The disassembly and assembly of marine oil-separators is a core experiment in marine engineering. To overcome the limitations of traditional physical disassembly and hands-on training, this study employs the implicit three-dimensional (3D) reconstruction theory. By utilizing a large dataset of high-definition images captured from specific angles and leveraging the Laplacian operator-based deep neural network Neural-Radiance-Field algorithm, high-precision 3D models of the oil separator body and its components are rapidly constructed. Subsequently, voxel rendering is performed, and finally, the Unity 3D is utilized to develop an immersive teaching and interactive virtual disassembly system for marine oil-separators. This system features high model accuracy, immersive experiences, and intelligent interactive operations. By serving as a supplementary tool to physical disassembly, the system adopts the Virtual-Object-Simulation teaching approach, combining virtual and physical elements, online and offline methods, and integrating classroom and extracurricular activities to reform existing experimental teaching methods. The practical results demonstrate that the reform of the course not only enhances students’ understanding of the oil separator’s functional principles, structure, and disassembly procedures, but also improves their knowledge integration and application skills, thereby strengthening both experimental and classroom teaching effectiveness.
Cite this paper
Huang, Z. , Wu, X. and Jing, C. (2026). The Immersive Teaching and Smart Interactive Training Platform for Virtual Simulation System in Educational Reform Application. Open Access Library Journal, 13, e14958. doi: http://dx.doi.org/10.4236/oalib.1114958.
Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R. and Srinivasan, P.P. (2021) Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 10-17 October 2021, 5835-5844. https://doi.org/10.1109/iccv48922.2021.00580
Wang, P., Liu, Y., Chen, Z., Liu, L., Liu, Z., Komura, T., et al. (2023) F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories. 2023 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 4150-4159. https://doi.org/10.1109/cvpr52729.2023.00404
Huang, X., Zhong, Z., Chen, S., Xu, Y., Guan, J. and Zhou, S. (2026) NeRF-MIR: Toward High-Quality Restoration of Masked Images with Neural Radiance Fields. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/tnnls.2026.3651302
Müller, T., Ev-ans, A., Schied, C. and Keller, A. (2022) Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. ACM Transactions on Graphics, 41, 1-15. https://doi.org/10.1145/3528223.3530127
Dewan, M.H., Godina, R., Chow-dhury, M.R.K., Noor, C.W.M., Wan Nik, W.M.N. and Man, M. (2023) Immersive and Non-Immersive Simulators for the Edu-cation and Training in Maritime Domain—A Review. Journal of Marine Science and Engineering, 11, Article 147. https://doi.org/10.3390/jmse11010147
Huang, X., Zhang, Q., Feng, Y., Li, H. and Wang, Q. (2024) LTM-NeRF: Em-bedding 3D Local Tone Mapping in HDR Neural Radiance Field. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 46, 10944-10959. https://doi.org/10.1109/tpami.2024.3448620
Wu, L., Zhu, H., Zheng, J., Li, M., Cheng, Y., Liu, Q., et al. (2024) Hi-NeRF: A Multicore Nerf Accelerator with Hierarchical Empty Space Skipping for Edge 3-D Rendering. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 32, 2315-2326. https://doi.org/10.1109/tvlsi.2024.3458032
Wang, H., Zeng, H., Ni, W.L., Jiang, D.Y. and Zhang, J.D. (2017) Ma-rine Auxiliary Disassembling Training System Based on Virtual Reality. Journal of Jiangsu University of Science and Tech-nology (Natural Science Edition), 31, 44-48.
Wang, S.W., Shen, Z.P., Zhang, N., Guo, C. and Wang, G.F. (2014) Simula-tion System of Fuel Oil Purifier for Large Container Ship. Navigation of China, 37, 15-19.
Shu, M. (2020) Research on Blending Teaching of Logistics Courses under the Background of Integration of Production and Education. Logistics Sci-Tech, 43, 169-170.