Predictive Maintenance Toolbox

Design and test condition monitoring and predictive maintenance algorithms

Predictive Maintenance Toolbox™ lets you manage sensor data, design condition indicators, and estimate the remaining useful life (RUL) of a machine.

The toolbox provides functions and an interactive app for exploring, extracting, and ranking features using data-based and model-based techniques, including statistical, spectral, and time-series analysis. You can monitor the health of batteries, motors, gearboxes, and other machines by extracting features from sensor data. To estimate a machine's time to failure, you can use survival, similarity, and trend-based models to predict the RUL.

You can organize and analyze sensor data imported from local files, cloud storage, and distributed file systems. You can label simulated failure data generated from Simulink^® models. The toolbox includes reference examples for motors, gearboxes, batteries, pumps, bearings, and other machines that can be reused for developing custom predictive maintenance and condition monitoring algorithms.

To operationalize your algorithms, you can generate C/C++ code for deployment to the edge or create a production application for deployment to the cloud.

What Is Predictive Maintenance Toolbox?

The Diagnostic Feature Designer app shows signal data in four panes: signal traces, power spectra, a table of features ranked by one-way ANOVA, and a bar chart sorting the features by importance.

Feature Engineering

Use the Diagnostic Feature Designer app or programmatically extract and rank features from sensor data with signal-based and model-based approaches for fault detection and prediction with AI.

Feature Design for Predictive Maintenance (3:03)

Documentation | Examples

A plot of two groups of power spectra. The black group is labeled normal and the red group is labeled faulty. The red group has larger magnitude peaks at some frequencies.

Fault and Anomaly Detection

Use AI, statistical, and dynamic modeling methods for condition monitoring. Track changes in your system, detect anomalies, and identify faults.

Documentation | Examples

RUL Estimation

Train RUL estimator models on historical data to predict time-to-failure and optimize maintenance schedules.

Three Ways to Estimate Remaining Useful Life

Documentation | Examples

A MATLAB plot of electrical data from a motor with colored bands highlighting the first six harmonic fault bands and side bands.

Application-Specific Algorithms

Use component-specific functions to develop algorithms to detect battery anomalies, classify bearing faults, detect leaks in pumps, track changes in motor performance, and more. Get started quickly with a library of reference examples.

Documentation | Examples

MATLAB code that shows how to create a fileEnsembleDatastore from a set of vibration data files stored locally. The output shows the ensemble represented as a tall table.

Data Management and Preprocessing

Access sensor data stored locally or remotely. Prepare data for algorithm development by removing outliers, filtering, and applying various time, frequency, and time-frequency preprocessing techniques.

Documentation | Examples

A Simscape model showing a pump housing, three plungers, and a crankshaft connected together.

Failure Data Generation

Generate simulated failure and degradation data using Simulink and Simscape™ models of your machine. Modify parameter values, inject faults, and change model dynamics. Create digital twins to monitor performance and predict future behavior.

What is a Digital Twin? (8:28)

Documentation | Examples

A MATLAB Coder Report shows MATLAB code for a Remaining Useful Life prediction function on the left and corresponding C++ code on the right. A colorful region maps a single line of MATLAB code to many lines of C++ code.

Code Generation

Use MATLAB Coder™ to generate C/C++ code directly from feature computation functions, condition monitoring algorithms, and predictive algorithms for real-time edge processing.

Documentation | Examples

Deploy Predictive Algorithms within Your Enterprise Ecosystem Using MATLAB Production Server

Cloud Deployment

Use MATLAB Compiler™ and MATLAB Compiler SDK™ to scale algorithms in the cloud as shared libraries, packages, web apps, Docker containers, and more. Deploy to MATLAB Production Server™ on Microsoft^® Azure^® or AWS^® without recoding.

Documentation | Examples