compare

Compare test data to historical data ensemble for similarity models

Syntax

compare(mdl,data)

compare(___,Name,Value)

Description

compare(mdl,data) plots the test component degradation data in data superimposed on the most similar data sets from the historical ensemble stored in the fitted similarity model mdl. The K most similar data sets from the ensemble are plotted, where K is the NumNearestNeighbors property of mdl.

compare(___,Name,Value) specifies plotting options using one or more name-value pair arguments.

Examples

Compare Test Data to Historical Data

Load training data.

load('pairwiseTrainTables.mat')

The training data is a cell array of tables. Each table is a degradation feature profile for a component.

Create and train a pairwise similarity model.

mdl = pairwiseSimilarityModel;
fit(mdl,pairwiseTrainTables,"Time","Condition")

Load testing data.

load('pairwiseTestData.mat')

Compare the degradation profile of the test data to the profiles of the historical data ensemble.

compare(mdl,pairwiseTestData)

Compare Test Data to Most Similar Historical Data

Load training data.

load('pairwiseTrainTables.mat')

The training data is a cell array of tables. Each table is a degradation feature profile for a component.

Create and train a pairwise similarity model.

mdl = pairwiseSimilarityModel;
fit(mdl,pairwiseTrainTables,"Time","Condition")

Load testing data.

load('pairwiseTestData.mat')

Compare the degradation profile of the test data to the profiles of the 10 most similar members of the historical data ensemble.

compare(mdl,pairwiseTestData,'NumNearestNeighbors',10)

Input Arguments

mdl — Similarity RUL model

hashSimilarityModel object | pairwiseSimilarityModel object | residualSimilarityModel object

Similarity RUL model, specified as a hashSimilarityModel object, a pairwiseSimilarityModel object, or a residualSimilarityModel object. The model must be fitted using fit before calling compare.

data — Degradation feature measurements

array | table | timetable

Degradation feature profiles for estimating the RUL of similarity models, measured over the life span of a component up to the current life time, specified as one of the following:

• N-by-(M_i+1) arrays, where N is the number of feature measurements (at different usage times) and M_i is the number of features. The first column contains the usage times and the remaining columns contain the corresponding measurements for degradation features. The order of the features must match the order specified in the DataVariables property of mdl.

• table or timetable object — The table must contain variables with names that match the strings in the DataVariables and LifeTimeVariable properties of mdl.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: 'NumNearestNeighbors','10' plots ten similar data sets

NumNearestNeighbors — Number of nearest neighbors

Inf | finite positive integer

Number of nearest neighbors, specified as the comma-separated pair 'NumNearestNeighbors' and either Inf or a finite positive integer. Use this option to select the number of most similar data sets to plot by overriding the NumNearestNeighbors property. If NumNearestNeighbors is Inf, then compare plots the degradation data for all the ensemble data sets.

Threshold — Degradation data bounds

two-column array

Degradation data bounds, specified as the comma-separated pair 'Threshold' and a two-column array with N rows, where N is the number of data variables used by mdl. The first column of Threshold contains the lower bounds for the variables, and the second column contains the upper bounds. The bounds are rendered as yellow-colored patches.

To disable the bounds for a given variable, specify the lower and upper bounds as -Inf and Inf, respectively.

Parent — Figure or axes on which to draw plot

figure handle | axes handle

Figure or axes on which to draw plot, specified as a figure handle or a plot handle. Use this argument especially when you are plotting multiple variables and want to control where the function plots them.

You cannot specify Parent as an axes handle when there are multiple variables that need multiple axes.

Version History

Introduced in R2018a