Data analysis is the heart of condition monitoring and predictive maintenance. Designing algorithms for predictive maintenance requires organizing and analyzing large amounts of data while keeping track of the systems and conditions the data represents.
Predictive Maintenance Toolbox™ provides tools for managing sensor data stored locally and remotely, as well as for generating simulated data by running a Simulink® model. The main unit for organizing and managing multifaceted data sets in Predictive Maintenance Toolbox is an ensemble. An ensemble is a collection of data sets, created by measuring or simulating a system under varying conditions. Manage your ensemble using ensemble datastore objects. For more information about how ensembles work and how to use them, see Data Ensembles for Condition Monitoring and Predictive Maintenance.
The Diagnostic Feature Designer app includes interactive tools for processing data and extracting features. The app accepts data sets in various forms, consolidates the data within the app, and manages that data internally during a session. For more information on the app, see Explore Ensemble Data and Compare Features Using Diagnostic Feature Designer.
|Manage ensemble data in custom file format|
|Manage ensemble data generated by |
|Manage ensemble data stored in the MATLAB workspace using code generated by Diagnostic Feature Designer|
|Generate ensemble data by running a Simulink model|
|Read member data from an ensemble datastore|
|Write data to member of an ensemble datastore|
|Determine if data is available to read|
|Reset datastore to initial state|
|Number of datastore partitions|
|Partition a datastore|
|Determine how much data has been read|
|Create tall array|
Algorithm design with Predictive Maintenance Toolbox uses data organized in ensembles. You can generate ensemble data from a Simulink model or create ensembles from existing data stored on disk.
If you have a Simulink model of your system under fault conditions, you can generate an ensemble of simulated data for developing predictive-maintenance algorithms.
Use a file ensemble datastore to manage and interact with large sets of data collected from operation of your system under varying conditions.
Create and use a
fileEnsembleDatastore object to manage an
ensemble of data stored in a plain-text format.
Follow this workflow for interactively exploring and processing ensemble data, designing and ranking features from that data, and exporting data and selected features, and generating MATLAB code.
Organize measurements and information for multiple systems into data sets that you can import into the app.
Import an ensemble member table from your workspace, define variable types, and view the data using interactive plotting options.
Convert single-member matrices to an ensemble table for import into the app.