JP2517165B2 - Control device for air conditioner - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to an indoor air conditioner equipped with a microcomputer, for example, by automatically controlling a comfortable air conditioning operation, by controlling an indoor temperature, an air volume and a wind direction. The present invention relates to an air conditioner control device for enhancing human comfort.

Conventional technology When controlling the room temperature with an air conditioner, in the heating example, in order to improve the characteristics when the room temperature rises, control to shift the indoor target temperature of the air conditioner to a higher value for a certain period of time The method of controlling the compressor operating frequency has been adopted. That is, FIG. 7 shows a control device for such a conventional air conditioner, and in FIG. 7, the control signal generating means 71 has a suction temperature 75 from the sensor 70,
A timer value 77 from a timer 73 that operates after turning on the power of the air conditioner 72 and a user set temperature from a remote control or an operation panel 74 that operates the air conditioner 72 from the outside.
The control signal 76 is generated by 78 or the like. For example, during heating, in order to quickly raise the room temperature within 60 minutes after the power is turned on, the target room temperature is 2 ° C higher than the user's set temperature set by the remote control or operation panel 74. The room temperature adjustment 79 of the air conditioner 72 is controlled so as to be set higher.

DISCLOSURE OF THE INVENTION Problems to be Solved by the Invention However, in the above-described conventional control device, since the control is performed only by the time after the power is turned on and the indoor temperature characteristic, the magnitude of the air conditioning load in the room in which the air conditioner is installed is small or large. Can't deal flexibly with. So, for example,
When the load is too low, the room temperature becomes higher than the target temperature, and when the load is too high, it takes a considerable amount of time for the room temperature to reach the target temperature. If the distance from the air conditioner is long, the set temperature may not be reached, and there is a problem in that it is not possible to consider the comfort of the human being in the room.

In view of the conventional problems as described above, the purpose of the present invention is to
(EN) Provided is a control device for an air conditioner, which can realize a more comfortable air conditioning and a living environment in consideration of the comfort of a person in a room.

Means for Solving the Problems To achieve this object, the present invention provides a plurality of sensor means for detecting indoor and outdoor environmental conditions provided in an air conditioner, and a storage means for holding a previous state of the sensor means. Human comfort from position detection means for detecting the position of a remote control for controlling the air conditioner from the outside, output from the sensor means and the storage means, temperature set by the user, and output from the position detection means Estimating means for estimating the comfort of a person in a room using a neural network model means that has learned the feeling, and the air blower of the air conditioner based on the comfort of the person in the room estimated by the estimating means A control device for an air conditioner, which is provided with a control signal generation means for generating control signals such as temperature, wind direction, and air volume.

According to the above-described configuration of the present invention, the estimating means detects the indoor and outdoor environmental conditions detected by the plurality of sensor means, the previous state of the sensor means held by the storage means, the temperature set by the user, and the position detection. The comfort of the person in the room is estimated from the position of the remote controller detected by the means. Then, based on the comfort feeling of the human being estimated by the estimating means, a control signal is generated by the control signal generating means to control the air conditioner, so that the indoor environment and the human state are taken into consideration, and more comfortable. An air conditioning environment can be realized.

Embodiments Embodiments of the present invention will be described in detail below with reference to FIGS. 1 to 6.

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. In FIG. 1, 10 is a sensor, 11 and 12 are sensor signal values from the sensor 10, 13 is a storage means, 14 is a slope of the suction temperature output from the storage means 13 at N second intervals, 15
Is a remote control or operation panel, 16 is an output signal from the remote control or operation panel 15, 17 is a neural network schematic means, 18
Is the comfort level (Predicted Mean Vote, hereinafter referred to as PMV) or Standard Effective Temperature (hereinafter referred to as SET) output from the means 17.
, 19 is a control signal generating means, 1a is a control signal output from the means 19, 1b is an air conditioner, and 1d is a remote controller 15.
Position sensor, 1e is the remote controller 15 from the position sensor 1d
Position signal.

Next, a more detailed configuration for explaining the learning method of the neural network model means will be described with reference to FIG. That is, FIG. 2 is a block diagram showing the learning method, 21 is the outdoor temperature, 22 is the suction temperature, 23 is the slope of the suction temperature,
24 is the air volume, 25 is the user's set temperature, 26 is the human body temperature, 27 is the neural network model means, 28 is the control signal generation means, 29 is the measured PMV (or SET), and 2a is the estimated PMV (or SE
T), 2c is a control signal, 2d is remote controller position information, 211, 221, 2
31,241,251,261,2dl are outdoor temperature 21, suction temperature 22, suction temperature gradient 23, air volume 24, user set temperature
25, human body temperature 26, and remote control position information 2d.

Since the air conditioner according to the illustrated embodiment is configured as described above, the sensor signal 11 is output from the plurality of sensors (outside air temperature sensor, intake temperature sensor, humidity sensor, human body temperature sensor) 10 in the air conditioner 1b. Will be done. The signal 11 includes outdoor temperature, suction temperature, humidity, human body temperature, and the like. Also, a signal similar to the signal 11 from the sensor 10
Although 12 is output and input to the storage unit 13, the storage unit 13 stores the history of the input sensor output signal 12 for the past N seconds (N is a positive real number). The air volume and the set temperature value 16 set by the user are output from the remote controller or the operation panel 15, and the storage means 13 stores N seconds (N is a positive real number) of the room temperature from the state before the sensor, for example, the history of N seconds described above. ) Output the interval slope 14. The position sensor 1d detects the position of the remote controller and outputs position information 1e. As shown in FIG. 3, this position sensor 1d divides the room into nxm zones and outputs in which zone of the room the remote controller 15 is placed. For example, in the i zone, the output signal 1e of the position sensor 1d becomes i. The output signals 11, 14, 16, 1e from the respective means 10, 13, 15, 1d are inputted to the neural network schematic means 17 as input signals. The neural network model 17 outputs the predicted average vote number PMV, which is the comfort level in the room from the input signal, or the estimated value 18 of the standard new effective temperature SET. PMV is
As for the factors that affect comfort, the subjects in the environmental test room changed the combination of 6 elements of temperature, humidity, air flow velocity, radiant temperature (surrounding wall), metabolic rate, and clothing condition, and about the heat and cold in the test room. It was quantified based on the results of the voting. That is, the PMV value calculated according to the human state (metabolic and clothing conditions) and the indoor environment (temperature, humidity, machine speed, ambient wall radiation) is -3: cold -2: cool -1: rather Cool 0: Nothing +1: Moderately warm +2: Warm +3: Can be evaluated as hot.

On the other hand, SET calculates the amount of thermal stimulation from physical factors of the environment,
It seeks to predict human physiological state values and sensations,
It is one of the physical evaluation methods for comfort that captures the relationship between pleasantness and discomfort with heat by the physiological response to the physical quantity of thermal stimulation. For example, in the case of using PMV, enter the outdoor temperature, the suction temperature, the suction temperature gradient, the air volume, the remote controller position information, the user's set temperature, the human body temperature and the indoor environment in the neural network model 17. By doing so, the estimated value 18 of PMV is output from the neural network pattern model means 17. The estimated value 18 of the PMV is input to the control signal generating means 19, and the generating means 19 generates the control signal 1a. The control signal generation means 19 generates the control signal 1a that maximizes the performance of the air conditioner 1b when the comfort level is unsatisfactory.

Further, when the comfort is satisfied, the control signal 1a is generated so that the comfort can be maintained. That is, the estimated PM
A signal 1a for controlling the air conditioner 1b is generated by the value 18 of V. The control signal 1a controls the inverter frequency, wind direction, air volume, and indoor target set temperature in the air conditioner 1b. As an example, the indoor target temperature targeted by the air conditioner 1b is calculated from the outside air temperature from each of the means 10, 13, 15, 1d, intake temperature, air volume, set temperature, inclination of intake temperature, position information, etc. Find the shift amount The relationship between the shift amount and the temperature set by the user and the indoor target temperature is: indoor target temperature = user set temperature + shift amount. Therefore, the control signal 1a of the air conditioner 1b generated by the control signal generating means 19 is input to the air conditioner 1b, and as an example, the operation of the air conditioner 1b is executed so as to reach the indoor target temperature based on the above formula.

 The room temperature adjustment 1c is performed through the above process.

Next, with reference to FIG. 2, the learning method of the neural network of FIG. 1 will be described. The outdoor temperature 21 and the suction temperature 22, the suction temperature gradient 23 at N second intervals, the air volume 24, the set temperature 25 of the user, the human body. Signal 21 from temperature 26, remote control position information 2d, etc.
1,221,231,241,251,261,2dl are input to the neural network model 27 and the estimated value 2a of PMV is output.

The neural network model means 27 learns the estimated value 2a of the PMV by using the actually measured PMV 29 measured indoors as the learning data 2b.

There are various methods of learning neural network learning algorithms, for example, backpropagation algorithm (reference: Ramelhart, DE and McClellan. JL "PDP model-cognitive science and search of neuron network") {Runmelha
rt, DE and Mcclelland, JL (Eds.), "Parallel Distr
ibuted Processing, Exploration in the Microstructur
e of Cognition.Vol.1,2, MIT Press, Cammbridge (198
6}) is used to find the optimal solution by the descent method. And
With these algorithms, the learning is performed until the PMV can be sufficiently estimated by the neural network schematic means 27. When learning is completed, the output value 2a of the neural network schematic means 27 causes
If the user does not feel comfortable, the control signal generation means 28 generates the control signal 2c that maximizes the capacity of the air conditioner. Further, when the comfortable feeling is satisfied, the control signal 2c is generated by the control signal generating means 28 so that the comfortable feeling can be maintained. That is, the PMV estimated by the neural network model 27
The signal 2c for controlling the air conditioner is generated by the control signal generating means 28 according to the value 2a. The control signal 2c controls the inverter frequency, wind direction, air volume, indoor target set temperature, and the like.

As described above, according to the present embodiment, the input from each sensor is input to the neural network schematic means, the PMV is estimated, and the control signal is generated according to the value of the PMV, whereby the indoor environment and It is possible to realize a comfortable air-conditioning environment in consideration of human condition.

Although the outputs 18, 2a from the neural network schematic means 17, 27 are PMVs in the above-mentioned embodiment, it is obvious that the same effect can be obtained by replacing them with SET or ambient wall radiation temperature. .

Next, a second embodiment of the present invention will be described with reference to FIGS.

FIG. 4 is a block diagram showing the flow of signals in the control device according to the second embodiment of the present invention, and FIG. 5 is a block diagram for explaining the method of creating the look-up table in FIG. In FIG. 4, 40 is a sensor, 41 and 42 are sensor signal values from the sensor 40, 43 is a storage means, 44 is an inclination of the suction temperature output from the storage means 43 at intervals of N seconds, and 45 is a remote control or operation. Panel, 46 is an output signal from the remote control or operation panel 45, 47 is a lookup table, 48 is a control signal output from the lookup table 47, 49 is an air conditioner, 4b is a position sensor, 4c is a position sensor 4b. The position signals of the remote controller 45 are shown.

Next, referring to FIG. 5, a method of creating a lookup table will be described. 51 is an outdoor temperature, 52 is an intake temperature, 53 is an inclination of the intake temperature, 54 is an air volume, 55 is a user set temperature, 56 Is the human body temperature, 57 is the neural network model means, 58 is the control signal generation means, and 59 is the measured PMV (or S
ET), 5a is PMV (or SET) estimated by the neural network model, and 5b is comfort level (PMV) from measured PMV (or SET).
Or SET), 5c is control signal, 5d is remote controller position information, 5
e is a lookup table, 511,521,531,541,551,561,5
d1 is the outdoor temperature 51, the suction temperature 52, the suction temperature gradient 53, the air volume 54, the user-set temperature 55, and the human body temperature 5
6, the signal from the remote control position information 5d.

Since the air conditioner according to the second embodiment is configured as described above, the sensor signals 41 are output from the plurality of sensors 40 in the air conditioner 49 as shown in FIG.
The signal 41 includes outside temperature, suction temperature, humidity, human body temperature, and the like.

Further, a signal 42 similar to the signal 41 is output from the sensor 40 and input to the storage means 43. The storage means 43 stores the history of the input sensor output signal 42 for the past N seconds (N is a positive real number). Remote control or operation panel 45
The air volume and the user-set temperature value 46 are output from the air conditioner, and the storage means 43 stores the state before the sensor, for example, N seconds (N seconds) of the room temperature.
Is a positive real number) and outputs slope 44 at intervals. Further, the position sensor 4b outputs position information 4c of the remote controller. Since the position sensor 4b has been described with reference to FIG. 3 of the first embodiment, it will be omitted here. Output signals 41,44,4 from each means 40,43,45,4b
6, 4c are input to the look-up table 47 as input signals, and the control signal 48 for the air conditioner 49 is obtained from the look-up table 47. With this control signal 48,
The inverter frequency, wind direction, air volume, indoor target set temperature, and the like in the air conditioner 49 are controlled. As an example, the shift amount for calculating the indoor target temperature targeted by the air conditioner 49 from the outside air temperature from each of the means 40, 43, 45, 4b, the intake temperature, the air volume, the set temperature, the slope of the intake temperature, etc. Is required. The relationship between the shift amount and the temperature set by the user and the indoor target temperature is: indoor target temperature = user set temperature + shift amount. Therefore, the control signal 48 obtained from the look-up table 47 is input to the air conditioner 49, and as an example, the operation of the air conditioner 49 is executed so as to reach the indoor target temperature based on the above formula.

Next, the method of creating the lookup table of FIG. 4 will be described with reference to FIG. 5. First, the outdoor temperature 51 and the suction temperature 52, the suction temperature gradient 53 at N second intervals, and the air volume 5
4. Signals 511, 521, 531, 541, 551, 561, 5dl from the user's set temperature 55, human body temperature 56, remote controller position information 5d, etc. are input to the neural network model means 57, and the estimated value 5a of PMV is output.

In this case, the neural network model means 57 uses the actual measurement PMV59 measured indoors as the learning data 5b and estimates the PMV.
Learn 5a.

There are various methods for learning the neural network. For example, the optimal solution may be obtained by the lowest descent method using the above-described backpropagation algorithm. And
Learning is carried out by these algorithms until PMV can be sufficiently estimated by the neural network schematic means 57, but when the learning is completed, the output value 5a of the neural network schematic means 57 indicates that the feeling of comfort is unsatisfactory. The control signal generating means 58 generates a control signal 5c that maximizes the capacity of the air conditioner. Further, when the comfortable feeling is satisfied, the control signal 5c is generated by the control signal generating means 58 so that the comfortable feeling can be maintained.

Although the control signal 5c controls the inverter frequency, the wind direction, the air volume, the indoor target set temperature, etc., the look-up table 5e includes the neural circuit network patterning means 57 and the control signal generating means 58 for outputting the control signal 5c. In order to replace, the input signal 511-5dl of the outdoor temperature 51-remote control position information 5d, which is the sensor input, is roughly quantized and input to the look-up table 5e, and the result is written to the look-up table 5e. Should be created.

FIG. 6 shows a specific example of the look-up table 5e described above. The look-up table 5a includes zones A to C,
Zone A has set temperatures ti to te, outside temperature toi to tom, and air volume fi
~ Fn, suction temperature si ~ so and suction temperature gradient ki ~
kp is written.

As described above, according to the air conditioner of the embodiment, the input from each sensor is input to the neural network schematic means, the PMV is estimated, and the control signal is generated according to the PMV value. It is possible to realize a more comfortable air conditioning environment in consideration of the indoor environment. Furthermore, the control device can be easily realized by inferring PMV from the neural network model means and replacing the part to be converted into the control signal with the look-up table.

Effects of the Invention As described above, according to the control device for an air conditioner of the present invention, it is possible to realize a more comfortable air conditioning and living environment in consideration of the indoor environment and the human condition. Also, it is obvious that it can be realized easily at low cost.

[Brief description of drawings]

FIG. 1 is a block diagram showing a flow of signals of a control device for an air conditioner according to a first embodiment of the present invention, and FIG. 2 is a block diagram for explaining a learning method of neural network schematic means in FIG. 1, FIG. 3 is a diagram showing position information of the remote controller in FIGS. 1 and 2, and FIG. 4 is a block diagram showing a flow of control device signals of the air conditioner according to the second embodiment of the present invention,
FIG. 5 is a block diagram for explaining a method of creating the lookup table in FIG. 4, FIG. 6 is a diagram showing an example of the lookup table in FIGS. 4 and 5,
FIG. 7 is a block diagram showing a conventional control device. 10,40 …… Sensor, 11,12,41,42 …… Sensor signal, 13,43
...... Memory means, 14,44 ...... Suction temperature gradient every N seconds, 15,45 ...... Remote control or operation panel, 16,46 ...... Air volume, set temperature, etc. 17 ...... Neural network model means, 18 ... … Estimated comfort level, 19 …… Control signal generation means, 1a, 48 …… Control signal, 1b, 49 …… Air conditioner, 1c, 4a …… Indoor temperature adjustment,
1d, 4b …… Position sensor, 1e, 4c …… Remote controller position information, 2
1,51 …… Outdoor temperature, 22,52 …… Suction temperature, 23,53 ……
Gradient of suction temperature, 24,54 …… Air volume, 25,55 …… Set temperature of user, 26,56 …… Human body temperature, 2d, 5d …… Remote controller position information, 27,57 …… Neural network model means , 28,58 ... Control signal generating means, 29,59 ... Measured PMV, 2a, 5a ... PMV estimated value, 2b, 5b ... PMV learning data, 2c, 5c ... Control signal, 2d,
5d ... Remote control position information, 47,5e ... Lookup table, 70 ... Sensor, 71 ... Control signal generating means, 72 ...
Air conditioner, 73 ... Timer, 74 ... Remote control or operation panel, 75 ... Suction temperature, 76 ... Control signal, 77 ...
Timer value, 78 ... Set temperature.

Claims (6)

(57) [Claims] 1. A plurality of sensor means for detecting indoor and outdoor environmental conditions of an air conditioner, a storage means for holding a previous state of the sensor means, and a position of a remote controller for controlling the air conditioner from the outside. Position detecting means for detecting the temperature of the human body, neural network type means for learning human comfort from the outputs from the sensor means and the memory means, the temperature set by the user, and the output from the position detecting means (neuronetwork). And a control means for generating a control signal such as a blowing temperature, a wind direction, and an air volume of the air conditioner based on the comfort feeling of the person in the room estimated by the estimating means. An air conditioner control device comprising: a signal generating unit. 2. The control device for an air conditioner according to claim 1, wherein the sensor means detects an outdoor temperature, a suction temperature and an air volume of the air conditioner, and a humidity. 3. The control device for an air conditioner according to claim 1, wherein the storage means stores the intake temperature gradient of the air conditioner at intervals of N seconds (N is a positive real value). 4. The estimating means and the control signal generating means control the blowing temperature of the air conditioner, the wind direction and the air volume from the outputs from the sensor means and the storage means, the temperature set by the user and the output from the position detecting means. The control device for an air conditioner according to claim 1, which is a storage means of a look-up table adapted to generate a signal. 5. The comfort level of a person in a room, which is estimated by the estimation means, is a predicted average number of votes (PM) calculated according to the state of a person or the environment of the room as an evaluation index for controlling an air conditioner.
V), or a standard new effective temperature (SET) for predicting human physiological condition and sensation.
Air conditioner control device described. 6. 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 ambient wall radiant temperature.