Summary
- Profile Type
- Research & Development Request
- POD Reference
- RDRTR20250408010
- Term of Validity
- 8 April 2025 - 8 April 2026
- Company's Country
- Türkiye
- Type of partnership
- Research and development cooperation agreement
- Targeted Countries
- Croatia
- Brazil
- Canada
- Czechia
- Denmark
- Italy
- Belgium
- France
- Bulgaria
- Estonia
- Latvia
- Hungary
- Finland
- Austria
- Lithuania
- Germany
- Luxembourg
- Spain
- Poland
- Norway
- Malta
- Sweden
- Switzerland
- Slovenia
- Slovakia
- Taiwan
- South Africa
- South Korea
- Greece
Contact the EEN partner nearest to you for more information.
Find my local partner
General information
- Short Summary
- The project aims to revolutionize the manufacturing of high-performance composite materials used in the aerospace industry by optimizing the press curing process of prepreg systems through advanced digital technologies. The project will develop a data-driven, AI-enhanced digital twin platform to simulate, monitor, and optimize key curing parameters (temperature, pressure, time, and material composition), resulting in sustainable, efficient, and intelligent production systems.
- Full Description
-
The aerospace industry increasingly relies on advanced composite materials due to their excellent strength-to-weight ratio, thermal performance, and fatigue resistance. Among these, prepreg-based composites are widely used for structural applications. However, the press curing process—a critical stage in the production of composite parts—remains highly energy-intensive, time-consuming, and prone to variability. Current methods rely heavily on trial-and-error, with long lead times and high scrap rates, especially when introducing new material systems or adapting to different curing profiles.
The project addresses these challenges through the development of a data-driven, AI-enhanced smart manufacturing framework that optimizes the curing process of epoxy and phenolic-based prepreg composites reinforced with carbon or glass fibers. By combining experimental validation, advanced process monitoring, and digital twin technology, the project aims to design and implement optimal curing protocols that yield high-performance composite parts with significantly reduced energy consumption, improved reliability, and minimized environmental impact.
The project follows a structured methodology beginning with the collection and analysis of baseline curing data across different prepreg systems. These datasets will inform a series of controlled experimental trials, where variations in temperature, pressure, cure time, and heating/cooling rates will be systematically studied. IoT sensors embedded in the curing setup will monitor real-time parameters such as temperature distribution, pressure dynamics, viscosity evolution, and moisture levels.
The collected data will feed into the development of a digital twin model of the curing process. This model will integrate finite element analysis (FEA) and machine learning algorithms to simulate material behavior and optimize process parameters. By applying artificial intelligence, the system will continuously learn from process outputs to enhance predictive accuracy and process control. This framework enables real-time feedback loops and adaptive process optimization, leading to reduced curing times, lower rejection rates, and improved material performance.
In the final phase, the optimized curing strategies and digital twin will be validated in an industrial setting through pilot production of aerospace-grade components. Key performance metrics—including mechanical strength, thermal resistance, fatigue life, and flame retardancy—will be tested to ensure compliance with industry standards and certification requirements. - Advantages and Innovations
-
The project introduces a transformative approach to aerospace composite manufacturing by integrating data-driven optimization, AI-enhanced modeling, and digital twin technology into the prepreg press curing process. Unlike conventional trial-and-error-based methods, this project leverages real-time data acquisition, machine learning, and advanced simulation to create a smart, adaptive, and energy-efficient production system.
The key innovation lies in the development of a real-time digital twin, capable of simulating and predicting material behavior during the entire curing cycle. This digital replica, fed by sensor data (temperature, pressure, viscosity, moisture), enables live feedback control and automated adjustment of process parameters. Coupled with AI, the system learns from experimental results to continuously refine process efficiency and accuracy.
Another major advantage is the holistic integration of process monitoring, simulation, and optimization, which allows the use of new and diverse prepreg systems with minimal calibration time. This reduces production ramp-up for novel aerospace components and minimizes waste caused by suboptimal parameter settings.
The project also contributes to sustainability through significant energy savings (up to 30%) and reduced material waste, aligning with EU Green Deal targets. It advances the state-of-the-art by enabling a shift from static to intelligent, predictive, and closed-loop composite manufacturing, which is not yet commercially available at this scale.
The resulting framework supports zero-defect manufacturing, rapid material introduction, and cost-efficient production, positioning European industries at the forefront of digital and sustainable composite processing. - Technical Specification or Expertise Sought
-
The consortium is seeking industrial and research partners with complementary expertise to strengthen the implementation and validation of the project. In particular, we welcome collaboration with:
Aerospace Component Manufacturers or Tier-1 Suppliers
– Expertise in composite part manufacturing, structural part design, or aerospace-grade certification processes.
– Capability to conduct pilot trials and support validation of optimized press cure processes.
Digital Twin and Simulation Experts
– Proven experience in developing physics-based and AI-enhanced digital twin models for manufacturing processes.
– Knowledge of rheological, thermal, and chemical modeling for polymer composites.
Sensor and IoT Technology Providers
– Development or integration of smart sensors (temperature, pressure, viscosity, moisture) for in-situ process monitoring.
– Experience in data acquisition systems and industrial connectivity.
AI and Machine Learning Specialists
– Ability to develop predictive algorithms and data-driven models based on experimental and process data.
– Experience with hybrid modeling (combining data-driven and physics-based approaches).
Sustainability and LCA Analysts
– Expertise in assessing environmental impact, particularly energy consumption and material waste in composite manufacturing.
– Capability to support eco-design and circular economy assessments aligned with EU climate goals. - Stage of Development
- Under development
- Sustainable Development Goals
- Goal 9: Industry, Innovation and Infrastructure
- IPR status
- No IPR applied
Partner Sought
- Expected Role of a Partner
- Industrial Aerospace Manufacturers / Tier-1 Suppliers Provide access to real-world production environments for pilot-scale demonstration. Support testing and certification of optimized composite components. Contribute practical constraints, performance requirements, and user feedback. Digital Twin Developers and Simulation Experts Lead the development of multiphysics simulation models for curing kinetics, heat transfer, and resin flow. Integrate digital twins with sensor data for real-time process simulation. Collaborate on model validation using experimental results. Sensor Technology and IoT Providers Supply and integrate smart sensors into press curing setups. Enable live data acquisition and transmission from temperature, pressure, viscosity, and humidity sensors. Ensure compatibility with industrial standards and real-time systems. AI and Data Analytics Specialists Develop machine learning algorithms for process optimization and fault prediction. Support the creation of a feedback loop between digital twin predictions and real-time process data. Train and validate AI models using historical and experimental datasets. Sustainability Experts / LCA Practitioners Perform life cycle analysis (LCA) to evaluate environmental and energy benefits. Quantify the impact of optimized processes in terms of CO₂ savings, waste reduction, and energy efficiency. Provide guidelines for sustainable scale-up and eco-design.
- Type and Size of Partner
- R&D Institution
- SME 11-49
- SME <=10
- Other
- University
- Big company
- SME 50 - 249
- Type of partnership
- Research and development cooperation agreement
Call details
- Framework program
- Eureka
- Call title and identifier
-
M-ERANET 2025
- Coordinator required
-
No
- Deadline for EoI
- Deadline of the call
- Eureka
Dissemination
- Technology keywords
- 02007005 - Composite materials
- Market keywords
- 08005 - Other Industrial Products (not elsewhere classified)
- Sector Groups Involved
- Energy-Intensive Industries - Materials
- Targeted countries
- Croatia
- Brazil
- Canada
- Czechia
- Denmark
- Italy
- Belgium
- France
- Bulgaria
- Estonia
- Latvia
- Hungary
- Finland
- Austria
- Lithuania
- Germany
- Luxembourg
- Spain
- Poland
- Norway
- Malta
- Sweden
- Switzerland
- Slovenia
- Slovakia
- Taiwan
- South Africa
- South Korea
- Greece