Presented by: Kenneth Gross of Oracle

Register below for the third installment of the Energy Systems Engineering Spring 2021 Seminar Series. No person to person, this seminar is available only online, audience will participate remotely via Zoom.

DATE: Tuesday, March 9, 2021
TIME: 12:00 PM - 1:30 PM Eastern Standard Time
LOCATION - Zoom MEETING link to be sent prior to the seminar date
CONTACT US: inesei@lehigh.edu 

Abstract:
The Multivariate State Estimation Technique (MSET) is an advanced prognostic pattern recognition method that was originally developed by Argonne National Laboratory (ANL) for high-sensitivity prognostic fault monitoring applications in commercial nuclear power and aerospace applications.  MSET has since been spun off and met with commercial success for prognostic machine-learning (ML) applications in a broad range of safety critical, mission critical, and business applications, including NASA space shuttles, military gas turbine and ship-propulsion prognostics, Oil-and-Gas exploration and refinery predictive and prescriptive maintenance, human-in-the-loop supervisory control, prognostic cyber security for SCADA assets and networks, as well as Utility distribution grid and renewable asset prognostics.

Over the last 20 years, Oracle has pioneered a suite of intelligent-data-preprocessing (IDP) algorithms and automated tuning and sensitivity-optimization algorithms for a second generation MSET called MSET2.   MSET2 possesses significant advantages over conventional ML algorithmic approaches, including neural networks, autoassociative kernel regression, and support vector machines.  MSET2 advantages: higher prognostic accuracy, earlier warning of incipient anomalies in complex/dynamic/chaotic time-series signatures, lower false-alarm and missed-alarm probabilities (Type-I and -II error rates), and much lower overhead compute cost, which is crucial for real-time dense-sensor streaming prognostics.  Each of these advantages for MSET2 will be demonstrated during the presentation for several challenging Energy Industry use cases.


You acknowledge that by attending the ESE Energy Seminar Series, you will abide by the rules as detailed:
- Unless specifically requested by the speaker, all questions will be deferred to the end of the talk.
- The Director or a designee will moderate the post-talk discussion, (questions and comments should be relevant to subject in discussion).
- Students will be given first preference in the Q&A session.

Please write to ras816@lehigh.edu if you have further questions.