Advanced Manufacturing

MATLAB is a multipurpose engineering tool for data analysis and data visualization through a wide variety of tools at the disposal of the user. This course is a hands-on introduction to MATLAB programming, script, live script, functions, and toolboxes. Students will learn to import and process the data sets in a wide variety of forms and formats. Further, a detailed exercise will be performed on the graphing and visualization functions and toolboxes in MATLAB. Data handling, organizing, filtering, and representation are the key deliverables of this course.

Key Learning Objectives:

• Understand the basics of the MATLAB
• Learn about the online and offline versions of MATLAB for data importing and handling.
• Apply the existing and customized filters to the data.
• Learn about data sources and their reliability
• Visualization of data in a wide variety of formats.

We are moving away from the traditional industries which are more automated focused but factories are not smart enough to interact with each other and react to the market stakeholders in the manufacturing. Besides, adapting to changing markets and demand patterns is a challenging aspect of the current industries. Although, the future of industries is based on collecting a large amount of data both from factories and markets to make our manufacturing systems intelligent. This course will cover the application of Artificial Intelligence (AI) to cater to the needs of the

complex and changing industrial landscape. Students will learn about smart and intelligent factories, data handling, and AI-based design and manufacturing workflows. A programming package will be introduced and utilized for this course.

Key Learning Objectives:

• Introduction to Artificial Intelligence and the role of data in developing AI algorithms.
• Learn about the Industry 4.0 and beyond: Future of factories
• AI-based approach to control and optimize the manufacturing process
• Learn about the data acquisition and management for intelligent manufacturing systems
• Design automation and customization through the application of the AI

Optimization is the act of obtaining the best results under a given set of constraints. Especially engineering systems often are faced with multivariable decision making which can be solved using mathematical algorithms and computational tools. This course will cover modeling and optimization theory and application covering linear, non-linear, and discrete optimization methods. There are three main components of this course: linear and non-programming (simplex and dual simplex method, multivariable optimization, constrained and unconstrained optimization), and discrete optimization. This course covers the applications of these techniques in engineering, statistics, and operations. MATLAB would be the primary computational tool for this course.

Key Learning Objectives:

• Use the MATLAB as a computational tool for optimization
• Apply the numerical essentials to learn optimization, matrices, and algorithms.
• Understand, formulate, and solve linear and non-programming problems.
• Learn and apply multi-objective optimization techniques
• Learn to use discrete optimization techniques such as evolutionary algorithms, simulated annealing, and branch and bound.
• Be able to apply numerical packages to solve optimization problems

Gathering, organizing, and processing data from an industrial process using computing technologies and solving data science problems play a vital role in the decision-making process for advanced manufacturing. This course assists students in exercising data science techniques in industrial scenarios. Designing, modeling, and simulating industrial systems and predicting using machine learning techniques such as regression models and Kernel density estimation (KDE) with the programming language and simulation tools are discussed. Case studies using examples such as confectionary production will be illustrated.

Key Learning Objectives:

• Understand key stages and technologies enabling analytical activities.
• Review probability density functions (PDF).
• Conceptualize operation to understand system for production planning and control in manufacturing.
• Use a program code to design and simulate a process and system.
• Understand machine learning techniques with regression models to predict data followed by case studies.