Augmented Intelligence for Smart Manufacturing (AISM) Lab

Teaching

 

  • EE611 Deterministic Systems (Fall 2019)

The course covers concepts of linear systems, singularity functions, convolution and superposition integrals, state-variable method for linear systems, relation between transfer function and state-variable equations, fundamental matrix, state-transition matrix, unit-impulse response matrix, and transmission matrix

  • EE 599/699 and ME 599/699 Process Monitoring and Machine Learning (Spring 2020, Spring 2021)

This course includes two major parts: machine learning theories and applications. Machine learning theories will cover legacy techniques (e.g. support vector machine, Bayesian inference) and then go deeper into deep learning (convolutional and recurrent neural network). The application part will cover some practical studies on how can we leverage the machine learning techniques to analyze the data collected from factory floors. Also, programming of the machine learning techniques ( Matlab and Python) will be covered in the class as well.

  • ME395 and ME699 Sustainable Manufacturing Project (Spring 2020, Co-Instructor) 

The objective of this course is to develop innovative solutions to sustainable manufacturing problems through team-based project-driven research. Each project will identify a sustainable manufacturing scope that is relevant to at least one of the United Nations Sustainable Development Goals. Teams will develop innovative solutions to address the sustainable manufacturing challenges with guidance from faculty advisors.

  • EE 599 Engineering Frontiers and Artificial intelligence (Summer 2020

The course explores the evolution of AI, the basic idea, state-of-the-art review of AI techniques, and their potential application in Engineering. The course covers different AI techniques that are developed for processing, analytics, and learning of different types of data and information in engineering applications, such as time series, image, video, natural language, etc., and their implementation in Python. 

  • EM 313 Dynamics (Fall 2020)

Study of the motion of bodies. Kinematics: cartesian and polar coordinate systems; normal and tangential components; translating and rotating reference frames. Kinetics of particles and rigid bodies: laws of motion; work and energy; impulse and momentum. 

  • EE 783 Specific Problem - Stochastic Modeling and Probabilistic Tracking (Fall 2020)

The course will develop robust stochastic models (e.g., combination and/or improvement of Brownian motion, Compound Poisson process, physics-guided models) for specific problems (e.g., machine/battery performance degradation) and their associated system variation characteristics (e.g., non-Gaussian, mix of global variation and local fluctuation). Also, probabilistic system tracking techniques, such as Kalman Filtering and Particle Filtering, will be investigated to recursively update the stochastic models to capture the system dynamics.