Short Course | Structural Health Monitoring | South Korea

A 12-hour blended short course introducing Structural Health Monitoring (SHM) within the framework of the Statistical Pattern Recognition (SPR) paradigm, providing participants with the fundamental concepts and methodologies to support damage identification and risk-informed integrity management. The course is organized in conjunction with the IABSE Congress 2026, to be held in Incheon, South Korea, from 16–18 September 2026. This edition features invited speakers from around the world who will present the latest developments and practical applications of SHM across the five continents, highlighting ongoing efforts to accelerate the transition of SHM from research to engineering practice. Registration is open only until 31 July 2026 on the IABSE Website. 

The remote part introduces the concept of SHM and accelerates the learning process, while the in-person part focuses on bridging the gap between research and practical application. The techniques are shown with hands-on experiences applied to bridges. Unsupervised learning techniques as Gaussian mixture Models; supervised learning algorithms like artificial neural networks or support vector machines; and transfer learning methods as the transfer component analysis are all covered. The role of SHM to support the climate change adaptation of bridges is also discussed. 

Target public: The course is tailored towards graduate students and/or practicing engineers working full-time in public and private institutions, like authorities and contractors.

Keywords: SHM, bridges, structural mechanical modeling, pattern recognition, machine learning, system identification, damage identification, uncertainty, probability, probabilistic digital twins, risk, resilience, sustainability.

Accreditation: This short course has been accredited by Ordem dos Engenheiros - the Portuguese regulatory and licensing body for the engineering profession in Portugal.

Sustainable Development Goals: This course contributes to the Sustainable Development Goals (SDGs) 7, 9, and 13, by promoting sustainable and resilient infrastructure through the introduction of new technologies and innovation to guarantee the safety and comfort of people, through optimization of design and integrity management to reduce embedded CO2 and thereby countering climate change, and finally by along the same lines facilitating the development and operation of sustainable energy infrastructure, like wide turbines and dams.

CREDITS

A Certificate of Attendance will be issued at the end of the short course for all participants. However, a special track is available for those who wish to obtain a Transcript of Records with 2 ECTS, provided they submit the homework.

REGISTRATION

The registration is open only until 31 July 2026 on the IABSE website. If you have any questions, we suggest you send an email to Este endereço de email está protegido contra piratas. Necessita ter o JavaScript autorizado para o visualizar..

SPECIFIC OBJECTIVES

• Pose the SHM in the context of a statistical pattern recognition paradigm.
• Understand the differences between quasi-static and dynamic monitoring.
• Overview of sensors and DAQ hardware for designing an optimum instrumentation scheme for SHM.
• Understand the applicability of finite element modeling and machine learning (unsupervised and supervised learning) for data enhancement and interpretation, as well as for damage identification.
• Understand the role of SHM to support climate change adaptation.
• Pose the concept of probabilistic digital twins in the context of SHM.
• Understand the role of SHM to support risk-informed integrity management.
• Understand the goal of SHM with current limitations, grand challenges, and future trends.

HIGHLIGHTS

After successful completion of this course, students will be capable to:

• Describe the historical and current real-world applications of damage identification in the civil engineering field, especially in bridges;
• Conduct damage identification using vibration-based SHM;
• Analyze and understand the condition of data sets of monitoring results;
• Employ machine learning algorithms for system and damage identification;
• Develop an integrated application of machine learning and probabilistic digital twin in the context of SHM;
• Evaluating critically the results of system and damage identification for quality control;
• Understand and apply commercial software for system and damage identification analysis.

REASONS TO ATTEND THIS COURSE

1. Gain a strong foundation in SHM theory and practice
2. Learn skills directly relevant to infrastructure safety and resilience
3. Professional accreditation and broad applicability

PROFESSIONAL OPPORTUNITIES

1. Infrastructure Monitoring Engineer / Consultant
2. Asset Management and Resilience Specialist
3. Research and Innovation Roles (R&D / Digital Engineering)

DURATION, LOCATION, DATE, AND TIME

• Duration: 12 hours
• Remote component (6h) - The link will be provided one day before each session. 
• In-person component (6h):
  • Location: Songdo ConvensiA, Incheon, South Korea
  • Date: September 15, 2026
  • Time: 9:00 to 16:00 (one hour for lunch)

COURSE SYLLABUS

OBSERVATIONS

• The instructors reserve the right to modify the course organization as necessary to maintain the highest standards of content quality.
• Course notes will be distributed during the course.
• A Certificate of Attendance will be issued at the end of the short course.
• A Transcript of Records will be issued at the end of the course for those who deliver the homework.
• If you have any questions, please send us an email: Este endereço de email está protegido contra piratas. Necessita ter o JavaScript autorizado para o visualizar.
• Last update: July 13, 2026.