Digital Twins for Condition and Fleet Monitoring of Aircraft: Toward More-Intelligent Electrified Aviation Systems

Alireza Sadeghi, Paolo Bellavista, Wenjuan Song, Mohammad Yazdani-AsramiIEEE Access 2024 · OpenReview

Abstract

The fourth industrial revolution has catalyzed the convergence of Information Technology (IT) and Operational Technology (OT), giving rise to the Digital Twin (DT)—a virtual representation that synchronizes with physical systems via real-time data. In aviation, DTs are revolutionizing design, manufacturing, and condition monitoring. This paper reviews the shift from reactive to predictive maintenance, highlighting how DTs enhance reliability and safety while reducing operational costs. By analyzing current developments in physics-based and data-driven modeling, we explore the remaining challenges and future trends, including the integration of DTs into electrified and hydrogen-powered aviation.

Introduction: The Need for Predictive Aviation

Despite significant technological advancements, the aviation industry continues to face between 1,500 and 1,900 incidents annually. Mechanical failures remain a primary concern, contributing to approximately 23% of crashes. Traditional Condition and Fleet Monitoring Methods (CFMM) are largely reactive, manual, and time-intensive, often failing to address issues before they become critical.

The industry requires a fundamental transition toward predictive and prescriptive monitoring. Digital Twins provide the necessary framework to manage the "Big Data" generated by modern aircraft—characterized by high volume, velocity, variety, and veracity—enabling real-time, safety-critical decision-making.

The evolution of Digital Twin technology across three distinct stages, from initial concept to multi-field application.

Methodologies in Digital Twin Modeling

Digital Twin implementations generally fall into two categories, with a growing trend toward hybrid approaches:

  1. Conventional (Physics-Based) Modeling: Often called "White Box" models, these utilize engineering methods like Finite Element Method (FEM) for structural integrity and Computational Fluid Dynamics (CFD) for engine performance. While highly accurate, their computational intensity often precludes real-time application.
  2. Data-Driven (AI-Based) Modeling: These "Black Box" models leverage Machine Learning (ML), Deep Learning (DL), and Bayesian Networks. They offer the speed required for real-time monitoring but are dependent on the quality of historical training data.
  3. Hybrid (Grey Box) Modeling: By combining physical logic with AI speed, hybrid models achieve high-fidelity, real-time monitoring. This is supported by the "Digital Thread" (DTH), a data-driven backbone ensuring information flow throughout the aircraft's lifecycle.

Key Insights: Beyond the Digital Shadow

A critical distinction in this field is between a "Digital Shadow" and a "Digital Twin." While a shadow only receives data from a physical object, a true Digital Twin features bidirectional communication, allowing the virtual model to send commands back to the aircraft to optimize operations or avoid failures.

To support this, the "Cloud Continuum" is essential. Real-time DTs cannot rely solely on centralized clouds; they require Edge Computing and 5G/6G connectivity to process data locally with sub-millisecond latency. Furthermore, DTs are hierarchical: unit-level twins (e.g., for a single turbine blade) feed into system-level twins (the engine), which in turn inform fleet-level management.

Google search trends illustrate the significant resurgence and current peak in global interest regarding Digital Twin technology.

Results and Impact

The adoption of DT technology has already yielded significant quantitative benefits:

  • Manufacturing: Boeing’s T-7A Red Hawk, designed using DTs, saw a 75% increase in initial quality and an 80% reduction in assembly time.
  • Predictive Accuracy: Long Short-Term Memory (LSTM) networks have achieved a Root Mean Square Error (RMSE) of 13.12 for maintenance prediction, outperforming standard neural networks.
  • Fault Detection: DT-based engine diagnosis systems have reached accuracy rates as high as 98.2%.
  • Sustainability: Implementing DTs in the Airbus A321XLR is estimated to reduce fuel burn by 30%.

Challenges and Future Horizons

Full deployment of DTs faces several "bottlenecks." Sensor vulnerability in extreme environments can lead to data corruption, potentially causing catastrophic virtual-to-physical errors. Data security is another major concern, with Private Blockchains proposed to secure the Digital Thread against cyber-attacks.

Future research is focused on Explainable AI (XAI), ensuring pilots and engineers can trust and understand DT recommendations. Additionally, Generative AI (GAI) may soon be used to autonomously generate optimal maintenance schedules and flight paths. Finally, in the realm of electrified aviation, DTs will be vital for managing the complex thermal-electrical balance of liquid hydrogen (LH2) systems, which serve as both fuel and cryogenic coolant.

Summary updated

Abstract

The convergence of Information Technology (IT), Operational Technology (OT), and Educational Technology (ET) has led to the emergence of the fourth industrial revolution. As a result, a new concept has emerged known as Digital Twins (DT), which is defined as “a virtual representation of various objects or systems that receive data from physical objects/systems to make changes and corrections”. In the aviation industry, numerous attempts have been made to utilize DT in the design, manufacturing, and condition monitoring of aircraft fleets. Among these research efforts, real-time, accurate, fast, and predictive condition monitoring methods play a crucial role in ensuring the safe and efficient performance of aircraft. Using DT for condition and fleet monitoring not only enhances the reliability and safety of aircraft but also reduces operational and maintenance costs. In this paper, the conducted studies on the applications of DT systems for condition monitoring of aircraft units and the aerospace sector are discussed and reviewed. The aim of this review paper is to analyse the current developments of DT systems in the aviation industry as well as explain the remaining challenges of DT systems. Then Finally, future trends of DT systems along with aircraft are presented. Among reviewed papers, most of them have used computational fluid dynamics, finite element methods, and artificial intelligence techniques for developing DT models for aircraft. At the same time, most of these analyses are dedicated to the failure and crack detection body of aircraft as well as engine fault detection. Life prediction is another popular application for using DT in aircraft units that could help the engineers predict the maintenance required for different parts of the aircraft. Finally, the application of DT in marine, power systems, and space programs has been also reviewed and the lessons learned from them have been translated to the aviation sector.
BibTeX
@inproceedings{sadeghi2024digital,
  author = {Alireza Sadeghi and Paolo Bellavista and Wenjuan Song and Mohammad Yazdani-Asrami},
  title = {{Digital Twins for Condition and Fleet Monitoring of Aircraft: Toward More-Intelligent Electrified Aviation Systems}},
  booktitle = {IEEE Access},
  year = {2024},
  url = {https://openreview.net/forum?id=UdiwIK28Qw},
}
Figure