Import individual datasets when:
Your source data in the MATLAB® workspace consists of an individual workspace variable for each machine member.
The size and number of your member datasets are small enough for app memory to accommodate
Data variables within these datasets can contain timetables, tables, cell arrays, or numeric arrays.
All independent time variables must be of the same type — either all double or all
duration or all
datetime. If your original
data was uniformly sampled and timestamps were not recorded, the app prompts you to
construct a uniform timeline during the import process
Condition variables in a member dataset contain a single scalar. The form of the scalar can be numeric, string, cell, or categorical. You can import condition variables with your data only if your member datasets are tables, timetables, or cell arrays.
Matrices can contain only one independent variable, but can have any number of data variables tied to that independent variable. Matrices cannot accommodate condition variables.
Before importing your data, it must already be clean, with preprocessing such as outlier and missing-value removal. For more information, see Data Preprocessing for Condition Monitoring and Predictive Maintenance.
Select the same-size datasets you want to import from your workspace. Import all the datasets you want to use in your session at one time. You cannot import data incrementally.
Review and modify the variable types and units that Diagnostic Feature Designer associates with your imported variables.
If a table variable consists of a timetable or table with its own variable names, then
the imported variable name combines these names. For example, if table variable
Vibration is a
Data variables, then the imported
variable names are
The import process infers the variable type from its source and type. Sometimes, the type or the units is ambiguous, and you must update the default setting.
Numeric scalars represent either condition variables or features. By default, numeric scalars are treated as features. If the default type is incorrect, select the correct variable type.
Independent variable type is explicit in timetables, but not in tables or matrices. Select the correct independent variable type for any unidentified independent variables.
Update units for variables if necessary by selecting or entering alternatives within Units.
Uniformly sampled data does not always have explicitly recorded timestamps. The app detects when your imported data does not contain an explicit independent variable and allows you to create a uniform one. Specify the type, starting value, and sampling interval.
Review the ensemble variables that result from your import. Each of these variables is an ensemble variable that contains information from all your imported members. The app maintains these variables in Ensemble name. Update the default if you want to use a different ensemble name.
Click Import once you are confident your ensemble is complete. If, after completing the import, you find that you need additional datasets, you must perform a fresh import that includes everything you want. This fresh import deletes existing imported variables, derived variables, and features.
if you plan to explore the data in multiple sessions, consider saving your session immediately after you import. Saving your session after import provides you with an option for a clean start for new sessions without needing to import your separate files again. You can save additional sessions after you have generated derived variables and features.
For more information about data ensembles, see Data Ensembles for Condition Monitoring and Predictive Maintenance.
For an example on converting member matrices into tables, see Prepare Matrix Data for Diagnostic Feature Designer.