AI-Supported Work-Integrated Learning for Electrical Engineering Students in Open Distance Learning: A Competency-Based Approach

Abstract

Work-Integrated Learning (WIL) is an essential part of electrical engineering education, providing students with the opportunity to take their theoretical knowledge and apply it to create professional competencies. Implementing good quality WIL requires overcoming some major hurdles in Open Distance Learning (ODL) environments, such as limited access to the physical industry, unequal mentorship opportunities and challenges in evaluating practical competencies remotely. This study outlines a proposed WIL framework using Artificial Intelligence (AI) that will be developed specifically for electrical engineering students in ODL environments. The proposed framework combines Intelligent Tutoring Systems (ITS), Learning Analytics (AL) and adaptive assessment models, allowing students to simulate actual workplace tasks aligned to defined industry competencies. Additionally, Machine Learning (ML) algorithms will analyse student interaction data to support personalised feedback, competency gap analysis and adaptive sequencing of tasks. A pilot initiative with ODL undergraduate electrical engineering students has proven that the AI-based WIL model is a superior method for developing practical competencies, encouraging greater knowledge retention, enhancing assessment reliability through robust validation techniques, etc., compared to previous WIL logbook models. The data from the pilot indicated that the AI/ML Driven WIL model has positively impacted the competencies, task accomplishment, and engagement of all student cohorts participating in the pilot project. Furthermore, many students provided qualitative feedback indicating they felt much more confident after participating in the AI-based WIL model in terms of preparedness for employment, ability to complete assignments/tasks, etc., compared to using the WIL logbook ODL. Thus, the AI-supported WIL approach provides solutions to the major weaknesses experienced in traditional methods of WIL delivery in ODL, providing scalable, data-driven supervision and transparent competency evaluations. Based on the study’s findings, there is evidence that AI-supported WIL provides an effective alternative to maintaining professional engineering accreditation while improving access to education through ODL. The structure of this study provides a clear theoretical model for incorporating AIinto competency-based engineering education in ODL environments with limited resources.