ТЕРЕҢ НЕЙРОНДЫҚ ЖЕЛІЛЕР ПЛАСТИКАЛЫҚ ҚАЛДЫҚТАРДЫ СҰРЫПТАУ ТИІМДІЛІГІН АРТТЫРУ ҚҰРАЛЫ РЕТІНДЕ

Қайта өңдеу өнеркәсібінде сапалы сұрыпталған материалға шұғыл қажеттілік туындауда. Сұрыптау орталықтарының мәселесі ретінде пластмассаны сұрыптау және тазалау қиындықтарына байланысты қалдықтар, қайта өңдеудің орнына полигондарда жиналуда. Бұл тиімді автоматтандырылған сұрыптау әдістерін дамыту қажеттілігін көрсетеді. Осы зерттеу жұмысы MobileNet, ResNet және EfficientNet сияқты архитектураларды қолдана отырып, конволюциялық нейрондық желіге (CNN) негізделген пластмассаларды жіктеудің интеллектуалды моделін ұсынады. Модельдер пластиктің бес санатына бөлінген 4000-нан астам кескіннен тұратын деректер жиынтығында оқытылды. Сыналған архитектуралардың ішінде EfficientNetSED классификацияның ең жоғары дәлдігін көрсетті – 99,1%, бұл осы саладағы алдыңғы зерттеулердің нәтижелеріне сәйкес келеді. Бұл нәтижелер пластикті қайта өңдеу процестерінің тиімділігін арттыру үшін жетілдірілген CNN архитектураларын пайдалану әлеуетін көрсетеді.

1. Waste management. The official site of the Ministry of Ecology and Natural Resources of the Republic of Kazakhstan. Application date: 08.03.2024. [electronic resource] URL: https://www.gov.kz/memleket/entities/ecogeo/activities/14791?lang=ru&parentId=14790.

2. Mannheim V. Life Cycle Assessment Model of Plastic Products: Comparing Environmental Impacts for Different Scenarios in the Production Stage. Polymers 2021, vol. 13, p. 777. https://doi.org/10.3390/polym13050777.

3. Antonis Vlasopoulos, Jurgita Malinauskaite, Alina Żabnieńska-Góra, Hussam Jouhara. Life cycle assessment of plastic waste and energy recovery. Energy, 2023, vol. 277, p. 127576. ISSN 0360-5442, https://doi.org/10.1016/j.energy.2023.127576.

4. Powerful optical sorting technologies, artificial intelligence and robotics reduce contamination for recycling operations. [electronic resources]. URL: https://www.recyclingproductnews.com/article/34294/powerful-optical-sorting-technologies-artificial-intelligence-and-robotics-reduce-contamination-forrecycling-operations.

5. Masoumi H., Safavi S.M., & Khani Z. Identification and classification of plastic resins using near infrared reflectance spectroscopy. International Journal of Mechanical and Industrial Engineering, 2012, no 6, pp. 213–220.

6. Wu X., Li J., Yao L., & Xu Z. Auto-sorting commonly recovered plastics from waste household appliances and electronics using near-infrared spectroscopy. Journal of Cleaner Production, 2020, 246, p. 118732. https://doi.org/10.1016/j.jclepro.2019.118732.

7. Zheng Y., Bai J., Xu J., Li X., & Zhang Y. A discrimination model in waste plastics sorting using NIR hyperspectral imaging system. Waste Management, 2018, no. 72, pp. 87–98. https://doi.org/10.1016/j.wasman.2017.10.015.

8. Zhu S., Chen H., Wang M., Guo X., Lei Y., & Jin G. Plastic solid waste identification system based on near infrared spectroscopy in combination with support vector machine. Advanced Industrial and Engineering Polymer Research, 2019, vol. 2, pp. 77–81.

9. Carrera B., Pinol V.L., Mata J.B., & Kim K. A machine learning based classification models for plastic recycling using different wavelength range spectrums. Journal of Cleaner Production, 2022, vol. 374, p. 133883.

10. Choi J., Lim B., & Yoo Y. Advancing plastic waste classification and recycling efficiency: Integrating image sensors and deep learning algorithms. Applied Sciences, 2023, vol. 13, no. 18, p. 10224. https://doi.org/10.3390/app131810224.

11. Abdallah N., Burhan R.H., Ali T., Alrehaili A., & Toqeer S. An ensemble learning based classification approach for the prediction of household solid waste generation. Sensors, 2022, vol. 22, no. 9, p. 3506. https://doi.org/10.3390/s22093506.

12. Kumar S., Yadav D., Gupta H., Verma O.P., Ansari I.A., & Ahn C.W. A novel YOLOv3 algorithmbased deep learning approach for waste segregation: Towards smart waste management. Electronics, 2021, vol. 10, no. 1, p. 14. https://doi.org/10.3390/electronics10010014.

13. Bobulski J., & Kubanek M. Deep learning for plastic waste classification system. Applied Computational Intelligence and Soft Computing, 2021, Article ID 6626948. https://doi.org/10.1155/2021/6626948.

14. Chowdhury S.S., Hossain N.B., Saha T., Ferdous J., & Zishan M.S.R. The design and implementation of an autonomous waste sorting machine using machine learning technique. AJSE, 2021, vol. 19, no. 3, pp. 134–142. https://doi.org/10.53799/ajse.v19i3.104.

15. Olowolayemo A., Ahmad Radzi N.I., & Ismail N.F. Classifying Plastic Waste Using Deep Convolutional Neural Networks for Efficient Plastic Waste Management. International Journal on Perceptive and Cognitive Computing, 2022, vol. 8, no. 2, pp. 6–15. Retrieved from https://journals.iium.edu.my/kict/index.php/IJPCC/article/view/282.

16. Cheema S.M., Hannan A., & Pires I.M. Smart waste management and classification systems using cutting edge approach. Sustainability, 2022, vol. 14, no. 16, p.10226. https://doi.org/10.3390/su141610226.

17. Ziouzios D., Baras N., Balafas V., Dasygenis M., & Stimoniaris A. Intelligent and real-time detection and classification algorithm for recycled materials using convolutional neural networks. Recycling, 2022, vol. 7, no. 1, p. 9. https://doi.org/10.3390/recycling7010009.

18. Howard A.G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., Andreetto M., & Adam H. MobileNets: Efficient convolutional networks for mobile vision applications. arXiv:1704.04861, 2017.

19. He K., Zhang X., Ren S., & Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

20. Tan M., & Le Q.V. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning, 2019, vol. 97, pp. 6105–6114.

21. Patrizi A., Gambosi G. & Zanzotto F.M. Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste. J. Imaging, 2021, vol. 7, p. 144. https://doi.org/10.3390/jimaging7080144.

22. Sunardi, Yudhana A., & Fahmi M. Improving waste classification using convolutional neural networks: An application of machine learning for effective environmental management. Revue d'Intelligence Artificielle, 2023, vol. 37, no. 4, pp. 845–855. https://doi.org/10.18280/ria.370404.

23. Cai Z., Yang J., Fang H., Ji T., Hu Y. & Wang X. Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion. Sensors. 2022, vol. 22, no. 20, p. 7974. https://doi.org/10.3390/s22207974.

24. Zheng D., Wang R., Duan Y., Pang Ch.P. & Pan T. Focus-RCNet: a lightweight recyclable waste classification algorithm based on focus and knowledge distillation. Vis. Comput. Ind. Biomed. 2023, Art 6, 19. https://doi.org/10.1186/s42492-023-00146-3.