Control device, control method, and program

Abstract

To provide a control device which can calculate a heat response parameter in a light algorithm even in the case where only limited calculation resources are loaded.SOLUTION: A control device includes: an extraction unit for extracting elements contained in a monitor section from a predetermined start condition to a finish condition of air conditioning control by an air conditioner by time series data in which an indoor temperature of an air-conditioning target space is measured; a division unit in which elements, during a cooling operation, at and after a time point where the indoor temperature has turned to drop out of the monitor section, and during a heating operation, at and after a time point where the indoor temperature has turned to rise out of the monitor section are made to be the element of primary delay response, and which divides the elements other than the primary delay response out of the monitor section as elements of waste time; and an estimation unit for estimating the length of the waste time as a waste time estimation value, and for estimating a time constant value in which a curve approximate error with the room temperature in the primary delay response becomes minimum.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a control device, a control method, and a program. [Background technology]

[0002] For example, when an air conditioner is operated in cooling mode, it takes time for the indoor temperature to reach the target temperature set by the user after it is turned on, and the indoor temperature during that time is not comfortable for the person in the room (user). For this reason, in order to make the room comfortable when the user arrives, the air conditioner (indoor unit) is manually turned on before the user begins to be in the room, or a function that automatically starts pre-cooling a certain amount of time before (for example, 15 minutes or 30 minutes before) (warming-up operation) is used.

[0003] The appropriate pre-cooling time not only differs for each air-conditioned space, such as a room, but also changes depending on conditions such as the outside temperature. Therefore, if the time at which pre-cooling starts automatically is fixed, as in the warm-up operation described above, the pre-cooling time may be too long or too short. If the pre-cooling time of the air conditioner is too long, it will waste energy and lead to higher electricity bills. Also, if the pre-cooling time is insufficient, comfort will be compromised.

[0004] In addition, air conditioners are designed to control in response to changes in conditions such as outside temperature, taking into account the dead time between when an operation is performed and when the result appears, and thermal response parameters including a first-order lag (see, for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2001-350503 A [Patent Document 2] JP 2002-054837 A Summary of the Invention [Problem to be solved by the invention]

[0006] Another possibility is to use a model that predicts thermal response parameters by learning conditions such as indoor and outdoor temperatures. For example, sufficient computational resources (memory and CPU) are required to predict thermal response parameters using a prediction model such as a neural network or random forest. However, in most cases, typical air conditioner control devices (microcomputers) are equipped with only limited computational resources.

[0007] An object of the present disclosure is to provide a control device, a control method, and a program that can calculate thermal response parameters using a lightweight algorithm even when only limited computing resources are installed. [Means for solving the problem]

[0008] According to one aspect of the present disclosure, the control device includes an extraction unit that extracts elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by an air conditioner from time series data measuring the indoor temperature in a space to be air conditioned, and an estimation unit that estimates a dead time estimate of the response of the indoor temperature to the air conditioning control and an estimate of the time constant of a first-order lag response based on the extracted elements.

[0009] According to one aspect of the present disclosure, the control method includes a step of extracting elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by an air conditioner from time series data measuring the indoor temperature in a space to be air conditioned, and a step of estimating a dead time estimate of the response of the indoor temperature to the air conditioning control and a time constant estimate of a first-order lag response based on the extracted elements.

[0010] According to one aspect of the present disclosure, the program causes a control device to execute the steps of: extracting elements included in a monitoring period from a specified start condition to an end condition of air conditioning control by an air conditioner from time series data measuring the indoor temperature in a space to be air conditioned; and estimating, based on the extracted elements, an estimated dead time value of the response of the indoor temperature to the air conditioning control and an estimated time constant value of the first-order lag response. Effect of the Invention

[0011] According to the above aspect, even if only limited computational resources are installed, it is possible to calculate the thermal response parameters using a lightweight algorithm. [Brief description of the drawings]

[0012] [Figure 1] 1 is a diagram showing a functional configuration of an air conditioning system according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a prediction model according to the first embodiment. [Diagram 3] FIG. 2 is a diagram showing an example of explanatory variables and level category assignment according to the first embodiment. [Figure 4] 5 is a flowchart showing an example of a thermal response parameter estimation process according to the first embodiment. [Diagram 5] FIG. 4 is a diagram showing an example of time-series data of indoor temperature according to the first embodiment. [Figure 6] 1 is a flowchart showing an example of a learning process of a prediction model according to the first embodiment. [Figure 7] FIG. 4 is a block diagram showing an example of a lookup table update process according to the first embodiment. [Figure 8] 10 is a flowchart showing an example of a prediction process of a predicted arrival time according to the first embodiment. [Figure 9] 4 is a block diagram showing an example of a prediction process of a predicted arrival time according to the first embodiment. FIG. [Figure 10] FIG. 4 is a diagram showing a display example of a terminal device according to the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] <First embodiment> Hereinafter, a control method according to the first embodiment will be described with reference to the drawings. The control method according to the present embodiment can be applied to the control of various heat source devices such as air conditioners, water heaters, and freezers, but the following description will be given taking the case of application to an air conditioner as an example.

[0014] (Overall configuration of air conditioning system) FIG. 1 is a diagram showing the functional configuration of an air conditioning system according to the first embodiment. As shown in FIG. 1, the air conditioning system 100 includes an air conditioner 1 and a terminal device 20. The air conditioner 1 includes an outdoor air temperature sensor 2, an indoor temperature sensor 3, a memory 4, an indoor unit 5, and an outdoor unit 6. The outdoor air temperature sensor 2 and the indoor temperature sensor 3 are connected to a control device 10, and the control device 10 acquires the temperatures measured by the outdoor air temperature sensor 2 and the indoor temperature sensor 3. The indoor unit 5 and the outdoor unit 6 are connected to the control device 10, and the control device 10 controls the indoor unit 5 and the outdoor unit 6 and detects their operating states. The control device 10 and the terminal device 20 are connected to be able to communicate with each other via a network NW. The terminal device 20 is, for example, a smartphone or tablet equipped with an application capable of remotely controlling the air conditioner 1.

[0015] (Functional configuration of the control device) The control device 10 is a computer equipped with a CPU (Central Processing Unit) such as a microcomputer or a MPU (Micro Processing Unit). The control device 10 includes an information acquisition unit 11, an extraction unit 12, a division unit 13, an estimation unit 14, a learning unit 15, a prediction unit 16, a control unit 17, and a communication unit 18.

[0016] The information acquisition unit 11 acquires the outdoor temperature measured by the outdoor temperature sensor 2 and the indoor temperature measured by the indoor temperature sensor 3 .

[0017] The extraction unit 12 extracts elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by the air conditioner 1 from time-series data of the room temperature in the room (air conditioned space) in which the air conditioner 1 is installed.

[0018] The dividing unit 13 divides the elements of the effective section from the point where the indoor temperature in the effective section starts to decrease during cooling operation, and from the point where the indoor temperature in the effective section starts to increase during heating operation, as first-order lag response elements, and divides the elements of the effective section other than the first-order lag response as dead time elements.

[0019] The estimation unit 14 estimates the length of the dead time as a dead time estimated value L, and estimates a time constant estimated value τ that minimizes the curve approximation error with the indoor temperature in the first-order lag response section. Parameters including the first-order lag time constant estimated value τ and the dead time estimated value L are also referred to as thermal response parameters.

[0020] The learning unit 15 learns a prediction model (lookup table) that associates explanatory variables, which are conditions that affect the air conditioning of the air conditioned space, with the dead time estimate value L and the time constant estimate value τ. The learned lookup table is stored in the memory 4.

[0021] The prediction unit 16 predicts a predicted time D from the current time until the conditioned space reaches the target temperature, based on the trained prediction model (lookup table) read out from the memory 4 and the current explanatory variables.

[0022] The control unit 17 controls the indoor unit 5 and the outdoor unit 6. Based on the settings of the set temperature and set time received from the terminal device 20 via the communication unit 18 and the predicted arrival time D predicted by the prediction unit 16, the control unit 17 operates the indoor unit 5 and the outdoor unit 6 so that the air-conditioned space approaches the set temperature at the set time. For example, the control unit 17 starts air conditioning at a time that is the predicted arrival time D earlier than the set time or slightly earlier than that time, and performs cooling operation or heating operation so that the set temperature is achieved by the set time.

[0023] The communication unit 18 communicates with the terminal device 20. For example, the communication unit 18 transmits the predicted arrival time D predicted by the prediction unit 16 to the terminal device 20. The communication unit 18 may also receive setting conditions such as a set temperature and a set time, and a control signal such as powering on the air conditioner 1 from the terminal device 20.

[0024] (About the prediction model) Fig. 2 is a diagram illustrating an example of a prediction model according to the first embodiment. Fig. 3 is a diagram illustrating an example of an explanatory variable and an allocation of a level category according to the first embodiment. As shown in FIG. 2, in this embodiment, the prediction model of the thermal response parameter is represented by a lookup table LUT of a time constant estimate value τ and a dead time estimate value L for each operation mode. In addition, in the example of FIG. 2, there are two operation modes, heating operation and cooling operation. Therefore, the lookup table LUT according to this embodiment has four tables, a time constant table LUT1 for cooling operation, a dead time table LUT2 for cooling operation, a time constant table LUT3 for heating operation, and a dead time table LUT4 for heating operation. Each table is composed of a combination of two or more explanatory variables. Each explanatory variable has multiple level categories. The level category of the explanatory variable is used as an index to identify a cell of each table.

[0025] For example, as shown in Fig. 3, assume that explanatory variable 1 is air volume and explanatory variable 2 is outdoor air temperature. For example, the air volume is assigned a level category for each air volume setting value of the fan of the indoor unit 5. Furthermore, the outdoor air temperature is assigned a level category for each range of the measurement value of the outdoor air temperature sensor 2. Note that the level category of the outdoor air temperature may be set to different temperature ranges for cooling operation and heating operation, as in the example of Fig. 3.

[0026] That is, in the examples of Fig. 2 and Fig. 3, each table records in each cell an estimated value of a thermal transient parameter (time constant τ or dead time L) corresponding to a combination of air volume and outside air temperature for each operation mode (heating operation or cooling operation). In this way, different thermal response parameters can be updated and referenced depending on the settings of the air conditioner 1 and environmental conditions. Also, each cell records the number of samples n (the number of times the thermal response parameter is recorded). The process of updating the lookup table (learning process) and the process of referencing it (prediction process) will be described later.

[0027] (Thermal response parameter estimation process) FIG. 4 is a flowchart showing an example of a thermal response parameter estimation process according to the first embodiment. Here, the flow of the process in which the control device 10 estimates the thermal response parameters will be described with reference to Fig. 4. When the air conditioner 1 is operating, the control device 10 repeatedly executes the series of processes shown in Fig. 2 at predetermined control cycles (for example, every 50 ms). During this time, the information acquisition unit 11 sequentially acquires sensor measurement values ​​and set values ​​such as the outdoor air temperature, indoor temperature, and air volume from the outdoor air temperature sensor 2, indoor temperature sensor 3, indoor unit 5, etc.

[0028] First, the extraction unit 12 determines whether the start condition of the monitoring period has been satisfied (step S100). The monitoring period is a period for monitoring (extracting and retaining) data to estimate a thermal response parameter in the air conditioning control of the air conditioner 1. For example, the extraction unit 12 determines that the start condition of the monitoring period has been satisfied when the indoor unit 5 is switched ON or the set temperature is changed.

[0029] If the start condition is not satisfied (step S100; NO), the extraction unit 12 ends the process. On the other hand, if the start condition is satisfied (step S100; YES), the extraction unit 12 starts extracting and storing the necessary information (step S101). Thereafter, the extraction unit 12 records the measured value (time series data) of the indoor temperature in a buffer secured in the memory 4 for each predetermined control period. Also, only when the extraction unit 12 starts recording the indoor temperature, it records in the memory 4 the operation mode of the air conditioner (heating operation or cooling operation) and explanatory variables used in the learning process described below. The explanatory variables are, for example, the time when the measured value retention start point, the outdoor air temperature, the air volume of the indoor unit 5, the temperature gap between the indoor temperature and the set temperature, etc.

[0030] Next, the extractor 12 determines whether a predetermined end condition is satisfied (step S102). For example, the extractor 12 determines that the end condition is satisfied when the end of the buffer (upper limit number or upper limit amount of time-series data) is reached, when the indoor unit 5 is switched OFF, when the set temperature is changed, etc.

[0031] If the termination condition is not satisfied (step S102; NO), the extraction unit 12 temporarily terminates the process. At this time, the time series data of the indoor temperature continues to be stored. Therefore, until the extraction unit 12 determines that the termination condition is satisfied, the indoor temperature at each step of the control cycle is extracted and stored in a buffer. On the other hand, if the termination condition is satisfied (step S102; YES), the extraction unit 12 further determines whether the monitoring section is a valid section (step S103).

[0032] For example, if the length of the data (time series data of indoor temperature) recorded in the buffer is less than a threshold value, or if the indoor temperature does not reach the set temperature before the end of the buffer is reached, the extraction unit 12 determines that the monitoring section is invalid (step S103; NO) when the time series data does not meet a predetermined criterion (i.e., it is difficult to estimate the thermal response parameters based on the time series data). In this case, the extraction unit 12 clears the buffer (step S106) and ends the process. On the other hand, if the time series data meets the criterion, the extraction unit 12 determines that the monitoring section is valid (step S103; YES).

[0033] Next, the dividing unit 13 divides the time series data of the monitoring section into a dead time element and a first-order lag element (step S104).

[0034] FIG. 5 is a diagram showing an example of time-series data of the indoor temperature according to the first embodiment. FIG. 5 shows an example of time series data of the indoor temperature during heating operation. In the example of FIG. 5, the extraction unit 12 extracts and records the time series data of the indoor temperature in the monitoring section from time t0 to time t2. The division unit 13 first identifies the element part of the first-order lag response from the time series data. For example, during heating operation, the division unit 13 considers the element after the point where the indoor temperature in the monitoring section turns to increase as the element of the first-order lag response. More specifically, the division unit 13 searches for an extreme value (a minimum value during heating operation) from the time series data, and determines that the indoor temperature has turned to increase when it has risen from the extreme value by a predetermined temperature (for example, 1°C) or more. At this time, the division unit 13 considers the extreme value immediately before the turn to increase as a boundary point, and considers the element after the boundary point as the element of the first-order lag response. In the example of FIG. 5, the indoor temperature rises from the minimum value by a predetermined temperature or more after time t1. Therefore, the dividing unit 13 regards the element at time t1 immediately before the indoor temperature starts to rise as a boundary point, and regards the elements from time t1 to time t2 as elements of a first-order lag response.

[0035] Similarly, during cooling operation, the dividing unit 13 considers elements after the point where the indoor temperature starts to decrease in the monitoring section to be elements of a first-order lag response. More specifically, the dividing unit 13 detects an extreme value (a maximum value during cooling operation) from the time-series data, and determines that the indoor temperature has started to decrease when it has decreased from the extreme value by a predetermined temperature (for example, 1°C) or more.

[0036] Furthermore, the dividing unit 13 regards elements other than the first-order lag response as elements of dead time in the monitoring section. In the example of Fig. 5, the dividing unit 13 regards elements before time t1 as elements of dead time.

[0037] Next, the estimator 14 estimates thermal response parameters (step S105). The estimator 14 according to the present embodiment estimates the length of dead time and the time constant of the first-order lag response as thermal response parameters.

[0038] First, the estimation unit 14 obtains the length of the dead time (the number of array elements) divided from the time series data by the division unit 13 as the dead time estimated value L. In the example of Fig. 5, the estimation unit 14 obtains the time from time t0 to t1 as the dead time estimated value L.

[0039] The estimation unit 14 also estimates the time constant τ of the first-order lag response based on the elements of the first-order lag response. For example, the estimation unit 14 performs a simulation (curve approximation) of the change over time of the indoor temperature for each assumed value of the time constant while sequentially changing the assumed value of the time constant from a lower limit value to an upper limit value in increments of a fixed time (for example, one minute). This simulation may use various known techniques. The estimation unit 14 obtains the error between the approximation curve for each assumed value of the time constant obtained by the simulation and the actual measured value (the first-order lag response part of the time series divided by the division unit 13), and sets the assumed value of the time constant that minimizes the error as the estimated time constant τ.

[0040] The estimation unit 14 stores the thermal response parameters, including the dead time estimate value L and the time constant estimate value τ, in the memory 4 in association with the previously recorded operation mode and explanatory variables (step S106). After that, the estimation unit 14 clears the buffer (step S107) and ends the process.

[0041] (Predictive model learning process) Fig. 6 is a flowchart showing an example of a learning process of a prediction model according to the first embodiment. Fig. 7 is a block diagram showing an example of an update process of a lookup table according to the first embodiment. Here, the flow of the process in which the control device 10 learns a prediction model will be described with reference to Fig. 6 to Fig. 7. Note that the control device 10 executes a series of processes shown in Fig. 6 every time the estimation unit 14 estimates a thermal response parameter.

[0042] First, the learning unit 15 reads out from the memory 4 the estimated value of the thermal response parameter newly estimated by the estimation unit 14 and the explanatory variables recorded together with the estimated value (step S200).

[0043] Next, the learning unit 15 determines the index of the cell in which the newly estimated value of the thermal response parameter is to be stored (step S201).

[0044] First, the learning unit 15 determines the storage destination to be either the table for heating operation or the table for cooling operation based on the operation mode read from the memory 4. Furthermore, the learning unit 15 determines the index of the storage destination cell based on the value of the explanatory variable read from the memory 4. For example, assume that the operation mode is heating operation, explanatory variable 1 (air volume) is Middle, and explanatory variable 2 (outdoor temperature) is 6°C. According to the example of Figs. 2 to 3, explanatory variable 1 corresponds to level 2, and explanatory variable 2 corresponds to level 3. Therefore, in this case, the learning unit 15 determines the cell where the row of explanatory variable 1 of level 2 intersects with the column of explanatory variable 2 of level 3 in the time constant table LUT3 for heating operation and the dead time table LUT4 for heating operation shown in Fig. 2 as the storage destination cell for the time constant estimate value τ(tau_est) and the dead time estimate value L(lag_est), respectively.

[0045] Next, the learning unit 15 calculates the average value of the new estimated value and the past estimated value (step S202). First, the learning unit 15 reads out the value recorded in the storage cell of each table as the past average value (tau_avg_old, lag_avg_old).

[0046] Furthermore, the learning unit 15 calculates the average value (tau_avg_new, lag_avg_new) of the new thermal response parameter estimates (tau_est, lag_est) and the past average values ​​(tau_avg_old, lag_avg_old) read from the storage cell. At this time, the learning unit 15 may calculate the new average value by a weighted average with a weight α added, as in the following formulas (1) and (2). The weight α may be set to any value within the range of "0<α≦1", for example.

[0047] tau_avg_new=α*tau_est+(1-α)*tau_avg_old …(1)

[0048] lag_avg_new=α*lag_est+(1-α)*lag_avg_old …(2)

[0049] The learning unit 15 inputs the calculated new average values ​​(tau_avg_new, lag_avg_new) into the storage cell and updates the lookup table LUT (step S203). At this time, the learning unit 15 increments the number of samples n in this storage cell by +1.

[0050] If the number of samples n of the storage cell is 0, that is, if this is the first time that thermal response parameters are input to this storage cell, the learning unit 15 does not calculate the average value, but inputs the thermal response parameter estimates (tau_est, lag_est) read from the memory 4 directly to the storage cell, and updates the lookup table LUT (step S202).

[0051] (Prediction process for estimated arrival time) Fig. 8 is a flowchart showing an example of a process for predicting a predicted arrival time according to the first embodiment. Fig. 9 is a block diagram showing an example of a process for predicting a predicted arrival time according to the first embodiment. Here, a process flow for predicting a predicted time for the room temperature to reach a set temperature will be described with reference to Fig. 8 and Fig. 9. Note that the control device 10 executes a series of processes shown in Fig. 8 when, for example, an application of the terminal device 20 is started or operated.

[0052] First, the information acquisition unit 11 acquires explanatory variables to be used for prediction (step S300). For example, when explanatory variable 1 is air volume and explanatory variable 2 is outdoor temperature, the information acquisition unit 11 acquires the air volume setting value of the air conditioner 1 (indoor unit 5) and acquires the current outdoor temperature from the outdoor temperature sensor 2. The information acquisition unit 11 may also acquire the current set temperature (when the power is OFF, the set temperature at the time of the previous operation) at the same time.

[0053] Next, the prediction unit 16 reads out the thermal response parameters corresponding to the obtained explanatory variables (step S301). For example, if the current operation mode (the operation mode during the previous operation in the case of power OFF) is heating operation, the prediction unit 16 reads out the parameters (tau_avg, lag_avg) corresponding to the explanatory variables from the time constant table LUT3 and the dead time table LUT4 for heating operation. The method of determining the index of the storage cell for each parameter is the same as that of step S201 in FIG. 6.

[0054] Furthermore, the prediction unit 16 predicts a predicted time D for the indoor temperature of the air-conditioned space to reach the target temperature based on the read thermal response parameters (step S302). The predicted time D is calculated, for example, by the following formula (3). The target temperature is expressed, for example, as x% (any value such as 90%, 95%) of the current set temperature. Furthermore, the coefficient C of the time constant τ (tau_avg) can be changed according to the target temperature. For example, when the target temperature is 95% of the set temperature, C=3, and when the target temperature is 90% of the set temperature, C=2.3.

[0055] D = C × tau_avg + lag_avg … (3)

[0056] Next, the communication unit 18 transmits the predicted arrival time D predicted by the prediction unit 16 to the terminal device 20 (step S303).

[0057] FIG. 10 is a diagram showing a display example of the terminal device according to the first embodiment. For example, as shown in Fig. 10, information such as current information C201 and predicted information C202 is displayed on the application screen of the terminal device 20, along with an operation reception section C203 that receives remote operation of the air conditioner 1 by the user. The current information C201 includes information such as the current date and time, the indoor temperature, the outdoor temperature, and the set temperature. The predicted information C202 includes the predicted arrival time D received from the control device 10 of the air conditioner 1. The predicted information C202 may also include a predicted time obtained by adding the predicted arrival time D to the current time. The operation reception section C203 may also include a "ON / OFF NOW button", a "TIMER SETTING ON / OFF button", a "TIMER DATE AND TIMER SETTING button", etc.

[0058] The user remotely controls the air conditioner 1 via the operation reception unit C203 while referring to the current time and the predicted time D until the set temperature is reached. For example, in the example of FIG. 10, the predicted time D until the set temperature is reached is approximately 13 minutes, and the user plans to be in the air-conditioned space for about 15 minutes. In this case, the user operates the "ON / OFF NOW button" to turn on the power of the air conditioner 1. Then, the control unit 17 of the control device 10 acquires an operation instruction (power ON) from the terminal device 20 via the communication unit 18 (step S304), and controls the power ON of the air conditioner 1 (indoor unit 5) (step S305).

[0059] Also, for example, if there is time before the user enters the air-conditioned space, the user may operate the "Timer setting ON / OFF" button in the operation reception unit C203 of the terminal device 20 to turn on the timer setting. Also, the user may operate the timer date and time setting to set the room temperature to the set temperature at any set time. In this case, the control unit 17 of the control device 10 acquires an operation instruction (timer setting ON and set time) from the terminal device 20 through the communication unit 18 (step S304), and automatically starts air conditioning at a time that is the predicted arrival time D before the set time or slightly before that time so that the air-conditioned space will reach the set temperature at the set time set by the user, and performs cooling operation or heating operation so as to achieve the set temperature by the set time (step S305).

[0060] The user may also change the current set temperature. For example, the user may be able to perform an operation to change the set temperature by tapping the set temperature portion of the current information C201. Then, the control device 10 acquires an operation instruction (an instruction to change the set temperature) from the terminal device 20 through the communication unit 18. In this case, the control device 10 may return to step S302 and re-predict the predicted arrival time.

[0061] (Action, effect) As described above, the control device 10 according to this embodiment includes an extraction unit 12 that extracts elements included in a monitoring period from a predetermined start condition to an end condition from time series data obtained by measuring the indoor temperature in the air-conditioned space, and an estimation unit 14 that estimates, based on the extracted elements, a dead time estimate L of the indoor temperature response to the air conditioning control of the air conditioner 1 and an estimated time constant τ of the first-order lag response.

[0062] The control device 10 can reduce the calculation load by estimating only two scalar quantities, the dead time estimate L and the first-order lag time constant τ, as thermal response parameters from a limited number of elements included in the monitoring section. Therefore, even the control device 10 of the air conditioner 1 with limited calculation resources can estimate the thermal response parameters.

[0063] The control device 10 also includes a division unit 13 that divides the elements in the monitoring section from the point where the indoor temperature starts to decrease during cooling operation, and from the point where the indoor temperature starts to increase during heating operation, into first-order lag response elements, and divides the elements in the monitoring section other than the first-order lag response into dead time elements, and the estimation unit 14 estimates the length of the dead time element as a dead time estimated value L, and estimates the time constant that minimizes the curve approximation error with the indoor temperature in the first-order lag response as a time constant estimated value τ.

[0064] In this way, the control device 10 can perform calculations excluding time series data corresponding to dead time when estimating the time constant of the first-order lag response, thereby reducing the calculation load accordingly. As a result, even if only limited calculation resources are installed, it is possible to calculate the thermal response parameters (dead time and the time constant of the first-order lag response) with a lightweight algorithm.

[0065] Furthermore, the estimation unit 14 stores the estimated dead time estimate L and the estimated time constant value τ, and deletes the extracted elements (buffer clear).

[0066] For example, when constructing a model for predicting thermal response parameters by machine learning, it is necessary to collect a large number of samples, with each element of a certain monitoring section as one sample, and perform learning. For example, if learning is performed using 100 samples with a length of N=120 points (time series data in which temperature changes every minute are recorded for 120 minutes), a memory for storing 120 points x 100 pieces of data must be prepared. However, as described above, since a general air conditioner control device has limited computational resources such as memory, it is difficult to store such a large amount of data. In contrast, in this embodiment, the estimation unit 14 estimates and stores the dead time estimate value L and the time constant estimate value τ from the elements of the monitoring section, and then deletes the elements used for the estimation. In this way, even if the control device 10 needs to accumulate a large number (100) of samples as past data, each sample only needs to include two numerical values, the dead time estimate value L and the time constant estimate value τ, so that it is possible to compress the past data and store it (compress it to 2 / N compared to the case of using machine learning). In addition, it is sufficient to temporarily store one sample of the elements used to estimate the thermal response parameters, and the elements may be deleted after each estimation, and new elements may be stored in the same buffer for the next estimation. Therefore, the control device 10 can reduce the overall buffer and memory capacity used.

[0067] In addition, the control device 10 further includes a prediction unit 16 that predicts the predicted time it takes for the air conditioned space to reach the target temperature from the current time, based on a lookup table LUT that associates explanatory variables, which are conditions that affect the air conditioning of the air conditioned space, with a dead time estimate value L and a time constant estimate value τ, and based on the current explanatory variables.

[0068] In this way, the control device 10 can use the thermal response parameters calculated while the air conditioner 1 is in operation to accurately predict the predicted time D until the temperature of the air conditioned space reaches the target temperature.

[0069] In addition, the control device 10 transmits the predicted arrival time D to a terminal device 20 carried by the user, and further includes a communication unit 18 that receives user operation instructions from the terminal device 20, and a control unit 17 that controls the air conditioner 1 based on the operation instructions.

[0070] In this way, the control device 10 can receive operational instructions from a user who has referred to the predicted arrival time D, and perform cooling or heating operation so that the indoor temperature approaches the set temperature before the user enters the space to be air-conditioned.

[0071] <Other embodiments> Although one embodiment has been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes are possible. That is, in other embodiments, the order of the above-mentioned processes may be changed as appropriate. Also, some of the processes may be executed in parallel.

[0072] For example, in the above embodiment, an example has been described in which the control device 10 (learning unit 15) of the air conditioner 1 learns a prediction model (lookup table LUT), but the present invention is not limited to this. In another embodiment, the thermal response parameters estimated by the control devices 10 (estimation units 14) of multiple air conditioners 1 may be transmitted to a server and aggregated, and the server may learn a prediction model. In this case, the server performs statistical processing or machine learning from a large number of thermal response parameters to generate and update a prediction model. In addition, the server periodically predicts thermal response parameters (time constant τ, dead time L) for each air conditioner 1 using the prediction model and transmits them to each air conditioner 1. The control device 10 (learning unit 15) of the air conditioner 1 overwrites the thermal response parameters received from the server to the lookup table LUT in the memory 4. In still another embodiment, an application of the terminal device 20 may acquire thermal response parameters from the control device 10 and learn a prediction model. The application of the terminal device 20 periodically predicts the thermal response parameters (time constant τ, dead time L) of the air conditioner 1 using a prediction model and transmits the predicted values ​​to the air conditioner 1. The control device 10 (learning unit 15) of the air conditioner 1 overwrites the lookup table LUT in the memory 4 with the thermal response parameters received from the terminal device 20. In this way, the processing load of the learning unit 15 can be reduced.

[0073] <Additional Notes> The control device, the control method, and the program described in the above-described embodiment can be understood, for example, as follows.

[0074] (1) According to the first aspect, the control device 10 includes an extraction unit 12 that extracts elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by the air conditioner 1 from time series data measuring the indoor temperature in the air conditioned space, and an estimation unit 14 that estimates a dead time estimate L of the indoor temperature response to the air conditioning control and a time constant estimate τ of the first-order lag response based on the extracted elements.

[0075] The control device 10 can reduce the calculation load by estimating only two scalar quantities, the dead time estimate L and the first-order lag time constant τ, as thermal response parameters from a limited number of elements included in the monitoring section. Therefore, even the control device 10 of the air conditioner 1 with limited calculation resources can estimate the thermal response parameters.

[0076] (2) According to the second aspect, the control device 10 according to the first aspect further includes a division unit 13 that divides the elements of the monitoring section from the point where the indoor temperature starts to decrease during cooling operation, and from the point where the indoor temperature starts to increase during heating operation, into first-order lag response elements, and divides the elements of the monitoring section other than the first-order lag response into dead time elements, and the estimation unit 14 estimates the length of the dead time element as a dead time estimated value L, and estimates the time constant at which the curve approximation error with the indoor temperature in the first-order lag response is minimized as a time constant estimated value τ.

[0077] In this way, the control device 10 can perform calculations excluding time series data corresponding to dead time when estimating the time constant of the first-order lag response, thereby reducing the calculation load accordingly. As a result, even if only limited calculation resources are installed, it is possible to calculate the thermal response parameters (dead time and the time constant of the first-order lag response) with a lightweight algorithm.

[0078] (3) According to the third aspect, in the control device 10 according to the first or second aspect, the estimator 14 stores the estimated dead time estimate value L and the estimated time constant estimate value τ, and deletes the extracted element.

[0079] For example, when constructing a model for predicting thermal response parameters by machine learning, it is necessary to collect a large number of samples, with each element of a certain monitoring section as one sample, and perform learning. For example, if learning is performed using 100 samples with a length of N=120 points (time series data in which temperature changes every minute are recorded for 120 minutes), a memory for storing 120 points x 100 pieces of data must be prepared. However, as described above, since a general air conditioner control device has limited computational resources such as memory, it is difficult to store such a large amount of data. In contrast, in this embodiment, the estimation unit 14 estimates and stores the dead time estimate value L and the time constant estimate value τ from the elements of the monitoring section, and then deletes the elements used for the estimation. In this way, even if the control device 10 needs to accumulate a large number (100) of samples as past data, each sample only needs to include two numerical values, the dead time estimate value L and the time constant estimate value τ, so that it is possible to compress the past data and store it (compress it to 2 / N compared to the case of using machine learning). In addition, it is sufficient to temporarily store one sample of the elements used to estimate the thermal response parameters, and the elements may be deleted after each estimation, and new elements may be stored in the same buffer for the next estimation. Therefore, the control device 10 can reduce the overall buffer and memory capacity used.

[0080] (4) According to a fourth aspect, the control device 10 according to any one of the first to third aspects further includes a learning unit 15 that learns a lookup table LUT that associates explanatory variables, which are conditions that affect the air conditioning of the air conditioned space, with a dead time estimate L and a time constant estimate τ, and a prediction unit 16 that predicts a predicted arrival time D from the current time until the air conditioned space reaches a target temperature, based on the lookup table LUT and the current explanatory variables.

[0081] In this way, the control device 10 can accurately predict the predicted time D until the conditioned space reaches the target temperature by using the thermal response parameters calculated during the operation of the air conditioner 1. Furthermore, unlike machine learning models such as neural networks and random forests that have a high computational load, the control device 10 uses a lightweight lookup table that associates explanatory variables with the dead time estimate L and the time constant estimate τ as a prediction model, making it possible to sufficiently learn the prediction model and execute predictions using the prediction model even with limited computational resources.

[0082] (5) According to the fifth aspect, the control device 10 according to the fourth aspect transmits the predicted arrival time D to a terminal device 20 carried by a user, and further includes a communication unit 18 that receives operation instructions from the user from the terminal device 20, and a control unit 17 that controls the air conditioner 1 based on the operation instructions.

[0083] In this way, the control device 10 can receive operational instructions from a user who has referred to the predicted arrival time D, and perform cooling or heating operation so that the indoor temperature approaches the set temperature before the user enters the space to be air-conditioned.

[0084] (6) According to a sixth aspect, the control method includes the steps of: extracting elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by the air conditioner 1 from time series data measuring the indoor temperature in the air conditioned space; and estimating a dead time estimate L of the indoor temperature response to the air conditioning control and a time constant estimate τ of the first-order lag response based on the extracted elements.

[0085] (7) According to the seventh aspect, the program causes the control device 10 to execute the steps of: extracting elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by the air conditioner 1 from time series data measuring the indoor temperature in the air conditioned space; and estimating, based on the extracted elements, an estimated dead time L of the response of the indoor temperature to the air conditioning control and an estimated time constant τ of the first-order lag response. [Explanation of symbols]

[0086] 1 Air conditioner 2. Outside Air Temperature Sensor 3. Indoor temperature sensor 4. Memory 5 Indoor unit 6 Outdoor unit 10 Control device 11 Information acquisition department 12 Extraction part 13 Division 14 Estimation part 15 Learning Department 16 Prediction Department 17 Control Unit 18 Communications Department 20 Terminal Equipment 100 Air Conditioning System LUT Lookup Table

Claims

1. an extraction unit that extracts elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by an air conditioner from time series data obtained by measuring indoor temperatures in an air conditioned space; an estimation unit that estimates a dead time estimate value of the indoor temperature response to the air conditioning control and a time constant estimate value of a first-order lag response based on the extracted elements; A control device comprising:

2. a dividing unit that divides the monitoring section into elements of a first-order lag response, the elements being from a point in the monitoring section where the indoor temperature starts to decrease during cooling operation, and the elements being from a point in the monitoring section where the indoor temperature starts to increase during heating operation, and divides the monitoring section into elements of a first-order lag response, the elements being from a point in the monitoring section where the indoor temperature starts to increase, the estimator estimates a length of the element of the dead time as a dead time estimated value, and estimates a time constant that minimizes a curve approximation error between the first-order lag response and the indoor temperature as the time constant estimated value. The control device according to claim 1 .

3. the estimation unit stores the estimated dead time estimate value and the estimated time constant estimate value, and deletes the extracted element. The control device according to claim 1 .

4. a learning unit that learns a lookup table in which explanatory variables, which are conditions that affect the air conditioning of the air conditioned space, correspond to the dead time estimated value and the time constant estimated value; a prediction unit that predicts a predicted time from a current time until the air conditioned space reaches a target temperature based on the lookup table and the current explanatory variables, A control device according to any one of claims 1 to 3.

5. a communication unit that transmits the predicted arrival time to a terminal device carried by a user and receives an operation instruction from the user from the terminal device; A control unit that controls the air conditioner based on the operation instruction; The control device of claim 4 further comprising:

6. extracting elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by an air conditioner from time series data obtained by measuring indoor temperatures in an air conditioned space; estimating a dead time estimate of the indoor temperature response to the air conditioning control and a time constant estimate of a first-order lag response based on the extracted elements; The control method includes:

7. extracting elements included in a monitoring period from a predetermined start condition to an end condition of air conditioning control by an air conditioner from time series data obtained by measuring indoor temperatures in an air conditioned space; estimating a dead time estimate of the indoor temperature response to the air conditioning control and a time constant estimate of a first-order lag response based on the extracted elements; A program that causes a control device to execute the above.

Images