JPH05141999A - Fuzzy sensor device - Google Patents

Abstract

(57) [Summary] [Object] To provide a fuzzy sensor device that can use a compact intangible sensing algorithm that does not require a large memory and that can adjust this algorithm according to the situation. [Configuration] When the detection signals from the signal detection units 11 to 1n are input, the CPU 31 calculates the sensory ambiguous amount according to an algorithm for quantifying the sensory ambiguous amount obtained by the fuzzy quantification II class. , Output as a numerical value. The algorithm stored in the algorithm storage unit 32 can be adjusted by the man-machine interface 43 according to the usage environment or usage conditions.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fuzzy sensor device for detecting an ambiguous sensation such as an indoor environment.

[0002]

2. Description of the Related Art In the case of realizing a so-called intangible sensor for detecting an ambiguous human sense, such as a sense of "hot" or "cold" in an indoor environment, a method of evaluating such sense As a method, it is proposed to use a multi-input information processing technology such as fuzzy inference or neural network.

[0003]

However, if the above-mentioned sensor is realized by using fuzzy inference, it takes time and labor to create a fuzzy rule or membership function based on a large amount of data, and fuzzy There is a problem that a large amount of memory is required to store the inference algorithm. On the other hand, when the above-mentioned sensor is realized by using a neural network, the evaluation algorithm is completely a black box, so that there is a problem that the characteristics cannot be adjusted according to the usage environment and usage conditions.

In view of these problems, the present invention can use a compact intangible sensing algorithm which does not require a large capacity memory, and
It is an object of the present invention to provide a fuzzy sensor device that can adjust this algorithm according to the situation.

[0005]

In order to achieve the above object, the present invention is characterized by adopting a method of "fuzzy quantification type II" described later in an intangible sensing algorithm. Therefore, in the present invention, one or a plurality of detection units, a storage unit for storing an algorithm for quantifying a sensory ambiguous amount obtained by fuzzy quantification II, and a detection signal from the detection unit are input. Then, the calculation means for calculating the sensory ambiguous amount according to the algorithm stored in the storage means and outputting it as a numerical value.

The algorithm used in the present invention can be configured to calculate the above-mentioned ambiguous amount on the basis of a non-linear function obtained as a result of data analysis by the fuzzy quantification class II for the input signal. Furthermore, this algorithm can be adjusted by the above-mentioned non-linear function according to the usage environment and usage conditions.

Here, the fuzzy quantification type II will be explained. This is a kind of fuzzy multivariate analysis method.
Fuzzy multivariate analysis is an extension of ordinary multivariate analysis to handle fuzzy numbers or fuzzy groups. The main fuzzy multivariate analysis techniques currently proposed are as follows. ..

Fuzzy regression analysis A method of obtaining a possibility linear regression model by treating the coefficients of regression analysis as fuzzy numbers.

Fuzzy time series analysis A method of analyzing the fuzzy number data given to the time series and reflecting the possibility distribution in the time series model.

Fuzzy Quantification Class I A method for obtaining the relationship between an objective function taking a real value and a qualitative explanatory variable represented by a value within the range of [0,1] in a fuzzy group of a given sample. ..

Fuzzy quantification II class From the data of qualitative objective variables represented by values in the range [0,1] and qualitative explanatory variables represented by values in the range of [0,1], fuzzy A method for finding a linear (first-order) expression that expresses a group.

Fuzzy Quantification III Based on qualitative data represented by values in the class [0,1], each sample and category are quantitatively classified in consideration of the membership function value of the fuzzy group. Technique.

Fuzzy Quantification Class IV A method of giving a numerical value such that the distance between individuals and the familiarity are in a monotonous relationship in consideration of membership function values of individuals belonging to the fuzzy group.

Of these, fuzzy quantification type I is a method for explaining a quantitatively given external criterion (objective variable) based on a qualitative factor (explaining variable).

On the other hand, the fuzzy quantification type II is a method for explaining qualitatively given external criteria (fuzzy groups) based on qualitative factors (explaining variables). The data handled by this fuzzy quantification type II are shown in FIG. The difference from the fuzzy quantification type I is that the external criterion is fuzzy group B.
_1, B _2, ‥‥, is that given by B _M. The purpose of this fuzzy quantification type II is that each category A _i (i = 1,
2, ..., K) Category weight a _{i line} format

[0016]

[Equation 1]

[0017] by as best represents the structure of the external reference on the real axis, in other words, the fuzzy set B ₁ of external criterion on the real axis, ‥‥, as B _M is best separated ,
To determine the category weight a _i .

When the category weights a _i are determined in this way, the value (sample score) of each sample ω is calculated by the equation (1).
Is required. Then, by plotting the membership value of the external criterion for each sample value, a graph showing the data analysis result by the fuzzy quantification class II is obtained.

[0019]

In the present invention, the method of fuzzy quantification type II as described above is adopted in the intangible sensing algorithm, and the detection signal from the detecting section is analyzed by this. Plotting the data based on the resulting sample scores provides a function that quantifies the sensory ambiguity. Based on this function, an algorithm for quantifying the amount of vagueness is constructed.

In this way, by introducing the algorithm for quantifying the perceptual ambiguous amount obtained by the fuzzy quantification II class, the calculation formula and the function of the sample score by the fuzzy quantification class II are stored in the memory. Well, the algorithm is adjustable.

[0021]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT FIG. 1 shows the configuration of a fuzzy sensor device according to the present invention. This apparatus is provided with one or a plurality of signal detection units 11 to 1n each of which includes various detectors which generate a data signal representing an environmental condition. Each signal detector 11,
The signals detected by 1n are subjected to A / D conversion and the like by the corresponding input signal converters 21 to 2n, and taken into the calculator 30. The calculation unit 30 has a CPU 31 and an algorithm storage unit 32, and the CPU 31 executes a calculation described later according to the algorithm stored in the algorithm storage unit 32.

The above algorithm quantifies the perceptual ambiguity obtained by the fuzzy quantification type II, and is constructed as shown in FIG. That is, CP
In U31, when the detection signals 1 to n from the respective signal detection units 11 to 1n are input via the signal conversion units 21 to 2n (step S1), sample scores corresponding to these inputs are calculated (step S2). ). Next, the sensory ambiguous amount is calculated using the non-linear function F1 for each sample score (step S3), and is output as a numerical value. This output value is subjected to D / A conversion and the like by the output signal conversion unit 41 and output from the signal output unit 42 (step S
4). This output signal is used to perform air conditioning control or the like according to the environment.

FIG. 3 shows a procedure for obtaining a non-linear function necessary for constructing the algorithm of FIG. First, a process of normalizing the input data is performed (step S11). The data is collected by a sensitivity test and a questionnaire in which a human being is the victim. Next, the normalized data is analyzed by the fuzzy quantification II class (step S12), and is approximated by a high-order nonlinear function obtained by the least square method or the like (step S1).
3).

The above algorithm can be adjusted according to the environment of use and the conditions of use by the man-machine interface 43 connected to the fuzzy sensor device of FIG.

FIG. 4 shows "hot" as a concrete example of FIG.
1 shows a comfort level sensor device that detects a sensory ambiguity such as "cold". In this device, the algorithm storage unit 32 of FIG. 1 stores the storage unit 33 that stores the procedure for calculating the sample score in step S2 of FIG. 2 and the non-linear function used in step S3 of FIG. And a storage unit 34. Furthermore, the man-machine interface 43
Is configured so that the origin of the sample score and the scaling value can be appropriately adjusted by an operator's input operation in order to adjust the above algorithm according to the usage environment and usage conditions.

First, as a problem setting, the comfort felt by human beings due to temperature and humidity is an ambiguous element and basically cannot be directly measured. Therefore, in this embodiment, the yearly differences in temperature, humidity and climate are set. And the amount of time that reflects the degree of human clothes, and the time that reflects the state of human activity are measurable amounts for determining comfort, and these are the signal detection units 11 to 11 of FIG. A clock 101, a thermometer 102, and a hygrometer 10, which are specific examples of 1n.
3 to detect. Then, the comfort level is determined based on these measured quantities.

Next, in order to connect the measurable amount and the comfort level, various feelings of the suffered person are investigated by a questionnaire method. For temperature and humidity, the degree of height is normalized to the range of [0,1]. The date is normalized to a range of [0,1] so that it becomes closer to "1" as it approaches summer, and the time becomes [0] as it approaches "1" as it approaches 2:00 pm. , 1].

FIG. 5 shows the data X thus normalized.
An example of 1 (temperature), X2 (humidity), X3 (date), and X4 (time) is shown. In the example of FIG. 4, these data are analyzed by the fuzzy quantification type II. That is, the storage unit 33 of FIG.
According to the sample score calculation procedure stored in, the category weight a in the above equation (1) for the normalized data
Determine _i . As a result, when plotting the data based on the sample score S obtained by the following equation (2),
Characteristic of "hot" and "cold" can be expressed.

S = a ₁ · X ₁ + a ₂ · X 2 + a ₃ · X 3 + a ₄ · X 4 (2) a ₁ = 0.661, a ₂ = 0.360, a ₃ = −0.306, a ₄ = −0.116 The above formula (2 ) Sample score S of each data obtained by
Becomes as shown in FIG. Also, when the horizontal axis is the sample score S and the vertical axis is the degree Y1 of feeling "hot" (or the degree Y2 of feeling "cold"), the data is plotted as shown in FIG.

Next, the function F1 that gives the degree Y1 of feeling "hot" and the function F2 that gives the degree Y2 of feeling "cold" are obtained based on the data distribution of FIG. 7, as shown in FIG. And these functions can be expressed as:

F1 = (1 / π) · tan ⁻¹ {0.109 (S−0.3)} + 0.5 (3) F2 = 1−F1 = − (1 / π) · tan ⁻¹ {0.109 (S−0.3) )} + 0.5 (4) Therefore, the measurable temperature, humidity, date, and time are [0,
1], the sample score S of each data obtained by the equation (1) is obtained, and the function F1 or F2 is used to obtain the degree of "hot" feeling, that is, the comfort level. The closer the F1 value is to 0.5, the closer to a comfortable situation.

According to the embodiment shown in FIG. 4, as described above, it is possible to realize an intangible sensor that quantifies a vague sense of human being, and the number of measurable inputs is not limited. Further, since the sampling score S is unrelated to the scaling and the position of the origin, the man-machine interface 43 can use the scaling factor and the position of the origin as parameters for adjusting deviation due to individual differences. Further, if a similar function is to be realized by fuzzy inference, a membership function and a fuzzy rule must be created, which requires a lot of time to create an algorithm and increases the required memory and operation time. Then, only the sample score calculation formula (2) and the function F1 (F2 is obtained as 1-F1) are sufficient.

Although the comfort level sensor has been described as the embodiment, the present invention is not limited to this, and can be similarly applied to "sweetness" and other intangible sensing.

[0034]

As described above, according to the present invention, the sensory ambiguous amount obtained by the fuzzy quantification type II is quantified, so that a compact intangible sensing algorithm that does not require a large capacity memory is used. This can be done, and the amount of memory for storing it can be small.
Also, the algorithm can be adjusted depending on the situation.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of a fuzzy sensor device according to the present invention.

FIG. 2 is a flowchart showing a configuration of an algorithm used in the present invention.

FIG. 3 is a flowchart showing a procedure for creating an algorithm.

FIG. 4 is a block diagram showing a comfort level sensor as a specific example of the fuzzy sensor device of FIG. 1.

5 is a diagram showing an example of normalized data in the comfort sensor of FIG.

6 is a diagram showing an example of sample scores in the comfort sensor of FIG.

7 is a diagram showing a data distribution of the degree of feeling "hot" and "cold" in the comfort sensor of FIG.

FIG. 8 is a diagram showing a non-linear function that gives the degree of feeling “hot” or “cold” in the comfort sensor of FIG. 4;

FIG. 9 is a diagram showing data handled in the fuzzy quantification class II.

[Explanation of symbols]

11 to 1n ... Signal detection unit, 21 to 2n ... Input signal conversion unit, 30 ... Calculation unit, 31 ... CPU, 32 ... Algorithm storage unit, 33 ... Sample score calculation procedure storage unit, 34 ...
Function storage unit, 41 ... Output signal conversion unit, 42 ... Signal output unit, 43 ... Man-machine interface, 101 ... Clock, 102 ... Thermometer, 103 ... Hygrometer.

Claims (3)

[Claims] 1. Fuzzy quantification II with one or more detectors
A storage unit for storing an algorithm for quantifying a sensory ambiguous amount obtained by a class, and a sensory ambiguous amount according to the algorithm stored in the memory unit when a detection signal from the detection unit is input. A fuzzy sensor device including a calculation unit that calculates and outputs a numerical value. 2. The fuzzy sensor device according to claim 1, wherein the algorithm is configured to calculate the ambiguous amount on the basis of a non-linear function obtained as a result of analysis by the fuzzy quantification class II for the detection signal. 3. The fuzzy sensor device according to claim 2, wherein the algorithm is adjusted by the non-linear function according to a use environment or a use condition.