The PHM2025 Proceedings is now published!

Workshops

Schedule

Time Monday, October 27
9:00 am – 10:30 am Axion
10:45 am – 12:00 pm Axion
Time Tuesday, October 28
3:30 pm – 6:00 pm MathWorks
Time Wednesday, October 29
3:30 pm – 6:00 pm MathWorks

 

Date and Time: Mon, October 27, 9:00 am – 10:30 am AND 10:45 am – 12:00 pm
Workshop: Axion
Description:

Axion will share context around how manufacturers across industries are leveraging additional data streams to improve product performance across the lifecycle. Attendees will then have the opportunity to explore a real-world use case on a representative aerospace data set, both using typical tooling and subsequently via a hands-on exercise in Axion’s software platform, showing how AI can supercharge identifying issues impacting fleet performance.

 

Date and Time: Tue, October 28,  3:30 pm – 6:00 pm AND Wed, October 29, 3:30 pm – 6:00 pm
Workshop: Anomaly Detection and Predictive Maintenance with MATLAB
Presenters:
  • Reece Teramoto, MathWorks
  • Rachel Johnson, MathWorks
  • Bora Eryilmaz, MathWorks
Description:
  • Be sure to register here for the workshop!
  • Space is limited! Please only register for one workshop slot. Both workshops have the same content.
Overview Engineers are using AI to design smarter ways to detect anomalies, identify faults, and estimate the remaining useful life of machines. In this hands-on workshop, you will write and execute code examples in MATLAB® Online™ – entirely in your browser – to learn and explore how to design AI algorithms for anomaly detection and predictive maintenance. This workshop will be most useful for engineers who work with time series sensor data that want to explore ways to apply MATLAB to design effective algorithms. MathWorks instructors will be available throughout the session to guide you. All necessary MATLAB licenses will be provided for the duration of the workshop, including Predictive Maintenance Toolbox. Please bring your laptop. Highlights
  • Familiarize yourself with MATLAB Online with an introductory example that trains a machine learning model to identify anomalies and faults.
  • Interactively extract, analyze, and rank features from machine sensor data, then train and compare multiple AI models based on these features.
  • Dive deep into two real-world examples that cover designing an anomaly detection algorithm and estimating remaining useful life.
Who Should Attend This workshop is open to anyone attending the PHM Society Conference in 2025 who is interested in learning how to design predictive maintenance and anomaly detection algorithms in MATLAB. Product Focus