Fuzzy Logic Controller

Evaluate fuzzy inference system

• 

Libraries:
Fuzzy Logic Toolbox

Description

The Fuzzy Logic Controller block implements a fuzzy inference system (FIS) in Simulink^®. You specify the FIS to evaluate using the FIS name parameter.

For more information on fuzzy inference, see Fuzzy Inference Process.

To display the fuzzy inference process in the Rule Viewer during simulation, use the Fuzzy Logic Controller with Ruleviewer block.

Examples

Simulate Fuzzy Inference System

Once you have implemented a fuzzy inference system using Fuzzy Logic Designer, using Neuro-Fuzzy Designer, or at the command line, you can simulate the system in Simulink.

Open Script

Water Level Control in a Tank

Implement a water level controller using the Fuzzy Logic Controller block in Simulink.

Open Script

Temperature Control in a Shower

Implement a water temperature controller using the Fuzzy Logic Controller block in Simulink.

Open Script

Fuzzy PID Control with Type-2 FIS

Create a type-2 fuzzy logic PID controller and compare its performance with a type-1 fuzzy PID controller and a conventional PID controller.

Since R2019b

Open Live Script

Ports

Input

in — Input signal

scalar | vector

For a single-input fuzzy inference system, the input is a scalar signal. For a multi-input fuzzy system, combine the inputs into a vector signal using blocks such as:

• Mux (Simulink)

• Vector Concatenate (Simulink)

• Bus Creator (Simulink)

Output

out — Defuzzified output signal

scalar | vector

For a single-output FIS, the output is a scalar signal. For a multi-output FIS, the output is a vector signal. To split system outputs into scalar signals, use the Demux (Simulink) block.

fi — Fuzzified input values

matrix

Fuzzified input values, obtained by evaluating the input membership functions of each rule at the current input values.

For a type-1 FIS, fi is an N_R-by-N_U matrix signal, where N_R is the number of FIS rules. Element (i,j) of fi is the value of the input membership function for the jth input in the ith rule.

For a type-2 FIS, fi is an N_R-by-(2*N_U) matrix signal. The first N_U columns contain the fuzzified values of the upper membership function for each rule, and the last N_U columns contain the fuzzified values from the lower membership functions.

For more information on fuzzifying input values, see Fuzzify Inputs.

Dependencies

To enable this port, select the Fuzzified inputs (fi) parameter.

rfs — Rule firing strengths

column vector

Rule firing strengths, obtained by evaluating the antecedent of each rule; that is, applying the fuzzy operator to the values of the fuzzified inputs.

For a type-1 FIS, rfs is a column vector signal of length N_R, where N_R is the number of rules, and element i is the firing strength of the ith rule.

For a type-2 FIS, rfs is an N_R-by-2 matrix signal. The first column contains the rule firing strengths generated using upper membership functions, and the second column contains the rule firing strengths generated using lower membership functions.

For more information on applying fuzzy operators, see Apply Fuzzy Operator.

Dependencies

To enable this port, select the Rule firing strengths (rfs) parameter.

ro — Rule outputs

matrix

Rule outputs, obtained by applying the rule firing strengths to the output membership functions using the implication method specified in the FIS.

For a type-1 Mamdani FIS, ro is an N_S-by-(N_RN_Y) matrix signal, where N_R is the number of rules, N_Y is the number of outputs, and N_S is the number of sample points used for evaluating output variable ranges. Each column of ro contains the output fuzzy set for one rule. The first N_R columns contain the rule outputs for the first output variable, the next N_R columns correspond to the second output variable, and so on.

For a type-2 Mamdani FIS, ro is an N_S-by-(2*N_R*N_Y) matrix signal. The first N_R*N_Y columns contain the rule outputs generated using upper membership functions, and the last N_R*N_Y columns contain the rule outputs generated using lower membership functions.

For a type-1 Sugeno system, each rule output is a scalar value. In this case, ro is an N_R-by-N_Y matrix signal. Element (j,k) of ro is the value of the kth output variable for the jth rule.

For a type-2 Sugeno system, ro is an N_R-by-(3*N_Y) array. The first N_Y columns contain the rule output levels. The next N_Y columns contain the corresponding rule firing strengths generated using upper membership functions. The last N_Y columns contain the rule firing strengths generated using lower membership functions. For example, in a three-output system, columns 4 and 7 contain the firing strengths for the output levels in column 1.

For more information on fuzzy implication, see Apply Implication Method.

Dependencies

• To enable this port, select the Rule outputs (ro) parameter.

• To specify N_S, use the Number of samples for output discretization parameter.

ao — Aggregated output

matrix | row vector

Aggregate output for each output variable, obtained by combining the corresponding outputs from all the rules using the aggregation method specified in the FIS.

For a type-1 Mamdani fuzzy inference system, the aggregate result for each output variable is a fuzzy set. In this case, ao is as an N_S-by-N_Y matrix signal, where N_Y is the number of outputs and N_S is the number of sample points used for evaluating output variable ranges. Each column of ao contains the aggregate fuzzy set for one output variable.

For a type-2 Mamdani FIS, the aggregate result for each output variable is a fuzzy set. In this case, ao is as an N_S-by-(2*N_Y) matrix signal. The first N_Y columns contain the aggregated outputs generated using upper membership functions, and the last N_Y columns contain the aggregated outputs generated using lower membership functions.

For a type-1 Sugeno system, the aggregate result for each output variable is a scalar value. In this case, ao is a row vector of length N_Y, where element k is the sum of the rule outputs for the kth output variable.

For a type-2 Sugeno system, ao is an N_R-by-(3*N_Y) array. aggregatedOut contains the same data as ro with the columns sorted based on the output levels. For example, in a three-output system, when the output levels in column 1 are sorted, the corresponding firing strengths in columns 4 and 7 are adjusted accordingly.

For more information on fuzzy aggregation, see Aggregate All Outputs.

Dependencies

• To enable this port, select the Aggregated outputs (ao) parameter.

• To specify N_S, use the Number of samples for output discretization parameter.

Parameters

General

FIS name — Fuzzy inference system

mamfis object | sugfis object | mamfistype2 object | sugfistype2 object | file name

Fuzzy inference system to evaluate, specified as one of the following:

• mamfis or sugfis object — Specify the name of a type-1 FIS object in the MATLAB^® workspace.

• mamfistype2 or sugfistype2 object — Specify the name of a type-2 FIS object in the MATLAB workspace. (since R2019b)

• File name — Specify the name of a FIS file (*.fis) in the current working folder or on the MATLAB path. Including the file extension in the file name is optional.

  To save a fuzzy inference system to a FIS file:

  • In Fuzzy Logic Designer, on the Design tab, under Save, select the system to save.

  • At the command line, use writeFIS.

Programmatic Use

Block Parameter: FIS

Type: string, character vector

Default: 'tipper.fis'

Number of samples for output discretization — Number of points in output fuzzy sets

101 (default) | integer greater than 1

Number of samples for discretizing the range of output variables, specified as an integer greater than 1. This value corresponds to the number of points in the output fuzzy set for each rule.

To reduce memory usage while evaluating a Mamdani FIS, specify a lower number of samples. Doing so sacrifices the accuracy of the defuzzified output value. Specifying a low number of samples can make the output area for defuzzification zero. In this case, the defuzzified output value is the midpoint of the output variable range.

Note

The block ignores this parameter when evaluating a Sugeno FIS.

Programmatic Use

Block Parameter: OutputSampleNumber

Type: string, character vector

Default: "101"

Data type — Signal data type

double (default) | single | fixed-point | expression

Signal data type, specified as one of the following:

• double — Double-precision signals

• single — Single-precision signals

• fixdt(1,16,0) — Fixed-point signals with binary point scaling

• fixdt(1,16,2^0,0) — Fixed-point signals with slope and bias scaling

• Expression — Expression that evaluates to one of these data types

For fixed-point data types, you can configure the signedness, word length, and scaling parameters using the Data Type Assistant. For more information, see Specifying a Fixed-Point Data Type (Simulink).

Programmatic Use

Block Parameter: DataType

Type: string, character vector

Values: "double", "single", "fixdt(1,16,0)", "fixdt(1,16,2^0,0)"

Default: "double"

Fuzzified inputs (fi) — Enable fi output port

off (default) | on

Enable output port for accessing intermediate fuzzified input data.

Programmatic Use

Block Parameter: FuzzifiedInputs

Type: string, character vector

Values: "off", "on"

Default: "off"

Rule firing strengths (rfs) — Enable rfs output port

off (default) | on

Enable output port for accessing intermediate rule firing strength data.

Programmatic Use

Block Parameter: RuleFiringStrengths

Type: string, character vector

Values: "off", "on"

Default: "off"

Rule outputs (ro) — Enable ro output port

off (default) | on

Enable output port for accessing intermediate rule output data.

Programmatic Use

Block Parameter: RuleOutputs

Type: string, character vector

Values: "off", "on"

Default: "off"

Aggregated outputs (ao) — Enable ao output port

off (default) | on

Enable output port for accessing intermediate aggregate output data.

Programmatic Use

Block Parameter: AggregatedOutputs

Type: string, character vector

Values: "off", "on"

Default: "off"

Simulate using — Simulation mode

Interpreted execution (default) | Code generation

Simulation mode, specified as one of the following:

• Interpreted execution — Simulate fuzzy systems using precompiled MEX files for single and double data types. Using this option reduces the initial compilation time of the model.

• Code generation — Simulate fuzzy system without precompiled MEX files. Use this option when simulating fuzzy systems for code generation applications.

For fixed-point data types, the Fuzzy Logic Controller block always simulates using Code generation mode.

Programmatic Use

Block Parameter: SimulateUsing

Type: string, character vector

Values: "Interpreted execution", "Code generation"

Default: "Interpreted execution"

Diagnostics

Out of range input value — Diagnostic message behavior when an input is out of range

warning (default) | error | none

Diagnostic message behavior when an input is out of range, specified as one of the following:

• warning — Report the diagnostic message as a warning.

• error — Report the diagnostic message as an error.

• none — Do not report the diagnostic message.

When an input value is out of range, corresponding rules in the fuzzy system can have unexpected firing strengths.

Dependencies

• Diagnostic messages are provided only when the Simulate using parameter is Interpreted execution.

Programmatic Use

Block Parameter: OutOfRangeInputValueMessage

Type: string, character vector

Values: "warning", "error", "none"

Default: "warning"

No rule fired — Diagnostic message behavior when no rules fire

warning (default) | error | none

Diagnostic message behavior when no rules fire for a given output variable, specified as one of the following:

• warning — Report the diagnostic message as a warning.

• error — Report the diagnostic message as an error.

• none — Do not report the diagnostic message.

When No rule fired is warning or none and no rules fire for a given output, the defuzzified output value is set to its mean range value.

Dependencies

• Diagnostic messages are provided only when the Simulate using parameter is Interpreted execution.

Programmatic Use

Block Parameter: NoRuleFiredMessage

Type: string, character vector

Values: "warning", "error", "none"

Default: "warning"

Empty output fuzzy set — Diagnostic message behavior when an output fuzzy set is empty

warning (default) | error | none

Diagnostic message behavior when an output fuzzy set is empty, specified as one of the following:

• warning — Report the diagnostic message as a warning.

• error — Report the diagnostic message as an error.

• none — Do not report the diagnostic message.

When Empty output fuzzy set is warning or none and an output fuzzy set is empty, the defuzzified value for the corresponding output is set to its mean range value.

Dependencies

• This diagnostic message applies to Mamdani systems only.

• Diagnostic messages are provided only when the Simulate using parameter is Interpreted execution.

Programmatic Use

Block Parameter: EmptyOutputFuzzySetMessage

Type: string, character vector

Values: "warning", "error", "none"

Default: "warning"

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

PLC Code Generation
Generate Structured Text code using Simulink® PLC Coder™.

Fixed-Point Conversion
Design and simulate fixed-point systems using Fixed-Point Designer™.

Version History

Introduced before R2006a

R2019b: Support for fuzzy inference system structures will be removed

Support for representing fuzzy inference systems as structures will be removed in a future release. Use mamfis and sugfis objects with this function instead. To convert existing fuzzy inference system structures to objects, use the convertfis function.

This change was announced in R2018b. Using fuzzy inference system structures with this block issues a warning starting in R2019b.

R2017b: Access intermediate fuzzy inference results

Using the Fuzzy Logic Controller block, you can access intermediate fuzzy inference results by enabling the following output ports.

• fi — Fuzzified input values

• rfs — Rule firing strengths

• ro — Rule outputs

• ao — Aggregated membership function for each output variable

R2017b: Expanded data type support

The Fuzzy Logic Controller block supports double-precision, single-precision, and fixed-point data types.

R2017b: Improved code generation support

When generating code using Simulink Coder™, the Fuzzy Logic Controller block supports code generation for fuzzy systems that use:

• Single-precision data.

• Fixed-point data. To generate code for fixed-point data, you need Fixed-Point Designer™ software.

• Custom membership functions and custom inference functions. For more information on specifying custom functions for a fuzzy system, see Build Fuzzy Systems Using Custom Functions.

R2017b: PLC code generation support

The Fuzzy Logic Controller block supports generation of IEC 61131-3 Structured Text for PLC deployment using Simulink PLC Coder™ software.