conditioning capacity using an air enthalpy method from data such as suction temperature, suction humidity, blowout temperature, blowout humidity, and air volume of an indoor unit.

JP2019-86243A

As in the invention disclosed in Patent Document 1, the air enthalpy method, the compressor curve method, and the like are generally used to estimate air conditioning capacity. However, these methods require parameters to be measured under a strict measurement environment (laboratory), and cannot be called simple methods.

One aspect of the present invention is to provide an estimation device or the like that can suitably perform simple measurement of air conditioning capacity.

An estimation device according to one aspect includes an acquisition unit that acquires refrigerant temperatures at multiple locations from temperature sensors attached to multiple locations on refrigerant piping in an outdoor unit of an air conditioner; an estimating unit that estimates the air conditioning capacity from the acquired refrigerant temperatures at the plurality of locations using a model that has learned the air conditioning capacity of the air conditioner, a third acquisition unit that acquires the rated capacity of the air conditioner to be estimated, and the model. The present invention is characterized by comprising a correction unit that corrects the air conditioning capacity estimated by the estimation unit based on the rated capacity of the air conditioner that is the learning target and the rated capacity of the air conditioner that is the estimation target.

In one aspect, air conditioning capacity can be easily measured.

FIG. 1 is a schematic diagram showing a configuration example of an air conditioning capacity estimation system. FIG. 2 is a block diagram showing a configuration example of a server. It is an explanatory view showing an example of the record layout of air conditioning DB and measurement value DB. It is an explanatory diagram regarding an estimation model. It is an explanatory diagram showing a Mollier diagram. It is an explanatory view showing an example of a display screen of an estimation result of air conditioning capacity. 3 is a flowchart illustrating a procedure for generating an estimated model. It is a flowchart which shows the procedure of estimation processing of air conditioning capacity. FIG. 2 is a block diagram illustrating a configuration example of a server according to Embodiment 2. FIG. FIG. 2 is an explanatory diagram showing an example of a record layout of a model DB. FIG. 7 is an explanatory diagram showing an example of a display screen of an estimation result of air conditioning capacity according to Embodiment 2; 7 is a flowchart illustrating a procedure for estimating air conditioning capacity according to Embodiment 2. FIG.

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below based on drawings showing embodiments thereof.
(Embodiment 1)
FIG. 1 is a schematic diagram showing a configuration example of an air conditioning capacity estimation system. In this embodiment, an air conditioning capacity estimation system for estimating the air conditioning capacity of the air conditioner 3 will be described. The air conditioning capacity estimation system includes an estimation device 1, a terminal 2, a gateway 35, and the like. Each device is communicatively connected to a network N such as the Internet.

The estimation device 1 is an information processing device capable of various information processing and transmission/reception of information, and is, for example, a server computer, a personal computer, or the like. In this embodiment, the estimation device 1 is assumed to be a server computer, and will be read as server 1 below. The server 1 estimates the air conditioning capacity of the air conditioner 3 installed in a predetermined facility, and outputs the estimation result to the terminal 2.

The air conditioner 3 is a central type air conditioner having, for example, one outdoor unit 31 and a plurality of indoor units 32 installed in each room in a predetermined facility, and is used for commercial purposes, for example. Note that the air conditioner 3 may be a distributed air conditioner in which one indoor unit 32 is connected to one outdoor unit 31. As will be described later, the server 1 calculates the refrigerant temperature measured by the temperature sensor 33 attached to the refrigerant pipe inside the outdoor unit 31 of the air conditioner 3, and the current value of the operating current of the outdoor unit 31 measured by the current sensor 34. is obtained via the gateway 35. Then, the server 1 estimates the air conditioning capacity from the refrigerant temperature and current value of the outdoor unit 31 using the estimation model 141 (see FIG. 4) that has been trained using teacher data by machine learning.

In this embodiment, it is assumed that the server 1 on the cloud performs the air conditioning capacity estimation process, but the estimation model 141 is installed on a local computer (for example, the terminal 2 in FIG. 1) to locally estimate the air conditioning capacity. You may do so.

The terminal 2 is a terminal device used by, for example, an administrator of a facility where the air conditioner 3 is installed, and is a personal computer, a tablet terminal, a smartphone, or the like. The server 1 outputs the estimation result of the air conditioning capacity to the terminal 2 and presents it to the facility manager.

The temperature sensor 33 is a thermometer attached inside the outdoor unit 31, and is a sensor that measures the temperature of the refrigerant flowing in the refrigerant pipe. Note that the temperature sensor 33 may be attached by an operator only during the simple measurement according to the present embodiment, or may be always installed. For example, the temperature sensor 33 is a thermometer using a thin film thermocouple, and a sensing portion (metal wire) is attached to the surface of the refrigerant pipe to measure the surface temperature of the refrigerant pipe. Note that the temperature sensor 33 is not limited to a sensor using a thin film thermocouple, and may be any other thermometer. In this embodiment, a plurality of temperature sensors 33 are respectively attached to a plurality of locations on the refrigerant piping, and each temperature sensor 33 measures the temperature of the refrigerant flowing to each location.

The current sensor 34 is an ammeter that measures the operating current of the outdoor unit 31, and is, for example, a wireless current sensor capable of wirelessly communicating with the outside. The current sensor 34 measures a current value by self-supplying power from the outdoor unit 31 that is the measurement target, and transmits the measurement result to the outside using a wireless communication standard such as Bluetooth (registered trademark).

FIG. 2 is a block diagram showing an example of the configuration of the server 1. As shown in FIG. The server 1 includes a control section 11 , a main storage section 12 , a communication section 13 , and an auxiliary storage section 14 .
The control unit 11 has one or more arithmetic processing units such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), and a GPU (Graphics Processing Unit), and processes the program P stored in the auxiliary storage unit 14. By reading and executing, various information processing, control processing, etc. are performed. The main memory unit 12 is a temporary storage area such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), flash memory, etc., and temporarily stores data necessary for the control unit 11 to perform arithmetic processing. Remember. The communication unit 13 is a communication module for performing processing related to communication, and sends and receives information to and from the outside.

The auxiliary storage unit 14 is a nonvolatile storage area such as a large capacity memory or a hard disk, and stores the program P and other data necessary for the control unit 11 to execute processing. Further, the auxiliary storage unit 14 stores an estimated model 141, an air conditioning DB 142, and a measured value DB 143. The estimated model 141 is a model generated by machine learning as described above, and is, for example, a neural network. The air conditioning DB 142 is a database that stores information about the air conditioner 3 in which the temperature sensor 33 and the current sensor 34 are installed. The measured value DB 143 is a database that stores measurement results of refrigerant temperature and current value.

Note that the auxiliary storage unit 14 may be an external storage device connected to the server 1. Further, the server 1 may be a multicomputer consisting of a plurality of computers, or may be a virtual machine virtually constructed by software.

Further, in this embodiment, the server 1 is not limited to the above configuration, and may include, for example, an input section that receives operation input, a display section that displays images, and the like. The server 1 also includes a reading unit that reads a portable storage medium 1a such as a CD (Compact Disk)-ROM or a DVD (Digital Versatile Disc)-ROM, and is configured to read and execute the program P from the portable storage medium 1a. You can also do it. Alternatively, the server 1 may read the program P from the semiconductor memory 1b.

FIG. 3 is an explanatory diagram showing an example of the record layout of the air conditioning DB 142 and the measured value DB 143.
The air conditioning DB 142 includes an air conditioning ID column, an installation facility column, and a rated capacity column. The air conditioning ID column stores air conditioning IDs for identifying the air conditioners 3. The installed facility column and the rated capacity column are associated with the air conditioner ID, respectively, and display the name of the facility where the air conditioner 3 is installed and the rated capacity of the air conditioner 3 (the air conditioning capacity of the air conditioner 3 measured by the air conditioner manufacturer). rated value).

The measured value DB 143 includes a date and time column, an air conditioning column, a temperature column, and a current column. The date and time column stores the date and time when the refrigerant temperature and current value were measured. The air conditioning column, temperature column, and current column each store the air conditioning ID, refrigerant temperature, and current value of the air conditioner 3 to be measured, in association with the date and time. The temperature column stores the temperatures of the evaporator inlet, evaporator outlet, condenser inlet, and condenser outlet of the outdoor unit 31.

FIG. 4 is an explanatory diagram regarding the estimation model 141. Based on FIG. 4, a machine learning process for generating the estimation model 141 and a process for estimating air conditioning capacity using the estimation model 141 will be described.

In this embodiment, the server 1 constructs (generates) a neural network as the estimation model 141. The estimation model 141 includes an input layer that receives input of measured values related to the air conditioner 3, an intermediate layer that performs calculations based on the measured values input to the input layer, and outputs air conditioning capacity based on the calculation results in the intermediate layer. and an output layer. The input layer has a plurality of neurons that accept input of various measurement values, and passes the input measurement values to the intermediate layer. The intermediate layer has a plurality of neurons for performing calculations based on the measured values, and performs calculations for extracting feature amounts from the measured values. Although FIG. 4 shows only one intermediate layer, deep learning may be performed using multiple intermediate layers. The output layer has a neuron that calculates an output value, and outputs an estimated value of air conditioning capacity based on the feature extracted in the intermediate layer. Note that although the output layer has a single neuron in FIG. 4, two (plural) neurons may be prepared separately for estimating the heating capacity and for estimating the cooling capacity.

Note that, for example, the intermediate layer may be a LSTM (Long-Short Term Memory), and the air conditioning capacity may be estimated from measured values at a plurality of points in time. Thereby, air conditioning capacity can be estimated from time-series data.

Further, the estimation model 141 is not limited to a neural network, and may be a model based on other learning algorithms such as SVM (Support Vector Machine), random forest, decision tree, etc., for example.

In this embodiment, the server 1 uses refrigerant temperatures measured at multiple locations on the refrigerant piping of the air conditioner 3 as parameters input to the estimation model 141. Specifically, the server 1 controls the evaporator inlet temperature T _e,i , the evaporator outlet temperature T _{e,o ,} and the condenser inlet temperature T _{c,i .} The refrigerant temperatures at four locations are used as input parameters: inlet temperature) and condenser outlet temperature T _c,o (condenser outlet temperature).

FIG. 5 is an explanatory diagram showing a Mollier diagram. FIG. 5 conceptually illustrates a Mollier diagram representing a refrigerant state change cycle. Note that the horizontal axis represents specific enthalpy (kJ/kg), and the vertical axis represents pressure (MPa). Further, the curves in the figure represent a saturated liquid line and a saturated vapor line of the refrigerant, and the substantially trapezoidal solid line with an arrow represents a change in the state of the refrigerant.

As can generally be understood from the Mollier diagram of FIG. The temperature is raised (B→C), the condenser performs condensation and heat radiation (C→D), and the expansion valve reduces pressure and temperature (D→A). Points A → B in the figure represent the heat absorption process, points C → D represent the heat release process, and points A, B, C, and D represent the evaporator inlet, evaporator outlet, and condenser inlet, respectively. The opening corresponds to the condenser outlet. In this embodiment, the air conditioning capacity is estimated using measured values measured at positions corresponding to these four locations.

Although refrigerant pressure or the like may be used as the measured values at the four locations, in this embodiment, refrigerant temperature, which is relatively easy to measure, is used. Specifically, a temperature sensor 33 using a thin film thermocouple is attached to the surface of the refrigerant pipe to measure the refrigerant temperature at each location. More specifically, a sensing part (metal wire) related to a thin film thermocouple is attached to a flange (not shown) that connects the refrigerant pipe and the evaporator and condenser to measure the refrigerant temperature. This makes it possible to measure input parameters easily and at low cost without requiring construction work such as cutting refrigerant piping or removing heat insulating material.

Note that in this embodiment, the refrigerant temperature is measured at the suction and discharge ports of the evaporator and condenser, but it is sufficient to measure the temperature at a location where changes in the state of the refrigerant can be appropriately estimated. The locations at which the refrigerant temperature is measured are not limited to the four locations mentioned above. Further, the number of measurement points may be two, or may be five or more.

Returning to FIG. 4, the explanation will be continued. In this embodiment, the current value I of the operating current of the outdoor unit 31 is used as an input parameter of the estimation model 141. For example, as described above, the self-powered current sensor 34 (wireless current sensor) is attached to the distribution board that supplies power to the air conditioner 3 (outdoor unit 31), and the current value I is measured. Similarly to T _e,i , T _e,o , T _c,i , and T _c,o described above, the server 1 performs estimation using the current value I, which is relatively easy to measure, and improves the estimation accuracy.

Note that in this embodiment, only the refrigerant temperature and current value are used for simple measurement, but refrigerant pressure, compressor rotation speed, outside temperature, indoor temperature, etc. may also be used as input parameters. Alternatively, the air conditioning capacity may be estimated only from the refrigerant temperature without using the current value.

The server 1 generates the estimation model 141 using the teacher data labeled with the correct value of the air conditioning capacity for the refrigerant temperature and current value of the air conditioner 3 for the teacher. The refrigerant temperature and current value data for the teacher may be data measured by the actual air conditioner 3, or may be data calculated using predetermined simulation software. The server 1 acquires teacher data including the refrigerant temperature, current value, air conditioning capacity (correct value), and the rated capacity of the air conditioner 3 that is the learning target, and performs machine learning.

The server 1 inputs the teacher's refrigerant temperature and current value into the estimation model 141 and estimates the air conditioning capacity of the air conditioner 3. The server 1 compares the estimated value of the air conditioning capacity with the correct value, and optimizes various parameters used in calculations, such as weights between neurons, so that the two approximate each other. As described above, the server 1 generates the estimation model 141. The server 1 stores the generated estimated model 141 in the auxiliary storage unit 14, and also stores the rated capacity of the air conditioner 3 that is the learning target in association with the estimated model 141.

When estimating the air conditioning capacity of the air conditioner 3 to be estimated, the server 1 inputs the refrigerant temperature and current value measured by the temperature sensor 33 and current sensor 34 attached to the outdoor unit 31 to the estimation model 141. For example, the server 1 inputs into the estimation model 141 the peak value, average value, etc. of measured values over a certain period of the past (for example, a period of one day, one month, one year, etc.). The server 1 performs calculations in the intermediate layer from the measured values input to the input layer, and obtains an estimated value of air conditioning capacity from the output layer.

The server 1 corrects the obtained estimated value of air conditioning capacity according to the rated capacity of the air conditioner 3 to be estimated. Naturally, the air conditioning capacity of the air conditioner 3 differs depending on the model and individual. Here, if the rated capacity of the air conditioner 3 to be learned and the rated capacity of the air conditioner 3 to be estimated are originally significantly different, the error in the estimation result will be large. Therefore, the server 1 corrects the estimated value output from the estimation model 141 to reduce the error.

Specifically, the server 1 performs the correction based on the rated capacity of the air conditioner 3 to be estimated and the rated capacity of the air conditioner 3 to be learned when generating the estimation model 141. For example, the server 1 divides the rated capacity of the air conditioner 3 to be estimated by the rated capacity of the air conditioner 3 to be learned, and calculates a scale factor for correcting the estimated value. The server 1 multiplies the estimated value of the air conditioning capacity by the calculated scale factor to calculate a correction value.

In addition, in the above, the ratio of both was simply used as a scale factor for air conditioning capacity correction, but considering the difference in scale between the rated capacity of the air conditioner 3 to be learned and the rated capacity of the air conditioner 3 to be estimated. It is sufficient as long as the estimated value can be corrected, and the calculation method at the time of correction is not particularly limited.

Further, for example, the server 1 may separately learn about a plurality of air conditioners 3 having different rated capacities, and prepare a plurality of estimation models 141 corresponding to each rated capacity. When estimating the air conditioning capacity, the server 1 selects an estimation model 141 whose rated capacity approximates that of the air conditioner 3 to be estimated, and estimates the air conditioning capacity using the selected estimation model 141. In this way, the server 1 only needs to be able to perform estimation according to the rated capacity, and its processing content is not particularly limited.

Further, for example, the server 1 may use the rated capacity of the air conditioner 3 as an input parameter of the estimation model 141 to be able to estimate the current air conditioning capacity in consideration of the rated capacity.

The server 1 outputs the corrected air conditioning capacity estimation result to the terminal 2 and presents it to the administrator of the air conditioner 3. FIG. 6 is an explanatory diagram showing an example of a display screen of the estimation result of air conditioning capacity. For example, the terminal 2 receives the output from the server 1 and displays the screen shown in FIG. Specifically, the terminal 2 records the heating capacity and cooling capacity of the air conditioner 3 in addition to the name of the facility where the air conditioner 3 is installed, the air conditioner ID, the estimated date and time of the air conditioning capacity (measurement period of refrigerant temperature and current value), etc. (and power consumption) are displayed respectively. For example, the terminal 2 displays the estimated value of the air conditioning capacity estimated by the estimation model 141, and also displays the rated capacity of the air conditioner 3 and presents it to the administrator.

Note that, for example, the server 1 may estimate the air conditioning capacity at each point in time from the measured values at each of a plurality of past points in time, and output a time-series change (decrease) in the air conditioning capacity. Thereby, it is possible to present to the administrator how much the air conditioning capacity has changed compared to when the air conditioner 3 was introduced.

As described above, according to the present embodiment, by estimating the air conditioning capacity using the refrigerant temperature and current value, which are relatively easy to measure, the air conditioning capacity can be easily measured.

FIG. 7 is a flowchart showing the procedure for generating the estimation model 141. Based on FIG. 7, the processing contents when generating the estimation model 141 by machine learning will be explained.
The control unit 11 of the server 1 acquires teacher data including the refrigerant temperature and current value, and the air conditioning capacity of the air conditioner 3 (step S11). Specifically, teacher data is obtained in which the correct value of the air conditioning capacity of the air conditioner 3 is labeled with respect to the temperatures at multiple locations of the refrigerant piping of the outdoor unit 31 and the current value of the operating current of the outdoor unit 31.

Based on the acquired teacher data, the control unit 11 generates an estimation model 141 that inputs the refrigerant temperature and current value and outputs the air conditioning capacity (step S12). Specifically, as described above, the control unit 11 generates a neural network as the estimation model 141. The control unit 11 inputs the refrigerant temperatures at multiple locations and the current values into the estimation model 141, and estimates the air conditioning capacity. The control unit 11 compares the estimated value of the air conditioning capacity with the correct value, and optimizes various parameters such as weights so that the two approximate each other. The control unit 11 stores the generated estimation model 141 in the auxiliary storage unit 14 in association with the rated capacity of the air conditioner 3 that is the learning target, and ends the series of processing.

FIG. 8 is a flowchart showing the procedure for estimating air conditioning capacity. Based on FIG. 8, the processing contents when estimating the air conditioning capacity will be explained.
The control unit 11 of the server 1 acquires the measurement results of the refrigerant temperature and current value from the temperature sensor 33 and current sensor 34 attached to the outdoor unit 31 of the air conditioner 3 (step S31). The control unit 11 inputs the acquired refrigerant temperature and current value into the estimation model 141, and estimates the air conditioning capacity of the air conditioner 3 (step S32).

The control unit 11 corrects the air conditioning capacity estimated in step S32 based on the rated capacity of the air conditioner 3 to be learned and the rated capacity of the air conditioner 3 to be estimated (step S33). Specifically, the control unit 11 calculates a scale factor by dividing the rated capacity of the air conditioner 3 to be estimated by the rated capacity of the air conditioner 3 to be learned, and multiplies the estimated value by the calculated scale factor. Calculate the correction value. The control unit 11 outputs the corrected air conditioning capacity estimation result to the terminal 2 (step S34), and ends the series of processing.

As described above, according to the first embodiment, the air conditioning capacity can be easily measured.

Further, according to the first embodiment, the air conditioning capacity can be suitably estimated by using the refrigerant temperature at the inlet and outlet of the evaporator and the inlet and outlet of the condenser.

Further, according to the first embodiment, by using the current value of the outdoor unit 31 in addition to the refrigerant temperature, the air conditioning capacity can be estimated more accurately.

Further, according to the first embodiment, by performing correction according to the rated capacity of the air conditioner 3, the air conditioning capacity can be estimated more accurately.

(Embodiment 2)
In this embodiment, a mode will be described in which updating (replacement) of the air conditioner 3 is recommended based on the estimation result of the air conditioning capacity. Note that the same reference numerals are given to the same content as in the first embodiment, and the explanation thereof will be omitted.

FIG. 9 is a block diagram showing a configuration example of the server 1 according to the second embodiment. The auxiliary storage unit 14 of the server 1 according to the present embodiment stores a model DB 144. The model DB 144 is a database that stores information regarding the air conditioners 3 of multiple models.

FIG. 10 is an explanatory diagram showing an example of the record layout of the model DB 144. The model DB 144 includes a model ID column, a model name column, a rated capacity column, and a price column. The model ID column stores model IDs for identifying the model of the air conditioner 3. The model name column, rated capacity column, and price column each store the model name, rated capacity, and selling price of the air conditioner 3 in association with the model ID.

FIG. 11 is an explanatory diagram showing an example of a display screen of the estimation result of air conditioning capacity according to the second embodiment. An overview of this embodiment will be explained based on FIG. 11.
Similarly to the first embodiment, the server 1 estimates the air conditioning capacity of the air conditioner 3 and presents it to the administrator. In this embodiment, the server 1 further selects a model of the air conditioner 3 whose air conditioning capacity (rated capacity) is lower than the current air conditioner 3 based on the estimated value of the air conditioning capacity, and downgrades the selected air conditioner 3. Recommend sizing (update) to administrator.

Specifically, the server 1 first calculates an allowable value of the air conditioning capacity when selecting a model based on the estimated value of the air conditioning capacity estimated by the estimation model 141. For example, the server 1 multiplies the estimated value by a predetermined coefficient exceeding 1.0 (for example, a value of 1.2 to 1.3) to calculate a lower limit value to be used as a threshold value when selecting a model. Although the allowable value is calculated in consideration of errors and safety when estimating the air conditioning capacity, the estimated value itself may be used as the threshold value. Further, the server 1 may calculate an upper limit value in addition to the lower limit value, and may set a numerical range between the upper limit value and the lower limit value as an allowable value.

The server 1 extracts from the model DB 144 models having a rated capacity greater than or equal to the calculated allowable value. Then, the server 1 selects the model with the lowest rated capacity (air conditioning capacity) among the extracted models as the air conditioner 3 to be recommended to the administrator. Note that the server 1 may select a model by referring not only to the air conditioning capacity but also to the price of the air conditioner 3. Further, the server 1 may select not only the model with the lowest rated capacity but also a plurality of models with the lowest rated capacity. When selecting a plurality of models, for example, the server 1 may recommend (display) the air conditioners 3 of each model in descending order of rated capacity.

The server 1 reads information on the selected model of air conditioner 3 from the model DB 144, and outputs the information together with the estimation result regarding the current air conditioning capacity of the air conditioner 3 to the terminal 2 for display. Specifically, as shown in FIG. 11, the terminal 2 displays the model name, price, etc. of the selected air conditioner 3. Furthermore, the terminal 2 displays the amount of reduction (difference) in the electricity bill due to the model change of the air conditioner 3. For example, the server 1 calculates the power consumption of each air conditioner 3 based on the current air conditioning capacity (estimated value) of the air conditioner 3 and the air conditioning capacity (rated capacity) of the selected model of air conditioner 3. The amount of reduction in electricity charges is calculated from the difference in power consumption and output to the terminal 2. Note that, for example, the server 1 may output a power consumption difference value in addition to or in place of the reduction amount in the electricity bill.

The terminal 2 displays various information including the amount of reduction in electricity charges and recommends updating the air conditioner 3. Note that, for example, the terminal 2 may accept an order for the air conditioner 3 on the screen shown in FIG.

FIG. 12 is a flowchart illustrating a procedure for estimating air conditioning capacity according to the second embodiment. After correcting the estimated value of the air conditioning capacity of the air conditioner 3 (step S33), the server 1 executes the following process.
Based on the estimated value of the air conditioning capacity, the control unit 11 of the server 1 calculates an allowable value (for example, a lower limit value) of the air conditioning capacity when selecting the model of the air conditioner 3 (step S201). The control unit 11 selects the model of the air conditioner 3 to be recommended to the administrator based on the calculated allowable value (step S202). For example, the control unit 11 compares the rated capacity of each model with a permissible value, and extracts models having a permissible value or higher. Then, the control unit 11 selects the model with the lowest rated capacity among the extracted models.

The control unit 11 calculates the amount of reduction in electricity charges required for operating the air conditioner 3 based on the rated capacity of the selected model (step S203). Then, the control unit 11 outputs the estimated value of the current air conditioning capacity of the air conditioner 3, the reduction amount calculated in step S203, the model name of the selected model, the price, etc. to the terminal 2 (step S204), and performs a series of Finish the process.

As described above, according to the second embodiment, updating (downsizing) of the air conditioner 3 can be proposed.

The embodiments disclosed herein are illustrative in all respects and should be considered not to be restrictive. The scope of the present invention is indicated by the claims rather than the above-mentioned meaning, and is intended to include meanings equivalent to the claims and all changes within the scope.

1 Server (estimation device)
11 Control unit 12 Main storage unit 13 Communication unit 14 Auxiliary storage unit P Program 141 Estimation model 142 Air conditioning DB
143 Measurement value DB
144 Model DB
2 Terminal 3 Air conditioner 31 Outdoor unit 32 Indoor unit 33 Temperature sensor 34 Current sensor 35 Gateway

Claims (7)

an acquisition unit that acquires refrigerant temperatures at the plurality of locations from temperature sensors attached to the refrigerant pipes at multiple locations in the outdoor unit of the air conditioner;
an estimation unit that estimates the air conditioning capacity from the obtained refrigerant temperatures at the plurality of places using a model that has learned the refrigerant temperatures at the plurality of places and the air conditioning capacity of the air conditioner ;
a third acquisition unit that acquires the rated capacity of the air conditioner to be estimated;
a correction unit that corrects the air conditioning capacity estimated by the estimation unit based on the rated capacity of the air conditioner that is the learning target of the model and the rated capacity of the air conditioner that is the estimation target;
An estimation device comprising: The acquisition unit acquires the refrigerant from the temperature sensor attached to a position corresponding to an evaporator inlet, an evaporator outlet, a condenser inlet, and a condenser outlet of the outdoor unit. The estimating device according to claim 1, wherein the estimating device obtains temperature. a second acquisition unit that acquires a current value of the operating current from a current sensor that measures the operating current of the outdoor unit;
The estimating device according to claim 1 or 2, wherein the estimator estimates the air conditioning capacity by inputting the refrigerant temperatures at the plurality of locations and the current value into the model. a storage unit that stores information on multiple types of air conditioners including rated capacity;
a selection unit that selects an air conditioner model based on the air conditioning capacity estimated by the estimation unit and the rated capacity of each model of air conditioner;
The estimating device according to any one of claims 1 to 3 , further comprising: an output section that outputs information about the selected model of air conditioner. A calculation unit that calculates an electricity charge or a difference in electricity charges due to a model change of the air conditioner based on the air conditioning capacity estimated by the estimation unit and the rated capacity of the air conditioner of the model selected by the selection unit. ,
The estimation device according to claim 4 , wherein the output unit outputs the electricity rate or a difference between the electricity rates. Obtaining refrigerant temperatures at multiple locations from temperature sensors attached to multiple locations on refrigerant piping in the outdoor unit of the air conditioner;
Using a model that has learned the refrigerant temperatures at the plurality of locations and the air conditioning capacity of the air conditioner, the air conditioning capacity is estimated from the obtained refrigerant temperatures at the plurality of locations ,
Obtain the rated capacity of the air conditioner to be estimated,
Correcting the estimated air conditioning capacity based on the rated capacity of the air conditioner that is the learning target of the model and the rated capacity of the air conditioner that is the estimation target.
An estimation method characterized in that processing is performed by a computer. Obtaining refrigerant temperatures at multiple locations from temperature sensors attached to multiple locations on refrigerant piping in the outdoor unit of the air conditioner;
Using a model that has learned the refrigerant temperatures at the plurality of locations and the air conditioning capacity of the air conditioner, the air conditioning capacity is estimated from the obtained refrigerant temperatures at the plurality of locations ,
Obtain the rated capacity of the air conditioner to be estimated,
Correcting the estimated air conditioning capacity based on the rated capacity of the air conditioner that is the learning target of the model and the rated capacity of the air conditioner that is the estimation target.
A program that causes a computer to perform processing.

Images