TÜRKÇE
ENGLISH
Information
| Unit | FACULTY OF ENGINEERING |
| CIVIL ENGINEERING PR. | |
| Code | IMS478 |
| Name | Artificial Intelligence in Structural Analysis and Design |
| Term | 2026-2027 Academic Year |
| Semester | 8. Semester |
| Duration (T+A) | 1-2 (T-A) (17 Week) |
| ECTS | 5 ECTS |
| National Credit | 2 National Credit |
| Teaching Language | Türkçe |
| Level | Belirsiz |
| Type | Normal |
| Label | E Elective |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Prof. Dr. AHMED KAMİL TANRIKULU |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
The aim of this course is to equip civil engineering students with advanced knowledge in structural engineering with the ability to apply artificial intelligence and machine learning techniques to structural analysis and design problems. Within the scope of the course, students learn data-driven structural analysis methods, solve complex engineering problems such as earthquake damage prediction and fragility analysis using artificial intelligence, apply structural design optimization algorithms, and develop structural health monitoring systems using computer vision methods. By the end of the course, students are expected to be equipped to independently design and implement AI-assisted structural engineering applications.
Course Content
Applications of artificial intelligence and machine learning to structural engineering; data-driven approaches in structural analysis problems; capacity and strength prediction using machine learning for steel, reinforced concrete and composite structures; artificial intelligence applications in earthquake engineering: damage prediction, fragility analysis and soil-structure interaction; structural design optimization: genetic algorithms, evolutionary computation and multi-objective optimization; structural damage detection and health monitoring with computer vision; technical specification and standard analysis with natural language processing; BIM integration and generative AI in structural design; ethical and professional dimensions of AI in structural engineering.
Course Precondition
None
Resources
Weekly lecture notes and laboratory materials prepared by the instructor will be shared via the course platform.
Notes
1. Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O'Reilly Media. 2. Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning. MIT Press. (Free: deeplearningbook.org) 3. Chollet, F. (2021). Deep Learning with Python (2nd ed.). Manning Publications. 4. McKinsey Global Institute. (2020). The Next Normal in Construction: How Disruption is Reshaping the World's Largest Ecosystem. McKinsey & Company. (Free PDF: mckinsey.com) 5. Autodesk & Deloitte. (2023). State of Data Capabilities in Construction. Autodesk. (Free PDF: autodesk.com) 6. Journal of Structural Engineering (ASCE) — AI special issues 7. Engineering Structures (Elsevier) — Articles on AI and structural engineering 8. Automation in Construction (Elsevier) — Articles on AI and construction technology 9. Google Colab: colab.research.google.com 10. Kaggle datasets and competitions: kaggle.com 11. OpenSeesWiki — Open source structural analysis platform: opensees.ist.berkeley.edu/wiki 12. PEER NGA-West2 Ground Motion Database: ngawest2.berkeley.edu 13. AFAD Open Data Portal: afad.gov.tr
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Evaluates the applicability of artificial intelligence and machine learning to structural engineering problems; selects appropriate methods and algorithms. |
| LO02 | Develops and validates data-driven capacity and strength prediction models for steel, reinforced concrete and composite structures. |
| LO03 | Performs damage prediction and fragility analysis in earthquake engineering problems using machine learning. |
| LO04 | Applies genetic algorithms and evolutionary computation methods for structural design optimization. |
| LO05 | Develops structural damage detection and structural health monitoring systems using computer vision methods. |
| LO06 | Creates structural design and analysis workflows by integrating BIM data with artificial intelligence. |
| LO07 | Identifies a real structural engineering problem, selects the appropriate AI method, and shares the solution as a technical report and presentation. |
| LO08 | Discusses the ethical dimensions, limitations and professional responsibilities of artificial intelligence in structural engineering. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | “Sufficient knowledge in mathematics, science, and discipline-specific topics in Civil Engineering; the ability to use theoretical and applied knowledge in these fields to solve complex engineering problems.” | 3 |
| PLO02 | Bilgi - Kuramsal, Olgusal | “The ability to identify, formulate, and solve complex Civil Engineering problems; and the ability to select and apply appropriate analysis and modeling methods for this purpose.” | 5 |
| PLO03 | Bilgi - Kuramsal, Olgusal | “The ability to design a complex system, process, device, or product to meet specified requirements under realistic constraints and conditions; and the ability to apply modern design methods for this purpose.” | 5 |
| PLO04 | Bilgi - Kuramsal, Olgusal | “The ability to select and use modern techniques and tools necessary for the analysis and solution of complex problems encountered in Civil Engineering applications; and the ability to use information technologies effectively.” | 5 |
| PLO05 | Bilgi - Kuramsal, Olgusal | “The ability to design experiments, conduct experiments, collect data, and analyze and interpret results for the investigation of complex Civil Engineering problems or discipline-specific research topics.” | 4 |
| PLO06 | Bilgi - Kuramsal, Olgusal | “The ability to work effectively in intra-disciplinary and multidisciplinary teams; and the ability to work independently.” | |
| PLO07 | Bilgi - Kuramsal, Olgusal | “The ability to communicate effectively in both oral and written form; proficiency in at least one foreign language; the ability to write effective reports and understand written reports, prepare design and production reports, deliver effective presentations, and give and receive clear and understandable instructions.” | 4 |
| PLO08 | Bilgi - Kuramsal, Olgusal | “Awareness of the necessity of lifelong learning; the ability to access information, follow developments in science and technology, and continuously improve oneself.” | 4 |
| PLO09 | Bilgi - Kuramsal, Olgusal | “Acting in accordance with ethical principles, having professional and ethical responsibility, and having knowledge of the standards used in engineering practices.” | 3 |
| PLO10 | Bilgi - Kuramsal, Olgusal | “Knowledge of business-life practices such as project management, risk management, and change management; awareness of entrepreneurship and innovation; and knowledge about sustainable development.” | |
| PLO11 | Bilgi - Kuramsal, Olgusal | “Knowledge of the universal and social impacts of Civil Engineering practices on health, environment, and safety, as well as the contemporary issues reflected in the field of engineering; and awareness of the legal consequences of engineering solutions.” |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction: Impact of AI on Structural Engineering; Fundamental Concepts (AI, ML, DL); Tools and Software to be Used | Test that your Google Colab account is working (colab.research.google.com). Create a free account on ChatGPT or Claude.ai. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma, Gösteri |
| 2 | Quick Introduction to Machine Learning: Algorithms, Data Types, Python and Google Colab; Data Analysis in Structural Engineering | Review the basic functions of Pandas and NumPy libraries. Create a free account on Kaggle.com. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama |
| 3 | Machine Learning in Reinforced Concrete Structures: Concrete and Reinforcement Steel Strength Prediction; Regression and Ensemble Models | Research Random Forest and Gradient Boosting algorithms. Review the topic of reinforced concrete material behavior. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 4 | Capacity Prediction in Steel and Composite Structures: Machine Learning Models at Section and System Level | Review the topic of steel structural section capacity calculation. Download the steel structure dataset shared on the course platform. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 5 | AI in Earthquake Engineering — I: Damage Prediction and Classification; Using PEER NGA-West2 Database | Log in to the PEER NGA-West2 database (ngawest2.berkeley.edu) and familiarize yourself with the interface. Research the concept of earthquake damage classification. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 6 | AI in Earthquake Engineering — II: Fragility Analysis and Soil-Structure Interaction; Integration with OpenSees | Research the concept of fragility curves. Review OpenSeesWiki (opensees.ist.berkeley.edu/wiki). | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 7 | Structural Design Optimization — I: Genetic Algorithms and Evolutionary Computation; Size Optimization Applications | Research the concept of genetic algorithms. Review the DEAP or pymoo libraries in Python. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama |
| 8 | Mid-Term Exam | Review topics from weeks 1-7. Revise your assignments and notes. | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Structural Design Optimization — II: Multi-Objective Optimization; Cost, Weight and Reliability Optimization | Research multi-objective optimization and Pareto front concepts. Download the optimization dataset shared on the course platform. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama |
| 10 | Structural Damage Detection with Computer Vision: Deep Learning Models, Crack and Corrosion Detection | Review the topic of convolutional neural networks (CNN). Log in to your Roboflow account and familiarize yourself with the interface. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 11 | Structural Health Monitoring: Sensor Data, Vibration Analysis and Anomaly Detection; Real Bridge and Building Applications | Research the concept of Structural Health Monitoring (SHM). Download the bridge sensor dataset shared on the course platform. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Örnek Olay |
| 12 | BIM Integration and Generative AI: Structural Analysis Automation with IFC Data; Structural Optimization with Generative Design | Check that your Autodesk Forma student license is active. Review the IFC data format. | Öğretim Yöntemleri: Anlatım, Gösteri, Alıştırma ve Uygulama, Beyin Fırtınası |
| 13 | Technical Specification and Standard Analysis with Natural Language Processing; Structural Engineering Applications with Large Language Models | Research basic concepts of Natural Language Processing (NLP). Try a structural engineering question with ChatGPT or Claude. | Öğretim Yöntemleri: Anlatım, Tartışma, Gösteri, Alıştırma ve Uygulama |
| 14 | Ethical and Professional Dimensions of AI in Structural Engineering; Reliability, Accountability and Standards; Term Project Presentations (Group 1) | Finalize your term project for presentation. Read an ethics discussion article on the use of AI in structural engineering. | Öğretim Yöntemleri: Tartışma, Soru-Cevap, Alıştırma ve Uygulama |
| 15 | Term Project Presentations (Group 2); General Course Evaluation; Future of Structural Engineering and Career Directions | Dönem projenizi sunuma hazır hale getiriniz. Diğer grupların sunumlarını değerlendirmek için not alma formatı hazırlayınız. Preparation (EN): Finalize your term project for presentation. Prepare a note-taking format to evaluate other groups' presentations. | Öğretim Yöntemleri: Tartışma, Soru-Cevap, Beyin Fırtınası |
| 16 | Term Exams | Review all semester topics, assignments and course notes. | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Review all semester topics, lab assignments and course notes. | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 4 | 56 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 4 | 5 | 20 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 3 | 3 |
| Final Exam | 1 | 3 | 3 |
| Total Workload (Hour) | 124 | ||
| Total Workload / 25 (h) | 4,96 | ||
| ECTS | 5 ECTS | ||