MathWorks has announced Predictive Maintenance Toolbox, a MATLAB product that helps engineers design and test condition monitoring and predictive maintenance algorithms. Predictive Maintenance Toolbox offers capabilities and reference examples for engineers who are designing algorithms to organize data, design condition indicators, monitor machine health, and estimate remaining useful life (RUL) to prevent equipment failures. The toolbox includes reference examples for motors, gearboxes, batteries, and other machines that can be reused for developing custom predictive maintenance and condition monitoring algorithms.
The product allows engineers to develop and validate algorithms that predict when an equipment failure might occur or to detect any underlying anomalies by monitoring sensor data. These algorithms are developed by accessing historical data that is stored in local files, on cloud storage systems such as Amazon S3 and Windows Azure Blob Storage, or on a Hadoop Distributed File System. Another source of data is simulation data from physical models of the equipment that incorporate failure dynamics, such as those generated by Simulink models. Engineers can extract and select the most suitable features from this data, and then use interactive apps to train machine learning models with these features to predict or detect equipment failures.
Find more information at mathworks.com/products/predictive-maintenance.