course-details-portlet

MIP4001

Foundations of Artificial AI & Machine Learning for Manufacturing

New from the academic year 2025/2026

Credits 7.5
Level Second degree level
Course start Autumn 2025
Duration 1 semester
Language of instruction Norwegian
Location Gjøvik
Examination arrangement Aggregate score

About

About the course

Course content

This course explores the integration of Artificial Intelligence (AI) within the manufacturing industry, emphasizing data-driven decision-making and process optimization. The course would provide the foundations to understanding of AI concepts and applications. Through a combination of theory, applied techniques, and case studies, students will learn to utilize machine learning to enhance manufacturing efficiency, improve quality control, and manage complex data sets. This course covers key AI concepts, data management, statistical foundations, and machine learning applications specific to manufacturing.

The course begins with an Introduction to AI in Manufacturing, covering core AI concepts, historical context, and specific applications in manufacturing, such as quality monitoring and operational control. Students will explore the benefits and challenges of implementing AI, gaining insights into its potential to enhance efficiency and decision-making in the industry.

Next, the Data Management for Machine Learning module teaches students essential data cleaning, processing, and preparation techniques to ensure high-quality datasets for AI. Emphasizing data integrity, this module highlights how data quality directly affects the accuracy of machine learning outcomes.

In the Basic Statistics Refreshment module, students gain foundational knowledge in descriptive statistics, probability theory, and regression analysis, along with dimensionality reduction techniques. These skills are critical for analyzing manufacturing data and supporting data-driven decisions.

The course concludes with the Machine Learning Module, where students learn about classification, prediction, and other machine learning types. By examining applications like predictive maintenance and quality control, students see how machine learning can drive improvements in manufacturing operations.

Learning outcome

Upon completing this course, students will acquire:

  1. Knowledge:
  • Define and explain core AI concepts and its role in the manufacturing industry.
  • Understand data quality principles, preprocessing techniques, and their significance in machine learning outcomes.
  • Comprehend foundational statistical methods and machine learning algorithms applicable to data-driven manufacturing.
  1. Skills:
  • Apply data cleaning, normalization, and transformation techniques to prepare datasets for machine learning.
  • Utilize descriptive statistics, probability theory, and regression analysis to interpret data relevant to manufacturing contexts.
  • Implement machine learning algorithms for predictive maintenance and quality control applications within manufacturing.
  1. General Competence:
  • Develop critical thinking skills to analyze the potential and limitations of AI in manufacturing.
  • Demonstrate an understanding of data-driven approaches for process optimization and in production.
  • Collaborate and communicate effectively on AI-related topics, data management, and machine learning applications, bridging the gap between technical and operational perspectives in manufacturing.

Learning methods and activities

Teaching Methods:

  • Interactive seminars utilizing the flipped classroom approach
  • E-learning modules for flexible learning
  • Project-based work to apply theoretical knowledge
  • Collaborative group work to enhance teamwork skills
  • Hands-on practical exercises using existing databases

The course is designed to be accessible to both on-campus and remote students. Each student can choose the pedagogical arrangement that best fits their needs. Seminars will be conducted on campus and are also available via streaming through Blackboard Collaborate/MS Teams, with recordings accessible through NTNU's learning management system. Tutoring will be available both on-campus and online at scheduled times. The medium of instruction is Norwegian/English, and all assignments, reports, and documentation must be submitted in Norwegian/English.

Further on evaluation

The examination of the course is divided in three deliveries: two written assignments and one written report. The assignments accounts for 40% of the final grade, 20% each. The final report accounts for 60% of the final grade.

In case of failing the course, it must be taken again the next time the course is given.

Specific conditions

Admission to a programme of study is required:
Production and Product Development (MIPRODPRO)

Course materials

Relevant articles and reports will be given at course start

Subject areas

  • Production and Quality Engineering - Production Management
  • Analysis

Contact information

Course coordinator

Lecturers

Department with academic responsibility

Department of Manufacturing and Civil Engineering

Examination

Examination

Examination arrangement: Aggregate score
Grade: Letter grades

Ordinary examination - Autumn 2025

Assignment
Weighting 20/100 Exam system Inspera Assessment
Assignment
Weighting 20/100 Exam system Inspera Assessment
Report
Weighting 60/100 Exam system Inspera Assessment