Periodic Reporting for period 2 - ENHAnCE (European training Network in intelligent prognostics and Health mAnagement in Composite structurEs)
Período documentado: 2022-01-01 hasta 2024-06-30
The ENHAnCE project aims to revolutionize the health management of composite structures by training the next generation of scientists to integrate advanced sensing technologies and prognostics engineering into structural systems. This initiative seeks to transform traditional composite structures into intelligent cyber-physical systems.
ENHAnCE focuses on converting composite structures from purely physical entities into cyber-physical systems through the integration of health monitoring data into onboard expert systems. These systems, equipped with diagnostic and prognostic capabilities, are developed from the design stage to full technology deployment, ensuring effective knowledge transfer to industry and practitioners. The project aims to extend the lifetime and optimize the serviceability of composite structures, significantly reducing maintenance costs. This transformation is expected to have a substantial economic and societal impact, particularly in aeronautics and wind energy industries where maintenance is critical for competitiveness and sustainability.
The project has several key objectives. It aims to develop innovative embedded sensors capable of real-time damage identification and integrate them within composite plates. Additionally, it seeks to formulate novel mathematical and simulation tools to analyze the interaction of sensor signals with damage in composites. Another goal is to create real-time, self-adaptive prognostics algorithms using integrated sensor data. Lastly, ENHAnCE aims to develop a cyber-physical structural information system based on the Plausible Petri Net (PPN) paradigm.
The project has made significant progress in several areas. Firstly, it has developed minimally invasive SHM sensors capable of real-time damage identification. These sensors can withstand high stress levels similar to those in aeronautics and wind applications. A method was also created to extract electronic signals from ultrasound sensors through carbon nanotube non-invasive wires, reducing traditional cabling issues. Additionally, an ultrasonic welding method for embedding these sensors was developed.
In conclusion, the ENHAnCE project has significantly advanced the sustainability and competitiveness of composite materials. The research and technologies developed have crucial applications in aeronautics, wind turbines, and other automotive sectors. The project's findings, published in top scientific journals, highlight the potential of integrating advanced sensing and prognostics technologies to enhance the maintenance and longevity of composite structures. This initiative has laid the groundwork for future innovations in the field, emphasizing the importance of integrating health management systems into composite structures to achieve optimal performance and cost-efficiency.
ENHAnCE focuses on converting composite structures from purely physical entities into cyber-physical systems through the integration of health monitoring data into onboard expert systems. These systems, equipped with diagnostic and prognostic capabilities, are developed from the design stage to full technology deployment, ensuring effective knowledge transfer to industry and practitioners. The project aims to extend the lifetime and optimize the serviceability of composite structures, significantly reducing maintenance costs. This transformation is expected to have a substantial economic and societal impact, particularly in aeronautics and wind energy industries where maintenance is critical for competitiveness and sustainability.
The project has several key objectives. It aims to develop innovative embedded sensors capable of real-time damage identification and integrate them within composite plates. Additionally, it seeks to formulate novel mathematical and simulation tools to analyze the interaction of sensor signals with damage in composites. Another goal is to create real-time, self-adaptive prognostics algorithms using integrated sensor data. Lastly, ENHAnCE aims to develop a cyber-physical structural information system based on the Plausible Petri Net (PPN) paradigm.
The project has made significant progress in several areas. Firstly, it has developed minimally invasive SHM sensors capable of real-time damage identification. These sensors can withstand high stress levels similar to those in aeronautics and wind applications. A method was also created to extract electronic signals from ultrasound sensors through carbon nanotube non-invasive wires, reducing traditional cabling issues. Additionally, an ultrasonic welding method for embedding these sensors was developed.
In conclusion, the ENHAnCE project has significantly advanced the sustainability and competitiveness of composite materials. The research and technologies developed have crucial applications in aeronautics, wind turbines, and other automotive sectors. The project's findings, published in top scientific journals, highlight the potential of integrating advanced sensing and prognostics technologies to enhance the maintenance and longevity of composite structures. This initiative has laid the groundwork for future innovations in the field, emphasizing the importance of integrating health management systems into composite structures to achieve optimal performance and cost-efficiency.
From a generic perspective, the project has progressed accordingly to the plan irrespective of the circumstances of the COVID pandemic, which precisely began in the project's M3, just few months after the start of the action. This situation made us adapt a number of management and working methodologies (meetings, some training events, etc.), but with no loss of any objective, milestones, training, nor research activities of the project.
As an overview, since the beginning of the project (M1) until the end, 39 out of 39 deliverables have been submitted, 12 out of 12 milestones achieved, and 11 out of 11 training weeks completed (some of them adapted via on-line or hybrid format depending on COVID restrictions).
From a technical & research perspective, the work performed from M1 to the end can be schematically described as per a number of scientific publications apart from the technical deliverables, most of them available for the public, and the conference papers. These papers, 27 as per M54, have been published in top and recognised scientific journals, being an internal quality standard established by the Supervisory Board. The research works are accessible from the project website: https://h2020-enhanceitn.eu/publications/articles/(se abrirá en una nueva ventana)
The dissemination media of these journal have been through top and well-recognised scientific journals like Reliability Engineering & Systems Safety, Automation in Construction, Mechanical Systems & Signal Processing, Journal of Composite Materials, Engineering Applications of Artificial Intelligence, etc. All the results of the project are Open Access available through Gold Open Access credits, or by repository-based open access, hence the project findings can be achievable by any interested user, scientific, practitioner, or by the society in general. Regarding exploitation of the results, the project, through its beneficiaries and partners will find the ways to move further the methods and algorithms developed towards the Digital Twin technology. Current steps have been done with the creation of new European research and innovation consortia like the BuildChain consortium (HORIZON-CL4-2022-TWIN-TRANSITION-01-09, https://buildchain-project.eu(se abrirá en una nueva ventana)) and the recently awarded project Intelliwind (HORIZON-MSCA-2023-DN-01-01, Ref.101168725) both of them with a more applied oriented focus. Additionally, it is worth mentioning that some of the ENHAnCE ERSs have funded a Spin-Off company named QuantIA, focused on predictive maintenance of critical infrastructures (https://quantia.me(se abrirá en una nueva ventana)). Hence, the exploitation pathways have just started towards a global objective of making impact using the results and the training obtained through the project.
As an overview, since the beginning of the project (M1) until the end, 39 out of 39 deliverables have been submitted, 12 out of 12 milestones achieved, and 11 out of 11 training weeks completed (some of them adapted via on-line or hybrid format depending on COVID restrictions).
From a technical & research perspective, the work performed from M1 to the end can be schematically described as per a number of scientific publications apart from the technical deliverables, most of them available for the public, and the conference papers. These papers, 27 as per M54, have been published in top and recognised scientific journals, being an internal quality standard established by the Supervisory Board. The research works are accessible from the project website: https://h2020-enhanceitn.eu/publications/articles/(se abrirá en una nueva ventana)
The dissemination media of these journal have been through top and well-recognised scientific journals like Reliability Engineering & Systems Safety, Automation in Construction, Mechanical Systems & Signal Processing, Journal of Composite Materials, Engineering Applications of Artificial Intelligence, etc. All the results of the project are Open Access available through Gold Open Access credits, or by repository-based open access, hence the project findings can be achievable by any interested user, scientific, practitioner, or by the society in general. Regarding exploitation of the results, the project, through its beneficiaries and partners will find the ways to move further the methods and algorithms developed towards the Digital Twin technology. Current steps have been done with the creation of new European research and innovation consortia like the BuildChain consortium (HORIZON-CL4-2022-TWIN-TRANSITION-01-09, https://buildchain-project.eu(se abrirá en una nueva ventana)) and the recently awarded project Intelliwind (HORIZON-MSCA-2023-DN-01-01, Ref.101168725) both of them with a more applied oriented focus. Additionally, it is worth mentioning that some of the ENHAnCE ERSs have funded a Spin-Off company named QuantIA, focused on predictive maintenance of critical infrastructures (https://quantia.me(se abrirá en una nueva ventana)). Hence, the exploitation pathways have just started towards a global objective of making impact using the results and the training obtained through the project.
The outputs produced during the project, which have been summarised next, are keystones for scientific research beyond the state of the art. After ENHAnCE, the following items can be considered as a progress done beyond the state of the art:
-New manufacturing method for efficiently embed piezoelectric sensors within a thermoplastic composite laminate, along with its numerical and mechanical verification.
-Novel semi-analytical method for lamb-wave propagation and its interaction with non-linear damage, with the ability to be implemented within micro-processor for its high computational efficiency. The method has applications to composite materials and beyond;
-New step-ahead filtering-based prediction algorithm for highly multidimensional spaces, with key applications in engineering fields where the states are highly-dimensional.
-Novel intelligent prediction algorithms with effective quantification of the uncertainty and with a novel non-gradient-based training method, with improved predictive capabilities through physics-based enrichment of the Artificial Intelligence;
-Novel intelligent self-adaptive management models to autonomously find the optimal maintenance policy of complex;
The potential impacts expected after ENHAnCE are envisioned as follows (both, from a training and research perspective):
-Enhancement of the career perspectives and employability of 10 researchers and contribution to their interdisciplinary training, skills development, and internationalisation.
-Contribution to structuring doctoral/early-stage research training at the European level and to strengthening European innovation capacity within the Digital Twin sector, one of the key technologies nowadays.
-Increase the competitiveness of the EU composite industry and make it converge towards the Industry 4.0 paradigm.
-New manufacturing method for efficiently embed piezoelectric sensors within a thermoplastic composite laminate, along with its numerical and mechanical verification.
-Novel semi-analytical method for lamb-wave propagation and its interaction with non-linear damage, with the ability to be implemented within micro-processor for its high computational efficiency. The method has applications to composite materials and beyond;
-New step-ahead filtering-based prediction algorithm for highly multidimensional spaces, with key applications in engineering fields where the states are highly-dimensional.
-Novel intelligent prediction algorithms with effective quantification of the uncertainty and with a novel non-gradient-based training method, with improved predictive capabilities through physics-based enrichment of the Artificial Intelligence;
-Novel intelligent self-adaptive management models to autonomously find the optimal maintenance policy of complex;
The potential impacts expected after ENHAnCE are envisioned as follows (both, from a training and research perspective):
-Enhancement of the career perspectives and employability of 10 researchers and contribution to their interdisciplinary training, skills development, and internationalisation.
-Contribution to structuring doctoral/early-stage research training at the European level and to strengthening European innovation capacity within the Digital Twin sector, one of the key technologies nowadays.
-Increase the competitiveness of the EU composite industry and make it converge towards the Industry 4.0 paradigm.