top of page
FH KAERNTEN - GEMEINNUETZIGE GmbH (CUS ).png

Partner

Beige Aesthetic Simple Elegant Photo iOS Icons (3).png

Patras, Greece

Beige Aesthetic Simple Elegant Photo iOS Icons (4).png

Scientist-in-Charge: Assoc. Prof. John Sakellariou

University of Patras (UPA)

Beige Aesthetic Simple Elegant Photo iOS Icons (5).png

Mechanical Engineering & Aeronautics/Design & Manufacturing/Stochastic Mechanical Systems & Automation

01

Brief Description

The University of Patras is the third largest University in Greece in terms of students, faculty members, administrative personnel, number of departments and degrees awarded. The University of Patras includes 35 Departments covering a wide range of disciplines. It also hosts 161 laboratories and 17 fully equipped clinics. Besides its distinguished path in education, the University of Patras excels in various fields of basic and applied research. A number of its academic Departments, laboratories and clinics have been recognized as centres of excellence on the basis of international assessment. The University of Patras has acquired a reputation for producing quality and innovative research and for taking part in a plethora of research projects, scientific organizations and research groups. Together with its educational and research work, the vibrant campus life of the University of Patras attracts many students every year as their first and foremost choice for Higher Education studies.
The Department of Mechanical Engineering & Aeronautics is one of the university’s flagship departments, specializing in areas such as mechanical engineering, aerospace engineering, structural dynamics, and materials science. The department is home to over 2,500 students and is widely known for its cutting-edge research in mechanical and aeronautical systems. It is recognized for its contributions to both fundamental research and applied technologies in industries such as aerospace, automotive, and renewable energy.
The Laboratory for Stochastic Mechanical Systems & Automation (SMSA Lab) has been a leader in the field for over 35 years, internationally recognized for its pioneering contributions to stochastic identification, dynamic analysis, and fault/damage diagnosis of mechanical and aeronautical systems. The lab is renowned for its work on advanced random vibration signal processing, statistical time series methods, and non-stationary signal modelling - key techniques used in Structural Health Monitoring (SHM) and Predictive Maintenance systems. SMSA Lab's research focuses on developing innovative solutions to diagnose and manage structural anomalies, particularly under uncertain conditions, such as material variability and fluctuating environmental factors. The lab's expertise extends to applying Machine Learning (ML) and data-driven approaches for the robust diagnosis and monitoring of complex mechanical systems, including smart composite structures used in aerospace and mechanical engineering. The lab provides state-of-the-art experimental and computational facilities that support its cutting-edge research in structural dynamics and vibration-based SHM. With strong industrial ties across Europe, the lab is involved in multiple European and national research projects (> 40). The SMSA Lab also plays a significant role in the organization of international conferences, thematic journal issues, and major technical encyclopedias. Additionally, the lab is deeply committed to education and training, offering specialized courses and workshops for students, researchers, and industry professionals at all levels.

02

Role in the ASSESS project

Host:

Doctoral Candidate 5 (Link to DC profile)

Research topic:

Work Package leader of WP3.
Research topic: ML vibration-based algorithms for damage diagnosis of smart FRP structures Scientific part in ASSESS: UPA will develop innovative AI/ML-based methods to enhance the Structural Health Monitoring (SHM) of smart fiber-reinforced polymer (FRP) structures. These methods will utilize random vibration signals captured by PZT (piezoelectric) sensors integrated into the smart FRPs developed in T1.1 in order to significantly enhance automation in damage detection and improve the sensitivity to early-stage damage, while maximizing robustness of the monitoring system under uncertainty and varying operating conditions. The AI/ML methods will achieve this with the use of a minimal number of sensors, ensuring cost-effectiveness and efficiency. Collaborating with leading institutions such as Polytechnic University of Bari (BARI), IWES (Fraunhofer Institute for Wind Energy and Energy System Technology), and TUD Dresden University of Technology (TUD), the research at UPA will focus on damage diagnosis in sandwich composite structures, aircraft wing CFRP structures, and wind turbine blades. Both OMMRs (Optimized Multiple Model Representations) and pooled model based novel methods will be developed to address current limitations in SHM. These innovative methods will aim to improve accuracy in detecting damage while simultaneously overcoming challenges associated with population-wide SHM, enabling effective health monitoring for a population of nominally identical structures.

03

Contacts

JOHN SAKELLARIOU

CO-SUPERVISOR

Assoc. Prof. John Sakellariou

Orange White Modern Gradient  IOS Icon.png

SPILIOS FASSOIS

SUPERVISOR

Professor & Lab Director at the University of Patras

Orange White Modern Gradient  IOS Icon (2).png
Orange White Modern Gradient  IOS Icon.png
bottom of page