Prediction of Mechanical Properties of Synthetic Waste Reinforced Polyolefins with GA-LSTM Hybrid Model

Abstract

In this study, the effects of the production parameters used in injection molding of particle-reinforced thermoplastics on the product quality and mechanical properties of the produced part are modeled using an optimized Genetic Algorithm-Long Short Term Memory (GA-LSTM) hybrid deep learning method. Here, LDPE, HDPE, and PP, the most important members of the polyolefins group, were used as thermoplastics, while powdered synthetic paint wastes were evaluated as reinforcement elements. Using different parameters, 819 specimens were produced by injection molding, and mechanical tensile, three-point bending, and izod impact tests were performed on each specimen. The GA-LSTM model was trained with the parameters used and the results obtained during the experimental process, and the predicted values were determined to correspond to the actual values. Well-known methods were used to measure the success of the hybrid GA-LSTM model. The designed GA-LSTM model produced the best outcomes, according to the results attained.

Keywords

• Deep Learning
• Injection Molding
• Machine Learning
• Mechanical Properties
• Thermoplastic

Sentetik Atık Takviyeli Poliolefinlerin Mekanik Özelliklerinin GA-LSTM Hibrit Modeli ile Tahmini

Abstract

Bu çalışmada, parçacık takviyeli termoplastiklerin enjeksiyon kalıplamasında kullanılan üretim parametrelerinin ürün kalitesi ve üretilen parçanın mekanik özellikleri üzerindeki etkileri optimize edilmiş bir Genetik Algoritma-Uzun Kısa Süreli Bellek (GA-LSTM) hibrit derin öğrenme yöntemi kullanılarak modellenmiştir. Burada termoplastik olarak poliolefinler grubunun en önemli üyesi olan AYPE, YYPE ve PP kullanılırken takviye elemanı olarak ise toz halde sentetik boya atıkları kullanılmıştır. Farklı parametreler kullanılarak enjeksiyon kalıplama yoluyla 819 numune üretilmiş ve her numune üzerinde mekanik çekme, üç nokta eğme ve izod darbe testleri gerçekleştirilmiştir. GA-LSTM modeli, kullanılan parametreler ve deneysel süreç boyunca elde edilen sonuçlarla eğitilmiş ve tahmin edilen değerlerin gerçek değerlere karşılık geldiği belirlenmiştir. Hibrit GA-LSTM modelinin başarısını ölçmek için iyi bilinen yöntemler kullanılmıştır. Elde edilen sonuçlara göre tasarlanan GA-LSTM modeli en iyi sonuçları üretmiştir.

Keywords

• Derin Öğrenme
• Enjeksiyon Kalıplama
• Mekanik Özellikler
• Makine Öğrenmesi
• Termoplastik

References

1. REFERENCES
2. [1] Kaiser W. Polyolefine: Kunststoffchemie für Ingenieure, 4th ed.,Carl Hanser Verlag, München, Germany, 2016.
3. [2] Ravve A. Pronciples of Polymer Chemistry, Springer, New York, 2000.
4. [3] Gysau D. Füllstoffe, Vincentz Network GmbH, Hannover, Germany, 2006.
5. [4] Xanthos M. Functional Fillers for Plastics, Wiley-VCH, Hoboken, NJ, 2005.
6. [5] Jeyaprakash P, Moshi A.A.M., Rathinavel S., Babu A.G. Mechanical property analysis on powderized tamarind seed-palm natural fiber hybrid composites, Mater Today-Proc 43:1919–1923, 2020.
7. [6] Kısmet Y., Wagner M.H. Mechanical, thermal, and morphological properties of powder coating waste reinforced acetal copolymer, Polymer Testing 82 (106322), 2020.
8. [7] Michaeli W. Einführung in die Kunststoffverarbeitung, Verarbeitungsverfahren für die Kunststoffe, 5th ed., Carl Hanser Verlag, München Germany, 2006.

9. [8] Maulidina L.N., Atmaji F.T.D., Alhilman J. The proposed maintenance task for plastic injection machine using reliability and risk centered maintenance (RRCM) method in manufacturing industry, Computer, Mathematics and Engineering Applications, 10, 83-92, 2019.
10. [9] Habbal A., Ali M.K, Abuzaraida M.A. Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, applications, challenges and future research directions, Expert Systems with Applications 240:122442, 2024.
11. [10] Dwivedi Y.K., Pandey N., Currie W., Micu A. Leveraging ChatGPT and other generative artificial intelligence (AI)-based applications in the hospitality and tourism industry: practices, challenges and research agenda, International Journal of Contemporary Hospitality Management. 36 (1):1-12, 2024.
12. [11] Wang W., Wang H., Zhou J., Fan H., Liu X. Machine learning prediction of mechanical properties of braided-textile reinforced tubular structures, Materials & Design. 212:110181, 2021.
13. [12] Ogorodnyk O., Lyngstad O.V., Larsen M., Wang K., Martinsen K. Application of machine learning methods for prediction of parts quality in thermoplastics injection molding. Advanced Manufacturing and Automation VIII (pp.237-244), 2019.
14. [13] Ogorodnyk O. Towards Intelligent Process Control for Thermoplastics Injection Molding, Norwegian University of Science and Technology, Thesis PhD, 2021.
15. [14] Jayabal S., Rajamuneeswaran R., Ramprasath et al., Artificial Neural Network Modeling of Mechanical Properties of Calcium Carbonate Impregnated Coir-Polyester Composites. Transactions of the Indian Institute of Metals. 66 (3):247–255, 2013.
16. [15] Rout A.K., Satapathy A. Study on mechanical and tribo-performance of ricehusk filled glass–epoxy hybrid composites, Materials & Design. 41:131–141, 2012.
17. [16] Ahmed T., Sharma P., Karmaker C.L., Nasir S. Warpage prediction of Injection-molded PVC part using ensemble machine learning algorithm, Materials Today: Proceedings, 2020.
18. [17] Schulze Struchtrup A., Kvaktun D., Schiffers R. A holistic approach to part quality prediction in injection molding based on machine learning. In Advances in Polymer Processing 2020 (pp. 137-149). Springer Vieweg, Berlin, Heidelberg, 2020.
19. [18] Kiehas F., Reiter M., Torres J.P., Jerabek M., Major Z. Predicting Ductile-Brittle transition temperatures for polyolefins using convolutional neural networks and instrumented notched Charpy experiments, Polymer. 126797, 2024.
20. [19] Wu F.Y., Yin J., Chen S.C et al. Application of machine learning to reveal relationship between processing-structure-property for polypropylene injection molding, Polymer. 269:125736, 2023.
21. [20] Nasri K., Toubal L. Artificial Neural Network Approach for Assessing Mechanical Properties and Impact Performance of Natural-Fiber Composites Exposed to UV Radiation, Polymer. 16(4):538, 2024.
22. [21] Kumar S., Gopi T., Harikeerthana N., Gupta M.K., Gaur V., Krolczyk G.M., Wu C. Machine learning techniques in additive manufacturing: a state of the art review on design, processes and production control, Journal of Intelligent Manufacturing. 34(1):21-55, 2023.
23. [22] Herriott C., Spear A.D. Predicting microstructure-dependent mechanical properties in additively manufactured metals with machine-and deep-learning methods, Computational Materials Science. 175:109599, 2020.
24. [23] Wang J., Ma Y., Zhang L., Gao R.X., Wu D. Deep learning for smart manufacturing: Methods and applications, Journal of Manufacturing Systems. 48:144-156, 2018.
25. [24] Jumin E., Zaini N., Ahmed A.N et al. Machine learning versus linear regression modelling approach for accurate ozone concentrations prediction, Engineering Applications of Computational Fluid Mechanics. 14(1):713-725, 2020.
26. [25] Su X., Yan X., Tsai C.L. Linear regression, Wiley Interdisciplinary Reviews: Computational Statistics. 4(3):275-294, 2012.
27. [26] Utku, A., Akcayol, M. A. Neural Network Based a Comparative Analysis for Customer Churn Prediction. Muş Alparslan Üniversitesi Fen Bilimleri Dergisi, 12(1): 137-148, 2024.
28. [27] Pal M. Random forest classifier for remote sensing classification, International Journal of Remote Sensing. 26(1):217-222, 2005.
29. [28] Vapnik V. The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995.
30. [29] Drucker H., Burges C.J., Kaufman L,. Smola A., Vapnik V. Support vector regression machines. Advances In Neural İnformation Processing Systems. 9, 155-161, 1997.
31. [30] Najah A., El-Shafie A., Karim O.A., El-Shafie A.H. Application of artificial neural networks for water quality prediction, Neural Computing and Applications. 22(1):187-201, 2013.
32. [31] Guo Y., Liu Y., Oerlemans A., Lao S., Wu S., Lew M.S. Deep learning for visual understanding: A review, Neurocomputing. 187:27-48, 2016.
33. [32] Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network, Phys D: Nonlinear Phenom. 404:132306, 2020.
34. [33] Ackerson J.M., Dave R., Seliya N. Applications of recurrent neural network for biometric authentication & anomaly detection, Information. 12(7):272, 2021.
35. [34] Kuanar S., Athitsos V., Pradhan N., Mishra A., Rao K.R. Cognitive analysis of working memory load from EEG, by a deep recurrent neural network. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2576-2580). IEEE, 2018.
36. [35] Hochreiter S., Schmidhuber J. Long short-term memory, Neural Computation. 9(8):1735-1780, 1997. [36] Utku, A. Hindistan'daki Turistik Şehirlerin İklim Değişkenlerinin Tahminine Yönelik Hibrit ConvGRU Modeli. Mühendislik Bilimleri ve Araştırmaları Dergisi, 6(2): 165-176, 2024.
37. [37] Utku, A., Can, Ü., Kamal, M., Das, N., Cifuentes-Faura, J., Barut, A. A long short-term memory-based hybrid model optimized using a genetic algorithm for particulate matter 2.5 prediction. Atmospheric Pollution Research, 14(8), 2023.
38. [38] Goldberg D.E., Holland J.H. Genetic algorithms and machine learning. 3 (2): 95-99, 1988.
39. [39] Mirjalili S. Genetic algorithm. In Evolutionary algorithms and neural networks (pp. 43-55). Springer, Cham, 2019.
40. [40] Katoch S., Chauhan S.S., Kumar V. A review on genetic algorithm: past, present, and future, Multimedia Tools Application. 80(5):8091-8126, 2021.
41. [41] Slowik A., Kwasnicka H. Evolutionary algorithms and their applications to engineering problems, Neural Computing and Applications. 32(16):12363-12379, 2020.