JP2000001116A - Air conditioning system for vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a twin type air conditioning system for one box vehicle permitting accurate presumption of the temperatures in the cabin at front and rear portions which are the main elements of the control logic using temperature detected by one in-cabin temperature detection means, and control of the temper ature in the cabin with high accuracy. SOLUTION: In this system, two temperature presumption units 12a, 12b constituted by neural network presume the temperatures in the cabin at front and rear portions. In this neural network, the in-cabin temperature detection means for detecting temperatures in the cabin is made to be one of inner temperature sensors 6. In addition, a detected temperature Ti by the inner temperature sensor 6, and the vehicle environmental factors including an outer temperature TA, an insolation amount TS, and a blower duty ratio and the state of the air conditioning unit are assumed to be input signals. Further, a presumed value TN1 for the temperature in the cabin at the front portion and a presumed value TN2 for the temperature in the cabin at the rear portion are assumed to output values for each.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle air conditioner for properly controlling the temperature in a passenger compartment to a target temperature, and more particularly to a vehicle air conditioner used for a one-box twin type vehicle. Things.

[0002]

BACKGROUND ART FIG. 12 is a diagram showing a control flow of a conventional vehicle air conditioner, a conventional air conditioner for a vehicle, with respect to the target temperature T _Z that is set in the temperature setting unit 4, the vehicle interior the located control logic 1p was the feedback value of the measured temperature T _i measured by the inside air temperature sensor 6 as the vehicle interior temperature detection means, so as to control the temperature and air volume, etc. of the conditioned air to be blown into the passenger compartment . However, the inside air temperature sensor 6 is normally therefore are installed below the front panel, due to the effect of such ambient temperature and solar radiation, different from the temperature (vehicle interior temperature) T ₀ of the occupant's seating position near I have. In order to approximate the feedback value to the actual cabin temperature T _0, provided an outside air temperature sensor and solar radiation sensor in the vehicle, or to correct the measured temperature T _i based on the output of the sensors, and further, The measured temperature _Ti was corrected based on the air-conditioning air blowing mode and the like.

[0003]

However, the internal temperature
Measurement temperature T measured by sensor_iAnd the actual vehicle interior temperature T₀
Is used in the above control logic to correct the difference
Because of the large number of parameters, it takes time to match
There was a problem. Also, JP-A-6-195323
In the official gazette, as shown in FIG. _Z， Car interior
Temperature (measured temperature of internal air temperature sensor) T_i, Outside temperature T_A,Day
Radiation T_SNeural network type with input signals
Using the additional learning device to control the amount of conditioned air
Techniques are disclosed. This is a neural network
Target blow temperature, blow mode status, blow
Controlling the final air flow by learning and calculating each formula such as air volume
The input / output function of the neural network
Because many teacher signals are used to learn
The problem is that the time is long and the learning is difficult to converge.
Was. In particular, the setting for each of the front and rear
Temperature T_Z1, T_Z2And air volume W_Z1, W_Z2In the settings
Air-conditioning system for one-box twin type vehicles
Indicates the condition of the conditioned air at the front and rear in the passenger compartment.
Learning is further converged because it affects the other conditioned air
It is difficult to learn and the learning time will be long
There was a problem. Furthermore, the conventional twin box for one box
In Ip's vehicle air conditioner, the front and rear
Since it is necessary to provide an internal temperature sensor,
Internal temperature sensor for the rear
Is located far from the control unit.
The length increases and the cost increases. Also the front
Only the control section has an internal temperature sensor, and controls the front and rear
Output of the above internal temperature sensor when
Input to the rear control unit, the front control unit is not moving
Sometimes, the rear control unit is of a type that performs manual operation.
There is also an air conditioner, but in this case, the output of the internal temperature sensor
Does not sufficiently reflect the rear temperature,
Not only not enough, the front controls are not moving
There is a problem that the functional deterioration at the time is significant.

SUMMARY OF THE INVENTION The present invention has been made in view of the conventional problems, and in a vehicle air conditioner of a type capable of setting a set temperature and an air flow rate at a front portion and a rear portion of a vehicle interior, one vehicle interior temperature is set. Provided is a vehicle air conditioner capable of estimating front and rear vehicle interior temperatures, which are main elements of the control logic of an air conditioner, using a temperature detected by a detection unit and controlling the vehicle interior temperature with high accuracy. The purpose is to:

[0005]

According to a first aspect of the present invention, there is provided a vehicle air conditioner having a single vehicle interior temperature detecting means for detecting a temperature in a vehicle interior, and detecting the temperature from the vehicle interior temperature detecting means. Two temperatures configured by a neural network using the temperature, the environmental factor of the vehicle, and the state of the air conditioner as input signals, and the estimated value of the temperature at the front of the vehicle interior and the estimated value of the temperature at the rear as the respective output values. An estimator is provided.
The temperature in the vehicle interior is controlled based on the two estimated values.

According to a second aspect of the present invention, there is provided a vehicle air conditioner having a single vehicle interior temperature detecting means for detecting the temperature in the vehicle interior, the detected temperature from each of the vehicle interior temperature detecting means, the environmental factors of the vehicle, and the air conditioning. A temperature estimator configured as a neural network that uses the state of the device as an input signal and outputs the estimated value of the temperature at the front of the vehicle compartment and the estimated value of the temperature at the rear as respective output values, based on the above two estimated values Thus, the temperature in the vehicle compartment is controlled.

According to a third aspect of the present invention, the temperature of the vehicle interior is adjusted by adjusting the temperature and the amount of conditioned air blown to the front and rear portions of the vehicle interior using the two estimated values as feedback values. It is intended to be controlled.

According to a fourth aspect of the present invention, the environmental factors are the outside air temperature and the amount of solar radiation, and the state of the air conditioner is determined based on the blow mode, the mix door opening, and the blow air flow of the front and rear portions of the passenger compartment. Or any combination of the above information.

According to a fifth aspect of the present invention, there is provided a vehicle air conditioner, comprising: a neural network for obtaining an estimated value of a temperature in a front portion of a vehicle interior; The average temperature of the four points at the position corresponding to the part.

According to a sixth aspect of the present invention, there is provided a vehicle air conditioner, comprising: a neural network for obtaining an estimated value of a temperature in a rear portion of a vehicle compartment;
It is the average temperature at the position corresponding to the head and foot at the center and left.

According to a seventh aspect of the present invention, the input state of the teacher signal used for learning the neural network is normalized from 0.02 to 0.98.

[0012] In the vehicle air conditioner according to the present invention, the sigmoid function used for the neural network is constituted by a linear function having a coefficient different depending on an input range,
And the absolute value of the error between the output value of the linear function and the output value of the sigmoid function in each input range is 3%.
Within the range, the input range and the coefficient of the linear function are approximated by a set function.

[0013]

Embodiments of the present invention will be described below with reference to the drawings. Embodiment 1 FIG. FIG. 1 is a diagram showing a configuration of a vehicle air conditioner according to Embodiment 1 of the present invention, wherein 1 is a control device, 2A is a front air duct, 2B is a rear air duct,
3 is a setting panel for setting the temperature and air volume of the conditioned air,
Reference numerals 4a and 4b _denote temperature setting devices for setting the target temperatures T _Z1 and T _Z2 of the front and rear portions of the vehicle compartment input from the setting panel 3 and outputting the target temperatures T _Z1 and T _Z2 to the control device 1, and 5a and 5b denote the inside of the air ducts 2A and 2B. A plurality of driving devices for respectively adjusting the opening degree of the mix door 2c, etc., and 6 is an inside air temperature sensor as a temperature detecting means at the front of the vehicle compartment. In the first embodiment, the inside air temperature sensor 6 is connected to the front panel. The inside temperature sensor for the front was installed below. 7 is an outside air temperature sensor installed near the bumper of the vehicle, 8 is a solar radiation sensor installed above the front panel, 9 is a front seat, and 10 is a rear seat. The air duct 2A includes an inside / outside air switching door 2a that adjusts a ratio of inside air and outside air introduced into the air duct 2A, a blower 2b that blows air taken in from the inside / outside air switching door 2a, and an evaporator 2c that cools the blowing air. A heater 2d for warming the blast air, a mix door 2e for controlling the temperature of the blast air by controlling the amount of air passing through the heater 2d out of the blast air cooled by the evaporator 2c according to the degree of opening and closing thereof, and Outlet switching door 2h for distributing the discharged air to the upper outlet 2f and the lower outlet 2g. The upper outlet 2f is provided with an upper outlet temperature sensor 2m for detecting the temperature of the upper outlet 2f, and the lower outlet 2g is provided with a lower outlet temperature sensor 2n for detecting the temperature of the lower outlet 2g. Is installed. The drive device 5a includes the inside / outside air switching door 2a, the mix door 2
e, a plurality of actuators for opening and closing the outlet switching door 2h, and a blower driving circuit for driving the blower 2b. The air duct 2B is also the same as the air duct 2A.
It has the same structure as. The control device 1 controls the opening degree and the like of the front or rear mix door 2e according to the environmental factors such as the outside air temperature and the states (control factors) of the front and rear air conditioners such as the air-conditioning air blowing mode. Control signal to drive device 5
a or the front seat control logic 11 to output to the driving device 5b
a and the rear seat control logic 11b and the inside air temperature sensor 6
And each input signal measuring the temperature _{T i} and the control logic 11a, environmental factors and air-conditioning equipment from 11b the state of information from the temperature estimated value of the vehicle compartment to output the control logic 11a, the 11b _{T N1, T N2} , And two temperature estimators 12a and 12b (in the figure, a front temperature estimator A and a rear temperature estimator B) which are formed by neural networks. The control factors include, for example, outputs from the outside air temperature sensor 7 and the solar radiation sensor 8, the degree of opening and closing of the inside / outside air switching door 2a, the mix door 2e, and the outlet switching door 2h, and the drive voltage of the blower 2b.

FIG. 2A shows a neural network (Front Inc.s) in the front temperature estimator 12a.
FIG. 3 is a diagram showing a configuration of a front neural network 12F. The front neural network 12F includes an input layer, a hidden layer, and an output layer.
It is a hierarchical network of layers. FIG. 2 (b)
It is a figure showing composition of a neural network (Inc.s model for rear) in temperature estimator 12b of the back, and rear neural network 12R has the same layer structure as above-mentioned neural network 12F for front. The input signal of the front neural network 12F is the measured temperature T from the internal temperature sensor (Inc.s) 6.
_i (° C.), the outside temperature T _A (° C.) from the outside temperature sensor 7, the amount of insolation from the insolation sensor 8 (Kcal / m ² hour),
The blowing mode (1, 2, 3, 3) set on the setting panel 3
4, 5), the opening degree (%) of the front mix door 2e, and the duty ratio (%) of the front blower motor corresponding to the drive voltage of the front blower 2b. The output value is an estimated value T of the temperature at the front of the vehicle compartment. _N1 (° C.). The input signal of the rear neural network 12R is the same as the input signal of the front neural network 12F, and of the input signals of the front neural network 12F, the control factor of the front air conditioner is used for the rear air conditioner. The output value is an estimated value T _N1 (° C.) of the temperature in the front part of the vehicle interior, which is replaced with a control factor. However, since no internal air temperature sensor is provided at the rear part, the measured temperature T _i (° C.) from the internal air temperature sensor 6 is used as an input signal as the measured temperature.

The neural networks 12F, 12F
In R, a sigmoid function such as the following equation (1) is used. _{y j = 1 / (1 +} exp (- | x j |) ‥‥‥ (1) where, _{x j} is the weight to each input signal _{v i} to the layer i w
_ij multiplied by the bias b _j (x _j
= In _{Σv i · w ij -b j)} , the _{y j} is the output signal from layer i (input signal to the layer j). As shown in FIG. 3, this sigmoid function outputs 0 to 1 when the input variable is -∞ to + ∞. Here, the temperature estimator 12a at the front uses the four-point average temperatures at positions corresponding to the head and foot of the driver's seat and the passenger's seat as teacher signals at the time of learning of the neural network 12F, The weight w _ij and the bias b _j for each input signal of the arithmetic expression for calculating the estimated value T _N1 of the temperature at the front portion are obtained by learning, and at the time of control, the temperature of the temperature at the front of the vehicle compartment is determined for each of the input signals. and outputs an estimated value _{T N1} to the control logic 11a. On the other hand, the rear temperature estimator 12b uses the average temperature at the position corresponding to the head, foot, and left of the right, center, and left portions of the rear seat as the teacher signal, and estimates the temperature T _{N2 at the} rear of the vehicle compartment. determined by learning the value of the weight w _ij and the bias b _j for each input signal of the operational expression for calculating the, at the time of control for each input signal, outputs the estimated value T _N2 in the vehicle interior rear of temperature control logic 11b I do. As an input state to the neural network, each input signal is normalized from the minimum value to the maximum value of the measurement data from 0 to 1, and the weight w for the type of each input signal is obtained.
_ij can be evaluated in the same way. On the other hand, the teacher signal normalizes the minimum value to the maximum value of the measurement data from 0.02 to 0.98 in consideration of the fact that 0 and 1 are saturation output values as output characteristics of the sigmoid function. That is, in the learning of the neural network using the sigmoid function as the input function of the neuron, in consideration of the learning efficiency and the safety, the training signal has a slightly narrower range of 0.02 than that of normalizing the teacher signal from 0 to 1.
Is more effective when the convergence speed is increased.

[0016] Figure 4, the temperature estimator 12a composed of a neural network as described above, at 12b, after sufficiently learned by the learning under the following conditions to estimate the temperature T ₂ of the vehicle interior rear enter the outside air temperature data It is a graph. In addition,
The temperature T _{2 at the} rear of the cabin (marked with a circle) is the right, center,
It is the average value of each measured temperature measured at the position corresponding to each head and foot on the left. A broken line indicates a temperature measured by installing an internal air temperature sensor for comparison data at a position where the conventional internal air temperature sensor for the rear part was located. Learning conditions Outside temperature ‥‥ -10 to 35 (° C.) Solar radiation ０〜 0 to 660 (Kcal / m ² hour) Vehicle speed ‥‥ Idle to 40 (equivalent to Km / h) In FIG. Looking at the change in the output value (estimated value T _N2 ) of the heater 12b, the maximum error is as large as 3.6 ° C., but compared with the change in the measured temperature T _i2 from the rear internal temperature sensor indicated by the broken line, ○ it can be seen that a good followability to changes in the vehicle interior temperature T ₂ shown in.

Next, a method of controlling the temperature in the passenger compartment of the vehicle air conditioner will be described with reference to the control flow of FIG. Front-seat control logic 11a, from the estimated value T _N1 Metropolitan from the front of the regulator and the front of the temperature estimator 12a, the temperature T ₁ of the vehicle compartment front is set at a temperature setting device 4a target temperature T
_The front air duct 2A is controlled so as to be _Z1 .
Similarly, the rear-seat control logic 11b, from the estimated value T _{N 2} Metropolitan from the rear of the regulator and rear temperature estimator 12b,
As the temperature T ₂ of the vehicle interior rear becomes equal to the target temperature T _Z2 is set at a temperature setter 12b, controls the rear of the air duct 2B. The front seat control logic 11a extracts a control factor to be an input signal of the temperature estimator 12a from each of the input environmental factors such as the outside air temperature and the control factors including the state of the air conditioning equipment such as the air-conditioning air blowing mode, Output to the temperature estimator 12a. The temperature estimator 12a calculates the extracted control factors,
Inc. Using the measured temperature T _i from the internal temperature sensor s 6 as an input signal, an estimated value T _N1 of the temperature at the front of the vehicle compartment is obtained by a neural network, and the control logic 11a is used.
Output to Control logic 11a from each regulator and the estimated value T _N1 Prefecture, as vehicle interior temperature T ₁ is equal to the target temperature T _Z1 is set at a temperature setter 4a, air duct 2A of opening degree of the mixing door 2e The feedback control of the temperature of the front part of the vehicle interior is performed for the control elements according to a preset control logic. Rear control logic 11b likewise, as the passenger compartment temperature T ₂ becomes the target temperature T _Z2 is set at a temperature setter 4b, preset control elements of the air duct 2B of opening degree of the mixing door 2e Feedback control of the temperature in the rear part of the vehicle compartment is performed according to the control logic.
That is, the front-seat control logic 11a and the rear-seat control logic 11b do not use the measured temperatures T _i1 and T _i2 from the front and rear inside air temperature sensors as in the prior art, but the temperatures T ₁ and T _{1 at} the front and rear of the vehicle compartment. temperature estimator 1 is very close to the T ₂
Since the control is performed using the estimated values T _N1 and T _N2 of the temperatures at the front and rear portions of the vehicle compartment from 2a and 12b as feedback values, the temperatures at the front and rear portions of the vehicle compartment are accurately and promptly set to the target temperature T _{Z 1.} , T _Z2 .

Embodiment 2 FIG. In the first embodiment, the inside temperature sensor 6 is used as one of the inside temperature sensors 6 for detecting the inside temperature of the vehicle.
Detected temperature T _i of the input signal of 1 Tsutoshi, two temperature estimation configured neural networks to the cabin front portion of the temperature estimate T _N1 and rear temperature estimates T _N2 and respective output values from the vessel 12a, but obtains the estimated value of the vehicle interior front and temperature by 12b, as shown in FIG. 6, 1 detected temperature T _i from the inside air temperature sensor 6 of the input signal Tsutoshi,
2 of the estimated value of the temperature at the front of the cabin and the estimated value of the temperature at the rear
The estimated values T _N1 and T _N2 of the temperatures at the front and rear of the vehicle cabin may be obtained by the temperature estimator 12 constituted by a neural network having one output value. FIG. 7 is a diagram showing a configuration of a neural network in the temperature estimator 12. An input signal of the neural network 12K is a measured temperature T _i from the internal temperature sensor (Inc.s) 6.
(° C.), the outside temperature T _A (° C.) from the outside temperature sensor 7, the amount of insolation (Kcal / m ² hour) from the insolation sensor 8, the front blowing mode which is a control factor for the front part of the cabin, the front mix door Opening degree (%), front blower motor duty ratio (%) corresponding to the front blower drive voltage, rear blow mode, which is a control factor for the rear part of the vehicle interior, rear mix door opening (%), rear blower motor duty ratio (%) ), And the output values are an estimated value T _N1 (° C.) of the temperature in the front of the vehicle compartment and an estimated value T _N of the temperature in the rear.
_N2 (° C).

The temperature estimator 12 outputs, as a teacher signal at the time of learning of the neural network 12K, a four-point average temperature at positions corresponding to the head and foot of the driver's seat and the passenger's seat, and the right side of the rear seat. The weight w for each input signal of the arithmetic expression for calculating the estimated values T _N1 and T _N2 of the front and inside of the vehicle cabin by using the six-point average temperatures at the positions corresponding to the head and the foot at the center and the left, respectively. _ij and bias b _j
Is obtained by learning, and at the time of control, an estimated value T _N1 ,
It outputs _TN2 to the front and rear control logics 11a and 11b, respectively.

FIGS. 8A and 8B show a temperature estimator 12 constituted by the above-described neural network.
7 is a graph in which outside temperature data is input and temperatures T ₁ and T ₂ at the front and rear of the vehicle compartment are estimated after sufficient learning under the following learning conditions. In FIG. 8A, circles indicate the average temperature of four points at the positions corresponding to the head and feet of the driver's seat and front passenger seat, respectively, and circles in FIG. 8B indicate the right and center of the rear seat. , And 6-point average temperatures of the respective measured temperatures measured at positions corresponding to the respective head and foot portions on the left. The broken line in FIG. 8A indicates the temperature measured by the internal air temperature sensor 6, and the broken line in FIG. 8B indicates the internal air temperature sensor for comparison data at the position where the conventional rear internal air temperature sensor was located. Is the temperature measured by installing Learning conditions Outside temperature ‥‥ -10 to 35 (° C.) Solar radiation ０〜 0 to 660 (Kcal / m ² hour) Vehicle speed ‥‥ Idle to 40 (equivalent to Km / h) In FIGS. 8A and 8B, solid lines The changes in the output values (estimated values T _N1 and T _N2 ) of the temperature estimator 12 indicated by have a large maximum error of 2.8 ° C., but the inside air temperature sensor 6 indicated by a broken line and the rear inside air temperature sensor Measured temperature T from
_i1, compared to a change in _{T i2,} vehicle interior temperature T indicated by ○
_It can be seen that it has good followability to changes in T ₁ and T ₂ and is sufficiently practical.

Next, the temperature of the cabin of the vehicle air conditioner is measured.
The control method will be described based on the control flow of FIG.
You. The front-seat control logic 11a controls each of the front control factors and the temperature.
Estimated value T from degree estimator 12_N1From the temperature in the front of the cabin
Degree T₁Is set by the temperature setting device 12a and the target temperature T_{Z 1}To
The front air duct 2A is controlled so that As well
In addition, the rear seat control logic 11b determines each control factor and temperature of the rear.
Estimated value T from degree estimator 12_N2From the rear cabin temperature
T₂Is set by the temperature setting device 12b and the target temperature T_Z2Nana
Thus, the rear air duct 2B is controlled. Control logistics
11a and 11b are input environmental factors such as the outside air temperature.
And the condition of the air conditioning equipment, such as air conditioning mode
Control that becomes an input signal of the temperature estimator 12 from each control factor
The factors are extracted and output to the temperature estimator 12. Temperature estimator
12 indicates the extracted control factor, Inc. s (shy
Temperature T) from the temperature sensor 6 _iAre input signals, and
By using the neural network, the temperature in the front and rear
Degree estimate T_N1, T_N2Control logic 11
a and 11b. The control logic 11a
Control factor and the above estimated value T_N1From the vehicle interior temperature T₁But
Target temperature T set by temperature setting device 4a_Z1To be
And control of the air duct 2A such as the opening degree of the mix door 2e.
Elements are adjusted to the front of the cabin according to preset control logic.
Temperature feedback control. Rear seat control logic 1
Similarly, the vehicle interior temperature T₂Is set by the temperature setting device 4b.
Set target temperature T_Z2Mix door 2e
The control elements of the air duct 2B such as the opening of the air duct are set in advance.
Feedback the temperature in the rear of the cabin according to the control logic.
Control. Therefore, the front seat control logic 11a, the rear
The seat control logic 11b is located between the front and rear
Measurement temperature T from air temperature sensor_i1, T_i2Not a car
Temperature T at the front and rear of the room₁, T₂Very close to
Front and rear from the temperature estimators 12a and 12b
Temperature estimate T_N1, T_N2Is the feedback value
Control so that the temperature in the front and rear
And quickly set the target temperature T _Z1, T_Z2Can be
You.

In the first and second embodiments,
Although the conventional inside air temperature sensor 6 is used as the detecting means for detecting the temperature in the vehicle interior, the set position of the inside air temperature sensor is not limited to this, but may be appropriately determined according to the size of the vehicle and the like. Needless to say. In addition, the teacher signal regarding the rear temperature used in the neural network was the average temperature at the positions corresponding to the head, foot, and right of the rear seat, respectively. In a vehicle having two rear seats, when the two rear seats are air-conditioned by one rear air conditioner, the teacher signal is transmitted to, for example, the right, center, and left heads of the second row, respectively. And six points at positions corresponding to the head and the foot on the right, center, and left of the third row in the third row.
What is necessary is just to make the average temperature of a total of 12 points.

Embodiment 3 FIG. In the first embodiment, the sigmoid function shown in equation (1) is used for the neural network. However, by approximating this sigmoid function with a plurality of straight lines, the number of required memories of the temperature estimators 11a and 11b can be reduced. At the same time, since the calculation time can be greatly reduced, the temperature in the vehicle compartment can be more quickly brought to the target temperature Tz. That is, when the sigmoid function shown in the equation (1) is programmed by, for example, an 8-bit embedded microcomputer, an exponential function and a floating-point arithmetic library are required to maintain accuracy.
The capacity and calculation time increase. On the other hand, since the linear function does not include division, there is no need for a floating-point operation, so that the operation accuracy can be maintained even when an integer operation is used, and the ROM capacity and the calculation time can be reduced. Therefore, when the neural network learns, the sigmoid function of the above equation (1) is used. When the learned network is programmed in an actual embedded microcomputer, the sigmoid function of the above equation (1) is used as shown in FIG. Is such that the error is within ± 0.005, for example,
By using a function approximated by 17 straight lines (linear function) as a substitute for the sigmoid function of the above equation (1), R
The OM capacity and the calculation time can be reduced, and the calculation accuracy can be maintained. FIG. 11 is a diagram showing an error between the sigmoid function of the equation (1) and a function obtained by approximating the sigmoid function with the linear function. It can be seen that the magnitude of the error is within ± 0.005 in the entire input range. .

In the above example, the sigmoid function is approximated to 17 straight lines such that the error is within ± 0.005. However, if the error is within ± 0.03 (± 3%), there is a practical problem. Absent. In addition, the approximated function does not necessarily need to be a broken line, and in some cases, it may be better to make the function discontinuous in order to reduce the number of straight lines (the number of divisions of the input range) and increase the calculation speed. In the first and second embodiments, the case where the logarithmic sigmoid function of the equation (1) is used has been described. However, other types of sigmoids such as the tanh-type sigmoid function shown in the following equation (2) are used. Of course, functions may be used. y _j = (tanh (x _j ) +1) / 2 ‥‥‥ (2)

[0025]

As described above, the vehicle air conditioner according to the first aspect of the present invention includes a single vehicle interior temperature detecting means for detecting the temperature in the vehicle interior, and detects the detected temperature from the vehicle interior temperature detecting means. And the environmental factors of the vehicle and the state of the air conditioner as input signals, respectively, and an estimated value of the temperature in the front part of the cabin and an estimated value of the temperature in the rear part as the respective output values, two neural networks constituted by a neural network. The temperature in the cabin is controlled based on the above two estimated values. Therefore, even when the set temperature and the air flow are different between the front seat and the rear seat, the control considering the mutual influence is performed. Can be
The temperatures at the front and rear portions of the vehicle interior can be quickly set to the respective target temperatures. In addition, since there is only one cabin temperature detecting means, the device can be easily manufactured, and the development period and cost can be reduced.

According to a second aspect of the present invention, there is provided a vehicle air conditioner having a single vehicle interior temperature detecting means for detecting the temperature in the vehicle interior, and further providing an estimated value of the temperature in the front part of the vehicle interior and an estimated value of the temperature in the rear part. Since the estimated values of the front and rear temperatures are obtained by one temperature estimator constituted by a neural network having each output value, the development period and cost can be further reduced.

The vehicle air conditioner according to the third aspect of the invention adjusts the temperature and air volume of the conditioned air to be blown to the front and rear portions of the cabin by using the two estimated values as feedback values to control the temperature of the cabin. Since the control is performed, the temperatures at the front and rear portions of the vehicle interior can be accurately and quickly set to the respective target temperatures.

According to a fourth aspect of the present invention, the environmental factors are the outside air temperature and the amount of solar radiation, and the state of the air conditioner is determined based on the blow mode, the mix door opening degree, and the blow air flow of the front and rear portions of the passenger compartment. Or all of the above information, it is possible to reliably control the front seat and the rear seat in consideration of each other's setting situation.

According to the vehicle air conditioner of the present invention, the teacher signal used for learning the neural network in the front of the passenger compartment is calculated by averaging the positions corresponding to the head and foot of the driver's seat and the passenger's seat. Since the temperature is used, the difference between the estimated value of the vehicle interior temperature and the actual vehicle interior temperature can be made extremely small.

According to the vehicle air conditioner of the present invention, the teacher signal used for learning the neural network in the front and rear portions of the vehicle compartment corresponds to the head, foot, and right of the rear seat on the right, center, and left, respectively. Since the average temperature at the position is set, the difference between the estimated value of the vehicle interior temperature and the actual vehicle interior temperature can be made extremely small.

In the vehicle air conditioner according to the present invention, the input state of the teacher signal used for learning the neural network is normalized from 0.02 to 0.98. Efficiency and safety can be improved.

In the vehicle air conditioner according to the present invention, the sigmoid function used at the time of learning of the neural network is determined by setting the absolute value of the error between the output value in each input range of the linear function and the output value of the sigmoid function to 3 %, The number of required memories can be reduced and the calculation time can be significantly reduced by approximating the input range and the function of the coefficient of the linear function. The target temperature can be quickly reached.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a configuration of a vehicle air conditioner according to a first embodiment of the present invention.

FIG. 2 is a diagram illustrating a configuration of a temperature estimation model according to the first embodiment of the present invention.

FIG. 3 is a diagram showing a sigmoid function used in a neural network.

FIG. 4 is a diagram illustrating a relationship between an estimated value of a vehicle interior temperature and an actually measured value by a temperature estimator according to the first embodiment of the present invention.

FIG. 5 is a diagram showing a control flow of the vehicle air conditioner according to the first embodiment of the present invention.

FIG. 6 is a diagram showing a configuration of a vehicle air conditioner according to Embodiment 2 of the present invention.

FIG. 7 is a diagram illustrating a configuration of a temperature estimation model according to a second embodiment of the present invention.

FIG. 8 is a diagram illustrating a relationship between an estimated value of a vehicle interior temperature and an actually measured value by a temperature estimator according to a second embodiment of the present invention.

FIG. 9 is a diagram showing a control flow of the vehicle air conditioner according to Embodiment 2 of the present invention.

FIG. 10 is a diagram illustrating an approximation method of a sigmoid function according to the third embodiment of the present invention.

FIG. 11 is a diagram showing an error between a sigmoid function and a linear function.

FIG. 12 is a diagram showing a control flow of a conventional vehicle air conditioner.

FIG. 13 is a diagram showing a configuration of a neural network of a conventional vehicle air conditioner.

[Explanation of symbols]

1 control device, 2A, 2B air duct, 3 setting panel, 4, 4a, 4b temperature setting device, 5a, 5b driving device, 6 inside temperature sensor, 7 outside temperature sensor, 8 sunlight sensor, 9 front seat, 10 rear seat , 11a Front seat control logic, 1b Rear seat control logic, 12, 12a, 1
2b Temperature estimator.

 ────────────────────────────────────────────────── ─── Continuing on the front page (72) Mr. Mamoru Masakazu 39, Higashihara, Chiyo, Oga-gun, Osato-gun, Saitama F-term (reference) 3L011 AF02

Claims (8)

[Claims] 1. A vehicle interior temperature detecting means for detecting a temperature in a vehicle interior is provided as one, and a temperature detected by the vehicle interior temperature detecting means, an environmental factor of the vehicle, and a state of an air conditioner are input signals respectively. Two temperature estimators, each of which is constituted by a neural network that uses the estimated value of the temperature at the front of the vehicle interior and the estimated value of the temperature at the rear, as output values, respectively, control the temperature in the vehicle interior based on the two estimated values. An air conditioner for a vehicle, characterized in that: 2. A vehicle interior temperature detecting means for detecting the temperature in the vehicle interior is provided as one unit, and the detected temperature from each of the vehicle interior temperature detecting means, the environmental factors of the vehicle and the state of the air conditioner are used as input signals. A temperature estimator configured by a neural network that uses the estimated value of the temperature at the front of the cabin and the estimated value of the temperature at the rear as output values, and controls the temperature in the cabin based on the two estimated values. An air conditioner for a vehicle, characterized in that: 3. The vehicle air conditioner according to claim 1, wherein the temperature in the passenger compartment is controlled using the two estimated values as feedback values. 4. The air conditioner according to claim 1, wherein the environmental factors are an outside air temperature and an amount of solar radiation, and the state of the air conditioner is a blowing mode of a front part and a rear part of a passenger compartment.
The vehicle air conditioner according to claim 1 or 2, wherein any one or all of the information on the mix door opening and the blown air volume is combined. 5. In a neural network for obtaining an estimated value of the temperature in the front part of the vehicle compartment, a teacher signal used at the time of learning is an average temperature at a position corresponding to a head and a foot of a driver seat and a passenger seat. The vehicle air conditioner according to claim 1 or 2, wherein: 6. A neural network for obtaining an estimated value of the temperature at the rear of the vehicle compartment, wherein a teacher signal used for learning is obtained by calculating the average temperature at the positions corresponding to the right, center, and left heads and feet of the rear seat. The vehicle air conditioner according to claim 1 or 2, wherein: 7. The vehicle according to claim 1, wherein an input state of a teacher signal used at the time of learning of the neural network is normalized from 0.02 to 0.98. Air conditioner. 8. A sigmoid function used for a neural network is constituted by a linear function having coefficients different depending on an input range, and an error between an output value in each input range of the linear function and an output value of the sigmoid function. The vehicle air conditioner according to claim 1 or 2, wherein the input range and the coefficient of the linear function are approximated by a function in which an absolute value is within 3%.