JPH05173604A - Air conditioning device - Google Patents

Abstract

PURPOSE:To automatically control a combustion quantity, an air blowing quantity, and an air direction, etc., by automatically generating the control rule of an air conditioner according to input data from respective sensors and their current data when the air conditioner is well controlled by employing a descent method which is a sort of nonlinear search method. CONSTITUTION:An inference rule storage part 1 is stored with a fuzzy inference rule and a membership function storage part 2 is stored with shape data on the membership function of an antecedent using fuzzy inference and the function expression of consequent. A descent method arithmetic part 5 performs arithmetic operations by the descent method from input and output data obtained by control engineers and inference results to find the direction of tuning. A membership function adjustment part 6 updates and adjusts parameters stored in the membership function storage part 2 according to the result of the arithmetic part 5. The membership function storage part 2 is stored with object parameters in inference rule order and then parameters including the knowledge of the control engineers are set as a result of the tuning.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION The present invention relates to an oil fan heater,
The present invention relates to an air conditioner capable of learning an operation control method suitable for each user's operation in controlling the room temperature of an air conditioner such as an air conditioner.

[0002]

2. Description of the Related Art Fuzzy inference is an attempt to execute the knowledge obtained by humans from conventional experience by a computer using inference rules in a complicated controlled object that cannot describe a mathematical model.

In the conventional fuzzy inference, as shown in FIG. 10, the input information obtained from the control observation value input unit 101, for example, the control deviation e and its change rate Δe, and the control operation amount output unit 103 output the information. If ~ then the relationship between the manipulated variables u
When describing as a rule, a plurality of the following inference rules are prepared in the fuzzy inference rule storage unit 104.

IF e is Zero (ZO) and Δe is Positive Small (PS) Then u is Negative Small (NS). Here, the if to part is called the antecedent part, and the part ... Then the consequent part. Zero, Positive Small, Negative Small, etc. are labels that represent the input and output membership functions used to describe inference rules. This membership function is stored in the membership function storage unit 105.

FIG. 11 shows an example of the membership function. The membership function is a symmetric triangle.

Commonly used membership functions include NB (negatively large), NS (negatively small), ZO (approximately zero), PS (positively small), PB (positively large), and the like.

Next, the fuzzy inference process performed by the fuzzy inference operation unit 102 will be described. Now, it is assumed that the following n inference rules are stored in the fuzzy inference rule storage unit 104. R ¹ : IF e is ZO and △ e is PS THEN u is NS R ² : IF e is ZO and △ e is PB THEN u is PB ・ ・ R ⁿ : IF e is NB and △ e is ZO THEN u is NB However, R ⁱ (i = 1,2, ... n) is an inference rule.

Here, the inference rule for the input information e, Δe
The first rule R is used to calculate the suitability μ _i of the antecedent part of R ^i.
This will be explained using ¹ as an example. Where μ _zo (e) and μ _ps (△ e) are the input information for the membership functions ZO and PM of the antecedent proposition.
Indicates the membership value of e, △ e. Now eo from the control observation value input portion 101, △ when eo have been inputted, rules fit mu ₁ for R _{^1, μ 1 = μ zo (eo} ) Λμ ps (△ eo) (1) However, lambda is min It becomes an operation.

The membership function ω ¹ of the conclusion of the consequent part of the inference rule R ¹ is the membership function NS of the consequent proposition.
The membership value of μ _ns (u) is used as follows. ω1 = μ ₁ Λμ _ns (u) (2) Since there are multiple inference rules R ⁱ , the membership function that combines the membership functions of all conclusions is u _T = ω1Vω2Vω3V ・ ・ ・ Vωn (3) where V indicates max operation. Becomes This membership function u _T is the conclusion membership function that indicates the control operation amount, but the actual control operation amount
Since uo is a real number, it is necessary to convert the membership function u _T to a real number. For example, the weighted center of gravity shown below is adopted as the conversion method. The control operation amount uo is

[0010]

[Number 1] _{uo = (∫u · μ T du} ) / (∫μ T du) (4) , and the output to the control operation amount output unit 103.

[0011]

However, with the above configuration, it is difficult to optimally construct the inference rules and membership functions for the following reasons. Especially, like an air conditioner, room temperature, radiation amount, air flow, humidity, all of these,
Alternatively, in consideration of either of them, complicated control such that there are a large number of input / output parameters such as controlling the combustion amount, the air flow amount, and the wind direction, and the range of each condition covers a wide range makes it impossible to construct. Because the reasoning rules and membership functions cannot be expressed by the user or the control engineer of the air conditioner, and therefore the rules when they are successfully controlled cannot be written, so when the fuzzy reasoning is successful There was a problem that the control of could not be automated.

Further, in the conventional configuration, since the inference rule and the membership function are fixed, there is a problem that the control cannot be changed according to the user's preference.

In view of the conventional problems such as fuzzy inference, the present invention provides an air conditioner capable of automatically creating a desired fuzzy inference rule without trial and error and incorporating the control method of a control engineer or each user. It is intended to be provided.

[0014]

According to the present invention, fuzzy inference is performed by inputting all or any one of environmental conditions such as room temperature, radiation amount, air flow, and humidity, and air-conditioning such as combustion amount, air flow amount, wind direction, etc. A fuzzy inference operation unit that outputs conditions,
An inference rule storage unit that stores inference rules used for fuzzy inference, a membership function storage unit that stores the shape data of the membership function of the antecedent part and the functions of the consequent part used for the inference rule, and the manufacturer Side input and output data obtained from the experiment on the side and inference results obtained from the fuzzy inference operation unit, the descent method operation unit that performs an operation by the descent method, and the output of the descent method operation unit, the membership function of the antecedent and the consequent A membership function adjustment unit that changes at least one of the functions of the department, and an inference error calculated from the input / output data and the inference result obtained from the fuzzy inference operation unit, and the descent method operation unit when the inference error is smaller than a predetermined value. It is an air conditioner including an error calculation unit that stops the operation of the membership function adjustment unit.

[0015]

In the present invention, the inference rule storage unit stores the inference rules used for fuzzy inference, and the membership function storage unit uses the shape data of the membership function of the antecedent part and the function of the consequent part used for the inference rule. I remember. Then, the fuzzy inference operation unit inputs all or any of the environmental conditions such as room temperature, radiation amount, air flow, and humidity, and performs fuzzy inference, and outputs the air conditioning conditions such as the combustion amount, the air flow rate, and the wind direction. The descent method calculation unit performs the calculation by the descent method from the input / output data obtained from the manufacturer's experiment and the inference result obtained from the fuzzy inference calculation unit, and the membership function adjustment unit outputs the result of the descent method calculation unit. Change at least one of the membership function of the department and the function of the consequent part,
The error calculation unit calculates an inference error from the input / output data and the inference result obtained from the fuzzy inference operation unit, and when the inference error is smaller than a predetermined value, the operations of the descent method operation unit and the membership function adjustment unit are stopped.

With this, the inference rule and the membership function of fuzzy inference are automatically generated based on the output data. After that, fuzzy inference can be performed by this automatically generated inference rule and membership function, and the control method when properly controlled can be automated.

[0017]

Embodiments of the present invention will be described below with reference to the drawings.

An embodiment of the first present invention will be described. First, the basic principle of the present invention will be described. The following input / output data are collected by an experiment by a control engineer on the manufacturer side. That is, the output data when the control engineer successfully controls the combustion amount, the air flow amount, and the wind direction with respect to the input data in various situations such as room temperature, radiation amount, air flow, humidity, or all of them. Is. The control engineer considers the indoor situation from various angles, and feels the most comfortable in that situation, that is, the combustion amount, the air flow rate, and the PMV (predictive average declaration index) become zero. Design so that the wind direction can be adjusted automatically. Here, PMV is a thermal sensation index established by ISO (International Organization for Standardization).
It represents the degree of comfort from six combinations of temperature, humidity, airflow, and radiation (indoor environment) and human clothing and activity (human condition). When PMV = 0, neither hot nor cold, It can be said that it is in a good condition. PMV = 1, slightly warm, P
It means that MV = -1 and it is a little cool. For example,
Even if the room temperature is the same, if the amount of radiation from the wall or ceiling changes, the sensible temperature changes, so in order to have a comfortable sensible temperature,
It is necessary to control operations such as the amount of combustion, the amount of blown air, and the wind direction. Among the six factors that determine the comfort of PMV, the high and low of the room temperature are related to the comfort, and the thermistor can be used as a sensor for input data. Humidity is uncomfortable when the humidity is too high or too low even if the temperature is just right. Therefore, input data necessary for operation control is used, for example, a sensor consisting of a Humicellum is used. The amount of radiation is necessary input data because the comfort changes depending on the temperature of the wall and floor that changes due to weather and sunlight, so it is a necessary input data.As a sensor, a thermistor installed in the center of the hemisphere consisting of a mirror surface is placed outside the device Calculated from the temperature difference with the thermistor installed inside. On the other hand, the airflow feels warm or cold depending on the strength of the warm air, so it is necessary data, and this may be the amount of airflow before control. There is a big difference in comfort depending on the amount of activity, whether it is moving or still, and the amount of clothing will naturally vary depending on whether you are wearing a shirt or a sweater. There is no choice but to inquire directly or to make an analogy with remote control operation or button operation on the panel surface. In each of the four seasons, the control engineer assumes the standard amount of clothing and activity, and determines the remaining room temperature, humidity, radiation,
Considering the air flow, it is possible to set the combustion amount, air flow rate, and wind direction that will result in PMV = 0 based on many years of experiments and experience under various conditions. In this way, the fuzzy rule can no longer be constructed with complicated control in which there are many input and output parameters and the range of each condition is wide. This is because the control engineer cannot express what the inference rules and membership functions are, and therefore cannot describe the rules when they are successfully controlled.
It is not possible to automate the successful control by fuzzy reasoning. Therefore, in the present invention, based on the input data from each sensor and the output data at that time when the control is successful, the control rule is automatically generated by using the descent method which is a kind of nonlinear search method. After that, based on this generated rule, the amount of combustion, the amount of airflow, and the direction of airflow are automatically fuzzy inferred for the input data from sensors,
Perform automatic control.

The configuration and operation of the air conditioner of the first invention will be described with reference to the configuration diagram of FIG. 1 and the flowchart of FIG.

In FIG. 1, the inference rule storage unit 1 is a storage unit that stores inference rules of fuzzy inference, and the membership function storage unit 2 is shape data of the membership function of the antecedent part used for fuzzy inference and the consequent. Storage unit for storing functional equations of parts, fuzzy inference operation unit 3 is an operation unit for performing inference operations for fuzzy inference, 4 is a control target, and descent method operation unit 5 is input / output data obtained from a control engineer. And the membership function adjusting unit 6 is a descent method computing unit 5
An adjustment unit and an error calculation unit 7 that update the parameters stored in the membership function storage unit 2 based on the calculation result of
Is an operation unit that calculates the inference error from the inference result of fuzzy inference and input / output data.

To simplify the description, a two-input one-output control system will be described as an example. The present invention can be similarly applied to N inputs and M outputs.

The inference rule storage unit 1 stores the following inference rules. R ¹ : IF x ₁ = A ₁₁ & x ₂ = A ₁₂ THEN y = f ₁ (x ₁ , x ₂ ) R ² : IF x ₁ = A ₂₁ & x ₂ = A ₂₂ THEN y = f ₂ (x ₁ , x ₂ ) .................................... R ⁿ : IF x ₁ = A _n1 & x ₂ = A _n2 THEN y = f _n (x ₁ , x ₂ ) R ⁱ is the inference rule number, n is the inference rule number, A _ij (i = 1,., nj = 1,
2) is the membership function of the antecedent part, and f _i (x ₁ , x ₂ ) is the linear function of the antecedent part.

The membership function A _ij is an isosceles triangle type as shown in FIG. 3, and its center value is a _ij and its width is b _ij .
The linear function of the consequent part is f _i (x ₁ , x ₂ ) = p _i · x ₁ + q _i · x ₂ + r _i (5) (i = 1, ..., n).

The membership function storage unit 2 stores these parameters to be tuned, a _ij , b _ij , p _i ,
q _i , r _i (these are called tuning parameters)
Store in the order of inference rules. [Step a1] First, the membership function adjusting unit 6 initializes the membership function used for fuzzy inference and the input / output data number p. For example, the initial value of the central value a _ij of the membership function A _{ij in} the antecedent part is
Set to divide the entire set of input variables into equal parts. Width b
_ij is set to be larger than the interval between the center values of the membership functions, and the membership functions are set to overlap. The coefficients p _i , q _i , r _i of the linear function of the consequent part are initialized to 0. The input / output data number is initialized to 1. "Step a2" Input / output data (x
_1p , x _2p , y _p ^r ). The input data (x _1p , x _2p ) is input to the fuzzy inference operation unit 3. The output data y _p ^r is input to the descent method calculation unit 5 and the error calculation unit 7. "Step a3" The fuzzy inference operation unit 3 performs fuzzy inference with ( _x1p , _x2p ) as an input. In this inference, the operation represented by the following equation is performed to obtain the manipulated variable y _p ^* for the controlled object 4. μ _i = A _i1 (x _1p ) ・ A _i2 (x _2p ) (6)

[0025]

[Equation 2]

[Step a4] In the descent method computing unit 5, the tuning parameters a _ij , b _ij , p _{i are} calculated from the inference result y _p ^* obtained in step a3 and y _p ^r input in step a2.
Calculate the tuning direction of q _i and r _i . Here, as an objective of tuning the membership function, the evaluation function of the following equation is minimized.

[0027]

[Equation 3]

This equation represents the difference between the inference result y _p ^* and the data y _p ^r obtained from the skilled driver, that is, the inference error. The descent method computing unit 5 uses the steepest descent method, which is one of the descent methods. In the steepest descent method, the differential value of the evaluation function is used to find the direction in which the tuning parameter for minimizing the evaluation function is updated.

Here, a method for obtaining a direction for minimizing the evaluation function E regarding the tuning parameter r _i will be described.

In FIG. 4, the horizontal axis is r._iShows the evaluation function E as
It was done. r_i= r_iDifferential value when'∂E (r_i') / ∂r_i
Is r as shown in FIG._i'The slope of the evaluation function at
means. Figure 4 (a) shows ∂E (r_i') / ∂r_iIs positive, Fig. 4 (b)
Is ∂E (r_i') / ∂r_iIs a negative time. Here, in FIG.
Tuning parameter r_i∂E (r_i') /
∂r_iIf a small amount is moved in the direction opposite to the sign of, the evaluation function E
Decreases. Similarly, ∂E (r_i') / ∂r_iIs negative
Even when the tuning parameter is ∂E (r_i') / ∂r _iof
When a small amount is adjusted in the direction opposite to the sign, the evaluation function E decreases
To do. That is, the tuning parameter r_iIs the differential amount ∂
E / ∂r_iAdjusting in the direction opposite to the sign of causes the evaluation function E to decrease.
By repeating this a little, the evaluation function E becomes minimal.
It will converge to the value.

Here, from Eqs. (7) and (8) for obtaining ∂E / ∂r _ij

[0032]

[Equation 4]

[Mathematical formula-see original document] Then, a numerical operation is performed by the equation (9) to obtain the value of ∂E / ∂r _ij .

Similarly, in the descent method calculation unit 5, ∂E / ∂
a _ij , ∂E / ∂b _ij , ∂E / ∂p _ij , ∂E / ∂q _ij , ∂E / ∂r _ij are calculated, and the adjustment direction to reduce the evaluation function is calculated. “Step a5” In the membership function adjusting unit 6, ∂E / ∂a _ij , ∂E / ∂b _ij , ∂E / ∂ calculated by the descent method calculating unit 5
Tuning parameters stored in the membership function storage unit 2 using p _i , ∂E / ∂q _i , and ∂E / ∂r _i
Update a _ij , b _ij , p _i , q _i , r _i .

The update is performed by the following formula. here
K _a , K _b , K _p , k _q , and K _r are constants.

[0036]

[Equation 5]

"Step a6" The membership function adjusting unit 6 continues the updating of step a5 as follows. Compare the input / output data number p with the total number N of input / output data. If the input / output data number p is smaller than the total number N of input / output data, proceed to step a7, increment the value of p by 1 and return to step a2. , Steps a2 to a7 are repeated until the data number p becomes equal to the total number N of input / output data. If the input / output data number p is larger than the total number N of input / output data, the update is stopped and the process proceeds to step a8. “Step a8” The inference error D and the variation ΔD thereof are calculated by the error calculation unit 7 from the equations (15) and (16).

[0038]

[Equation 6]

Here, t represents the number of times of tuning, and ΔD is the difference between the inference error at the time of tuning one time before and the current inference error. [Step a9] The error calculator 7 further compares the variation ΔD of the inference error with a predetermined threshold value T. If the amount of change ΔD is larger than the predetermined threshold value T, the process proceeds to step a10 to initialize the input / output data number p to 0, and step a2
To step a8 are repeated. If the amount of change ΔD is smaller than the predetermined threshold value T, it is determined that the tuning has converged, the error calculation unit 7 stops the operations of the descent method calculation unit 5 and the membership function adjustment unit 6, and ends the tuning.

In this way, at the end of tuning, the tuning parameters a _ij , b _ij , p _i corresponding to the inference rules that incorporate the knowledge of the control engineer are stored in the inference rule storage unit 1 and the membership function storage unit 2. , Q _i , r _i have been set.

At this point, when shipped, when the user operates the air conditioner, the fuzzy inference operation section 3 makes an inference similar to that of the control engineer in response to the input from the sensor, and the result of the control target 4 The air conditioner can be operated.

As described above, according to this embodiment, it is possible to obtain the optimum inference rule by the descent method from the input / output data obtained from the control engineer. Therefore,
By using the acquired inference rule, it is possible to realize an air conditioner in which the knowledge and know-how of the control engineer are easily installed in the device.

In this embodiment, the membership function is of an isosceles triangle type, but the same effect can be obtained even if it has another shape. The consequent part may be a non-linear function or a membership function instead of a linear function.

Further, in the present embodiment, the steepest descent method is used as the descent method of the descent method computing unit 5, but the Newton method, the conjugate gradient method, the Porell method, etc. may be used. Although the error calculation unit 7 determines the end of tuning based on the value of the inference error, a method of giving the number of times of tuning in advance before starting the tuning may be used.

Next, an embodiment of the second invention will be described. The present invention is to perform tuning with the consequent part of the membership function storage unit 2 described in the first present invention as a real value.

Since the consequent part of the inference rule is a real value, the number of tuning parameters is small, and faster automatic tuning and fuzzy inference are possible as compared with the first embodiment of the present invention.

FIG. 5 is a block diagram of the fuzzy inference apparatus according to the second aspect of the present invention. The same components as those in FIG. 1 are designated by the same reference numerals. That is, in FIG. 5, the inference rule storage unit 1 is a storage unit that stores inference rules of fuzzy inference, and the membership function storage unit 21 is the shape data and consequent part of the membership function of the antecedent part used for fuzzy inference. Fuzzy inference operation unit 3
Is an operation unit for performing inference operations for fuzzy inference, 4 is a control target, and descent method operation unit 23 is an operation unit for performing an operation by a descent method from input / output data obtained from a control engineer and an inference result to obtain a tuning direction. The membership function adjustment unit 24 is an adjustment unit that updates the parameters stored in the membership function storage unit 22 based on the calculation result of the descent method calculation unit 23. The error calculation unit 7 is the inference result of fuzzy inference and input / output data. This is a calculation unit that calculates the inference error from.

Differences from the first aspect of the present invention will be described.

In the inference rule storage unit 21, the consequent part is a real number. In the inference rule storage unit 1, the consequent part uses the linear form shown by the equation (5), but in the present invention, the real value w _i (i = 1, .., n). n is the number of inference rules. Therefore, in the fuzzy inference operation unit 3, f _{i in the} expression (7) becomes a real value w _i , which simplifies the operation and speeds up the inference time. The tuning parameters stored in the membership function storage unit 22 are a _ij , b _ij , and w _i , which are smaller than a _ij , b _ij , p _i , q _i , and r _{i in the} membership function storage unit 2. .. In the descent method computing unit 23, ∂E / ∂a _ij , ∂E / ∂b _ij , ∂E / ∂p _i , ∂E / ∂w _i may be calculated in order to calculate the parameter updating direction. ∂E / ∂a _ij , ∂E / ∂b _ij , ∂E of descent method calculation unit 5
Compared with / ∂p _i , ∂E / ∂q _i , and ∂E / ∂r _i , the number of calculations is reduced.

Compared to the membership function adjusting unit 6, the parameter updating operation in the membership function adjusting unit 24 is the same as in the expressions (10) and (11), but (12), (1)
Equations (3) and (14) are simplified by the following one equation. here
K _w is a constant.

[0051]

[Equation 7]

The method of minimizing the inference error by the descent method computing unit 23 is the same as that described with reference to FIG. 2, and the tuning is completed. At the end of tuning, the inference rule storage unit 1 / membership function storage unit 22 is constructed with an inference rule incorporating the knowledge of the control engineer.

As described above, according to this embodiment, it is possible to obtain the optimum inference rule by the descent method from the input / output data obtained from the control engineer. In particular, since the consequent part of the inference rule is a real value, the number of tuning parameters is small, and higher-speed automatic tuning is possible as compared with the first embodiment of the present invention. Further, by using the present invention, since the consequent part is a real number, even after tuning, fuzzy inference can be realized by a simple program or hardware, and a control method similar to that of a control engineer can be easily installed in the device. it can.

Next, an embodiment of the third invention will be described.

In the air conditioner based on the inference rule tuned based on the input / output data obtained by the manufacturer's experiment, the rule is that of the control engineer or the user with the greatest common divisor. That is, control is performed so that PMV = 0 under the standard amount of clothing and activity.

On the other hand, the control method differs slightly depending on the amount of clothing of each user, the amount of activity immediately after exercising, the age, the gender difference, and the like. For example, a little warmer (PMV = 1) is more comfortable for an infant or an elderly person, or a person with a heavy weight is hot and somewhat cooler (PMV =-).
1) Some people find it more comfortable. In the third aspect of the present invention, a user's preference is selected from a control method set by a control engineer, and a user's preference is given to a remote control device (hereinafter referred to as a remote controller).
And input from the panel surface, etc., and sequentially tune the fuzzy inference rules to realize the control that matches the user's taste and sensitivity. As a result, the air conditioner is equipped with adaptive fuzzy control that learns the user's taste in real time.

FIG. 6 is a block diagram of the fuzzy inference apparatus according to the third aspect of the present invention. The same components as those in FIG. 1 are designated by the same reference numerals. In FIG. 6, the inference rule storage unit 1 is a storage unit that stores inference rules of fuzzy inference, and the membership function storage unit 2 is the shape data of the membership function of the antecedent part used for fuzzy inference and the function of the consequent part. A storage unit that stores expressions, a fuzzy inference operation unit 3 is an operation unit that performs fuzzy inference operations, and a descent method operation unit 5 is a tuning direction based on input / output data and an inference result obtained from a control engineer by the descent method operation. Membership function adjusting unit 6 for calculating
Is an adjusting unit that updates the membership function based on the operation result of the descent method operation unit 5, and the error operation unit 7 is an operation unit that calculates the inference error from the fuzzy inference result and the input / output data.
The inference result display unit 31 is a display unit that displays the inference result calculated by the fuzzy inference operation 3, and the user input unit 32 is an input unit that inputs the user's preference for the inference result.

The operation of this embodiment will be described with reference to the flowchart of FIG. "Step b1" As the fuzzy inference rules stored in the inference rule storage unit 1 and the membership function storage unit 2, the inference rules obtained by experiments by the control engineer are set before shipment. The construction of this initial inference rule may use the first aspect of the present invention, or an experiment by trial and error or a method by an interview with a control engineer. "Step b2" Next, from the above-mentioned sensors to room temperature,
Input data such as radiation amount, humidity, and air flow. "Step b3" Based on these input data, the fuzzy inference operation unit 3 performs fuzzy inference, and the inference result y ^*
To get The operation procedure of fuzzy inference is the same as step a3 of the first embodiment. “Step b4” The inference result y ^* is displayed to the user on the inference result display unit 31. The display method is a display or voice output.
Based on the inference result y ^* , a quantitative expression such as “temperature is 3, air volume is 5” or the inference result y ^* is converted into a fuzzy number, and “temperature is medium, air volume is medium” With such output, the man-machine interface is further improved. [Step b5] Next, the user inputs the correction amount from the user input unit 32 according to his / her preference. For example, when the user is in that input situation, it is better to make it a little hotter for his or her skin sensation, and if that is desirable, a quantitative expression such as "temperature is 5, air volume is 8", Input the instruction by correction using the fuzzy number such as "the temperature is large and the air volume is large". It may be input using a remote control, a touch panel, a keyboard, or voice recognition. If the user does not change the displayed inference result, the correction amount is 0. "Step b6" The error calculation unit 7 checks whether the correction amount y ^', which is the output from the user input unit 32, is zero. In the membership function adjusting unit 6, if the correction amount y ′ is 0,
We think that the fuzzy inference rule that led to the inference result represents the user's preference or that the control engineer's method is better, so proceed to step b2 without tuning the inference rule and proceed to the next different situation. Wait for sensor input at. If the correction amount calculated by the error calculating unit 7 is not 0, the membership function adjusting unit 6 performs step b7.
Go ahead.

[0059] "step b7, b8" inference result y ^* to the correction amount y ^'
And add y ^r . This y ^r is the output data and the input data
With x ₁ and x ₂ as one input / output data, the membership function is tuned by the descent method. The calculation of this tuning is performed in steps a4 and a of the first embodiment of the present invention.
Same as 5. After updating the membership function, the process returns to step b2 and waits for the next sensor input.

In this way, when the user is operating the air conditioner and when the setting method of the manufacturer's control engineer is different from the setting method in various situations, tuning is started and the parameters are adjusted to suit the user's preference. The setting method according to can be changed thereafter. The user inputs whether to adjust the parameters.

As described above, according to the present embodiment, the result of fuzzy inference is displayed to the user by the inference result display unit 31, and the user's preference for the result is input from the user input unit 32. Use to change the membership function of fuzzy reasoning. As a result, an air conditioner that can be controlled according to the user's preference can be realized as the device is used.

In this embodiment, the structure of the portion for automatic tuning is the same as that of the first embodiment of the present invention, but the structure of the second embodiment of the present invention may be used for this portion. In this case, the consequent part of the inference rule becomes a real value, and the merits of the second aspect of the present invention such as high-speed tuning are also realized.

Next, an embodiment of the fourth invention will be described.

In the third aspect of the present invention, when the user indicates the preference, the user's preference is automatically learned and the fuzzy inference rules are tuned sequentially to realize the control suitable for the user's preference and sensitivity. ing. In this case, if the user has different setting values with respect to the inference rules like the control engineer set by the manufacturer at the time of shipment, tuning is started regardless of the size of the difference. Therefore, if there is a big difference in any situation, start tuning to match it. In this case, if the difference is large, the user may mistakenly consider it as a malfunction, and in the present invention, if the difference is larger than a predetermined value, tuning of the membership function is not started immediately.

FIG. 8 shows a block diagram of an apparatus according to the fourth aspect of the present invention. 8, the same components as those in FIG. 6 are designated by the same reference numerals. Differences from the third invention will be described. The difference from the configuration of FIG. 6 is that the error level determination unit 41 determines the magnitude of the error from the output of the error calculation unit 7, and when it is larger than a predetermined value, the occurrence frequency is counted by the counter 42. When the count number reaches a certain number or more, the count number comparing unit 43 drives the descent method computing unit 5 and corrects the parameter of the membership function adjusting unit 6. This tuning operation is similar to that of the third aspect of the present invention. If the output of the error level determination unit 51 shows a large error, the counter may be reset and the correction may not be performed.

As described above, according to the present invention, when the set value of the user is largely deviated, the same instruction is repeatedly given without correcting the parameters of the membership function or immediately. Since this is the first time to make corrections, the air conditioner will be equipped with a safe driving method that suits the user's preference.

Next, a fifth embodiment of the present invention will be described.
FIG. 9 is a block diagram of the fuzzy inference apparatus according to the fifth aspect of the present invention. In the figure, an inference rule storage unit 1 stores an inference rule of fuzzy inference, and a membership function storage unit 2 shows shape data of a membership function of an antecedent part used in fuzzy inference and a functional expression of a consequent part. , A fuzzy inference operation unit 3 is an operation unit that performs fuzzy inference operations, a descent method operation unit 4 is a control target, and 5 is an input / output data obtained from a control engineer and an inference result by the descent method. A calculation unit for calculating the tuning direction by calculation, a membership function adjustment unit 6 is an adjustment unit for updating the membership function based on the calculation result of the descent method calculation unit 5, and an error calculation unit 7 is inferred from fuzzy inference results and input / output data. This is a calculation unit that calculates an error. The above is the same as the configuration of FIG. The difference from the configuration of FIG. 1 is that the inference rule storage unit 1 and the membership function storage unit 2 are searched to obtain an inference rule with a large adaptation range, and an inference rule obtained by the inference rule search unit 51. The reason is that an inference rule display section 52 for displaying is provided.

The operation of the fuzzy inference apparatus of this embodiment constructed as above will be described below.

In the first and second aspects of the present invention, the construction of the fuzzy reasoning membership function similar to that of the control engineer is automatically performed. In the third and fourth aspects of the present invention, the membership function is set according to the user's preference. It could be tuned to the membership function. However, if the input / output data obtained from the control engineer or the user contains a lot of noise, the tuning may proceed in an unexpected direction. In addition, due to excessive tuning, inference with a small inference error can be performed on given input / output data, but the inference error may be extremely large for data not given at the time of tuning. In order to avoid such a situation, it is necessary for designers and users to understand and check the automatically constructed inference rules and membership functions.

In the present invention, in order to solve these problems, the inference rule display section 52 displays the inference rules obtained by the automatic tuning. Further, the inference rule searching unit 51 displays the inference rules having a wide matching range first in order to efficiently check the inference rules.

The operation procedure of the automatic tuning is the same as the flowchart of FIG. 2 of the first embodiment of the present invention. The difference is that the inference rules are displayed after the tuning is completed. After the tuning is completed, the inference rule search unit 51 searches the membership function storage unit 2 and calculates the following equation.

[0072]

[Equation 8]

S _i indicates the width of the applicable range of the inference rule R _i .
The inference rule R _i , the shape of the membership function thereof, and the parameters of the functional expression of the consequent part are sent to the inference rule display unit 52 in the order of increasing S _i .

The inference rule display section 52 is composed of, for example, a CRT or a liquid crystal display, and displays information such as the inference rules sent from the inference rule retrieval section 51 and the membership function used therein.

As described above, according to this embodiment, the fuzzy inference rules obtained by the descent method can be displayed in the descending order of matching range. Therefore, the inference rule obtained by the automatic tuning can be known by the user, and the progress of tuning and the inference rule can be checked.

Although the first embodiment of the present invention has been described in this embodiment, it goes without saying that the second to fourth embodiments of the present invention can also have a display function.

The environmental conditions are room temperature, radiation amount, air flow,
Not only humidity but other environmental conditions may be used.

The air conditioning conditions are not limited to the combustion amount, the air flow amount, and the wind direction, and may be other air conditioning conditions.

[0079]

As described above, according to the first aspect of the present invention,
It is possible to obtain the optimal inference rule by the descent method from the input / output data obtained from the control engineer. Therefore, the knowledge and know-how of the control engineer can be easily installed in the air conditioner as an inference rule.

According to the second aspect of the present invention, the optimum inference rule can be obtained by the descent method from the input / output data obtained from the control engineer. In particular, since the consequent part of the inference rule is a real value, the number of tuning parameters is small, and higher-speed automatic tuning and inference are possible as compared with the first aspect of the present invention.

According to the third aspect of the present invention, the result of the fuzzy inference is displayed to the user by the inference result display unit, and the user's preference for the result is input from the user input unit. Change the membership function. With this, the more you use the device,
It is possible to realize an air conditioner that can be controlled according to the taste of the user.

According to the fourth aspect of the present invention, when the set value of the user is largely deviated, the same instruction is given many times without correcting the parameters of the membership function or immediately. Since it is corrected for the first time when it comes, it is possible to safely realize an air conditioner equipped with an operation method according to the user's preference.

According to the fifth aspect of the present invention, by displaying the fuzzy inference rules obtained by the descent method in the order of widening the matching range, the user can know the inference rules obtained by the automatic tuning, and the tuning The progress status and inference rules can be checked.

[Brief description of drawings]

FIG. 1 is a configuration diagram showing an operation of a first device of the present invention according to the present invention.

FIG. 2 is a flow chart showing the operation of the first inventive device of the present invention.

FIG. 3 is a configuration diagram of a membership function.

FIG. 4 is an operation explanatory diagram of a descent method.

FIG. 5 is a block diagram showing the operation of the second inventive device of the present invention.

FIG. 6 is a block diagram showing the operation of the third inventive apparatus of the present invention.

FIG. 7 is a flowchart showing the operation of the device of the third aspect of the present invention.

FIG. 8 is a block diagram showing an operation of the apparatus of the fourth present invention in the present invention.

FIG. 9 is a configuration diagram showing an operation of the device of the fifth invention of the present invention.

FIG. 10 is a block diagram of a conventional fuzzy inference apparatus.

FIG. 11 is a configuration diagram of a membership function.

[Explanation of symbols]

 1, 21 Inference rule storage unit 2, 22 Membership function storage unit 3 Fuzzy inference operation unit 4 Control target 5, 23 Descent method operation unit 6, 24 Membership function adjustment unit 7 Error operation unit 31 Inference result display unit 32 User input Part 41 Error level determination part 42 Counter 43 Count number comparison part 51 Inference rule search part 52 Inference rule display part

Claims (5)

[Claims] 1. A fuzzy inference operation which inputs fuzzy inference by inputting all or any of environmental conditions such as room temperature, radiation amount, air flow, humidity, etc., and outputs air conditioning conditions such as combustion amount, air flow amount, wind direction, etc. Section, an inference rule storage section that stores inference rules used for the fuzzy inference, and a membership function that stores shape data of the membership function of the antecedent section and functions of the antecedent section that are used for the inference rule. A storage unit, a descent method computation unit that performs computation by a descent method from the input / output data obtained by an experiment and the inference result obtained from the fuzzy inference computation unit, and the output of the descent method computation unit is used to output the antecedent unit. From a membership function adjustment unit that changes at least one of a membership function and a consequent part function, from the input / output data and the inference result obtained from the fuzzy inference operation unit. Air conditioning system inference error by calculating the logical error is characterized in that and a error calculation unit for stopping the operation of the said descent calculation unit membership function adjusting portion when less than a predetermined value. 2. A fuzzy inference operation in which fuzzy inference is performed by inputting all or any one of environmental conditions such as room temperature, radiation amount, air flow, and humidity, and air conditioning conditions such as combustion amount, blast amount, wind direction, etc. are output. Section, an inference rule storage section that stores inference rules used for the fuzzy inference, and an antecedent section parameter storage section that stores parameters representing the shape of the membership function of the antecedent section used for the inference rules. , The consequent part real value storage unit that stores the real value of the consequent part used for the inference rule, and the antecedent result from the input / output data obtained by the experiment and the inference result obtained from the fuzzy inference operation unit. The antecedent part descent method computing part that performs a descent method calculation on the parameter representing the shape of the membership function of the part, and the antecedent part descent method computing part stores it in the antecedent part parameter storage part The antecedent parameter adjustment unit that changes the parameter that represents the shape of the membership function, and the descent method for the real value of the consequent unit from the input / output data given in advance and the inference result obtained from the fuzzy inference operation unit. And the consequent part real-value adjustment for changing the real value of the consequent part stored in the consequent part real-value storage unit by the output of the consequent part descent method calculator An inference error from the input / output data and the inference result obtained from the fuzzy inference operation unit, and when the inference error is smaller than a predetermined value, the antecedent part descent method operation unit and the antecedent part parameter adjustment unit An air conditioner comprising: a consequent part descent method calculation part and an error calculation part for stopping the operations of the consequent part real value adjustment part. 3. A fuzzy inference operation in which fuzzy inference is performed by inputting all or any of environmental conditions such as room temperature, radiation amount, air flow, humidity, etc., and air conditioning conditions such as combustion amount, air flow amount, wind direction, etc. are output. Section, an inference rule storage section that stores inference rules used for the fuzzy inference, and a membership function that stores shape data of the membership function of the antecedent section and functions of the antecedent section that are used for the inference rule. A storage unit; a user input unit for inputting a human preference for the output of the fuzzy inference operation unit; an inference result obtained from the fuzzy inference operation unit when the user input unit receives an input; and the user input unit Of the antecedent part stored in the membership function storage part by the output of the descent method calculation part. A membership function adjustment unit that changes either one of the function and the consequent function, and an inference error is calculated from the input / output data and the inference result obtained from the fuzzy inference operation unit, and the inference error is smaller than a predetermined value. An air conditioner comprising: a descent method calculation unit and an error calculation unit that stops the operation of the membership function adjustment unit. 4. The error calculator calculates an inference error from an inference result obtained from the fuzzy inference calculator, and when the inference error is larger than a predetermined value, the number of occurrences thereof is counted, and the count number is a predetermined number. Only when it gets bigger,
The air conditioner according to claim 3, wherein the descent method calculation unit and the membership function adjustment unit are operated until the inference error becomes smaller than a predetermined value. 5. A fuzzy inference operation that inputs fuzzy inference by inputting all or any of environmental conditions such as room temperature, radiation amount, air flow, humidity, etc., and outputs air conditioning conditions such as combustion amount, blast amount, wind direction, etc. Section, an inference rule storage section that stores inference rules used for the fuzzy inference, and a membership function that stores shape data of the membership function of the antecedent section and functions of the antecedent section that are used for the inference rule. A storage unit, a descent method calculation unit that performs a descent method from the inference results obtained from the input / output data and the fuzzy inference calculation unit, and a membership function and consequent of the antecedent unit based on the output of the descent method calculation unit. A membership function adjustment unit that changes at least one of the functions of the unit, and an inference error is calculated from the inference error obtained from the input / output data and the fuzzy inference operation unit. Is smaller than a predetermined value, an error operation unit that stops the operations of the descent method operation unit and the membership function adjustment unit, the inference rule storage unit and the membership function storage unit are searched, and the inference rule is displayed. And an inference rule display section for controlling the air conditioner.