Michigan Technological University
Automated Generation of Smart Manufacturing Machine Learning Models Using Explainable AI
Abstract
dc:description.abstractIndustry 4.0 has brought about a significant transformation in manufacturing by merging the digital and physical systems. It introduced innovations such as Internet of Things (IoT), Big Data, Artificial Intelligence (AI), and automation into industrial processes to promote the concept of smart manufacturing. Our current research focuses on creating methodologies for effectively using data in manufacturing through AI and Machine Learning (ML). Many US manufacturers, particularly Small to Medium Manufacturers (SMM), struggle to utilize ML due to financial constraints or a shortage of data science expertise. While Industry 4.0 emphasizes automation, Industry 5.0 introduces the idea of human-machine collaboration, where Industry 4.0 technology enhances human productivity using technologies like IoT and Big Data with an emphasis on trust as a key factor in their cooperation. This research concentrates on building trustworthy ML models that can be easily developed by SMM's for democratized AI, a central aspect of Industry 5.0. This involves developing interpretable ML models capable of explaining their decision-making processes by employing Explainable AI (XAI) concepts for interpretation. Subsequently, this work leverages the insights from XAI to improve ML performance through the domain manufacturing knowledge. By leveraging the aforementioned research thrusts, the final outcome of this research is a framework that establishes both trustworthy and generalizable ML models for SMMs.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy in Mechanical Engineering-Engineering Mechanics (PhD)
- Level thesis:degree_level
- Campus Access Dissertation
- Discipline thesis:degree_discipline
- Department of Mechanical and Aerospace Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Valizadeh Sotubadi, Saleh
- Committee members dc:contributor.committeemember
-
- Jung Yun Bae
- David Labyak
- Sriram Malladi
- Contributors dc:contributor
-
- Vinh Nguyen
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Identifier
- https://digitalcommons.mtu.edu/etdr/1867