JPH03271811A - Fuzzy controller - Google Patents

Abstract

PURPOSE:To freely change the arithmetic contents of a consequent part operation of the fuzzy controller by constituting a consequent part arithmetic means of a hierarchical network structure in which an internal coupling is constituted between an input layer and an intermediate layer of the front stage, between each intermediate layer and between the intermediate layer of the final stage and an output layer. CONSTITUTION:A consequent part arithmetic part 18 is constituted of a network structure part 20 constituted of, for instance, a hierarchical network structure. This network structure part 20 executes a processing for converting an input signal which is inputted, to the corresponding output signal in accordance with a data converting function prescribed by the network structure and an internal state value allocated to an internal coupling of its network structure part. When an application value of each fuzzy control rule to the same consequent part membership function is given as an input signal from an antecedent part arithmetic part 17, the network structure part 20 outputs an output signal corresponding thereto as an arithmetic result value of the consequent part operation. In such a way, the arithmetic contents of the consequent part arithmetic part 18 can be changed freely.

Description

[Detailed Description of the Invention] [Summary] Regarding a fuzzy controller that calculates and outputs a control operation amount corresponding to a control state quantity by executing fuzzy inference according to a fuzzy control rule, the consequent calculation function of the fuzzy control rule is used. In order to be able to change the consequent flexibly, the consequent part calculation means that performs the consequent calculation function is connected to an input unit that distributes the input signal value, one or more inputs from the previous layer, and the input unit. A basic unit that receives internal state values to be multiplied to obtain a product sum value and obtains an output value by functionally converting the product sum value, and a plurality of input units as an input layer. , and has one or more intermediate layers with one or more basic units as the intermediate layer, and one basic unit as the output layer, and between the input layer and the foremost intermediate layer, and between the intermediate layers. [Field of Industrial Application] The present invention relates to a fuzzy controller that calculates and outputs a control operation amount corresponding to a control state amount by executing fuzzy inference according to fuzzy control rules, and particularly relates to a fuzzy controller that calculates and outputs a control operation amount corresponding to a control state amount by executing fuzzy inference according to fuzzy control rules. This invention relates to a fuzzy controller that allows the consequent calculation function described in a rule to be changed flexibly.

Fuzzy control is becoming popular as a new control processing method. This fuzzy control expresses a control algorithm that includes ambiguity such as human judgment in a 1f-then format, and executes this control algorithm according to fuzzy reasoning to calculate the control operation amount from the detected control state amount. It calculates and controls the controlled object. The fuzzy controller that implements this fuzzy control needs to be configured so that the arithmetic functions described in the control algorithm can be easily changed in order to absorb the ambiguity of the control algorithm.

[Conventional technology]

The fuzzy control rule is if X+ is bi@ and Xi is sm
All then y+ is big (I
The F part is called the antecedent part and is a part that describes the conditions for control state quantities such as temperature data, and the THEN part is called the consequent part and describes the conditions for control manipulated variables such as operating terminals. The fuzzy controller manages a plurality of such fuzzy control rules prepared as the control logic of the controlled object, and also writes the control logic in each fuzzy control rule. A configuration will be adopted in which the meaning of ambiguous linguistic expressions such as "large" or "small" is quantified and managed as a membership function.

When the fuzzy controller is given control state quantities such as temperature data and water level data from the controlled object, it first calculates the member knob function (antecedent membership function) of the control state quantity it is managing. ) to calculate the membership function value (truth value) of the given control state quantity.

Next, in accordance with antecedent part calculations such as selecting the minimum value, a process is executed to determine a common value for the consequent part in each fuzzy control rule. That is, to explain using the example of the fuzzy control rule mentioned above, if the truth value of rx, isbigJ is °'0.8", and the truth value of rx, is smallJ is 0.5", then the minimum value According to the antecedent operation that selects , 20゛'0.5'' is determined as the value to be applied to the consequent of the fuzzy control rule.

Subsequently, the fuzzy controller calculates each fuzzy control rule given for the same membership function (which becomes the consequent membership function) of the same control manipulated variable according to the consequent operation, such as selecting the maximum value. A process is executed to determine the applicable value for the membership function from the common value for the consequent. In other words, in the fuzzy control rule described above, for the consequent 'V+ is big'
0.5" is the applied value, and on the other hand, if you use another fuzzy control rule to set "0.6" as the applied value for 'y+ is bjg', then according to the consequent operation that selects the maximum value, , this "0.6" is the control operation amount y, 'big'
It is processed so that it is determined as the applied value for the membership function of .

Subsequently, the fuzzy controller reduces the membership function of the control manipulated variable according to the determined application value, and
In accordance with the process of finding the center of gravity of the figure of the function sum of this reduced membership function for the same control operation amount, the process of calculating the control operation amount which is a fuzzy inference value is executed and output to the operation terminal etc. This process will be executed.

That is, the membership function of rbigJ of the control operation amount y1 is reduced according to its determined application value, and the control operation amount yI obtained from another fuzzy control rule is
The membership functions such as malJ are reduced according to the determined application value, and the center of gravity of the figure of the sum of the functions of these membership functions is determined.
Processing is performed to calculate the control operation amount that is the output of the fuzzy controller.

Conventional fuzzy controllers have adopted a configuration in which execution of such fuzzy control rules is achieved by executing them programmatically. That is, according to the software means of the computer system that performs sequential processing, first, the truth value of the control state quantity is calculated, then the applied value for the consequent is determined according to the antecedent part operation, and then Then, the application value of the control operation amount to the membership function is determined according to the consequent part calculation, and then the control operation amount is calculated and output by center of gravity calculation or the like.

(Problems to be Solved by the Invention) However, fuzzy control rules are generated according to the knowledge of the target process of an operator who is familiar with the control of the controlled target.

The reality is that it is not possible to generate fuzzy control rules that can achieve the desired control from the beginning, so the generated fuzzy control rules should be tuned on a trial basis while being evaluated through simulation and field tests. By doing so, we have no choice but to complete the fuzzy control rules that are suitable for the control target.

From now on, there may be cases where it is more appropriate to use a consequent operation that is different from the originally assumed operation function.

However, if a conventional method of configuring a fuzzy controller using software means is adopted, various consequent functions must be prepared in advance as subroutines in the device in order to meet such demands. be. However, since only one consequent part calculation function is originally used, this configuration poses the problem of wasteful use of memory capacity. Furthermore, if a fuzzy controller that has already been shipped does not have a subroutine for its arithmetic function, a problem arises in that more appropriate fuzzy control logic cannot be implemented.

The present invention has been made in view of the above circumstances, and it is possible to flexibly perform the consequent calculation function described in the fuzzy control rule without increasing the memory capacity (and also in the fuzzy controller shipped). The purpose is to provide a new fuzzy controller that can be changed.

[Means to solve the problem]

FIG. 1 is a diagram showing the basic configuration of the present invention.

In the figure, 10 is a fuzzy controller equipped with the present invention, 11 is a fuzzy rule management unit that manages fuzzy control rules that describe control logic for a controlled object,
12 is a fuzzy rule selection unit that sequentially selects the fuzzy control rules managed by the fuzzy rule management unit 11 to be processed; 13 is an antecedent membership function management unit that selects fuzzy control rules managed by the fuzzy rule management unit 11 as processing targets; 14 is a consequent membership function management unit which is described in the fuzzy control rule. 15 is an input data reception unit for accepting control state quantity data collected from a controlled object; The unit that executes the processing is an antecedent truth value calculation unit 16, which calculates the truth value of the antecedent membership function of the input control state quantity using the selected fuzzy control rule as a processing unit. 17 is an antecedent calculation unit which performs an antecedent calculation on the truth value of the calculated antecedent membership function to apply the antecedent calculation to the consequent of the fuzzy control rule to be processed. 18 is a consequent calculation unit which determines the consequent member from the applied value for the consequent of each fuzzy control rule given for the same consequent membership function. 19 is an inference value calculation unit that determines the common value for the ship function, and for example, calculates the consequent membership for the same control operation amount according to the applied value determined by the consequent calculation unit 18. Control operation amount data, which is a fuzzy inference value, is calculated by reducing the function and finding the graphic center of gravity of the function sum of the reduced consequent member-knob function.

The consequent calculation unit 18 of the present invention receives one or more inputs and an internal state value by which the inputs are to be multiplied to obtain a sum of products value, and also converts the sum of products into a function. A network structure unit 20 configured by internally connecting a plurality of basic units 1 to obtain an output value and executes a consequent operation.
and an internal state value management section 21 that manages internal state values assigned to internal connections of this network structure section 20. This network structure section 20 has a basic unit 1 and an input unit 1'' that distributes input signal values as constituent units, and a plurality of input units 1''--
h, an intermediate layer composed of one or more basic units 1-i and provided in one or more stages, and an output layer composed of one basic unit 1-j. Input unit 1'-h
A hierarchical network structure may be adopted in which internal connections are made between the basic units 1-4 and 1-4, between the basic units ii, and between the basic units 1-i and 1-j. Further, as the internal state value managed by the internal state value management section 2, a value that causes the network structure section 20 to operate to output the maximum value of the input signal value may be set.

[Effect]

The consequent computation unit 18 of the present invention is configured by a network structure unit 20 that includes, for example, a hierarchical network structure. This network structure unit 20 executes a process of converting an input signal input into a corresponding output signal according to a data conversion function defined by a network structure and internal state values assigned to internal connections of the network structure. . From now on, when the application value of each fuzzy control rule for the same consequent membership function is given as an input signal from the antecedent part calculation part 17, the network structure part 20 converts the corresponding output signal into the consequent part membership function. It operates to output the result value of the partial operation.

Even if the network structure is the same, the data conversion function of the network structure section 20 can freely change the calculation content by changing the value of the internal state value assigned to the internal connection.

That is, when the learning value of the internal state value at which the network structure unit 20 operates to output the maximum value of the input signal value is set in the internal state value management unit 21, the consequent part calculation unit 18 calculates the same consequent. The calculation process is to calculate the maximum value of the calculation result value of the antecedent part calculation of each fuzzy control rule given to the partial Menharsisop function. When the learning value of the internal state value that operates to output the average value of the input signal value is set, the consequent part calculation unit 18 calculates the values of each fuzzy control rule given to the same consequent part membership function. By simply changing the value of the internal state value registered in the internal state value management unit 21, the consequent part calculation can be performed by simply changing the value of the internal state value registered in the internal state value management unit 21. [Part] 8 can be freely changed.

As described above, according to the present invention, the consequent calculation section 18 can be freely executed even if it is not prepared in advance as a subroutine in the device.
Since the calculation content of can be changed, it is possible to easily respond to a request to change the consequent part calculation function described in the fuzzy control rule. From now on, it will be possible to improve the performance of fuzzy controllers.

〔Example〕

Hereinafter, the present invention will be described in detail according to an embodiment applied to a hierarchical network configuration data processing device.

FIG. 2 illustrates an embodiment of the present invention. In the figure, the same parts as those explained in FIG. 1 are indicated by the same symbols. 20a is a hierarchical network structure unit that executes the consequent operation, and corresponds to the network structure unit 20 in FIG. 1; 21a is the hierarchical network structure unit 2
A weight value management unit 21a that manages weight values assigned to internal connections of 0a, which is similar to the internal state value management unit 2 in FIG.
This corresponds to 1.

As explained in FIG. 1, the antecedent part calculation unit 17 performs processing to calculate the application value of each fuzzy control rule for the same consequent part membership function. That is, for example, when rules 1 to n out of a plurality of prepared fuzzy control rules describe "rSmall of control operation amount Y," as a consequent description, the antecedent part calculation unit 17 As shown in FIG. 2, the applied value for the membership function of the control operation amount Y1 defined by Rule 1 and the membership function of rSma I ]J of the control operation amount Y1 defined from Rule 2. The rs of the control operation amount Y, such as the application value for the membership function and the common value for the membership function of the control operation amount Y, specified from rule n.
The application value of each fuzzy control rule is calculated for the membership function of ma l l J. In Figure 2, for convenience of explanation, these membership function values (truth values) are calculated in parallel. Although the diagram shows the values to be determined, in reality, they are determined one by one in chronological order.

The hierarchical network structure section 20a has this antecedent section calculation section 1.
By performing the consequent operation on the applied value given from 7, the applied value for the consequent membership function to be processed is determined.

FIG. 3 illustrates the basic configuration of the basic unit 1 that will constitute the hierarchical network structure section 20a. As shown in this figure, the basic unit 1 is a multi-car output system, and includes a multiplication processing section 2 that multiplies multiple inputs by the weight values of their respective internal connections, and a multiplication processing section 2 that adds all the multiplication results. It is equipped with an accumulation processing section 3 and a dark value processing section 4 that performs nonlinear dark value processing on the accumulated value and outputs one final output, and the h layer is the first layer and the i layer is the first layer. In the latter layer, the accumulation processing section 3 of the i-th basic unit 1 of the i-th layer executes the calculation of the following formula (1), and the dark value processing section 4 executes the calculation of the following formula (2). Process as follows.

x,,=Σ)'phWlh (1
) formula Y p+ = 1 / (1+ exp(-x p
i+θi)) (2) where, h: Unit number of h layer p: Input signal pattern number 6. Darkness value Jl of the 1st unit of 21st layer: Weight value yph'P of internal connection between 11-i layer The output from the h-th unit of the h-th layer in response to the input signal of the h-th pattern.The hierarchical network structure section 20a is an input unit that distributes the applied values calculated by the basic unit 1 having such a configuration and the antecedent part calculation section 17. 1" as a structural unit, and as shown in FIG.
an input layer formed by h, an intermediate layer formed by one or more basic units 1-i and provided in one or more stages (in this example, one stage), and one basic unit 1-i. The output layer constituted by
It is configured to have a hierarchical network structure formed by mutually internally connecting i and basic units ij. Here, the number of units of the input unit]'-h is such that the consequent calculation section 18 is divided into one hierarchical network structure section 20a.
When implemented in , the number of fuzzy control rules that describe the consequent membership function that will be described most often will be prepared.

The hierarchical network structure unit 20a configured in this way converts an input signal into a corresponding output signal according to a data conversion function defined by a hierarchical network structure and a weight value assigned to an internal connection of the hierarchical network structure. , and the consequent operation is executed according to this data conversion function.

The hierarchical network structure section 20a can be constructed by either a program means or a hardware means, but in the case of constructing it by a hardware means, it can be constructed as described in Japanese Patent Application No. 1983-216865 filed by the present applicant. It is possible to use the one disclosed in "'Network Configuration Data Processing Apparatus'" filed August 1988, No. 318.

That is, as shown in FIG. 5, the basic unit 1 is a multiplication type D that multiplies the output from the previous layer input via the input switch section 7 by the weight value held by the weight value holding section 8.
/A converter 2a, an analog adder 3a that adds the output value of the multiplication type D/A converter 2a and the previous accumulated value to calculate a new accumulated value, and holds the addition result of the analog adder 3a. A sample-and-hold circuit 3b that converts the data held in the sample-and-hold circuit 3b into nonlinear form when the accumulation process is completed, and an analog signal of the nonlinear function generation circuit 4a that outputs the data to the subsequent layer. This is realized by including an output holding section 5 that holds a value, an output switch section 6 that outputs the data held by the output holding section 5, and a control circuit 9 that controls each of these processing sections.

The hierarchical network structure section 20a is realized in a configuration in which basic units 1 having this configuration are electrically connected through one common analog lotus 70, as shown in FIG. Here, in the figure, 71 is a weight output circuit that gives a weight value to the weight holding section 8 of the basic unit 1, 72 is an initial signal output circuit corresponding to the input unit 1, and 73 is a synchronous control signal that is a control signal for data transfer. The weight output circuit 7
1. A synchronous control signal line 74 that transmits the initial signal output circuit 72 and the control circuit 9 is a main control circuit that sends out the synchronous control signal.

In the hierarchical network structure section 20a having this configuration, the main control circuit 74 sequentially selects the basic units 1 in the previous layer in chronological order, and in synchronization with this selection process, the output holding section of the selected basic unit 1. 5 is processed so as to be outputted to the multiplication type D/A converter 2a of the basic unit 10 in the subsequent layer via the analog bus 70 in accordance with the time-division transmission format. Upon receiving this input, the multiplication type D/A converter 2a of the basic unit 1 in the subsequent layer sequentially selects the corresponding weight value, multiplies the input value and the weight value, and connects the analog adder 3a and sample hold. The accumulation processing section 3 constituted by the circuit 3b sequentially accumulates the multiplied values. Subsequently, when all the accumulation processing for the basic unit 1 in the previous layer is completed, the main control circuit 74 activates the nonlinear function generation circuit 4a of the basic unit 1 in the subsequent layer to calculate the final output. The output holding unit 5 performs processing to hold the final output of the conversion processing result. Then, the main control circuit 74 uses this subsequent layer as a new previous layer and repeats the same process for the next subsequent layer so that an output cover turn corresponding to the input cover turn is output. .

The hierarchical network structure unit 20a is characterized in that even if the hierarchical network structure is fixed, its data conversion function can be freely changed by changing the weight values assigned to internal connections of the hierarchical network structure. There is.

FIG. 7 illustrates an embodiment of a learning system for learning weight values assigned to internal connections of this hierarchical network structure section 20a. Next, according to an embodiment of this learning system, a learning process for determining internal connection weight values of the hierarchical network structure section 20a will be described in detail.

In FIG. 7, 30 is a hierarchical network simulator constructed on a computer, which simulates the data processing function of the hierarchical network structure section 20a, and 40 is a learning signal presentation device, which is a hierarchical network structure section 20a.
A learning signal group (a pair of a learning presentation signal and a learning teacher signal is used as a basic unit) used for learning the weight value of the internal connection of a is managed, and the learning presentation signal in the learning signal group is managed. The signal is presented to the hierarchical network simulator 30, and a learning teacher signal is presented to the learning processing device 50, which will be described later. In order to realize this process, the learning signal presentation device 40 includes a learning signal storage section 4 that manages a group of learning signals.
1, and a learning processing device which reads learning signals for learning from the learning signal storage unit 41, presents a learning presentation signal among them to the hierarchical network simulator 30, and generates the other learning teacher signal forming the pair, which will be described later. 50 and a learning signal presentation unit 42 that presents the learning signal to the learning convergence determination unit 43, which will be described next.
Based on the output signal outputted from the hierarchical network simulator 30 and the learning teacher signal from the learning signal presentation unit 42, it is determined whether the error of the data processing function of the hierarchical network simulator 30 is within an allowable range. and a learning convergence determination section 43 that notifies the learning signal presentation section 42 of the determination result.

Reference numeral 50 denotes a learning processing device that implements the hack propagation method, which is known as a learning algorithm for weight values of the hierarchical network configuration data processing device, and outputs the learning presentation signal in response to the presentation of the learning presentation signal by the learning signal presentation section 240. The error value between the output signal group from the hierarchical network simulator 30 and the learning teacher signal group presented from the learning signal presentation device 40 is calculated, and the weight value to be studied is calculated based on the error value. By sequentially updating , the weight value of the internal connection that makes the error value fall within the allowable range is learned.

That is, the learning processing device 50 follows the back propagation method C, and if explained in terms of the hierarchical network structure section 20a having a three-layer structure of the hiH layer and the J layer shown in FIG. When the output signal yp1 of the output layer, which is output when a signal) is presented, and the learning teacher signal d8, which is the signal that the output signal ypJ should take, first, the output signal ypJ and the teacher signal d are determined. ,
, J and calculate the difference value (dp=-)'p=), and then,
αpi=VpJ(1)'pJ)(dpJVp;) is calculated, and then ΔWji(t)=εΣαpj)'pt+ζΔWJi(t
-1), update amount ΔW of weight values between layer 1 and layer j.

Calculate (1). Here, t represents the number of learning times, and the reason for adding the weight value update amount determined at the previous update cycle is to speed up the learning.

Next, the learning processing device 50 first calculates βp=-yp+(1y□)Σαp=WJt(t-1) using the calculated α and J, and then ΔWlh(t)= εΣβpi ) ph+ζΔW,,(
t-1), update amount ΔW of weight values between layer h and layer 1
,.

Calculate (1). Then, according to the calculated update amount, a weight value W, (t) = W, for the next update cycle is determined.
, (t-1)+ΔWJi(t)Wth(t) =Wih
By repeating the method of determining (t-1)+ΔWik(t), the output signal y□ from the output layer that is output when the learning presentation signal is presented, and the output signal y
The weight value W j i + W i h and the threshold value θ8. with which the learning teacher signal d□, which is the signal to be taken by pJ, match. θ1 will be learned.

In addition, the present applicant previously applied for the “Japanese Patent Application No. 62-3334”.
No. 84 (filed on December 28, 1988, "Network configuration data processing device"), "1" is always output to the h layer on the input side, and a threshold value θ is weighted on the output. It has been proposed that the threshold value θ is incorporated into the weight value W by providing a unit for assigning it as a value, so that the threshold value θ is handled as a weight value. From now on, the threshold value θ will also be learned by the same learning process as the weight value W learning process.

As shown in FIG. 7, the hierarchical network simulator 30 includes a network structure management section 31 that manages the internal connection relationship between the input unit 1'' and the basic unit 1 of the hierarchical network structure section 20a, and a network structure management section 31 that controls the entire calculation process. an arithmetic control unit 32 that executes; and a hierarchical network structure unit 20
input unit of a].

and an input data expansion section 33 that temporarily expands human input values input to each unit of the basic unit 1, a weight value management section 34 that manages weight values assigned to each internal connection, and an arithmetic function of the basic unit 1. , and an output data management section 36 that manages the calculation results of the calculation execution section 35. The calculation execution unit 35 includes a multiplication value calculation unit 37 that calculates a multiplication value of the weight value and the input value, a summation value calculation unit 38 that calculates the summation value of the calculated values of the multiplication value calculation unit 37, and It is configured to include a threshold value calculation unit 39 that performs threshold value processing on the value calculated by the total sum value calculation unit 38.

By being configured as in 2, the hierarchical network simulator 30 simulates the data processing function executed by the hierarchical network structure section 20a installed in the fuzzy controller. In addition, the hierarchical network structure part 2
When configuring 0a by a program means, it can be realized by using such a hierarchical network simulator 30, for example.

When realizing the desired arithmetic function of the consequent part arithmetic unit 18 according to the hierarchical network structure part 20a, the user first generates the input/output signal relationship realized by the arithmetic function and then uses the learning signal presentation device 40. A process of registering in the learning signal storage unit 41 is executed. In other words, the consequent part calculation unit 18
If you want to assign an arithmetic function that extracts the maximum value of the common values (corresponding to the logical OR operation) calculated by the antecedent part arithmetic unit 17 as the arithmetic function of A process is performed to generate an input/output signal relationship in which the input signal that takes the maximum value is the output signal, and to register it in the learning signal storage section 41c. FIG. 8 illustrates the input/output signal relationship of this logical OR operation when the number of input units 1'' in the input layer of the hierarchical network structure section 20a is two. In the example of FIG. This figure shows an example of the relationship between input and output signals.

Next, the user activates the learning signal presentation device 40 by instructing that the input signal in the registered input/output signal relationship be used as a learning presentation signal and the output signal associated with this as a learning teacher signal. At the same time, by activating the learning processing device 50 in response to this activation process, the hierarchical network simulator 300 weight value management unit 340 instructs the weight value to enter learning as much as possible to realize this input/output signal relationship. .

In accordance with this startup instruction, the hierarchical network simulator 30 operates as the hierarchical network structure section 20a installed (or planned to be installed) in the fuzzy controller,
In addition to converting and outputting the presented learning presentation signal according to the data conversion function defined by the weight value, the learning processing device 50 receives the output signal from the hierarchical network simulator 30 and performs the above-mentioned hack The learning signal presentation device 40 updates the weight value (managed by the weight value management unit 34) of the internal connection according to the propagation method.
The presentation of the learning signal is repeated until the output signal from the hierarchical network simulator 30 is substantially inferior to the learning teacher signal. Through this process, the weight values of the internal connections of the hierarchical network structure section 20a that realize the registered input/output signal relationship are stored in the weight value management section 34 of the hierarchical network simulator 30.

FIG. 9 shows learning data when learning is performed using the input/output signal relationship shown in FIG. 8 as a learning signal. Here, FIG. 9(a) shows the floor N, ? for presentation of each learning presentation signal when the number of learning times is 0 (that is, at the start of learning). , the output signal data of the network simulator 30, and FIG.
The output signal data of the simulator 30, FIG. 9(C), is
The output signal data of the hierarchical network simulator 30 for presentation of each learning presentation signal when the number of learning times is 16802 is shown. Here, this learning was performed using a hierarchical network structure section 20a whose middle layer consisted of 10 units in one stage.

Furthermore, at the start of learning, random numbers generated by a random number generator were assigned as initial values for the weight values (including dark values) of each internal connection. This figure shows that, for example, when the rEO5J learning presentation signal of the learning signal in FIG. 8 is given to the hierarchical network simulator 30, the number of learning times is 16802.
This indicates that "0.519" was output from the hierarchical network simulator 30 at the time. Here, '0.500', which is associated with this '0.519' in parentheses, is the 'EO5J learning teacher signal.

FIG. 10 shows a plot of the number of times of learning and the error of the data processing function of the hierarchical network simulator 30. As shown in this figure, when the number of times of learning exceeds 15,000, the floor N-1 work computer 30 roughly responds to the presentation of the learning signal shown in FIG. It will be output. In this state, even when something that is not in the learning signal is presented, an output signal that is similar to the content of the OR operation is output.

FIG. 11 shows the weight values and dark values (managed by the weight value management unit 34 of the hierarchical network simulator 30) assigned to each internal connection of the hierarchical network structure unit 20a when the number of learning times is 16802. Illustrate learning values. Here, "-5,564990" is the weight value of the internal connection between the first unit of the input layer and the first unit of the hidden layer, and '4.059475' is the weight value of the internal connection between the first unit of the input layer and the first unit of the hidden layer. The weight value of the internal connection with one unit, ”-
1,050942'' is the threshold of the first unit of the middle layer,
"-0,553113" represents the darkness value of the unit in the output layer.

As can be seen from Figures 9(c) and 10, this first
The weight value management unit 2 of the hierarchical network structure unit 20a implemented in the fuzzy controller stores the weight values and darkness values shown in FIG.
1a, the hierarchical network structure section 20a
The consequent part calculation section 18, which executes the calculation process, selects and outputs the maximum value of the applied values calculated by the antecedent part calculation part I7.

On the other hand, the user performs the calculation function of the consequent part calculation unit 18 as follows.
The average value of the common values calculated by the antecedent calculation unit 17 (input unit 1 of the input layer of the hierarchical network structure unit 20a)
If you want to assign an arithmetic function that outputs the average value of the two applied values because it is assumed that the number of By generating an input/output signal relationship in which the output signal is the average value of these input signals and registering it in the learning signal storage unit 41, and subsequently starting the learning signal presentation device 40 and the learning processing device 50, the hierarchy The weight value of the weight value management unit 34 of the network simulator 300 instructs to start learning as much as possible to realize this input/output signal relationship.

FIG. 13 illustrates learning data when learning is performed using the input/output signal relationship shown in FIG. 12 as a learning signal. Here, this learning is performed on the floor N2, similar to the learning of the logical sum. The middle layer of the Nodowaku barrel making section 20a has a single stage structure.
The test consisted of 0 units. Also, Figure 13 shows
It represents the output signal data of the hierarchical network simulator 30 when the number of learning times is 2596, when the learning error has almost converged.

In the 14th section, the learning values of the weight values and dark values assigned to each internal connection of the hierarchical network structure section 20a at this number of learning times are illustrated. If the weight values and threshold values shown in FIG. 14 are registered in the weight value management unit 21a of the hierarchical network structure unit 20a installed in the fuzzy controller, the consequent part that executes arithmetic processing by the hierarchical network structure unit 20a The calculation unit 18 executes the consequent calculation of calculating and outputting the average value of the applied values calculated by the antecedent calculation unit 17.

In addition, the user can perform the calculation function of the consequent part calculation unit 18 as follows:
The applied value calculated by the antecedent calculation unit 17 is expressed by the following formula, which is the limit Wasu 2 (the number of input units 1 in the input layer of the hierarchical network structure unit 20a is 2).
If you want to assign an arithmetic function that outputs z=l△(χ+y), which is the marginal sum of two truth values because By generating an input/output signal relationship in which the output signal is a signal and the marginal sum of those input signals and registering it in the learning signal storage unit 41, and subsequently starting the learning signal presentation device 40 and the learning processing device 50, The weight value of the weight value management unit 34 of the hierarchical network simulator 30 instructs learning to be started to realize this input/output signal relationship.

FIG. 16 illustrates learning data when learning is performed using the input/output signal relationship shown in FIG. 15 as a learning signal. Here, in this learning, the middle layer of the hierarchical network structure section 20a is composed of 10
It was made up of units. Further, FIG. 16 shows the output signal data of the work simulator 30 at layer 2 when the number of learning times is 3867, when the learning error has almost converged.

FIG. 17 illustrates the learning values of the weight values and dark values assigned to each internal connection of the hierarchical network structure section 20a at this number of learning times. If the weight values and dark values shown in FIG. 17 are registered in the weight value management section 21a of the hierarchical network structure section 20a installed in the fuzzy controller, the consequent for which the arithmetic processing is executed by the hierarchical network structure section 20a is set. The part calculation part 18 executes the consequent part calculation of calculating and outputting the limit sum of the applied values calculated by the antecedent part calculation part 17.

As described above, according to the present invention, the calculation of the consequent part calculation performed by the consequent part calculation part 18 can be performed by simply changing the value of the weight value (dark value) assigned to the internal connection of the hierarchical network structure part 20a. This allows you to freely change and configure the contents.

Although the illustrated embodiment has been described, the present invention is not limited thereto. For example, the network structure of the network structure section 20 is not limited to a hierarchical network structure. Further, the calculation processing of the basic unit 1 is not limited to the dark value conversion processing. In addition, the applicant:
In the earlier application, ``Patent Application No. 1983-227825 (filed on September 12, 1988, ``Learning Processing Method for Network Configuration Data Processing Device''), we attempted to improve the bank propagation method to shorten the time. However, the present invention also utilizes other weight value learning methods other than the improved bank propagation method and back propagation method. can do. Then, the network structure unit 20 is implemented in the fuzzy controller without using a simulator or the like.
It is also possible to use that information to learn the weight values.

〔Effect of the invention〕

As described above, according to the present invention, the calculation contents of the consequent part calculation of the fuzzy controller can be freely changed without having to prepare a subroutine in advance in the apparatus. Furthermore, even with fuzzy controllers that have already been shipped, it is possible to implement changes in the calculation contents of the consequent part calculation without adding or changing hardware or software. From now on, requests to change the consequent part calculations described in the fuzzy control rules can be easily handled, so that the performance of the fuzzy controller can be improved.

[Brief explanation of drawings]

Figure 1 is a diagram of the principle configuration of the present invention, Figure 2 is an embodiment of the present invention, Figure 3 is a diagram of the basic configuration of the basic unit, Figure 4 is a diagram of the basic configuration of the hierarchical network structure, and Figure 5 is a diagram of the basic configuration of the hierarchical network structure. FIG. 6 is an example of the basic unit; FIG. 6 is an example of the hierarchical network structure; FIG. 7 is an explanatory diagram of the learning system used in the present invention; FIG. 8 is the learning signal generated when assigning logical sum operations. 9 and 10121 are explanatory diagrams of the learning data of the logical sum operation, Figure 1 is an explanatory diagram of the learning data of the weight value and dark value of the logical sum operation, and Figure 12 is an explanatory diagram of the learning data of the logical sum operation. An explanatory diagram of the learning signal that is sometimes generated, Figure 13 is an explanatory diagram of the learning data for the average calculation, Figure 14 is an explanatory diagram of the learning data of the weight value and dark value of the average calculation, and Figure 15 is an illustration of the assignment of the marginal sum calculation. FIG. 16 is an explanatory diagram of learning data for marginal sum calculation, and FIG. 17 is an explanatory diagram of learning data of weight values and threshold values for marginal sum calculation. In the figure, 1 is a basic unit, 1 is an input unit, 10 is a fuzzy controller, 16 is an antecedent part truth value calculation unit, 17 is an antecedent part calculation unit, 18 is a consequent part calculation unit, and 20 is a network structure. 20a is a hierarchical network structure section, 21 is an internal state value management section, 21a is a weight value management section, 30 is a floor N2 software work simulator, 40 is a learning signal presentation device, 5
0 is a learning processing device.

Claims (3)

[Claims] (1) An antecedent truth value calculation unit (16) that calculates the membership function value for the input control state quantity, and a logical operation on the calculated value of the antecedent truth value calculation unit (16). an antecedent part calculation unit (17) that obtains an output value; a consequent part calculation unit (18) that performs a logical operation on the output value of the antecedent part calculation unit (17) to obtain an output value; A fuzzy controller comprising an inference value calculation unit (19) that calculates and outputs a control operation amount from the output value of the operation unit (18) and a membership function value regarding the control operation amount, the consequent operation unit (1
8) receives one or more inputs and an internal state value to be multiplied by the inputs to obtain a product-sum value, and also obtains an output value by functionally converting the product-sum value. A fuzzy controller characterized in that it is constituted by a network structure section (20) constituted by internal connections of basic units (1). (2) In the fuzzy controller according to claim (1), the network structure section (20) distributes the output value of the antecedent section calculation section (17) inputted to the basic unit (1). ') as a structural unit, a plurality of input units (1'-h) as an input layer, and one or more basic units (1-i) as an intermediate layer in one or more stages. and between the input layer and the foremost intermediate layer, between the intermediate layers, and between the final intermediate layer and the output layer. A fuzzy controller characterized in that it is constituted by a hierarchical network structure that constitutes internal connections in which internal state values are set. (3) In the fuzzy controller according to claim (1) or (2), the network structure section (20) has a maximum input signal value as an internal state value assigned to an internal connection of the network structure section (20). A fuzzy controller characterized in that a value is set that causes the controller to operate so as to output.