Syllabus

Introduction to Optimization (5 hours): Introduction to optimization in engineering, emphasizing its definition, significance, and classification of optimization problems. Formulation of optimization problems including identification of decision variables, objective functions, constraints and graphical method of solving optimization problem. Overview of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL), with emphasis on their distinctions and interrelationships, along with a discussion on the applications and potential of AI in various areas of civil engineering.

Linear Programming (LP) and its applications (6 hours): Formulation of linear programming models; solution of LP problems using the Simplex method; artificial variable approaches, including the Penalty (Big-M) method and the Two-Phase method; special cases in the Simplex algorithm, such as degeneracy and other exceptional conditions.

Classical Optimization Techniques (6 hours): Single-variable optimization: bracketing methods, Region-Elimination Methods: Interval Halving Method, golden section search; Multivariable optimization: gradient-based methods, Newton-Raphson method; Constrained optimization: Lagrange multipliers, Kuhn-Tucker conditions.

Nonlinear Programming (NLP) (6 hours): Unconstrained NLP: gradient descent, conjugate gradient methods; Constrained NLP: penalty and barrier methods; Applications in structural optimization and geotechnical engineering.

Metaheuristic Optimization Techniques (6 hours): Genetic Algorithms (GA); Particle Swarm Optimization (PSO); Applications in structural design and material optimization.

Introduction to Artificial Neural Networks (ANN) and Deep Learning (7 hours): This module covers the fundamental concepts of Artificial Neural Networks, including network architectures and learning processes. It also introduces the principles of Deep Learning with emphasis on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), along with their applications in solving civil engineering problems.

Introduce fundamental concepts and classifications of optimization problems in civil engineering.

Develop proficiency in classical and modern optimization techniques.

Apply optimization methods and AI to real-world civil engineering problems.

To apply AI and Deep learning techniques for civil engineering applications

Students will be able to formulate and solve basic optimization problems and understand the distinctions and applications of AI, ML, and DL in civil engineering.

Apply the Simplex method to solve linear programming problems arising in engineering applications.

Apply classical optimization techniques to solve unconstrained and constrained problems.

Employ nonlinear programming methods and metaheuristic algorithms for complex optimization scenarios.

Apply ANN and Deep learning techniques for civil engineering design and optimization problems.

S. S. Rao, Engineering Optimization: Theory and Practice, Wiley

J. S. Arora, Introduction to Optimum Design, Academic Press

K. Deb, Optimization for Engineering Design, PHI

-