58933 - Data Fusion: A Project Update & Pathway Forward 

At the Turbo Expo 2018: Turbomachinery Conference & Expedition, in Oslo, Norway, an innovative approach for assessing operating and near real-time data from power generating assets with meaningful predictive analytics was presented and discussed.  GT2018-75030, entitled; Energy Innovation: A Focus on Power Generation Data Capture & Analytics in a Competitive Market established a challenging objective for the industry:

“To advance the notion that the fusion of total plant data, from three primary sources, with the ability to transform, analyze, and act based on integrating subject matter expertise is essential for effectively managing assets for optimum performance and profitability; executing and delivering on the promise of “Big Data” and advanced analytics.”

Throughout 2019 and 2020, a team comprised of members from Strategic Power Systems, Inc.® (SPS), Turbine Logic (TL), and two National Labs; National Energy Technology Laboratory (NETL) and Oak Ridge National Laboratory (ORNL), collaborated on the paper’s hypothesis.  The team worked with the support of funding from DOE’s Fossil Energy Program through its HPC4Materials Program, which provided access to the High-Performance Computing assets at both laboratories.  The team brought unique skills, strengths, and capabilities that would serve as the basis for an effective, open, and challenging collaboration.  The engineering and data science disciplines that converged on this project provided the back-bone for the unbiased analysis and model building that took place; relying on a unique and up-to-date source of plant operating and design data essential for performing the engineering scope of work.  A key objective was to use the data and the modeling to be predictive; to characterize remaining life, expended life, and to determine the “next failure” for critical systems and components.

The scope of work focused on two primary areas:

1.      Predicting incipient failures for thermal power plants using rapid data analysis and Machine Learning (ML) – ORNL focused here:

-A focus on “time series data”

-Integrating process data for predicting outage and impact

-An opportunity to test ML, Neural Networks, NLP for use in real-time, high sample rate anomaly detection with a goal towards trip and outage avoidance

2.      HPC analysis of near-real-time data and engineering design and specific metallurgy of down-stream boiler tubes to model and determine expended and remaining life – NETL focused here:

-The Effect of Cyclic Operation on HRSG and Coal Fired Boiler Tubes – using Finite Element Analysis (FEA) and Computational Fluid Dynamics (CFD)

-Failures Induced by High Thermal Stress and Component Fatigue

-An Opportunity for Predictive Maintenance

This paper will present the effort that was performed – testing the hypothesis that was presented in Oslo.  The paper will discuss how the effort progressed and delivered significant results – setting a pathway for follow-on activity.  A key project goal was to add measurable value for today’s operating plant – operating in a competitive and challenging market; understanding the impact of cyclic duty on advanced, highly efficient, technology systems; the value of Data Fusion.