AI-Enhanced Problem-Based Learning for Sustainable Engineering Education: The AIPLE Framework for Developing Countries
Abstract
1. Introduction
1.1. Engineering Education and Sustainable Development: A Critical Nexus
1.2. The Student Apprehension Challenge: Barriers to Sustainable Engineering Education
1.3. The AIPLE Framework: A Sustainable Engineering Education Solution
- Problem-Based Learning (PBL) grounded in real-world sustainability challenges.
- Hands-on experimentation that connects theory to practical application.
- Strategic AI integration that provides personalized learning support and enhances problem-solving capabilities.
1.4. Research Objectives and Contributions
- Examine the limitations of traditional engineering education in developing sustainable engineering competencies.
- Present the AIPLE framework as a comprehensive solution for sustainable engineering education.
- Analyze instructor perspectives on PBL and AI integration in engineering education.
- Demonstrate the framework’s alignment with sustainable development objectives.
- Provide implementation guidelines for similar institutions in developing countries.
2. Literature Review
2.1. Engineering Education for Sustainable Development
2.2. Problem-Based Learning in Engineering Education
2.3. Artificial Intelligence in Engineering Education
3. Methodology
3.1. Research Design
3.2. Participants
3.3. Data Collection
3.4. Data Analysis
3.5. Limitations
4. The AIPLE Framework: A Context-Adapted Pedagogical Model
4.1. Theoretical Foundation
- Experiential Learning Theory: The framework’s five-stage cyclical process mirrors Kolb’s cycle of concrete experience, reflective observation, abstract conceptualization, and active experimentation, ensuring that learning is an iterative and deeply embedded process [27].
- Social Constructivist Theory: AIPLE emphasizes learning through social interaction and collaborative problem-solving. Students work in diverse teams, engaging in peer-to-peer learning and co-constructing knowledge, which is particularly effective for bridging the skill gaps present in the classroom [28].
- Education for Sustainable Development (EESD) Theory: The framework embeds sustainability principles into the core learning process, moving beyond treating sustainability as an add-on topic. It encourages students to develop the systems thinking and ethical reasoning necessary to address complex, real-world sustainability challenges [29].
4.2. The Five Stages of AIPLE: An Implementation and Assessment Guide
5. Results: Diverse Instructor Perspectives on Pedagogy and Innovation
5.1. The Core Challenge: Student Apprehension and the Culture of Passive Learning
5.2. Strategies in Practice: Adapting Problem- and Project-Based Learning
- Instructor KT employs a year-long, multi-group PBL project for first-year students in “Introduction to Industrial Engineering Science.” A complex, real-world problem, such as designing a briquette-making machine, is broken down into seven sub-problems (raw materials, mechanical design, electrical circuits, etc.), with each group tackling one piece. The process is iterative, involving a loop of research, expert consultation, and integration until a functional prototype is presented. This model is designed to build foundational skills and teamwork from the very beginning of the engineering curriculum.
- Instructor JNM utilizes a more formally structured, eight-phase PBL model for projects like designing a traffic light system. The phases—Go-Phase, Individual Research, Guidance, Collaborative Research, Presentation, Knowledge Sharing, Evaluation, and Feedback—provide a clear and rigorous process for students to follow. This highly structured approach ensures that all key aspects of problem-solving, from initial definition to final reflection, are systematically addressed.
- Instructor TNK, working with Master’s students, implements Project-Based Learning focused on research. Students are assigned topics related to real-world challenges, such as energy issues in the DRC, and are guided through a phased research project with set milestones for progress tracking and feedback. This approach develops advanced research skills, often leading to an initial draft of a scientific paper, and teaches students to use professional tools like LaTeX.
- Instructor David integrates a single, course-long project into his computer science courses. By assigning a project title at the beginning of the term, “each lecture becomes a step closer to reaching the main project.” This strategy provides a practical, unifying context for all theoretical lectures and lab sessions, helping students see the direct application of each new concept they learn.
5.3. Navigating AI Integration: Between Cautious Optimism and Practical Hurdles
- Infrastructure and Cost: High implementation costs and the fact that “not all students have access to high-performance computers and stable internet” create significant barriers to equitable access.
- Ethical Concerns: Instructors worry about accountability for incorrect AI-generated answers (“hallucinations”), the potential loss of human interaction between students and teachers, and the scientific rigor of unverifiable sources.
- Faculty Readiness: Instructors themselves require training to understand AI tools, their limitations, and how to adapt their teaching methods accordingly. As Instructor David noted, resistance is likely to come from educators who need to change long-held habits.
6. Discussion: Implications for Sustainable Engineering Education
6.1. Applying the AIPLE Framework to Overcome Foundational Learning Barriers
6.2. A Call for Responsible AI Integration: Navigating Ethics and Infrastructure
6.3. The Critical Role of Community and Stakeholder Engagement
7. Conclusions and Future Research
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
AIPLE | AI-Integrated Practical Learning in Engineering |
DRC | Democratic Republic of Congo |
EESD | Engineering Education for Sustainable Development |
ICT | Information and Communication Technology |
PBL | Problem-Based Learning |
SDG | Sustainable Development Goal |
ULC | Université Loyola du Congo |
UN | United Nations |
UNESCO | United Nations Educational, Scientific and Cultural Organization |
USA | United States of America |
Appendix A
Survey Questions
- Could you walk us through your typical teaching process for an engineering course, including how you structure lectures, assignments, and lab sessions?
- How do you adapt your teaching for students who lack strong backgrounds in mathematics and physics?
- What are the main challenges you encounter when using traditional teaching methods in engineering education?
- Have you incorporated digital resources or online tools into your teaching? If so, what tools or platforms have you found most effective?
- How do you currently measure the balance between theoretical and practical learning in your courses?
- Are there specific teaching strategies you’ve tried that have noticeably improved student engagement or outcomes?
- When did you first start incorporating Problem-Based Learning (PBL) into your teaching? What motivated this shift?
- Could you describe a specific PBL activity or project you have used? What was the focus, and how was it structured?
- How do you ensure that students stay engaged and collaborative during PBL activities?
- What changes have you noticed in students’ problem-solving skills, creativity, or teamwork abilities since implementing PBL?
- Have you observed any differences in how students approach engineering challenges when using PBL versus traditional methods?
- How do students typically respond to PBL activities, particularly those who might initially lack confidence in STEM subjects?
- What logistical or resource-related barriers have you encountered when implementing PBL?
- How do you adapt PBL methods for large classes, limited lab access, or time constraints?
- Could you share an example of a challenge you faced with PBL and how you resolved it?
- What is your current understanding of Artificial Intelligence (AI), and how do you see its role in engineering education?
- Have you personally used any AI-based tools (e.g., virtual labs, adaptive learning platforms, simulations) in your teaching? If so, which ones, and what has been your experience with them?
- Do you actively teach students about AI concepts or applications in engineering? If yes, how is this incorporated into your curriculum?
- What specific areas of engineering education (e.g., labs, assessments, personalized learning) do you think AI has the most potential to improve?
- How do you think AI could help overcome barriers to education in resource-constrained settings?
- Have you observed any improvements in student engagement, understanding, or performance when using AI tools?
- What challenges or limitations do you foresee in integrating AI into engineering education (e.g., cost, ethical concerns, technical barriers)?
- Are there any potential risks you see in over-relying on AI in the classroom?
- How would you address potential resistance from students or educators to adopting AI-based teaching tools?
- Have you implemented service learning as part of your teaching? If so, what type of projects or partnerships have you facilitated?
- Could you provide an example of how service learning has helped students apply their engineering skills to real-world problems?
- How do you assess the impact of service learning on students’ technical skills and their understanding of community needs?
- What are the most significant gaps you see in current engineering education methods, particularly in resource-limited settings?
- What specific types of support (e.g., funding, training, infrastructure) would be necessary to implement an effective AI and PBL-integrated approach in under-resourced areas?
- Are there any policies or institutional changes you believe are critical to advancing engineering education in the Sub-Saharan Africa?
- How do you envision engineering education evolving in the next decade, particularly in light of advancements in AI and other digital technologies?
- What steps can educators take to prepare students for addressing global challenges like climate change and sustainable development?
- How can engineering education better align with the UN’s Sustainable Development Goals?
- “Can you provide a specific example?”
- “What tools or strategies were particularly effective in this scenario?”
- “How did students respond to this method or technology?”
References
- UNESCO. Engineering for Sustainable Development: Delivering on the Sustainable Development Goals; UNESCO Publishing: Paris, France, 2021. [Google Scholar]
- UN-Habitat. World Cities Report 2022: Envisaging the Future of Cities; United Nations Human Settlements Programme: Nairobi, Kenya, 2022. [Google Scholar]
- Ukhurebor, K.E.; Egenti, G.; Uduehi, I. The role of continuous engineering and scientific education for sustainable development in Sub-Saharan Africa: Insights from Nigeria. J. Infrastruct. Policy Dev. 2025, 9, 8989. [Google Scholar] [CrossRef]
- African Development Bank. Skills for the Future: Engineering Education in Africa; AfDB Knowledge Series; African Development Bank: Abidjan, Cote D’Ivoire, 2023. [Google Scholar]
- World Bank. Democratic Republic of Congo: Building Human Capital for Sustainable Development; World Bank Group: Washington, DC, USA, 2023. [Google Scholar]
- African Union. Continental Education Strategy for Africa 2016–2025: Engineering Education Progress Report; AU Commission: Nairobi, Kenya, 2022. [Google Scholar]
- Kule, D.; Nzalalemba, T. Passive learning in African engineering education: Challenges and solutions. Afr. J. Eng. Educ. 2024, 15, 45–62. [Google Scholar]
- Wiek, A.; Withycombe, L.; Redman, C.L. Key competencies in sustainability: A reference framework for academic program development. Sustain. Sci. 2011, 6, 203–218. [Google Scholar] [CrossRef]
- Lozano, R.; Lukman, R.; Lozano, F.J.; Huisingh, D.; Lambrechts, W. Declarations for sustainability in higher education: Becoming better leaders, through addressing the university system. J. Clean. Prod. 2013, 48, 10–19. [Google Scholar] [CrossRef]
- Mathebula, M. Engineering Education for Sustainable Development: A Capabilities Approach; Routledge: London, UK, 2018. [Google Scholar]
- d’Escoffier, L.N.; Guerra, A.; Braga, M. Problem-Based Learning and Engineering Education for Sustainability: Where we are and where could we go? J. Probl. Based Learn. High. Educ. 2024, 12, 18–45. [Google Scholar] [CrossRef]
- Kelly, W.E. Engineering Education for Sustainable Development; Brief for the UN Global Sustainable Development Report; UN: New York, NY, USA, 2016. [Google Scholar]
- Hmelo-Silver, C.E. Problem-based learning: What and how do students learn? Educ. Psychol. Rev. 2004, 16, 235–266. [Google Scholar] [CrossRef]
- Mills, J.E.; Treagust, D.F. Engineering education—Is problem-based or project-based learning the answer? Australas. J. Eng. Educ. 2003, 3, 2–16. [Google Scholar]
- Strobel, J.; Van Barneveld, A. When is PBL more effective? A meta-synthesis of meta-analyses comparing PBL to conventional classrooms. Interdiscip. J. Probl.-Based Learn. 2009, 3, 44–58. [Google Scholar] [CrossRef]
- Kolmos, A.; De Graaff, E. Problem-Based and Project-Based Learning in Engineering Education. In Cambridge Handbook of Engineering Education Research; Cambridge University Press: Cambridge, UK, 2014; pp. 141–161. [Google Scholar]
- Dahms, M.-L.; Stentoft, D. Does Africa need Problem Based Learning? Educational Change in Engineering Education. Presented at American Society of Engineering Education (ASEE)–Global Colloquium, Cape Town, South Africa, 19–23 October 2008. [Google Scholar]
- Farahani, M.S.; Ghasmi, G. Artificial Intelligence in Education: A Comprehensive Study. Forum Educ. Stud. 2024, 2, 1379. [Google Scholar] [CrossRef]
- Zawacki-Richter, O.; Marín, V.I.; Bond, M.; Gouverneur, F. Systematic review of research on artificial intelligence applications in higher education. Int. J. Educ. Technol. High. Educ. 2019, 16, 39. [Google Scholar] [CrossRef]
- Holmes, W.; Bialik, M.; Fadel, C. Artificial Intelligence in Education: Promises and Implications for Teaching and Learning; Center for Curriculum Redesign: Boston, MA, USA, 2021. [Google Scholar]
- Prinsloo, P.; Slade, S. An elephant in the room: Educational data mining and learning analytics in African higher education. J. Learn. Anal. 2017, 4, 46–70. [Google Scholar]
- Adarkwah, M.A. “I’m not against online teaching, but what about us?”: ICT in Ghana post COVID-19. Educ. Inf. Technol. 2021, 26, 1665–1685. [Google Scholar] [CrossRef] [PubMed]
- Bryceland, M.; Thomas, S. Engineering education in developing countries: A systematic review. Int. J. Eng. Educ. 2021, 37, 892–908. [Google Scholar]
- Mohamedbhai, G. Engineering Education in Sub-Saharan Africa: Quest for Quality. Int. J. Afr. High. Educ. 2016, 2. [Google Scholar] [CrossRef]
- Muller, J. The future of knowledge and skills in science and technology higher education. High. Educ. 2015, 70, 409–416. [Google Scholar] [CrossRef]
- Braun, V.; Clarke, V. Using thematic analysis in psychology. Qual. Res. Psychol. 2006, 3, 77–101. [Google Scholar] [CrossRef]
- Kolb, D.A. Experiential Learning: Experience as the Source of Learning and Development; Prentice-Hall: Englewood Cliffs, NJ, USA, 1984. [Google Scholar]
- Vygotsky, L.S. Mind in Society: The Development of Higher PSYCHOLOGICAL Processes; Harvard University Press: Cambridge, MA, USA, 1978. [Google Scholar]
- Sterling, S. Transformative learning and sustainability: Sketching the conceptual ground. Learn. Teach. High. Educ. 2011, 5, 17–33. [Google Scholar]
- Schleiss, J.; Johri, A.; Stober, S. Integrating AI Education in Disciplinary Engineering Fields: Towards a System and Change Perspective. arXiv 2024, arXiv:2410.12795. [Google Scholar] [CrossRef]
- Bervell, B.; Mireku, D.; Dzamesi, P.; Nimo, E.; Andoh, R.; Segbenya, M. AI Acceptance and Usage in Sub-Sahara African Education: A Systematic Review. J. Advocacy Res. Educ. 2025, 5, 1–39. [Google Scholar]
- Empowering Students in Learning Engineering and Design: Ethical and Transformative Pedagogy for a Socially Conscious Future—ISLS Repository. Available online: https://repository.isls.org/bitstream/1/10854/1/ICLS2024_2029-2036.pdf (accessed on 27 September 2025).
Stage | Objective | Key Activities & Instructor Examples | Strategic AI Integration | Assessment Methods (Formative & Summative) |
---|---|---|---|---|
Stage 1: Problem Identification & Contextualization | Present real-world sustainability challenges relevant to the local context, connecting them to foundational scientific principles. | - Identify community-based problems related to SDGs (e.g., clean energy, sustainable housing) through engagement with local stakeholders. - Frame the problem: The instructor presents a real-world challenge, such as designing a semi-automatic system for making fired briquettes. - Brainstorming & Division: Students brainstorm and divide the macro-problem into manageable sub-problems for different teams (e.g., raw material research, mechanical design, electrical systems). | - AI-Powered Problem Databases: Use AI tools to search for and curate case studies and real-world engineering problems relevant to local SDG challenges. - Context Analysis Tools: Employ AI to analyze local data (e.g., environmental reports, community surveys) to help contextualize the problem. | - Formative: Group discussion participation; initial problem statement draft. - Summative: Finalized project proposal outlining the problem, scope, and objectives. |
Stage 2: Collaborative Investigation & Research | Develop research, analytical, and teamwork skills through guided and independent inquiry. | - Individual & Group Research: Students research existing systems, identify knowledge gaps, and explore theoretical concepts needed to solve their sub-problem. - Resource Consultation: Students consult academic papers, technical manuals, and online resources. They can also consult with experts, such as local craftsmen or industry professionals. - Deliverables: Teams submit study documents or research summaries to the instructor for feedback. | - Intelligent Research Assistants: Use AI tools like Elicit or Copilot to find, summarize, and synthesize relevant academic literature and technical documents. - Literature Analysis Tools: Employ AI to identify key themes, methods, and gaps in a body of research. | - Formative: Research journal entries; annotated bibliography; peer review of research summaries. - Summative: Comprehensive literature review and problem analysis report. |
Stage 3: Theoretical Foundation & Concept Mapping | Connect the practical problem to underlying scientific and engineering principles, bridging the theory-practice gap. | - Expert Input/Mini-Lectures: The instructor provides targeted lectures or “expert time” on complex concepts that students struggle with, directly addressing knowledge gaps identified during research. - Concept Mapping: Students create visual maps linking abstract theories (e.g., mechanics, electronics) to their practical application in the project. - Guided Discovery: The instructor acts as a facilitator, guiding students to discover theoretical principles for themselves rather than providing “recipes”. | - Adaptive Tutoring Systems: Use AI platforms that provide personalized exercises and explanations on foundational math and physics concepts based on student performance data. - Concept Visualization Tools: Employ AI to generate diagrams, simulations, or interactive models that help students visualize complex engineering principles. | - Formative: Quizzes on foundational concepts; concept map submissions; participation in problem-solving sessions. - Summative: Mid-project exam or presentation demonstrating mastery of relevant theoretical principles. |
Stage 4: Hands-on Experimentation & Prototyping | Apply theoretical knowledge through practical experimentation, simulation, and prototype development. | -Simulation: Students use Computer Aided-Design (CAD)/Computer Aided-Engineering(CAE) software (e.g., LTSpice 24.0.12, MATLAB/SIMULINK 24.2) to design, simulate, and verify their solutions before building physical prototypes. - Workshop Sessions: Students participate in hands-on workshops to learn practical skills (e.g., soldering, programming an Arduino) relevant to their project. - Prototyping: Teams build real or virtual prototypes of their sub-systems (e.g., a manual brick-making machine, an electronic display). - Integration: Teams meet regularly to integrate their sub-systems into a coherent final product. | - Simulation Tools: Leverage AI-enhanced simulation software (e.g., Ansys SimAI 2025 R2) to test complex systems and predict performance under various conditions. - AI-Assisted Coding: Use tools like GitHub Copilot (v1.104) to assist with programming tasks, with a focus on understanding, modifying, and debugging the generated code. - Data Analysis Assistance: Use AI to analyze experimental data, identify patterns, and visualize results. | - Formative: Lab notebook submissions; prototype demonstrations; code reviews. - Summative: A functional real or virtual prototype; a technical report detailing the design, testing, and validation process. |
Stage 5: Reflection, Assessment & Iteration | Consolidate learning through reflection, peer evaluation, and presentation of the final solution to a wider audience. | - Feedback & Iteration: The instructor and peers provide feedback, and teams may be asked to make corrections or improvements. - Self & Peer Assessment: Students reflect on their own learning process and the effectiveness of their team’s collaboration. - Sustainability Evaluation: Solutions are evaluated against sustainability criteria (environmental impact, social benefit, economic viability). | - Automated Feedback Systems: Use AI tools to provide initial feedback on written reports (e.g., for clarity, structure, plagiarism) or code (e.g., for efficiency, style). - Learning Analytics: Instructors use AI dashboards to track student progress and engagement throughout the project, identifying individuals or teams that may need additional support. | - Formative: Reflective essays or journal entries; peer evaluation of teamwork. - Summative: Final project presentation and demonstration; portfolio of work; final project report assessing the solution’s sustainability impact. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kazadi Tshikolu, R.; Kule Mukuhi, D.; Nzalalemba Kabwangala, T.; Ntiaka Muzakwene, J.; Sunda-Meya, A. AI-Enhanced Problem-Based Learning for Sustainable Engineering Education: The AIPLE Framework for Developing Countries. Sustainability 2025, 17, 9038. https://doi.org/10.3390/su17209038
Kazadi Tshikolu R, Kule Mukuhi D, Nzalalemba Kabwangala T, Ntiaka Muzakwene J, Sunda-Meya A. AI-Enhanced Problem-Based Learning for Sustainable Engineering Education: The AIPLE Framework for Developing Countries. Sustainability. 2025; 17(20):9038. https://doi.org/10.3390/su17209038
Chicago/Turabian StyleKazadi Tshikolu, Romain, David Kule Mukuhi, Tychique Nzalalemba Kabwangala, Jonathan Ntiaka Muzakwene, and Anderson Sunda-Meya. 2025. "AI-Enhanced Problem-Based Learning for Sustainable Engineering Education: The AIPLE Framework for Developing Countries" Sustainability 17, no. 20: 9038. https://doi.org/10.3390/su17209038
APA StyleKazadi Tshikolu, R., Kule Mukuhi, D., Nzalalemba Kabwangala, T., Ntiaka Muzakwene, J., & Sunda-Meya, A. (2025). AI-Enhanced Problem-Based Learning for Sustainable Engineering Education: The AIPLE Framework for Developing Countries. Sustainability, 17(20), 9038. https://doi.org/10.3390/su17209038