Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on the Hybrid Teaching Mode of Mechanical Fundamentals in the Context of Artificial Intelligence

Download as PDF

DOI: 10.23977/jaip.2024.070123 | Downloads: 9 | Views: 134


Zifeng Liu 1,2, Siyu Lu 2, Jiaxin Luo 2


1 College of Mechanical and Transportation Engineering, China University of Petroleum, Beijing, 102249, China
2 Engineering College, China University of Petroleum-Beijing at Karamay, Karamay, Xinjiang, 834000, China

Corresponding Author

Zifeng Liu


The purpose of this study is to explore the innovation and application of mechanical foundation teaching mode in the context of artificial intelligence, and to improve students' learning efficiency and understanding ability through a hybrid teaching mode, which combines online and offline teaching methods. In the experiment, by comparing and analyzing the differences between traditional teaching mode and blended teaching mode in student learning effectiveness, the superiority of blended teaching mode in mechanical foundation courses was obtained. At the same time, this study also pointed out the problems and solutions in the implementation of blended learning mode, providing strong theoretical support and practical guidance for the optimization of future teaching modes. In the experimental stage, we explored the effectiveness of Long Short Term Memory (LSTM), Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) in educational technology applications through four experiments. In the benchmark performance evaluation experiment, the accuracy based on the LSTM model was 75%, the recall was 80%, and the F1 score was 77%. In the second learning path recommendation effectiveness evaluation experiment, the LSTM model improved the average score of students by 15 points in recommending learning paths. In the evaluation experiment of improving learning motivation and participation, the learning motivation score based on the LSTM model was 90 points, and the participation score was 92 points. From the above experimental data conclusions, it can be seen that the LSTM model has great potential in educational technology applications, especially in designing personalized learning paths, improving learning motivation and engagement, and promoting long-term learning outcomes. 


Artificial Intelligence Education, Blended Teaching Mode, LSTM Model, Learning Motivation and Engagement


Zifeng Liu, Siyu Lu, Jiaxin Luo, Research on the Hybrid Teaching Mode of Mechanical Fundamentals in the Context of Artificial Intelligence. Journal of Artificial Intelligence Practice (2024) Vol. 7: 154-161. DOI:


[1] Liu Dong, Zhang Xiao, Mo Shuya. Exploring the Reform of Flipped Classroom Teaching Mode in Economic Law. Education Research, 2020, 3 (5): 87-88.
[2] Hu Chunyi, Li Jianhui, Hu Chunrong, et al. Construction of Flipped Classroom Teaching Model Based on OBE Concept: Taking the Course of "Microcomputer Principles and Interface Technology" as an Example. Internet of Things Technology, 2023, 13 (8): 159-162.
[3] Deng Hui. The Application of MOOC Perspective Teaching Model in Music Teaching - Taking "Flipped Classroom" as an Example. Education Research, 2023, 6 (3): 10-12.
[4] Mascaro D J, Mascaro S. An integrated project-driven course in computer programming for mechanical engineering students. Computers in Education Journal, 2016, 16(2):58-72.
[5] Gao S, Yanhua M A. Teaching Reform of Fundamentals of Combustion for Energy and Power Engineering Majors in Agricultural Colleges and Universities in the Context of New Engineering Course. Asian Agricultural Research, 2023, 15(11):46-49.
[6] Luo S Z. The Course Reform of Mechanical Design Fundamentals to Cultivate Engineering Literacy and Innovation Ability. Contemporary Education Research (Hundred Images), 2022, 6(7):6-11.
[7] Lv X, Sun Y, Chen G. Application of Blended Learning Model to Computer Fundamentals Courses in an Online Environment. Contemporary Education Research (Hundred Images), 2020, 004(007):P. 63-67.
[8] Piedade J. Teaching Programming Foundations and Computational Thinking with Educational Robotics: A Didactic Experience with Pre-service Teachers. Education Sciences, 2020, 10(214):1-15.
[9] Rui Xiaoguang, Liu Xinpei, Wang Chuanyang. Theory and Practice of Teaching Reform for Mechanical Fundamentals in Industrial Design. Mechanical Manufacturing and Automation, 2022, 51 (6): 40-44.
[10] Shu Xin. Practical Research on Innovative Education in the Teaching of Mechanical Fundamentals. Mold Manufacturing, 2023, 23 (8): 107-109.
[11] Li X, Wang S, Jiang Z, et al. Study on soil cracks in pneumatic subsoiling based on LSTM. Soil Use and Management, 2023, 39(1): 298-315.
[12] Li F. Creation of Deep Learning Scenarios in the Network Teaching of Physical Education Technical Courses. Scalable Computing: Practice and Experience, 2024, 25(1): 271-284.
[13] Bousnguar H, Najdi L, Battou A. Forecasting approaches in a higher education setting. Education and Information Technologies, 2022, 27(2): 1993-2011.
[14] Lee J, Lee N, Son J, et al. An LSTM model with optimal feature selection for predictions of tensile behavior and tensile failure of polymer matrix composites. Korean Journal of Chemical Engineering, 2023, 40(9): 2091-2101. 
[15] James Y. Teaching Methods of Power Mechanical Engineering Based on Artificial Intelligence. Kinetic Mechanical Engineering, 2022, 3(3): 54-61.

Downloads: 6729
Visits: 190307

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.