JPH04186044A - Control device for air conditioning machine - Google Patents

Abstract

PURPOSE:To realize more comfortable air conditioning and living environment by a method wherein an air conditioning machine is controlled by a control signal which is formed by a control signal forming means, based on a comfortable feeling of human beings, which is presumed by a presuming means. CONSTITUTION:A neural circuit network simulating means 17 determines whether an indoor environmental condition is transitional or stable by an input signal, and outputs a determination value 18a, and outputs a presumed mean number of votes PMV, which is a comfort degree of the room, or a presumed value 18b of a standard new effective temperature SET. The determination value 18a of the indoor environmental condition and the presumed value 18b of the presumed mean number of votes PMV are input in a control signal forming means 19, and a control signal 1a is formed by this forming means 19. The control signals forming means 19 forms the control signal 1a which can maximize the capability of an air conditioning machine 1b when the indoor environmental condition is transitional, and the comfortable feeling is unsatisfactory. When the indoor environmental condition is stable, and the comfortable feeling is satisfactory, the control signal 1a by which the comfort degree can be maintained is formed.

Description

[Detailed description of the invention] Industrial application field of the present invention (air) For example, an air conditioner equipped with a microcomputer automatically performs comfortable air conditioning operation, and controls indoor temperature, air volume, and air direction. This technology relates to a control device for an air conditioner to improve the comfort of people indoors.Conventional technologyIn the example of heating, it is necessary to control the room temperature with an air conditioner. For this purpose, methods have been adopted to control the indoor target temperature of the air conditioner by shifting it to a higher level for a certain period of time, and to control the compressor operating frequency depending on the indoor temperature. The control signal generating means 61 is a sensor 60.
a timer value 66 from a timer 63 that operates after the air conditioner 62 is powered on, a user-set temperature 68 from a remote control or operation panel 64 that operates the air conditioner 62 from the outside, etc. controlled by
Even if the signal 66 is generated, for example, during heating (Table 1), if the time from turning on the power is within 60 minutes, the user sets the indoor target temperature from the remote control or the operation panel 64 in order to quickly raise the indoor temperature. 2 than the set temperature of
Since the indoor temperature of an air conditioner is controlled to be set at a higher temperature, the problem that the invention attempts to solve is only tentative. It is not possible to flexibly deal with the size of the air conditioning load in the room where the air conditioner is installed and the indoor environmental conditions (transient/stable). Sometimes, when the room temperature is higher than the target temperature, or when the load is excessive, it takes a considerable amount of time for the room temperature to reach the target temperature, and the comfort of the people in the room cannot be considered. A.Purpose of the present invention (In view of the conventional problems as mentioned above)
An object of the present invention is to provide a control device for an air conditioner that can realize more comfortable air conditioning and a living environment, taking into consideration the sense of comfort of people indoors. A plurality of sensor means for detecting indoor and outdoor environmental conditions included in the harmonizer;
storage means for retaining the previous state of the sensor means; determination means for determining whether the indoor environmental condition is a transient or stable state based on outputs from the sensor means and the storage means; and outputs from the sensor output and the determination means. and an estimating means for estimating the sense of comfort of people in the room from the temperature set by the user, and control of the temperature, wind direction, air volume, etc. of the air conditioner based on the sense of comfort of the people in the room estimated by the estimating means. The present invention proposes a control device for an air conditioner, which includes a control signal generating means for generating a signal.

According to the configuration of the present invention described above, the estimation means determines the indoor and outdoor environmental conditions and indoor environmental conditions (transient/stable) detected by a plurality of sensor means, and the sensor means stored in the storage means. The comfort level of people in the room is estimated from the previous state of the room and the temperature set by the user. Based on the human's sense of comfort estimated by the estimation means, the control signal generation means generates a control signal to control the air conditioner.This creates a more comfortable air conditioning and living environment that takes into account the indoor environment and the human condition. can be realized.

Embodiments Hereinafter, embodiments of the present invention will be explained in detail using FIGS. 1 to 5.・ FIG. 1 is a block diagram showing the flow of signals in the control device according to the first embodiment of the present invention, and FIG. 2 is a block diagram showing the learning method of the neural network schematic means in FIG. 1. , in FIG. 1, 10 is a sensor, 11.1
2 is a sensor signal from the sensor 10 (iiIL) 13 is a storage means, 14 is a slope of the suction temperature outputted from the storage means 13 at N second intervals 15 is a remote control or operation panel, 16 is an output from the remote control or operation panel 15 Signal 17 is a neural network model means including means for determining whether the indoor environmental state is transient or stable; 18a is a signal for determining the indoor environmental state; and 18b is the comfort level (predicted average number of votes) output from the means 17; Mean
Vote (hereinafter referred to as PMV) or Standard Effective Temperature (Standard Effective Te
19 is a control signal generating means, 1a is a control signal output from the means 19, and 1b is an air conditioner.

Next, the learning method of the neural network schematic means will be explained with reference to Figure 2. In Figure 2, 21 is the outdoor temperature, 22
is the suction temperature, 23 is the gradient of the suction temperature, 24 is the air volume, 25 is the user's set temperature, 26 is the human body temperature, 2
7 is a neural network model means including a determining means for determining whether the indoor environmental condition is transient or stable; 28 is a control signal generating means;
29 is the actually measured PMV (or 5ET), 2a is the judgment of the indoor environmental condition (transient/stable), and 2b is the estimated P
MV (or 5ET), 2d is the control signal 211,
221, 231. 241. 251. 261 are signals from the outdoor temperature 21, the suction temperature 22, the suction temperature gradient 23, the air volume 24, the user's set temperature 25, and the human body temperature 26. Multiple sensors (outside temperature sensor, suction temperature sensor, humidity sensor, human body temperature sensor) in the air conditioning mlb 10
Therefore, the sensor signal 11 is outputted. This signal 1IIL is the outdoor temperature, suction temperature, humidity, human body temperature, etc. A signal 12 similar to the signal 11 is output from the sensor 10 and is input to the storage means 13.The storage means 13 is input to the sensor output. The history of the signal 12 for the past N seconds (N is a positive real number) is stored. Since the air volume and the user's set temperature value 16 are output from the remote control or the operation panel 15, the storage means 13 also records the state before the sensor, for example, the indoor temperature for N seconds (N is a positive real number ) interval slope I4 is output. Each means 10, 13. 15 output signals 11, 14,
This neural network model means 17 determines from the input signal whether the indoor environmental condition is transient or stable and outputs a judgment value 18a, which indicates the comfort level of the room. Outputs the predicted average number of votes PMV or the estimated value 18b of the standard new effective temperature SET.The indoor environmental condition is determined based on whether the temperature, humidity, etc. are within the set range relative to the target value. V ii Subjects were tested in an environmental test room where the combination of six factors that affect comfort: temperature, humidity, air velocity, radiant temperature (surrounding walls), metabolic rate, and clothing condition. It was quantified based on the results of the vote. PMVO value 1 Table-3: Cold -2: Cool -1: Slightly cool 0: Fair +1: Slightly warm +2: Warm +3: Can be evaluated as hot.

On the other hand, SET calculates the amount of thermal stimulus from the physical factors of the environment.
It attempts to predict human physiological state values and sensations.
It is one of the physical comfort evaluation methods that captures the relationship between comfort and discomfort with heat based on the physiological response to the physical quantity of thermal stimulation. Suction temperature gradient
By inputting the human condition such as the air volume, the user's temperature setting, and the human body temperature and the indoor environment, the neural network model means 17 determines whether the indoor environmental condition is transient or stable using a judgment value 18a.
and the estimated value 18b of the PMV are output.
is input to the control signal generating means 19, and this generating means 19
The control signal 1a is generated by the control signal generating means 19.
1 friend: When the indoor environment is transient and the comfort level is unsatisfactory (
It is necessary to generate a control signal 1a that maximizes the capacity of the air conditioner 1b.In this case, if the indoor environmental condition is stable and the feeling of comfort is satisfactory, a control signal that allows the feeling of comfort to continue is generated. 1a is generated, that is, the judgment value 18a of the environmental state and the estimated PMV value 1
8b generates a signal 1a that controls the air conditioner 1b, but this control signal 1a causes the air conditioner 1 to
For example, the inverter frequency, wind direction, air volume, indoor target set temperature, etc. at・The shift amount for calculating the indoor target temperature of the air conditioner 1b is determined by determining whether the air conditioner 1b is stable or not. Target temperature = User set temperature + shift amount Therefore, the air conditioner 1b generated by the control signal generation means 19
For example, the control signal 1a of the air conditioner 1a is inputted to the air conditioner 1b, and the air conditioner 1
Even if operation b is executed, the indoor temperature adjustment 1c is performed.

Next, the details of the learning method of the neural network shown in FIG. 1 will be explained with reference to FIG. 2. In FIG.
, air volume 24, user's set temperature 25, human body temperature 26, etc. signals 211°221, 231. 241. 2
51. 261 is input to the neural network model means 27, the indoor environmental state determination result 2a and the estimated PMV value 2b
Even if the above neural network model means 27ζ clothing is output, the judgment of the indoor environmental state and the actual measured PMV29 measured indoors are used as the learning data 2.
There are various learning algorithms for the neural network to learn the measured value 2b of PMV as c.
J, LrpDp model - Cognitive science and the search for neuronal networks J (Runmelhart, D.
E and McClelland, J.

L (Eds,), Parallel Distr.
ibutedProcessing, Expl
Oration in the Microst
structure of Cognition,
Vol, 1. 2. MIT Pres'
Cambridge (1986))), and learning is performed using these algorithms until the PMV can be sufficiently estimated by the neural network model means 27. When the learning is completed, the output value 2a for determining the indoor environment state and the neural network schematic means 2
According to the output value 2b of 7, when the indoor environmental condition is transient and the feeling of comfort is unsatisfactory, the control signal generating means 28 generates a control signal 2d that maximizes the capacity of the air conditioner. When the stable and comfortable feeling is satisfied, the control signal 2d is generated by the control signal generating means 28 so that the comfortable feeling can be maintained.In other words, the neural network model means 27 generates the control signal 2d to maintain the comfortable feeling. Judgment output value 2a
A signal 2d for controlling the air conditioner is generated based on the estimated PMV value 2b.The control signal 2d controls the inverter frequency, wind direction, air volume, indoor target temperature setting, etc.

As can be understood from the above explanation &ζ
f. More comfortable air conditioning that takes into account the indoor environment by inputting the input from each sensor into a neural network model means, determining the indoor environmental state (transient/stable), and generating a control signal based on the estimated PMV value. and living environment can be realized.

In this example, neural network schematic means 17゜27
The same effect can be obtained by replacing the outputs 18b and 2b with PMV and the surrounding wall radiant temperature. FIG. 3 is a block diagram showing the flow of signals in the control device according to the second embodiment of the present invention, in which 30 is a sensor, and 31 and 32 are sensors from the sensor 30. Signal direct 33 is a storage unit 34 is a suction temperature outputted from the storage means 33 at N second intervals 35 is a remote control or operation spring & 36 is an output signal from the remote control or operation panel 35 37 is a look-up tape pickup 38 is a Control signals outputted from the look-up table 37. Reference numerals 39 indicate air conditioners, respectively.The look-up table creation method will be explained with reference to FIG. 4. 41 is the outdoor temperature, 42 is the intake temperature, and 43 is the intake temperature. Inclination K 44 is air volume, 45 is user's set temperature 1, 46 is human body temperature, 47 is neural network model means, 48 is control signal generation means, 49 is actually measured P
MV (also (!5ET), 4a is the judgment of the indoor environment state determined by neural network model means [4b is the estimated PM
V (or 5ET), 4c is the measured PMV (or 5
4d is the control signal - IJ4e is the lookup tape/l, 411,
421, 431. 441. 451. 461 indicates signals from the outdoor temperature 41, the suction temperature 42, the suction temperature slope 43, the air volume 44, the user's set temperature 45, and the human body temperature 46, respectively. If the sensor signal 31 is output from the plurality of sensors 30 in the air conditioner 39, the sensor signal 31 may be the outside temperature, suction temperature, humidity, human body temperature, etc. A signal 32 similar to the signal 31 is output, and this signal is input to the storage means 33. The storage means 33 stores the history of the input sensor output signal 32 for the past N seconds (N is a positive real number). Alternatively, the air volume and the user's set temperature value 36 are output from the operation panel 35, and the storage means 33 is stored in the state before the sensor.
For example, the slope 34 of the room temperature at intervals of N seconds (N is a positive real number)
Each means 30. 33. Output signal from 35 31. 34. 361;! , is inputted to the lookup table 37 as an input signal, determines the indoor environmental state, and obtains a control signal 38 for the air conditioner 39 from the lookup table 37 corresponding to the determination.This control signal 38 determines the inverter frequency in the air conditioner 39. , the wind volume, the indoor target temperature setting, etc. may be controlled. - For example, each of the means 30. 33. Outside air clothes from 35 Suction temperature Air volume, set temperature The shift amount for calculating the indoor target temperature of the air conditioner 39 is determined from the slope of the suction temperature, etc. This shift amount and the temperature set by the user And the relationship ζ with the indoor target temperature is given by: indoor target temperature - user set temperature + shift amount. Therefore, the control signal 38 obtained from the lookup table 37 is input to the air conditioner 39, and the indoor target temperature is determined based on the above formula, for example. Next, the method of creating the lookup table shown in FIG. 3 will be explained with reference to FIG. Incline 43, air volume 4
4. Signals 411 from user's set temperature 45, human body temperature 46, etc. 421. 431, 441. 451.
461 to the neural network model means 47, and outputs the indoor environmental state determination 4a and the estimated PMV value 4b. Learning data 4
A neural network learning algorithm that learns the estimated value of PMV 4b as c (there are various methods). Learning is performed until the PMV can be sufficiently estimated by the neural network schematic means 47.
When the learning is completed, the output value 4 of the neural network model means 47
According to b, when the indoor environmental condition is transient and the feeling of comfort is unsatisfactory, the control signal generating means 48 generates the control signal 4d that maximizes the capacity of the air conditioner. If the above is satisfied, a control signal 4d is generated by the control signal generating means 48 so that the feeling of comfort can be maintained. By replacing the neural network model means 47 and the control signal generation means 48 that outputs the control signal 4d with a lookup table 4e corresponding to the indoor environmental condition, each input signal of the outdoor temperature 41 to human body temperature 46, which are sensor inputs, is replaced. 411 to 461 are roughly quantized and input into the lookup table 4e, and the result is written to the lookup table 4e.Create a lookup table.I,%Figure 5 is an example of the lookup table 4e. The lookup table 4e has zones A-C, and zone A has a set temperature ti-te, an outside temperature toi-torrh, and an air volume fi.
-fn, the suction temperature 5i-so, and the suction temperature gradient ki-kp are written.As stated above, according to this embodiment, the inputs from each sensor are input to the neural network model means, and the indoor environment is Judging the state (transient/stable) and estimating PMVL By generating control signals based on the indoor environmental state judgment value and PMVO value, it is possible to realize more comfortable air conditioning and living environments that take into account the indoor environment. Furthermore, the control device can be easily realized by replacing the part that estimates the indoor environmental state and PMV from the neural network schematic means and converts it into a control signal with a look-up table corresponding to the indoor environmental state. As described in detail, the air conditioner control device according to claim (1) of the present invention can realize a more comfortable air conditioning and living environment that takes into account the indoor environment and human condition. According to the specifications of the neural network in 2),
By adding claim (3), it becomes possible to control the air conditioner more precisely, improving room temperature fluctuations, etc. by adding claim (3). However, by inputting 8 values of indoor and outdoor temperature, temperature, and humidity into the neural network according to the specifications of claim (4), control suitable for the conditions of use can be achieved for each individual person and group. By further providing an appropriate time interval for the suction temperature gradient as claimed in claim (5), the load condition of the room during use can be accurately determined, and comfort can be improved as claimed in claim (6). Due to the specifications, if a neural network were to be implemented in an air conditioner, the estimation calculation time would be long and a large computer would be required. According to the specifications in claim (8), comfort can be dramatically improved by performing Lx PMV evaluation, which is the most desirable index for evaluating human comfort.
Although the same effect as the specification in claim (7) can be achieved, the specification in claim (9) can further improve comfort by directly inferring the human condition based on the temperature of the human body.

[Brief explanation of the drawing]

FIG. 1 shows a control sJ of an air conditioner according to a first embodiment of the present invention.
FIG. 2 is a block diagram showing the flow of signals in the J device. FIG. 2 is a block diagram for explaining the learning method of the neural network schematic means in FIG. 1. FIG. 3 is a control device for an air conditioner according to a second embodiment of the present invention. Figure 4 is a block for explaining the method of creating the lookup table in Figure 3. Figure 5 is an explanatory block showing an example of the lookup table in Figures 3 and 4. 6th
The figure is a block diagram showing a conventional control device.
...Sensor, 11. 12. 31. 32...
...Sensor signal 13.33...Memory hand [14,3
4... Suction temperature gradient at N second intervals 15°35...
・・Remote control or operation spring t<16.36・・・・
Air volume, set temperature 17... Neural network model 1 set % Temperature [22,42... Suction temperature L 23.43...
...Inclination of suction temperature! 24.44...Air volume, 25
．． 45... User's set temperature [26, 46... Large body temperature [27, 47... Neural network model hand pressure 28.4
8...Control signal generation means, 29.49...Actually measured PMV, 2a, 4b...Indoor environment state determination device
2b, 4b---PMV guessed enemy 2c, 4c
...PMV learning day 2d, 4d...control signal 37.4e...lookup table k 60.
...Sensor, 61...Control signal generation means 62.
...Air conditioning [63...Timer, 64...
Remote control or operation spring/u, 65... Suction temperature i 66... Control signal, 67... Timer 68... Set temperature 2nd ward kite 4 figure, t0

Claims (9)

[Claims] (1) A plurality of sensor means for detecting indoor and outdoor environmental conditions, a memory means for retaining the previous state of the sensor means, and outputs from the sensor means and the memory means to determine whether the indoor environmental condition is transient or stable. a determination means for determining whether the person in the room is in a state of 1. A control device for an air conditioner, comprising: control signal generation means for generating control signals for the air outlet temperature, wind direction, air volume, etc. of the air conditioner based on the air temperature. (2) The air conditioner control device according to claim 1, wherein the estimation means is a neural network model means (neural network) that has learned human comfort. (3) The control of the air conditioner according to claim 1, wherein the determining means determines that the sensor output value is in a stable state when it is within a range set with respect to the target value, and otherwise determines that it is in a transient state. Device. (4) The control device for an air conditioner according to claim 1, wherein the sensor means detects indoor and outdoor temperatures, air volume of the air conditioner, and humidity. (5) The control device for an air conditioner according to claim 1, wherein the storage means stores the intake air temperature gradient of the air conditioner at intervals of N seconds (N is a positive real value). (6) The control signal generation means is storage means for a look-up table corresponding to the indoor environmental state that generates the control signal from the output of a function for estimating the comfort of a person in the room. air conditioner control device. (7) The sense of comfort of people in the room estimated by the estimation means is the predicted average number of votes (PMV) calculated based on the condition of the person and the indoor environment as an evaluation index for controlling the air conditioner.
2. The control device for an air conditioner according to claim 1, wherein the temperature is a standard new effective temperature (SET) that predicts human physiological conditions and sensations. (8) The control device for an air conditioner according to claim 1, wherein the comfort feeling of a person in the room estimated by the estimating means is the surrounding wall radiant temperature. (9) The control device for an air conditioner according to claim 1, wherein the estimating means estimates the condition of the person in the room using a human body temperature sensor as the sensor means.