Session: 05-08 CDI Topics on Additive Manufacturing

Paper Number: 127925

127925 - Combining Machine Learning, Embedded Sensor Networks and Additive Burner Design for Combustor Structural Health Monitoring 

The combination of novel technologies such as machine learning, embedded sensor networks and additive burner design can significantly improve structural health monitoring compared to state-of-the-art methods using thresholding, pattern recognition and alarm levels. An aircraft combustor that 'feels' its effective operating conditions in real-time and accurately assesses its adaptive maintenance needs is key to meeting tomorrow's more demanding requirements specific to hydrogen-fuelled aircraft engines. The combination of these three technologies is being addressed in the crystAIr project.

An additively manufactured, highly sensitised burner (of the Recursive Sequential Combustion type, where avoidance of flashback is crucial) is used as an experimental combustion test case. In this part the fuel is propane.

One goal is to use AI to predict flashback from fast pressure sensor data as early as possible. To obtain reliable ground truth, a model is trained with signals representing the normal combustion process under desired conditions. These processes are recorded on the instrumented setup (with fast pressure sensors, temperature sensors and differential pressure sensors monitoring the flow in the burner), combined with a photodiode observing the flame and other operational data. All this optimises an auto-encoder model that learns how to reconstruct the sensor data describing the normal combustion process. A series of flash-back data is then presented where the large deviations in the reconstruction error indicate and pinpoint the disturbance in the combustion process. These events in the data are then used in the next stage to train a classifier and later an early predictor of flashback events based on the fast-pressure transducer data alone.

The paper describes the concept, the burner, the measurement chain and the AI architecture. It comments on best practice in terms of measurement location and the relevance of these, and reports about the first results.

 

Presenting Author: Fabrice Giuliani Combustion Bay One e.U.

Presenting Author Biography: Priv.-Doz. Dipl.-Ing. Dr.techn. Fabrice Louis Michel GIULIANI


Born in France in 1974.


Studied mechanical engineering at the Polytech Nancy, University of Lorraine, France (then called ESSTIN and Henri Poincaré Nancy I). Engineering degree in 1997 in fluid mechanics and power engineering.

Diploma course at the von Karman Institute for Fluid Dynamics near Brussels, Belgium, 1998.

Doctorate (with honours) at the ISAE-SUPAERO National School of Aeronautical Engineering in Toulouse, France, 2002.

Habilitation in Combustion Technology at TU Graz in 2010.


Research engineer at VKI near Brussels, ONERA Toulouse and DLR Cologne, Germany from 1998 to 2004.

Lecturer in fluid dynamics and combustion at ENAC (Ecole Nationale d'Aviation Civile), ENSICA (École nationale supérieure d'ingénieurs de constructions aéronautiques), ISAE-SUPAERO in Toulouse at the beginning of the century, and at TU Graz and FH Joanneum in Graz, Austria since 2004.

Head of the Combustion Department at TU Graz from 2004 to 2011.

Founder and CEO of Combustion Bay One e.U. since 2012. CBOne is an advanced combustion management engineering company. It provides expertise, design and manufacturing services of hot core parts with extreme thermal and mechanical loads for laboratory and industrial applications. In parallel, it carries out its own research and development, with more than 30 scientific publications and 4 patents since the company was founded.

Authors:

Fabrice Giuliani Combustion Bay One e.U.
Nina Paulitsch Combustion Bay One e.U.
Andrea Hofer Combustion Bay One e.U.
Vojislav Petrovic-Filipovic JOANNEUM RESEARCH Forschungsgesellschaft mbH
Benjamin Maier JOANNEUM RESEARCH Forschungsgesellschaft mbH
Werner Bailer JOANNEUM RESEARCH Forschungsgesellschaft mbH
Martin Winter JOANNEUM RESEARCH Forschungsgesellschaft mbH
Roland Unterberger JOANNEUM RESEARCH Forschungsgesellschaft mbH
Alexander Schricker Piezocryst GmbH