Introduction

This course introduces the innovative theme of probabilistic analysis in the design and evaluation of reinforced concrete structures, enhanced by advancements in Artificial Intelligence (AI). As the construction industry increasingly seeks to address uncertainties in material behaviour, loading conditions, and environmental influences, integrating probabilistic methods with AI presents new opportunities to improve the reliability and efficiency of structural engineering practices.

Objetives

The primary objective of this course is to familiarize students with the principles of probabilistic analysis and its applications in reinforced concrete structures, while exploring how AI can augment these methods to provide deeper insights and more accurate predictions.

By the end of the course, participants will:

• Understand the basic principles of probabilistic analysis and how they apply to reinforced concrete
• Recognize the role of uncertainty in structural engineering and the significance of integrating probabilistic methods for reinforced concrete
• Gain exposure to AI techniques and their applications in enhancing probabilistic analysis for improved decision-making.
• Develop skills to implement AI-supported probabilistic models in practical structural engineering scenarios related to reinforced concrete

Limited places.

1. Fundamentals of Probabilistic Analysis

• – Overview of deterministic vs. probabilistic approaches in structural engineering.
• – Introduction to basic concepts such as random variables, distributions, and stochastic processes.
• – Understanding how uncertainty affects structural performance and safety assessments

2.  Reinforced Concrete Behaviour Under Uncertainty

• – Discussion on the inherent variability in material properties, loading conditions, and environmental factors.
• – Techniques for modelling uncertainty in reinforced concrete structures, including load and resistance factor design principles.

3.  Statistical and Reliability Analysis

• – Methods for conducting reliability assessments of reinforced concrete structures.
• -Introduction to failure probability calculations and the importance of safety factors.

4.  Artificial Intelligence in Structural Analysis:

• – Exploration of AI techniques, including machine learning and data analytics, and their relevance to structural engineering.
• – Case studies demonstrating how AI can improve predictions of structural behaviour under uncertain conditions.

5.  Integration of AI with Probabilistic Models:

• – Methodologies for combining probabilistic analysis with AI algorithms to enhance predictive modelling.
• – Development of a framework for using AI to optimize the design and assessment processes of reinforced concrete structures under uncertainty.

6.  Practical Applications and Case Studies:

• – Real-world applications showcasing the implementation of probabilistic analysis and AI in the assessment of existing reinforced concrete structure.
• – Lessons learned from case studies that highlight the benefits of using AI- enhanced probabilistic approaches.

Helder Sousa

Dr Helder Sousa is an expert, with 17 years of international experience and strong exposure to the industry sector, on Structural Health Monitoring (SHM) applied on Civil Engineering infrastructures and Visiting Professor at the University of Surrey, UK.

With core expertise in Civil Engineering (PhD, 2012, http://repositorio-aberto.up.pt/handle/10216/68424), his scientific knowledge spans from (before PhD conclusion) advanced Finite Element Analysis of full-scale structures to (after PhD conclusion) Bayesian statistics and Value of Information theory, mainly single and sequential updating methods, passing through wide experience in tacking big-data streams collected by monitoring systems installed on full-scale bridges. Altogether makes Dr Sousa holding a holistic and singular profile with a comprehensive view and perception on the different levels of science, i.e. fundamental research and applied research.

With 42 conference papers, 15 scientific journal papers, 2 book chapters, more than 35 oral presentations in several countries of Europe and beyond, as well as 4 short-scientific missions at top leading R&D Institutes in Europe (ETH Zurich in Switzerland, TNO R&D institute in Netherlands, CEREMA in France and COWI in Denmark), makes Dr Sousa has one of the leading researchers in his research field.

Awarded with several research grants and consultancy funding, highlighting his Individual Marie Skłodowska-Curie Fellowship (2015-17, http://www.lostprecon.eu/) and his recent role as the leader of the Innovation Committee of the European COST Action TU1402 – Quantifying the Value of Structural Health Monitoring, as a legal representative of the BRISA Group (2014-19, http://www.cost-tu1402.eu/Action/Innovation-Committee). Currently, he is Guest Editor in the top-ranked scientific journal Structure & Infrastructure Engineering and (co-)leads two special sessions in the next European Workshop on Structural Health Monitoring (Italy, 2020) and in the 13th ASCE Specialty Conference on Probabilistic Mechanics and Reliability (New York, 2020). His enrolment in scientific committees at the European level and wide experience in acting as a reviewer for national and international science councils is also a clear demonstration of his leadership and independence skills.

In the context of this course, the following publications on international top-scientific journals in the field of Civil Engineering might be of relevance for interested people:

• – Sousa, H. (2020) “Advanced FE modelling supported by monitoring towards management of large civil infrastructures – The case study of Lezíria Bridge.” Structural Concrete, the official journal of the fib (accepted for publication, 18th March 2020).
• – Sousa, H., A. Rozsas, A. Slobbe and W. Courage (2020). “A novel pro-active approach towards SHM-based bridge management supported by FE analysis and Bayesian methods.” Structure and Infrastructure Engineering 16(2): 233-246. (http://doi.org/10.1080/15732479.2019.1649287)
• – Sousa, H., L. O. Santos and M. Chryssanthopoulos (2019). “Quantifying monitoring requirements for predicting creep deformations through Bayesian updating methods.” Structural Safety 76: 40-50. (http://doi.org/10.1016/j.strusafe.2018.06.002)
• – Sousa, H., B. J. A. Costa, A. A. Henriques, J. Bento and J. A. Figueiras (2016). “Assessment of traffic load events and structural effects on road bridges based on strain measurements.” Journal of Civil Engineering and Management 22(4): 457-469. (http://doi.org/10.3846/13923730.2014.897991)
• – Sousa, H., J. Bento and J. Figueiras (2014). “Assessment and Management of Concrete Bridges Supported by Monitoring Data-Based Finite-Element Modeling.” Journal of Bridge Engineering 19(6): 05014002. (http://doi.org/10.1061/(ASCE)BE.1943-5592.0000604)

All of our courses are offered 100% online, through our intuitive Virtual Campus. Topics are taught through:

• – Videos
• – Interactive multimedia content
• – Live classes
• – Texts
• – Case studies
• – Evaluation exercises
• – Additional documentation

The content is updated in each new course edition, so that knowledge is acquired around the latest news and state-of-the-art in the field.

One of the most interesting aspects of our courses is the use of live videoconferences, in which teachers and students interact in a continuous exchange of knowledge and problem solving. In addition to this, students can make use of the platform’s forum, a meeting point where they can interact with teachers and other students.

A tutoring system will also be established by email, which will resolve any possible doubts about the course, and which will serve as a point of connection for students with specific questions on each module.

Students can also download the course documentation, including texts, videos and exercises.

This introductory course is designed for undergraduate students in civil engineering, graduate students seeking a comprehensive introduction in the field seeking to integrate AI into their practice, and researchers interested in advancing the application of probabilistic methods in the assessment of existing structures. Hence, this course might be of interest to (but not limited, of course):

• – Graduated engineers with interest in getting into the subject to towards a postgraduate course in structural engineering,
• – Postgraduate engineers with interest to review concepts and improve skills related to advanced structural analysis methods,
• – Researchers aiming for deep learning on advanced structural analysis supported by probabilistic methods enhanced by AI

Once a student finishes the course and successfully completes the assignments and evaluation tests, they are sent an accreditation certificate. The certificate is issued by Ingeoexpert to verify that the student has passed the course. It is a digital certificate that is unique and tamper-proof – it is protected by Blockchain technology. This means it is possible for anyone to check that it is an authentic, original document.

You will be able to download the certificate in an electronic format from the Virtual Campus platform. The certificate can be forwarded by email, shared on social networks, and embedded on websites. To see an example, click here.

The field of structural analysis is of paramount importance in the context of Structural Engineering. Indeed, it is envisaged that in the XXI century, the structural problems become more and more complex and those with robust skills in probabilistic and AI methods, allied to the fundamentals in structural analysis, will be in a better position in the job market. Taking into account the comprehensive approach of this course, the following job prospects are envisaged, mainly:

• – Expert for advanced design offices;
• – Consultant for concrete structure owners, insurance companies, professional associations, among others;
• – Advanced structural engineering towards the assessment of the effective structural behaviour of civil engineering