Session: 24-01: Emerging Methods in Engine Design and Life Assessment

Paper Number: 153121

Sparse Identification of Nonlinear Dynamics (SINDy) for Digital Twinning and Performance Modeling in Hybrid Engines 

Accurate and efficient modeling of turbojet engine performance is crucial for design, optimization, and real-time control however data-driven approaches hold the potential to revolutionize the aerospace industry by facilitating the development of intelligent systems capable of optimizing engine performance, enhancing safety, and improving diagnostics. In this matter the literature reveals a gap in the use of Sparse Identification of Nonlinear Dynamics (SINDy), specifically in the implementation of PySINDy for turbojet engine performance analysis. Additionally, there is a notable lack of an overall investigative application of SINDy on multiple engine parameters to evaluate their state. This research investigates the application of SINDy in creating a predictive model for turbojet engine performance. By extracting governing equations from synthetic data generated using established turbojet engine formulations, we focus on predicting specific thrust power, TSFC, air specific impulse, thermal efficiency, and overall efficiency as functions of increasing Mach number. Our methodology involves generating synthetic data through analytical engine modeling, followed by the application of SINDy using the PySINDy package to identify the underlying nonlinear dynamics. The resulting models are evaluated for their predictive capabilities. The SINDy model successfully captures the behavior of specific thrust power (93.13% accuracy), air specific impulse (79.15% accuracy), thermal efficiency (98.97% accuracy), and overall efficiency (96.57% accuracy) with respect to Mach number. However, further investigation is required to create a data-based predictive model for TSFC. These results were obtained after training on 80% of the data and testing on the remaining 20%. By demonstrating the potential of SINDy in extracting interpretable models from synthetic data, this research contributes to advancing turbojet engine modeling. Future work will focus on enhancing the model’s predictive capabilities for all performance parameters and exploring the application of SINDy to real-world engine data.

Presenting Author: Antonio Ficarella Green Engine Lab, Dipartimento di Ingegneria dell'Innovazione, University of Salento

Presenting Author Biography: Ali AGHAZADEH ARDEBILI holds a Ph.D. in Engineering Risk Analysis from the University of Trieste and a 2nd Ph.D. at the UniSalento in Complex System's Engineering; he is currently working at the department of the Research and Development of HSPI SpA and collaborating with CRISR research center and Data Lab at University of Salento on cyber-Physical Systems Resilience through Digital Twining. His research field is Digital Twins, UAS/RPAS/AAM, Cyber-Physical-Social Systems, uncertainty analysis/assessment, engineering/project risks, Critical Infrastructures resilience, and Data-Oriented solutions. He has 4 patents, and 8 years of professional career experience in international engineering design/consultant companies. He speaks English, Italian, Persian, Azerbaijani, and Turkish. In 2018 he was selected among the 13 redefiners of the next 100 years in N100 Symposium out of 650 applicants from 55 countries; he was peace ambassador certified by the global peace chain from 2018 to 2020. In 2019 he won the TATA Steel challenge award for a sustainable solution for HYSARNA industrial steel production process.

Authors:

Ali Aghazadeh Ardebili HSPI SpA - Roma
Adem Khalil Istanbul Gelişim University
Sabri Khalil Istanbul Gelişim University
Elio Padoano University of Trieste
Antonio Ficarella Green Engine Lab, Dipartimento di Ingegneria dell'Innovazione, University of Salento