MathWorks adds predictive maintenance tools for MATLAB
MathWorks has announced the Predictive Maintenance Toolbox, a new 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 organise data, design condition indicators, monitor machine health and estimate remaining useful life (RUL) to prevent equipment failures.
'Predictive maintenance is a key application of the industrial Internet of Things. This is critical to reduce unnecessary maintenance costs and eliminate unplanned downtime. Engineers who typically don’t have a background in machine learning or signal processing find designing algorithms for predictive maintenance particularly challenging,' said Paul Pilotte, technical marketing manager, MathWorks. 'Now, these teams can quickly ramp up by using Predictive Maintenance Toolbox as a starting point for learning how to design and test these algorithms.'
Engineers can use the Predictive Maintenance Toolbox to analyse and label sensor data imported from files that are stored locally or on cloud storage. They can also label simulated failure data generated from Simulink models to represent equipment failures. Signal processing and dynamic modeling methods that build on techniques such as spectral analysis and time series analysis let engineers preprocess data and extract features that can be used to monitor the condition of the machine. Using survival, similarity, and trend-based models to predict the RUL helps engineers estimate a machine’s time to failure. 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.
Now, engineers can develop and validate the algorithms needed to 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. 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.