Note: This page has been translated by MathWorks. Click here to see

To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Mamdani fuzzy inference system

Use a `mamfis`

object to represent a Mamdani fuzzy inference
system (FIS). For more information on Mamdani systems, see What Is Mamdani-Type Fuzzy Inference?

As an alternative to Mamdani systems, you can create a Sugeno FIS using a `sugfis`

object. For a
comparison of Mamdani and Sugeno systems, see Comparison of Sugeno and Mamdani Systems.

To create a Mamdani FIS object, use one of the following methods:

The

`mamfis`

function.If you have input and output training data (

`inputData`

and`outputData`

, respectively), you can use the`genfis`

function with the FCM clustering method.opt = genfisOptions('FCMClustering','FISType','mamdani'); fis = genfis(inputData,outputData,opt);

If you have a

`.fis`

file for a Mamdani system, you can use the`readfis`

function.

`fis = mamfis`

`fis = mamfis(Name,Value)`

`fis = mamfis`

creates a Mamdani FIS with default property values.
To modify the properties of the fuzzy system, use dot notation.

`fis = mamfis(`

specifies FIS
configuration information or sets object properties using name-value pair arguments. You
can specify multiple name-value pairs. Enclose names in quotes.`Name,Value`

)

`addInput` | Add input variable to fuzzy inference system |

`removeInput` | Remove input variable from fuzzy inference system |

`addOutput` | Add output variable to fuzzy inference system |

`removeOutput` | Remove output variable from fuzzy inference system |

`addRule` | Add rule to fuzzy inference system |

`addMF` | Add membership function to fuzzy variable |

`removeMF` | Remove membership function from fuzzy variable |

`evalfis` | Evaluate fuzzy inference system |

`writeFIS` | Save fuzzy inference system to file |

You can interactively create a Mamdani FIS using the **Fuzzy Logic
Designer** app. You can then export the system to the MATLAB workspace.