Research Article
BibTex RIS Cite

Using Gray Wolf Algorithm for Raw Material Mix Ratio Optimization in Thermoplastic Hybrid Composites

Year 2022, Volume: 12 Issue: 2, 749 - 762, 15.12.2022
https://doi.org/10.31466/kfbd.1140989

Abstract

Difficulty in raw material supply and rapid consumption of natural resources have made it necessary to turn to composite production, which is an alternative method. Accordingly, there has been an increase in research and industrial use of composite materials in recent years. The main reasons for this are the difficulties in obtaining raw materials, the cost and time factor. On the other hand, another important reason why composites are preferred is that they have a higher strength-density ratio than other materials, they are more durable and lighter. Composite materials require high technology production in order to keep homogeneous structure, high quality, and production costs at an acceptable level. In the composite production stages, thermoplastic and filler reinforcement mixtures are applied with extremely complex processes. Optimizing such formulations requires a lot of experimental production but incurs high costs. As a result, it is essential to reduce these high costs and produce with optimized mixing ratios. In this study, the Gray Wolf Optimization algorithm (GWO), an artificial intelligence method was used as a solution. It has been observed that optimum production recipes and production process parameters can be obtained with the GWO algorithm. In order to produce hybrid thermoplastic composites, the raw material ratios in all possible mixtures were prepared in a simulation environment and the problem was tried to be solved with an approach based on finding the best solution, and it was aimed to produce the desired quality product for experimental use without the need for a large number of productions.

References

  • Balasubramanian, M. (2013). Composite Materials and Processing. Florida: CRC Press.
  • Bao, X., Wang, Z., Fu, D., Shi, C. , Iglesias, G., Cui, H., & Sun, Z. (2022). Machine learning methods for damage detection of thermoplastic composite pipes under noise conditions. Ocean Engineering, 110817248.
  • Chen, Z., Peng, S.-H., Meng, Y., Wang, R.-Y., Fu, Q., & Chen, T. (2022). Composite components damage tracking and dynamic structural behaviour with AI algorithm. Steel and Composite Structures, 42(2), 151-159.
  • Dönmez Çavdar, A., Mengeloğlu, F., Çavdar, T., Boran Torun, S., Avcı, B., & Öztürk, E. (2021). Yapay Zekâ Optimizasyon Tekniği ile Hibrit Kompozit Bileşenlerinin Optimizasyonu: Lignin / Zeolit / Doğal Lif Takviyeli Termoplastik Esaslı Hibrit Kompozit Örneği. Trabzon: TUBİTAK.
  • Dönmez Çavdar, A., Öztürk, E., & Çavdar, T. (2018). A Novel Approach to Determine the Amount of Natural Fiber and Polymer of Composite Materials via Artificial Neural Networks. International Conference on Artificial Intelligence and Data Processing (IDAP). Malatya.
  • Hastie, J., Kashtalyan, M., & Guz, I. (2019). Failure analysis of thermoplastic composite pipe (TCP) under combined pressure, tension and thermal gradient for an offshore riser application. International Journal of Pressure Vessels and Piping, 178, 103998.
  • Islam, F., Wanigasekara, C., Rajan, G., Swain, A., & Prusty, B. (2022). An approach for process optimisation of the Automated Fibre Placement (AFP) based thermoplastic composites manufacturing using Machine Learning, photonic sensing and thermo-mechanics modelling. Manufacturing Letters.
  • Karakaş, M., & Yüzgeç, U. (2019). Opposition based gray wolf algorithm for feature selection in classification problems. 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). IEEE.
  • Kirenci, Ü. (2021). Ocak 11, 2021 tarihinde https://acemimuhendis.com/2011/06/22/kompozit-malzeme-uretim-yontemleri/ adresinden alındı
  • Matthews, F. L., & Rawlings, R. D. (1999). Composite Materials: Engineering and Science. Florida: CRC Press.
  • Mech, L. (1999). Alpha status, dominance, and division of labor in wolf packs. Canadian journal of zoology, 77(8), 1196-1203.
  • Meyers, R. (2002). Encyclopedia of Physical Science and Technology. Academic.
  • Mirjalili, S. (2015). How effective is the Grey Wolf optimizer in training multi-layer perceptrons. Applied Intelligence, 43(1), 150-161.
  • Mirjalili, S., Mirjalili, S., & Lewis, A. (2014). Grey wolf optimizer. Advances in engineering software, 69, 46-61.
  • Muro, C., Escobedo, R., Spector, L., & Coppinger, R. (2011). Wolf-pack (Canis lupus) hunting strategies emerge from simple rules in computational simulations. Behavioural Processes, 88(3), 192-197.
  • Öztürk, E., Dönmez Çavdar, A., & Çavdar, T. (2021). Yusufçuk Algoritması ile Termoplastik Hibrit Kompozitlerin Üretiminde Katkı Maddeleri Oranlarının Optimizasyonu. 1.Uluslararası Yapay Zeka ve Veri Bilimi Kongresi. İzmir.
  • Öztürk, E., Dönmez Çavdar, A., Çavdar, T., & Mangeloğlu, F. (2021). Optimization of Hybrid Thermoplastic Composite Production via Artificial Intelligence Approach. Automotive Composites Conference and Exhibition (ACCE 2021). Michigan, USA.
  • Qiu, Y., Zhou, J., Khandelwal, M., Yang, H., Yang, P., & Li, C. (2021). Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Engineering with Computers, 1-18.
  • Shirmohammadi, M., Goushchi, S. J., & Keshtiban, P. M. (2021). Optimization of 3D printing process parameters to minimize surface roughness with hybrid artificial neural network model and particle swarm algorithm. Progress in Additive Manufacturing, 6(2), 199-215.
  • Trost, B. M. (2002). On inventing reactions for atom economy. Accounts of chemical research, 35(9), 695-705.
  • URL-1: https://www.mar-bal.com (Erişim Tarihi: 02.07.2022)
  • URL-2: https://tr.wikipedia.org (Erişim Tarihi: 01.07.2022)
  • URL-3: https://www.eurolab.com.tr (Erişim Tarihi: 03.07.2022)
  • URL-4: https://www.merriam-webster.com (Erişim Tarihi: 05.07.2022)
  • URL-5: https://huskyintelligence.com (Erişim Tarihi: 04.07.2022)
  • URL-6: https://byjus.com/maths/bisection-method/ (Erişim Tarihi: 04.07.2022)
  • URL-7: https://tr.wikipedia.org (Erişim Tarihi: 02.07.2022)
  • Xia, H., Shi, C., Wang, J., Bao, X., Li, H., & Fu, G. (2021). Effects of thickness and winding angle of reinforcement laminates on burst pressure capacity of thermoplastic composite pipes. Journal of Offshore Mechanics and Arctic Engineering, 143(5).
  • Zor, M. (2021). Kompozit Malzeme Mekaniği Ders Notları. Ocak 11, 2021 tarihinde http://mehmetzor.com/dersler/kompozit-malzeme-mekanigi/ders-notlari/ adresinden alındı

Termoplastik Hibrit Kompozitlerde Hammadde Karışım Oranı Optimizasyonu için Gri Kurt Algoritmasının Kullanılması

Year 2022, Volume: 12 Issue: 2, 749 - 762, 15.12.2022
https://doi.org/10.31466/kfbd.1140989

Abstract

Hammadde temininin zor olması ve doğal kaynakların hızla tüketilmesi alternatif bir yöntem olan kompozit üretimine yönelmeyi zorunlu hale getirmiştir. Bu nedenle son yıllarda kompozit malzemeler ile ilgili araştırmalarda ve endüstriyel kullanımda artışlar olmuştur. Bunun temel nedenleri hammadde teminindeki zorluklar, maliyet ve zaman faktörüdür. Diğer taraftan kompozitlerin tercih edilme nedenlerinden önemli bir sebep de diğer malzemelere göre mukavemet-yoğunluk oranının daha yüksek olması, daha dayanıklı ve daha hafif olmasıdır. Kompozit malzemelerin homojen yapısı, yüksek kalite ve üretim maliyetlerini kabul edilebilir seviyede tutabilmek için yüksek teknolojili üretim gerektirir. Kompozit üretim aşamalarında termoplastik ve dolgu takviye karışımları son derece karmaşık işlemlerle uygulanmaktadır. Bu tür formülasyonları optimize etmek çok fazla deneysel üretim gerektirir ancak yüksek maliyetler doğurur. Sonuç olarak, bu yüksek maliyetleri azaltmak ve optimize edilmiş karışım oranları ile üretim yapmak elzemdir. Bu çalışmada çözüm olarak bir yapay zekâ yöntemi olan Gri Kurt optimizasyon algoritması (GWO) kullanılmıştır. GWO algoritması ile optimum üretim reçetelerinin ve üretim proses parametrelerinin elde edilebildiği gözlemlenmiştir. Hibrit termoplastik kompozitlerin üretilebilmesi için olası tüm karışımlardaki hammadde oranları simülasyon ortamında hazırlanarak en iyi çözümü bulmaya dayalı bir yaklaşımla problem çözülmeye çalışılmış, deneysel kullanım için çok sayıda üretime gerek kalmadan istenilen kalitede ürün üretilmesi hedeflenmiştir.

References

  • Balasubramanian, M. (2013). Composite Materials and Processing. Florida: CRC Press.
  • Bao, X., Wang, Z., Fu, D., Shi, C. , Iglesias, G., Cui, H., & Sun, Z. (2022). Machine learning methods for damage detection of thermoplastic composite pipes under noise conditions. Ocean Engineering, 110817248.
  • Chen, Z., Peng, S.-H., Meng, Y., Wang, R.-Y., Fu, Q., & Chen, T. (2022). Composite components damage tracking and dynamic structural behaviour with AI algorithm. Steel and Composite Structures, 42(2), 151-159.
  • Dönmez Çavdar, A., Mengeloğlu, F., Çavdar, T., Boran Torun, S., Avcı, B., & Öztürk, E. (2021). Yapay Zekâ Optimizasyon Tekniği ile Hibrit Kompozit Bileşenlerinin Optimizasyonu: Lignin / Zeolit / Doğal Lif Takviyeli Termoplastik Esaslı Hibrit Kompozit Örneği. Trabzon: TUBİTAK.
  • Dönmez Çavdar, A., Öztürk, E., & Çavdar, T. (2018). A Novel Approach to Determine the Amount of Natural Fiber and Polymer of Composite Materials via Artificial Neural Networks. International Conference on Artificial Intelligence and Data Processing (IDAP). Malatya.
  • Hastie, J., Kashtalyan, M., & Guz, I. (2019). Failure analysis of thermoplastic composite pipe (TCP) under combined pressure, tension and thermal gradient for an offshore riser application. International Journal of Pressure Vessels and Piping, 178, 103998.
  • Islam, F., Wanigasekara, C., Rajan, G., Swain, A., & Prusty, B. (2022). An approach for process optimisation of the Automated Fibre Placement (AFP) based thermoplastic composites manufacturing using Machine Learning, photonic sensing and thermo-mechanics modelling. Manufacturing Letters.
  • Karakaş, M., & Yüzgeç, U. (2019). Opposition based gray wolf algorithm for feature selection in classification problems. 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). IEEE.
  • Kirenci, Ü. (2021). Ocak 11, 2021 tarihinde https://acemimuhendis.com/2011/06/22/kompozit-malzeme-uretim-yontemleri/ adresinden alındı
  • Matthews, F. L., & Rawlings, R. D. (1999). Composite Materials: Engineering and Science. Florida: CRC Press.
  • Mech, L. (1999). Alpha status, dominance, and division of labor in wolf packs. Canadian journal of zoology, 77(8), 1196-1203.
  • Meyers, R. (2002). Encyclopedia of Physical Science and Technology. Academic.
  • Mirjalili, S. (2015). How effective is the Grey Wolf optimizer in training multi-layer perceptrons. Applied Intelligence, 43(1), 150-161.
  • Mirjalili, S., Mirjalili, S., & Lewis, A. (2014). Grey wolf optimizer. Advances in engineering software, 69, 46-61.
  • Muro, C., Escobedo, R., Spector, L., & Coppinger, R. (2011). Wolf-pack (Canis lupus) hunting strategies emerge from simple rules in computational simulations. Behavioural Processes, 88(3), 192-197.
  • Öztürk, E., Dönmez Çavdar, A., & Çavdar, T. (2021). Yusufçuk Algoritması ile Termoplastik Hibrit Kompozitlerin Üretiminde Katkı Maddeleri Oranlarının Optimizasyonu. 1.Uluslararası Yapay Zeka ve Veri Bilimi Kongresi. İzmir.
  • Öztürk, E., Dönmez Çavdar, A., Çavdar, T., & Mangeloğlu, F. (2021). Optimization of Hybrid Thermoplastic Composite Production via Artificial Intelligence Approach. Automotive Composites Conference and Exhibition (ACCE 2021). Michigan, USA.
  • Qiu, Y., Zhou, J., Khandelwal, M., Yang, H., Yang, P., & Li, C. (2021). Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Engineering with Computers, 1-18.
  • Shirmohammadi, M., Goushchi, S. J., & Keshtiban, P. M. (2021). Optimization of 3D printing process parameters to minimize surface roughness with hybrid artificial neural network model and particle swarm algorithm. Progress in Additive Manufacturing, 6(2), 199-215.
  • Trost, B. M. (2002). On inventing reactions for atom economy. Accounts of chemical research, 35(9), 695-705.
  • URL-1: https://www.mar-bal.com (Erişim Tarihi: 02.07.2022)
  • URL-2: https://tr.wikipedia.org (Erişim Tarihi: 01.07.2022)
  • URL-3: https://www.eurolab.com.tr (Erişim Tarihi: 03.07.2022)
  • URL-4: https://www.merriam-webster.com (Erişim Tarihi: 05.07.2022)
  • URL-5: https://huskyintelligence.com (Erişim Tarihi: 04.07.2022)
  • URL-6: https://byjus.com/maths/bisection-method/ (Erişim Tarihi: 04.07.2022)
  • URL-7: https://tr.wikipedia.org (Erişim Tarihi: 02.07.2022)
  • Xia, H., Shi, C., Wang, J., Bao, X., Li, H., & Fu, G. (2021). Effects of thickness and winding angle of reinforcement laminates on burst pressure capacity of thermoplastic composite pipes. Journal of Offshore Mechanics and Arctic Engineering, 143(5).
  • Zor, M. (2021). Kompozit Malzeme Mekaniği Ders Notları. Ocak 11, 2021 tarihinde http://mehmetzor.com/dersler/kompozit-malzeme-mekanigi/ders-notlari/ adresinden alındı
There are 29 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Tuğrul Çavdar 0000-0003-3656-9592

Ercüment Öztürk 0000-0001-9623-6955

Publication Date December 15, 2022
Published in Issue Year 2022 Volume: 12 Issue: 2

Cite

APA Çavdar, T., & Öztürk, E. (2022). Termoplastik Hibrit Kompozitlerde Hammadde Karışım Oranı Optimizasyonu için Gri Kurt Algoritmasının Kullanılması. Karadeniz Fen Bilimleri Dergisi, 12(2), 749-762. https://doi.org/10.31466/kfbd.1140989