The Doctoral Network on Prognostics and heAlth management of nexT GeneRatiOn drivetraiNs

Project Information

PATRON

Grant agreement ID: 101120172

DOI

10.3030/101120172

EC signature date 14 July 2023

Start date 1 February 2024

End date 31 January 2028

Funded under

• Marie Skłodowska-Curie Actions (MSCA)

Total cost

No data

EU contribution

€ 2 659 982,40

Coordinated by

KATHOLIEKE UNIVERSITEIT LEUVEN
Belgium

Periodic Reporting for period 1 - PATRON (The Doctoral Network on Prognostics and heAlth management of nexT GeneRatiOn drivetraiNs)

Reporting period: 2024-02-01 to 2026-01-31

Summary of the context and overall objectives of the project

Europe’s industrial sector creates fantastically complex machines that rely on the synergy of multiple disciplines, such as mechanics, materials science, electronics, mathematics, and computer science. Moreover, the arrival of new technologies as part of Industry 4.0/5.0 Aviation 4.0/5.0 and Agriculture 4.0/5.0 lead to the new generation of drivetrains. PATRON will promote cooperation between top European universities, research institutes, OEMs and industrial stakeholders with an expertise in mechanical engineering, tribology, signal processing, computer science, vibrations, operations & maintenance and data analytics. PATRON will train the new generation of European expert engineers and scientists in the field of Prognostics and Health Management (PHM) for online, on-time, accurate monitoring/fault detection/diagnosis/prognosis for next generation drivetrains for better safety, minimal environmental impact, as well as production and energy efficiency.
PATRON will pave the way for Prognostics and Health Management of the new generation of drivetrains, answering to the hot European industrial needs, by developing ground-breaking monitoring approaches, bridging Signal Processing, Physical Modelling, Artificial Intelligence and Tribology.
Research objectives: The objective of the PATRON project is to develop the next generation of PHM methodologies, algorithms and technologies, so enabling condition monitoring, with the focus on real-time diagnostics and prognostics. This objective will be achieved by having 10 Doctoral Candidates (DCs) working closely and interacting frequently in this inter-disciplinary and multi-disciplinary area. The following sub-objectives have been drawn up to ensure that the objective of PATRON is achieved:
• Novel physics inspired machine learning techniques for condition monitoring of planetary gearboxes
• Novel monitoring indicators linking vibrations with surface topology
• Novel sensing and data analysis techniques based on cameras and fiber optics
• New lubrication quality parameters for monitoring of elastohydrodynamically lubricated contacts
• New boundary layer interface for reduced friction and wear
• New gear contact models including gear cracks and surface pitting propagation
• Novel data driven methodologies for diagnostics and prognostics of planetary gearboxes
• New data driven model for the estimation of the remaining useful life of rotating machinery
• Validation of new prognostics and health management methodologies and technologies for the aerospace, agriculture and general industrial sectors
The above-mentioned objectives will be met through the following activities of the PATRON project:
Bundling knowledge and research activities in the inter/multidisciplinary fields within PHM involved in the various aspects of condition monitoring and maintenance of drivetrains.
Preparing new researchers for challenges ahead in smarter and safer air and land vehicle transport by equipping them with the skills necessary to compete for high-profile positions in industry.
Exposing DCs to the world of engineering in Europe, providing them with the necessary industrial anchoring.
Providing a stimulating and balanced training program to the DCs that includes not just science and engineering, but the important transferrable skills they will need throughout their careers.
Stimulating interactions to match industrial needs with academic research capacity in an exciting training programme for DCs.
Motivating the DCs through research & training that is simply not available to them anywhere else in the world
Promoting the transfer of knowledge between the project’s participants and to disseminate, communicate and exploit the research outputs to the fullest extent.

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

PATRON is organised in 2 research WPs: WP1: Physics-based & Hybrid Modelling and WP2: Automatic Feature Learning & Decision Making. WP3 focuses in training while WP4 focused on the communication, dissemination and exploitation of the MOIRA results. WP5 takes care of the management running smoothly and via GA meetings and SB meetings, organized twice a year, the project is followed-up closely.
The Individual training programs are adjusted to the needs of the DCs, while all foreseen network wide training courses are taking place.
WP1 focuses in Physics-based & Hybrid Modelling. The main achievements till now are:
• the development of a novel physics inspired machine learning techniques for condition monitoring of (planetary) gearboxes
• the proposal of a new lubrication quality parameters for monitoring of elastohydrodynamically lubricated contacts
• the investigation of a new boundary layer interface for reduced friction and wear
• the development of a new data driven methodology for diagnostics and prognostics of (planetary) gearboxes
• the development of an indicator for severity quantification of defects in drivetrains.

WP2 focuses in Automatic Feature Learning & Decision Making
• the development of compression methods and irregular sampling techniques for vibration signals,
• the integration of explainability into autoencoders for fault detection in planetary gearboxes.

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)

PATRON brings together academic and industrial expertise in the fields of experimental and numerical Tribology, Signal Processing, Condition Monitoring, Fault Detection, Diagnosis and Prognosis, System Modelling and Machine Learning, which are all important components in the world of Prognostics and Health Management of new generation drivetrains, involving representatives from various industry stakeholder groups and research organizations, including a leading international high-technology supplier of systems and equipment for aerospace (SAFRAN group), a test & simulation solution provider (SISW), a global leader in agricultural and construction equipment, trucks, commercial vehicles, buses and specialty vehicles (CNHI) and a global leader in gearmotors, drive systems, planetary gearboxes and inverters for the industrial automation, mobile machinery and renewable energy sector (Bonfiglioli), a research centre (IKERLAN) and top level universities (KU Leuven, INSA, LTU, UNIFE, MGEP, UJM). The knowledge and complementary expertise of the Beneficiaries in multiple disciplines, such as mechanical, aerospace, agriculture, tribology, signal processing, machine learning, big data, testing and simulation, from fundamentals and concept solutions to real industry applications form an excellent basis for the project.
The DCs with the support of their supervisors propose novel data driven methodologies for diagnostics and prognostics of gearboxes as well as new boundary layer interfaces for reduced friction and wear and new lubrication quality parameters for monitoring of elastohydrodynamically lubricated contacts. The 10 Doctoral Candidates are now on board, work on the various tasks of the proposal and started presenting the outcome of the research to conferences such as teh upcome ISMA 2026 and PHME 2026.