What Is Predictive Maintenance Toolbox?
Predictive Maintenance Toolbox provides functions and apps for designing condition monitoring and predictive maintenance algorithms for motors, gearboxes, bearings, batteries, and other applications. The toolbox lets you design condition indicators, detect faults and anomalies, and estimate remaining useful life (RUL).
With the Diagnostic Feature Designer app, you can interactively extract time, frequency, time-frequency, and physics-based features. You can rank and export the features to develop application-specific algorithms for fault and anomaly detection. To estimate RUL, you can use survival, similarity, and trend-based models.
The toolbox helps you organize and analyze sensor data imported from local files, cloud storage, and distributed file systems. You can generate simulated failure data from Simulink and Simscape models.
To operationalize your algorithms, you can generate C/C++ code for edge deployment or create production applications for cloud deployment. The toolbox includes application-specific reference examples that you can reuse for developing and deploying custom predictive maintenance algorithms.
Published: 15 Jan 2024
Predictive Maintenance Toolbox provides functions and apps for designing condition monitoring and predictive maintenance algorithms for motors, gearboxes, bearings, batteries, and other applications. The Toolbox lets you design condition indicators, detect faults and anomalies, and estimate remaining useful life from time-series sensor data. With the Diagnostic Feature Designer app, you can interactively explore and extract features from machine sensor data, including time, frequency, and time-frequency features.
For rotating machinery like motors, bearings, pumps, and gearboxes, you can extract physics-based features specific to those components. And once you've extracted the best features, you can rank them, generate MATLAB code to recompute them from new data, or export Simulink blocks to integrate into your system simulations.
Then you can apply a variety of AI, statistical, and dynamic algorithms for fault and anomaly detection. You can also apply functions programmatically to preprocess data, extract and rank features, and train models. To estimate remaining useful life, you can train degradation, similarity, or survival models, depending on the type of historical data you have available. The Toolbox also helps you organize and preprocess sensor data imported from local files, cloud storage, and distributed file systems.
If you don't have enough failure data, you can also generate simulated failure data from Simulink models of your machine that incorporate fault conditions. And when you're ready to deploy your algorithms into operation, you can generate code for edge devices or create production applications in the cloud.
To help you get started, the Toolbox includes a library of reference examples that you can reuse. For more information on Predictive Maintenance Toolbox or to learn how MathWorks can help with your predictive maintenance project, visit the links below.