Transformative Digital Air Vehicle with IoT Sensors for Safer Urban Skies

Project Information

AVATAR

Grant agreement ID: 101096073

DOI

10.3030/101096073

Project closed

EC signature date 30 November 2022

Start date 1 February 2023

End date 31 January 2026

Funded under

• Climate, Energy and Mobility

Total cost

€ 2 890 339,25

EU contribution

€ 2 890 339,25

Coordinated by

EVEKTOR SRO
Czechia

Periodic Reporting for period 2 - AVATAR (Transformative Digital Air Vehicle with IoT Sensors for Safer Urban Skies)

Reporting period: 2024-08-01 to 2026-01-31

Summary of the context and overall objectives of the project

AVATAR’s objective was to create a Digital Twin (DT) framework to continuously monitor the operation of transformative air vehicles (TAVs) through an innovative smart IoT sensing skin, informed by accurate physical models and advanced analytics. AVATAR’s DT framework builds on verified physical models for TAVs' design, enabling extended safe-life design and predictive maintenance under real operational conditions.

The 4 key objectives were successfully achieved at system integration level:

1. IoT Sensing Skin: Development and validation of a multifunctional, self-powered smart skin embedded with sensors (printed and conventional strain, acceleration, temperature) and low-power acquisition nodes to provide real-time structural health data.
2. Digital Twin Platform: Creation of a virtual counterpart combining inverse Finite Element modelling (iFEM), surrogate models, and probabilistic Remaining Useful Life (RUL) estimation to predict structural behavior and provide early warnings.
3. Advanced Analytics: Implementation of machine learning (ML), explainable AI (XAI), and load profiling techniques for fault detection, load reconstruction, and flight profile optimization.
4. Communication and Cloud Platform: Deployment of a secure multi-layer communication architecture (onboard acquisition, edge processing, BLE/RF transmission, AWS cloud storage) ensuring data integrity, security, and real-time processing.

The overall impacts of AVATAR include: i) reduced operational and maintenance costs through condition-based predictive maintenance, ii) improved structural safety for urban air mobility (UAM), and iii) providing data-driven insights to optimize air vehicle design for future generations.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

To reach the above 4 main objectives, AVATAR was structured around a building block approach, progressing from laboratory component testing to full system-level integration and flight campaigns.
The final achievements across each objective are summarized below against the reached technology readiness levels (TRL 4–5):

IoT Sensing Skin: Successfully developed, manufactured, and validated lightweight multifunctional sensing systems (printed strain gauges/thermistors alongside conventional accelerometers and PZT transducers) integrated into both metallic aircraft structures (SportStar RTC, Cobra VUT-100) and composite UAV components (ASTERO). The MCU-based Data Acquisition (DAQ) unit was embedded for onboard passive monitoring, while active SHM was validated via controlled ground-based acquisition. Self-powered energy harvesting concepts were successfully demonstrated in laboratory and wind-tunnel environments.

Digital Twin: Developed an end-to-end DT framework combining high-fidelity FE models with inverse methods (iFEM) for real-time load spectrum reconstruction. The framework processes operational flight data, updates structural integrity after each flight cycle, and visualizes real-time load history and RUL estimation via an interactive user-facing Digital Twin Dashboard. System functionality was validated across ~42 flight hours on SportStar RTC, 93 flight hours on Cobra VUT-100, and campaign flights on the ASTERO UAV.

Advanced Analytics: Created physics-informed hybrid surrogate models ("digital clones") and explainable AI algorithms for automated structural diagnosis and mission-based load clustering. Probabilistic RUL estimation models were fully integrated, replacing generic certification load spectra with mission-specific operational data to support condition-based maintenance decisions.

Communication and Cloud Platform: Deployed a complete communication architecture handling onboard acquisition, edge processing, wireless transmission (BLE/RF), and AWS cloud management. Edge processing included rainflow counting to reduce bandwidth. To resolve hardware transmission limits during high-frequency sampling, MCU data streams were downsampled to 50 Hz, ensuring continuous, reliable telemetry without disrupting Digital Twin operation.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The AVATAR IoT sensing skin provides a lightweight, energy-efficient, modular technology offering a flexible multi-sensing solution for health monitoring and predictive maintenance. Current industrial data acquisition systems are bulky, costly, and lack integration for multiple sensors like PZT, strain gauges, thermal sensors, and accelerometers. AVATAR bridges this gap with its novel flexible sensor system and tailored data acquisition solution, compatible with advanced cloud-based platforms like AWS for secure transmission, processing, and storage. Compliance with European data strategies positions AVATAR for industrialization as a potential new product.

Building on these advances, AVATAR's Digital Twin (DT) platform pushes predictive maintenance and structural health monitoring for air vehicles, providing key scientific and industrial contributions:

Flexible and Configurable Solution: Adaptable to different airframe structures, AVATAR supports varied sensor configurations for composite and metallic materials (demonstrated on SportStar RTC, Cobra VUT-100, and ASTERO UAV), enhancing versatility across general aviation and Urban Air Mobility (UAM).

Continuous Data-Driven Monitoring & Dynamic RUL: Transitioning from static, predefined design load spectra to continuous in-flight monitoring, AVATAR reconstructs real mission-specific load histories and updates Remaining Useful Life (RUL) dynamically. Combining high-fidelity physical simulations with explainable machine learning (XAI) delivers accurate, transparent structural health evaluations, significantly boosting flight safety, extending aircraft service life, and reducing operational downtime.

These contributions were fully validated through AVATAR's building block approach, progressing from laboratory and wind tunnel coupon tests to integrated flight campaigns across diverse manned and unmanned platform configurations.