Computer Applications in Engineering Education最新文献

The rapid evolution of Industry 4.0 necessitates that engineering education equips students with skills that bridge traditional instrumentation and modern data-driven analytics. This paper addresses this need by presenting a comprehensive project-based learning module that fuses LabVIEW-based virtual instrumentation with machine learning (ML) for teaching industrial condition monitoring. Implemented in a senior-level undergraduate course, the module tasks student teams with diagnosing the health of an industrial fan. Using the NI ELVIS educational platform instrumented with an accelerometer, students acquire real-time vibration data. A key innovation is the seamless integration of LabVIEW, used for data acquisition and visualization, with a Python-based Convolutional Neural Network (CNN) model, which classifies the fan's condition (normal, minor, or severe malfunction) and rotational speed. The technical implementation achieved high classification accuracy (exceeding 95% on test data) and low inference latency (approximately 0.1 s), demonstrating the feasibility of real-time ML deployment. Pedagogically, the project provided an authentic, interdisciplinary learning experience, enhancing student understanding of vibration analysis, sensor integration, and the practical application of deep learning. The module successfully demonstrates a scalable framework for incorporating AI into engineering laboratories, effectively preparing students for roles that require synthesizing physical system knowledge with intelligent algorithm deployment.

Engineering education is a cornerstone of national development in the Maldives, driving technological progress and supporting essential infrastructure growth. However, the steady decline in student enrolment in engineering programs has become a growing concern. This research examines the key factors influencing students' interest in engineering by analyzing responses from students, faculty, and the public. Using data analysis techniques such as descriptive statistics, correlation, regression, and predictive modelling, a total of 48 factors were evaluated, of which 15 emerged as the most influential. These include financial support, career awareness, and the relevance of the curriculum to industry needs. The predictive model demonstrated strong reliability, achieving 75% accuracy, an F1-score of 80%, and an R² value of 0.89. The analysis showed that financial barriers (mean = 4.76 ± 0.98), limited awareness (95.6%), and insufficient industry exposure (87.6%) were the most significant challenges. Other issues, such as inadequate employer sponsorship, job market uncertainty, and gender imbalance, also contribute to low enrolment. Based on these insights, the research recommends introducing scholarship programs, updating curricula to reflect current industry standards, and strengthening collaboration between academia and employers. The findings offer practical guidance for policymakers to make engineering education in the Maldives more accessible, relevant, and capable of preparing a skilled workforce for future national needs.

Laboratories are essential to engineering education, yet traditional setups often face challenges such as limited accessibility for students with disabilities and constraints imposed by events like pandemics. To address these issues, this paper introduces an innovative remote laboratory platform to overcome these barriers. The platform integrates specialized control boards and hardware with advanced laboratory management software, offering a versatile and accessible educational tool. Its fault detection and control system ensures reliable operation while safeguarding both equipment and users from potential risks. The platform supports both in-person and remote access to laboratory resources, providing a cost-effective and high-precision alternative to conventional labs. Furthermore, it can be easily and swiftly implemented in existing traditional labs at a reasonable cost. This remote laboratory system enhances educational equity and operational flexibility, with practical applications in teaching, research, and industrial settings.

While retrieval-augmented generation (RAG) systems have substantially improved the factual accuracy of Large Language Models (LLMs) in educational contexts, they exhibit a fundamental limitation: an inability to adapt responses to a student's specific academic proficiency. This is a particularly critical gap in Artificial Intelligence (AI) education, where a learner's foundational knowledge in subjects like mathematics, programming, and core AI concepts exhibits significant heterogeneity. To address this, we introduce Personalized RAG for Education (PRAG-EDU), a novel context-aware RAG framework that dynamically calibrates response complexity by leveraging students' historical module grades as pedagogical signals. Unlike conventional RAG implementations that treat all learners uniformly, our model integrates these academic profiles with retrieved course materials to generate responses precisely tailored to individual proficiency levels. We establish the first benchmark for grade-aware educational RAG within the AI domain, comprising 250 expert-validated question-answer pairs linked to specific academic profiles and difficulty-calibrated reference responses. Through a rigorous evaluation of seven open-source LLMs against our framework, we demonstrate that PRAG-EDU achieves a 23.7% improvement in BERTScore F1 (0.555 vs. 0.451) and 18.3% higher ROUGE-L over non-personalized baselines. A qualitative analysis of 250 student evaluations further confirms its pedagogical efficacy, with expert raters awarding an average of 4.09/5 stars, significantly outperforming the next-best model (Qwen3:1.7B at 3.94). This work reveals a notable trade-off between factual alignment and generative fluency, as our method leads in accuracy while a model like Smollm2:1.7B excels in expressiveness. Ultimately, this research bridges the gap between technical RAG implementations and domain-specific educational theory by operationalizing academic performance data as a personalization mechanism, offering a scalable solution for heterogeneous AI engineering classrooms.

Cable accessories installation (CAI) education is a crucial component of practical teaching in the power engineering major. It aims to cultivate students' mastery of standardized installation procedures and operational skills, ensuring the safe and stable operation of the power system. Due to the traditional teaching of CAI mostly adopting the “apprenticeship” approach, which relies on on-site practical training and experience transmission for instruction, there are problems such as tight teaching resources and high operational risks in actual application, making it challenging to meet the urgent demand of modern engineering education for practical ability cultivation. Therefore, this paper constructs a virtual training system (VTS) for CAI. This system integrates virtual reality and 3D modeling technologies to realistically simulate the structure of cable accessories and the construction environment. It combines the cognitive characteristics and skill training requirements of CAI to create an integrated teaching framework based on the “demonstration—practice—examination—evaluation” approach. Finally, to verify the application effect of the system, 40 college students were invited to participate in the training experiment and were randomly divided into an experimental group and a control group. The experimental process included three stages: pre-test, training, and post-test. The results show that VTS had a comparable learning effect to the traditional teaching mode and demonstrated significant effectiveness in reducing cognitive load. Meanwhile, the system could stimulate students’ interest in professional knowledge during the training process, help them discover their strengths and abilities, and further enhance their initiative and enthusiasm for professional learning.

Manual grading of engineering drawing assignments is often time-consuming, inconsistent, and error-prone, particularly in large-scale engineering education. To address these challenges, we present “CAD-AG”, an automated grading system designed to evaluate two-dimensional engineering drawings exported from any CAD tool in DXF format. The system streamlines the grading process by comparing student submissions with a reference solution through geometric feature extraction and rule-based error detection. Key criteria assessed include shape accuracy, scale, alignment, and element completeness. Developed in Python and deployed via a web-based platform, CAD-AG enhances accessibility and usability. In testing with over 1000 student submissions, the system achieved 100% grading accuracy and significantly reduced average grading time. These results demonstrate the potential of automated grading to improve efficiency and consistency in engineering education, providing timely and objective feedback to support both instructors and learners.

Computational thinking (CT) and programming are essential competencies in the Fourth Industrial Revolution, spurring interest in learner-centered and artificial intelligence (AI)-based education. Combining the active environment of flipped learning with the personalized support of generative AI is a promising new strategy for programming education; however, research integrating these elements remains limited. This study investigated the effects of programming education that incorporates both flipped learning and generative AI on students' CT and problem-solving skills, with particular attention to variations by university size and educational setting. Participants were students enrolled in introductory software courses at two universities (K and J). Programming lessons integrating generative AI and flipped learning were developed, and changes in students' CT and problem-solving skills were evaluated using pre- and post-surveys and analyses of programming assignments. The study also examined the relationship between programming-related CT components (problem decomposition, abstraction, algorithm design, automation, and simulation) and students' programming difficulties, as well as key factors contributing to differences in learning outcomes between institutes. The results revealed significant improvements in the CT and problem-solving skills of students. Based on these findings, pedagogical strategies were proposed to optimize the use of generative AI and flipped learning in diverse educational contexts. This study provides valuable insights into the application of active, personalized learning in various settings, including introductory software education and online learning.