Control Surface

The Control Surface document shows the output values from the active FIS design for all possible combinations of two input variables.

In the Axes section, select the input variables for the X and Y axes, and an output variable for the Z, axis. The preceding figure shows the variable selections when analyzing a single FIS, the drop-down lists contain the names of the selected variables. When you analyze a FIS tree, the drop-down list entries specify the name of the component FIS along with the variable name, for example, fis1/input1.

In the Mesh Points section, you can specify the plot resolution along the X and Y axes. For a smoother plot, specify a larger number of points mesh points.

If your system has more than two inputs, you must specify a reference value for each input variable not shown in the plot. To do so, specify the Reference Inputs parameter. For example, the following figure shows a reference input for a three-input system for which the first and second variables are used in the control surface plot.

For each variable that is used in the control surface plot, specify a reference value of NaN.

You can also view a control surface for a single input variable. In this case, in the Axes section, in the X drop-down list, select the input variable and, in the Y drop-down list, select none. Then, specify the reference values for all unused input variables using the Reference Inputs parameter.

For example, the following figure shows a control surface for a two-input system where the output is plotted against the first input variable.

Rule Inference

In the Rule Inference document, you specify values for your input variables, inspect the inference process, and view the resulting output value produced by the active FIS design. The Rule Inference document does not support FIS trees.

For more information on the fuzzy inference process for different FIS types:

To select input values, in the Rule Inference document, specify the Input values parameter. Alternatively, you can drag the input bars.

The preceding figure shows the Rule Inference document for a type-1 Mamdani system.

The fuzzified inputs activate the second and third rules. The firing strengths of these rules are applied to the output variable. When the resulting output membership functions are aggregated and defuzzified, the final output value is 21.7.

The following figure shows the same inference process for a type-2 Mamdani system. In this case, the fuzzified inputs generate firing strengths for both the upper and lower membership functions.

System Validation

Since R2023a

To validate your FIS designs, you can compare output values to corresponding reference validation data.

The System Validation document shows simulation results for all designs that you select in the Design Browser. To select a FIS design, select the corresponding entry in the Compare column.

To perform system validation for your FIS, you must first specify reference input and output data. For more information, see Specify Validation Data.

Using the System Validation document, you can view plots of:

To view corresponding numerical values from across all the plots, point to any of the plot lines.

Error Distribution

Since R2023a

The Error Distribution document is a graphical representation of the output error for the active FIS design as compared to reference output data.

For a multi-output FIS, in the Calculate drop-down list, select the output for which you want to analyze the error distribution. When you analyze a FIS tree, the outputs listed in this drop-down list display the name of the component FIS along with the variable name, for example, fis1/input1.

To analyze the error distribution for your FIS, you must first specify reference input and output data. For more information, see Specify Validation Data.

Using the Error Distribution document, you can:

For example, the following figure shows the error distribution for a tipping system with two inputs, service quality and food quality. The FIS performs well for most of the input space. However, there are significant errors in the upper-right region of the plot, which corresponds to situations where both the service and food have a high quality rating. In this case:

FIS Tree Data Flow

Since R2024a

To analyze the behavior of FIS tree design, you can view the propagation of inference results through the FIS tree for specified input values.

When you select FIS Tree Data Flow in the Simulation gallery, the FIS Tree Plot document displays input and output values for each FIS in the FIS tree.

To specify FIS input values, use the Input values field.

For example, the following figure shows the FIS tree data flow for the weightedTipper system from Build FIS Tree Using Fuzzy Logic Designer.

By examining the data flow, you can assess the behavior of each FIS in the tree and the resulting overall behavior. For example, if the overall FIS behavior does not match your expectations, you can identify potentially problematic intermediate FIS outputs. You can then further analyze and modify the behavior of the corresponding FIS.

Specify Validation Data

The System Validation and Error Distribution analysis documents require reference validation data.

To select validation data, on the Design tab:

For both input and output data, you can select previously imported data, such as training data from tuning, or data from the MATLAB workspace.

The Input Data and Output Data drop-down lists show only data that is compatible with the input and output configurations of your FIS.