Introduction

Mechanical Vibrations is a core undergraduate mechanical engineering course that integrates mathematical modeling, differential equations, dynamics, and engineering design. Students are expected to understand the behavior of vibrating systems and apply analytical and computational techniques to solve practical engineering problems. Because many vibration concepts are abstract and highly mathematical, students often struggle to connect theoretical equations with physical behavior. Generative Artificial Intelligence (AI) provides new opportunities to improve course design, instruction, and student learning.

This paper presents a framework for redesigning an undergraduate Mechanical Vibrations course using generative AI throughout the course lifecycle.

Course Design and Learning Outcomes

Generative AI can assist faculty in developing course structures aligned with program outcomes and industry needs.

AI can generate draft learning outcomes such as:

• Model single-degree-of-freedom vibrating systems.
• Analyze free and forced vibration behavior.
• Evaluate the effects of damping.
• Apply numerical and computational methods.
• Design engineering solutions for vibration control.

AI can also help organize topics into a logical progression that builds from fundamental concepts toward advanced applications.

 Syllabus and Schedule Development

AI tools can quickly generate course schedules, assignment structures, and project timelines.

A typical semester sequence may include:

• System modeling
• Free vibration
• Damped vibration
• Forced vibration
• Resonance
• Multi-degree-of-freedom systems
• Modal analysis
• Vibration isolation
• Computational simulation
• Design applications

Faculty members can use AI-generated schedules as starting points and adapt them to institutional requirements and student needs.

Development of Instructional Materials

Generative AI can significantly reduce preparation time by producing lecture outlines, summaries, worked examples, and visual explanations.

Particularly valuable applications include:

• Physical interpretations of damping.
• Resonance demonstrations.
• Real-world engineering case studies.
• Step-by-step derivations.
• MATLAB and Python simulation examples.

For example, AI can generate multiple engineering applications involving automotive suspensions, rotating machinery, aircraft structures, manufacturing equipment, and seismic systems.

These examples help students connect mathematical models with practical engineering problems.

Visualization and Simulation-Based Learning

One of the strongest applications of AI in a Vibrations course is the development of visual learning materials.

AI can assist in creating:

• Motion animations.
• Frequency response visualizations.
• Resonance demonstrations.
• Mode shape illustrations.
• Parameter studies.

These visualizations can improve conceptual understanding by helping students observe the physical meaning of vibration equations and system behavior.

Generative AI can also create MATLAB and Python scripts that allow students to experiment with damping ratios, excitation frequencies, and system parameters.

Active Learning and Project-Based Instruction

AI can support student-centered learning through case studies and design projects.

Example projects include:

• Design of a vibration isolation system.
• Analysis of machine vibration problems.
• Investigation of resonance in engineering structures.
• Condition monitoring using vibration data.

AI can assist students in brainstorming approaches, identifying design alternatives, and generating preliminary analyses.

Faculty supervision remains essential to ensure engineering validity and appropriate decision making.

Assessment Design

Generative AI can assist in developing diverse assessment materials that align with course objectives.

Examples include:

• Homework assignments.
• Conceptual quizzes.
• Midterm and final examinations.
• Design project rubrics.
• Laboratory reports.

AI can rapidly generate multiple versions of vibration problems with varying numerical parameters, reducing opportunities for academic dishonesty while preserving learning objectives.

Instructors should review all AI-generated assessments to ensure correctness and appropriate difficulty levels.

Student Learning Support

Outside the classroom, AI can function as a personalized learning assistant.

Students can use AI to:

• Review derivations.
• Generate additional practice problems.
• Receive explanations of difficult concepts.
• Explore alternative solution approaches.
• Debug MATLAB and Python code.

This continuous support can improve student engagement and provide immediate feedback when faculty assistance is unavailable.

Students must nevertheless verify all AI-generated results and maintain responsibility for their own learning.

Responsible AI Integration

The redesigned course should include guidance regarding ethical and effective AI use.

Students should understand that AI:

• May generate incorrect solutions.
• Cannot replace engineering judgment.
• Should be used for learning support rather than answer generation.
• Requires verification through engineering principles.

Assignments can require students to document how AI was used and how generated results were validated.

Continuous Improvement

Generative AI can assist instructors in evaluating course effectiveness by analyzing assessment results, student feedback, and common misconceptions.

The resulting insights can support evidence-based revisions to instructional materials, laboratory activities, and assessments.

Such continuous improvement aligns well with accreditation processes and outcomes-based education models.

Conclusion

Generative AI has the potential to transform the design and delivery of undergraduate Mechanical Vibrations courses. Applications span course planning, syllabus development, instructional materials, visualization, assessment, student support, and continuous improvement. When implemented responsibly, AI can enhance student learning while allowing faculty members to devote greater attention to mentoring, design thinking, and engineering judgment. The result is a more engaging, adaptive, and effective learning environment for future mechanical engineers.