Hybrid Pedagogical Strategies in Mechanical Engineering: Skill Assessment through Simulation and Project Based Learning with Machine Learning

Abstract

The effectiveness of the proposed framework was evaluated through Course Outcome (CO) and Program Outcome (PO) attainment analysis, performance-based assessment rubrics, and machine learning classification models. The results demonstrated improved attainment of key COs and POs related to problem-solving, system design, teamwork, and communication skills. Feature importance analysis identified design innovation, code accuracy, and teamwork efficiency as the most influential indicators of student competency. Furthermore, Artificial Neural Network (ANN), Random Forest (RF), and Extra Trees (ET) models successfully classified students into four skill categories, providing an objective mechanism for competency assessment. The findings indicate that the integration of SBL and PBL not only enhances technical and professional skill development but also contributes significantly to outcome attainment in engineering education. The proposed framework offers a scalable approach for competency-based learning, assessment, and continuous improvement in accordance with Outcome-Based Education principles.