The Grainger College of Engineering
AI Guidance and Resources

AI-Supported Learning

AI-Supported Learning


 

Innovative AI-Supported Learning Activities

Currently, students in many courses use AI to support their learning activities without guidance from the instructor.  AI offers a variety of ways which can assist a student from emulating web search to finding resources to editing their text to refining language. So it is natural for students to want to use it to assist their learning.  Some uses can push the boundaries of what is acceptable. One way to handle this situation is for the instructor to offer constructive ways in which AI can be used in their classroom and specific guidance as to the limit of its acceptable use. As with any tool, it is expected that what may be an unacceptable use in one class may be entirely appropriate in another; clear and early communication is needed to reduce student confusion (refer to the sample syllabi section for example communications).   This section suggests a variety of the different types of assignments that instructors can add to their courses.  We also offer a list of example assignments.

Incorporating AI-based assignments into engineering education represents a significant advancement in preparing students for real-world challenges across various disciplines. By utilizing AI to tackle complex, authentic problems, students will be immersed in predictive analysis, optimization, and decision-making processes essential for modern engineering roles. Beyond technical skills, these innovative assignments foster interdisciplinary thinking, ethical considerations, and iterative problem-solving skills. Such assignments will provide students with a holistic understanding of AI’s transformative potential in their fields. 

Types of AI-Integrated Assignments

Using an LLM to summarize a paper to get a high-level idea about its content can be helpful, for example, in deciding whether to read it., but copy-pasting that summary as a concluding paragraph for a paper you have written could be problematic.  AI might produce text in perfect English, but it often produces over-generic text less useful for a reader.

  • Using ChatGPT as a Thesaurus
    Students use AI to overcome writer's block, using it as a thesaurus to find synonyms, antonyms, and definitions during the writing process.

  • Thesis Generation
    Students paste a prompt into ChatGPT to generate a thesis. They then critique and refine the AI-generated thesis to better understand argument construction.

  • Idea Brainstorming
    Assignments involve using AI for brainstorming ideas or to generate essay outlines based on a provided topic.

  • Peer Editing via AI
    Have students submit an AI-generated thesis alongside their own work for comparison, encouraging deeper reflection on their own writing•.

Mathematical/Statistical Data Analysis
Students use AI to propose study designs and analyze data in statistics. For example, after human-generated analysis, students compare AI-driven conclusions with their own​.
 
Coding Assignments with AI Assistance
AI can generate code snippets or fix errors for students, with them reflecting on the AI’s reliability and their process. Examples include using AI tools such as Copilot to assist in data analysis coding​.
 
Teacher Salary and Academic Outcomes Analysis
In this stats class activity, students compare AI-generated insights and their own findings from datasets concerning teacher salary and academic performance.

Exploring Geologic Time with ChatGPT
Students ask ChatGPT to summarize geologic events during a chosen period. After receiving AI-generated responses, they evaluate the depth, clarity, and accuracy of the AI's answers.

Exploring Geologic Topics with ChatGPT
Students query ChatGPT on topics they've studied and compare the AI's responses to their own knowledge, assessing how AI explanations could support their learning.

AI for Career Planning
ChatGPT helps students assess personal strengths and explore career options by providing job descriptions, required degrees, certifications, and tips for job searches. Students can also use AI to generate personalized resumes.

Podcast Assignments with AI Assistance
AI can assist students in planning and structuring podcast episodes on specific academic topics, such as summarizing data from scientific papers.

Interpreting Scientific Papers
AI helps students interpret complex academic papers by simplifying and summarizing them, which can be followed by human analysis and reflection.

AI’s Role in Society and Education
Students read articles about the implications of AI in education and write reflections on whether AI tools are beneficial or a means of cheating, providing a balanced discussion on ethics and learning​.

Understanding Concepts
Use AI to generate multiple explanations for a concept and ask students to critique the AI-generated explanations. Ask them to cite/use specific course readings, notes from lectures, etc., in their critiques.

Evaluate Design
Ask an AI to code/draw an image/create a script/design an experiment. Evaluate the results. Make a list of errors or how this result could have been better. Adjust your prompt to improve the output. Take the best output and make it even better with human editing. (Track changes)


AI-Based Failure Prediction in Structural Engineering

Discipline: Civil and Structural Engineering

Description: Students will use AI models, such as machine learning algorithms, to predict failures in structural engineering systems. They will be provided with a dataset containing historical data on various structural failures and environmental conditions (e.g., load stress, material fatigue, seismic activity). The task will be to train the model to predict future failures based on current conditions and propose preventive measures.

Learning Objectives: 

  1. Understand and apply machine learning algorithms for predictive analysis. 
  2. Analyze real-world data related to structural engineering.
  3. Develop insights into preventive maintenance using AI.

Tools: Python (Scikit-learn, TensorFlow), MATLAB, or specialized AI platforms.


Optimization of Electrical Grid Using AI

Discipline: Electrical Engineering

Description: In this assignment, students will simulate and optimize an electrical grid using AI algorithms such as reinforcement learning. They will model the behavior of various power sources (e.g., renewable energy, fossil fuels) and consumers, using AI to optimize the distribution of energy to reduce costs and emissions.

Learning Objectives:

  1. Use AI to optimize complex, dynamic systems.
  2. Apply reinforcement learning to real-world engineering problems.
  3. Understand the implications of energy distribution and environmental impact.

Tools: OpenAI Gym for Reinforcement Learning, Python, Simulink.


AI-Assisted Circuit Design

Discipline: Electronics and Electrical Engineering

Description: Students will leverage AI tools such as genetic algorithms to design efficient circuits. They will input constraints such as power consumption, size, and cost, and the AI will generate optimized designs. Students will then evaluate and refine the AI-generated designs.

Learning Objectives:

  1. Understand the use of AI in electronics design.
  2. Apply optimization techniques to circuit development.
  3. Evaluate AI-generated solutions for real-world feasibility.

Tools: Python (SciPy, NumPy), LTspice.


AI for Sustainable Building Design

Discipline: Civil Engineering / Environmental Engineering

Description: Students will use AI models to design sustainable buildings, considering factors such as energy efficiency, material sustainability, and cost. They will use AI to simulate different designs and optimize for sustainability metrics, such as minimizing carbon footprints and maximizing natural lighting.

Learning Objectives: 

  1. Use AI for environmental impact assessments.
  2. Develop sustainable design solutions with real-world applicability.
  3. Understand the trade-offs between cost, sustainability, and design efficiency

Tools: AI-based simulation tools (e.g., Rhino + Grasshopper with AI plug-ins), Python, MATLAB.


AI for Predictive Maintenance in Manufacturing

Discipline: Mechanical Engineering

Description: Students will work with real-world data from manufacturing systems and use AI to predict when machinery will need maintenance. The AI model will be trained to recognize patterns of wear and tear in machine parts, and students will be asked to propose strategies for cost-effective, predictive maintenance.

Learning Objectives:

  1. Understand predictive maintenance and its industrial applications.
  2. Use AI to analyze real-time data and predict equipment failure.
  3. Develop data-driven maintenance strategies.

Tools: Python (Pandas, TensorFlow), MATLAB, Simulink.


AI for Autonomous Vehicle Navigation

Discipline: Automotive Engineering / Robotics

Description: In this project, students will use AI to program an autonomous vehicle to navigate a simulated urban environment. The AI model will process inputs from sensors (such as LIDAR, cameras, GPS) to make real-time decisions about path planning, obstacle avoidance, and traffic management.

Learning Objectives:

  1. Learn how AI models process sensor data for autonomous systems.
  2. Apply machine learning algorithms for real-time decision-making.
  3. Understand the safety, ethical, and environmental considerations of autonomous vehicles.

Tools: ROS (Robot Operating System), Python, TensorFlow, Simulink.


AI-Enhanced Chemical Process Optimization

Discipline: Chemical Engineering

Description: Students will develop an AI-based system to optimize chemical manufacturing processes. Given a set of input parameters (e.g., temperature, pressure, concentration), the AI will suggest optimal process conditions to maximize yield while minimizing costs and environmental impacts.

Learning Objectives:

  1. Apply AI to complex process optimization in chemical engineering.
  2. Use simulation tools to predict the outcomes of AI-driven optimization.
  3. Analyze the trade-offs between production efficiency and environmental sustainability.

Tools: Aspen Plus, Python (SciPy, TensorFlow).


AI-Based Water Quality Monitoring


Discipline: Environmental Engineering

Description: In this assignment, students will develop AI models to monitor and predict changes in water quality based on environmental data. Students will use historical water quality data and environmental factors (such as rainfall, industrial discharge) to train the AI model.

Learning Objectives:

  1. Develop an understanding of AI in environmental monitoring.
  2. Use AI to predict and mitigate environmental hazards.
  3. Apply data analytics to environmental datasets.

Tools: Python (Pandas, Scikit-learn), MATLAB, R.


AI for Dynamic Load Balancing in Network Systems

Discipline: Computer Engineering / Telecommunications

Description: Students will create an AI model that dynamically balances network loads in real-time. Using AI algorithms like reinforcement learning, the system will predict traffic patterns and adjust load balancing to optimize bandwidth usage and minimize latency.

Learning Objectives:

  1. Apply AI to network management and optimization.
  2. Use reinforcement learning to optimize dynamic systems.
  3. Evaluate the performance of AI-based systems in real-world applications.

Tools: Python (SciPy, TensorFlow), MATLAB, NS-3 (Network Simulator).


AI-Driven Biomedical Signal Processing

Discipline: Biomedical Engineering

Description: This assignment involves using AI to process biomedical signals, such as ECG or EEG data, to detect abnormalities or predict health outcomes. Students will work with real-world medical datasets and develop AI models to assist in medical diagnoses.

Learning Objectives:

  1. Use AI for signal processing in biomedical applications.
  2. Analyze real-world medical data to predict health outcomes.
  3. Understand ethical issues related to AI in healthcare.

Tools: Python (NumPy, Scikit-learn, TensorFlow), MATLAB.


AI in Aerospace Flight Path Optimization

Discipline: Aerospace Engineering

Description: Students will design an AI-based system to optimize flight paths for efficiency, taking into account factors such as fuel consumption, wind speed, and weather conditions. The AI will be trained to propose optimal flight paths that minimize fuel use and emissions.

Learning Objectives:

  1. Use AI for optimization in aerospace applications.
  2. Apply machine learning to dynamic, real-time systems.
  3. Analyze environmental and cost trade-offs in aerospace design.

Tools: Python, MATLAB, Simulink.


AI in Engineering Lab Data Analysis

Discipline: Bioengineering

Description: Students compare the process of fitting a curve to experimental data by hand, with MATLAB, and with AI.

Learning Objective: For students to be able to critically think about the difference between doing analysis by hand, with purpose-built and validated software, & with a tool based on a large language model.

Tools: Excel, MATLAB, Python

Assignment and other resources: GenAI Data Analysis (Box) 

Resources: