Frontier Materials & TechnologiesFrontier Materials & TechnologiesFrontier Materials & Technologies2782-40392782-6074Togliatti State University102910.18323/2782-4039-2025-1-71-8ArticlesСтатьиResearch ArticleMathematical modelling to predict the tensile strength of additively manufactured AlSi10Mg alloy using artificial neural networksМатематическая модель прогнозирования предела прочности сплава AlSi10Mg, изготовленного аддитивным способом, с использованием искусственных нейронных сетейhttps://orcid.org/0009-0005-2174-2067SrivastavaSunita K.ШриваставаСунита К.
India

researcher of Department of Mechanical Engineering

научный сотрудник кафедры машиностроения

sunita.shri45@gmail.comhttps://orcid.org/0000-0003-1903-2005MathivananN. RajeshМативананН. Раджеш
India

PhD, professor of Department of Mechanical Engineering

кандидат наук, профессор кафедры машиностроения

rajesh.mathivanan@pes.eduPES UniversityОбщественный университет народного просвещения310320251931103103202531032025Copyright ©; 2025, Srivastava S., Mathivanan N.Copyright ©; 2025, Шривастава С., Мативанан Н.2025Srivastava S., Mathivanan N.Шривастава С., Мативанан Н.https://creativecommons.org/licenses/by/4.0https://vektornaukitech.ru/jour/article/view/1029

Integrating machine learning in additive manufacturing to simulate real manufacturing outcomes can significantly reduce the cost of manufacturing through selective manufacturing. However, limited research exists on developing a prediction model for the mechanical properties of the material. The input variables include key selective laser melting process parameters such as laser power, layer thickness, scan speed, and hatch spacing, with tensile strength as the output. The artificial neural network (ANN) based mathematical model is compared with a second-degree polynomial regression model. The robustness of both models was further assessed with the new data points beyond those used in the development of ANN-based mathematical model and regression model. The results demonstrate that the proposed ANN-based mathematical model offers superior accuracy, with a mean absolute percentage error (MAPE) value of 4.74 % and the R2 (goodness of fit) value of 0.898 in predicting the strength of AlSi10Mg. The ANN-based mathematical method also demonstrates the strong performance on the new data, achieving a regression value of 0.68. This concludes that the model shows sufficient proof to consider a viable option for predicting the tensile strength.

Внедрение машинного обучения в аддитивное производство для моделирования реальных результатов может значительно снизить его стоимость за счет селективного производства. В настоящее время существует недостаточно исследований, посвященных разработке модели прогнозирования механических свойств материала. Входные переменные предложенной модели включали ключевые параметры процесса селективной лазерной плавки, такие как мощность лазера, толщина слоя, скорость сканирования и шаг штриховки, на выходе получая предел прочности. Математическая модель на основе искусственной нейронной сети сравнивалась с моделью полиномиальной регрессии второй степени. Надежность обеих моделей дополнительно оценивалась с новыми наборами данных, отличных от тех, которые использовались при разработке математической модели на основе искусственной нейронной сети и модели регрессии. Результаты показали, что предложенная математическая модель на основе искусственной нейронной сети обеспечивает превосходную точность: при прогнозировании прочности сплава AlSi10Mg среднее абсолютное процентное отклонение (MAPE) составило 4,74 %, критерий соответствия R2=0,898. Математический метод на основе искусственной нейронной сети также показал высокую производительность на новых данных – значение регрессии достигало 0,68. Таким образом, разработанную модель возможно рассматривать как перспективный вариант для прогнозирования предела прочности материала.

AlSi10Mg alloyadditive manufacturingartificial neural network (ANN)machine learningselective laser meltingmathematical modelсплав AlSi10Mgаддитивное производствоискусственная нейронная сеть (ИНС)машинное обучениеселективная лазерная плавкаматематическая модельRouf S., Malik A., Singh N., Raina A., Naveed N., Siddiqui M.I.H., Haq M.I.Ul. Additive manufacturing technologies: Industrial and medical applications. Sustainable Operations and Computers, 2022, vol. 3, pp. 258–274. DOI: 10.1016/j.susoc.2022.05.001.Rouf S., Malik A., Singh N., Raina A., Naveed N., Siddiqui M.I.H., Haq M.I.Ul. Additive manufacturing technologies: Industrial and medical applications // Sustainable Operations and Computers. 2022. Vol. 3. P. 258–274. DOI: 10.1016/j.susoc.2022.05.001.Sercombe T.B., Li X. Selective laser melting of aluminium and aluminium metal matrix composites: review. Materials Technology, 2016, vol. 31, no. 2, pp. 77–85. DOI: 10.1179/1753555715Y.0000000078.Sercombe T.B., Li X. Selective laser melting of aluminium and aluminium metal matrix composites: review // Materials Technology. 2016. Vol. 31. № 2. P. 77–85. DOI: 10.1179/1753555715Y.0000000078.Chowdhury S., Yadaiah N., Prakash Ch., Ramakrishna S., Dixit S., Gulta L.R., Buddhi D. Laser Powder Bed Fusion: A State-of-the-Art Review of the Technology, Materials, Properties & Defects, and Numerical Modelling. Journal of Materials Research and Technology, 2022, vol. 20, pp. 2109–2172. DOI: 10.1016/j.jmrt.2022.07.121.Chowdhury S., Yadaiah N., Prakash Ch., Ramakrishna S., Dixit S., Gulta L.R., Buddhi D. Laser Powder Bed Fusion: A State-of-the-Art Review of the Technology, Materials, Properties & Defects, and Numerical Modelling // Journal of Materials Research and Technology. 2022. Vol. 20. P. 2109–2172. DOI: 10.1016/j.jmrt.2022.07.121.Xu Yongjun, Liu Xin, Cao Xin et al. Artificial intelligence: A powerful paradigm for scientific research. The Innovation, 2021, vol. 2, no. 4, article number 100179. DOI: 10.1016/j.xinn.2021.100179.Xu Yongjun, Liu Xin, Cao Xin et al. Artificial intelligence: A powerful paradigm for scientific research // The Innovation. 2021. Vol. 2. № 4. Article number 100179. DOI: 10.1016/j.xinn.2021.100179.Osman E.-S., Aggour M.A. Artificial neural network model for accurate prediction of pressure drop in horizontal and near-horizontal-multiphase flow. Petroleum Science and Technology, 2002, vol. 20, no. 1-2, pp. 1–15. DOI: 10.1081/LFT-120002082.Osman E.-S., Aggour M.A. Artificial neural network model for accurate prediction of pressure drop in horizontal and near-horizontal-multiphase flow // Petroleum Science and Technology. 2002. Vol. 20. № 1-2. P. 1–15. DOI: 10.1081/LFT-120002082.Shubham P., Sharma A., Vishwakarma P.N., Phanden R.K. Predicting Strength of Selective Laser Melting 3D Printed AlSi10Mg Alloy Parts by Machine Learning Models. 8th International Conference on Signal Processing and Integrated Networks (SPIN). India, 2021, pp. 745–749. DOI: 10.1109/SPIN52536.2021.9566142.Shubham P., Sharma A., Vishwakarma P.N., Phanden R.K. Predicting Strength of Selective Laser Melting 3D Printed AlSi10Mg Alloy Parts by Machine Learning Models // 8th International Conference on Signal Processing and Integrated Networks (SPIN). India, 2021. P. 745–749. DOI: 10.1109/SPIN52536.2021.9566142.Ghetiya N.D., Patel K.M. Prediction of Tensile Strength in Friction Stir Welded Aluminium Alloy Using Artificial Neural Network. Procedia Technology, 2014, vol. 14, pp. 274–281. DOI: 10.1016/j.protcy.2014.08.036.Ghetiya N.D., Patel K.M. Prediction of Tensile Strength in Friction Stir Welded Aluminium Alloy Using Artificial Neural Network // Procedia Technology. 2014. Vol. 14. P. 274–281. DOI: 10.1016/j.protcy.2014.08.036.Khalefa M. Use of artificial neural network for prediction of mechanical properties of Al–Si alloys synthesized by stir casting. Journal of Petroleum and Mining Engineering, 2019, vol. 21, pp. 97–103. DOI: 10.21608/jpme.2019.13857.1004.Khalefa M. Use of artificial neural network for prediction of mechanical properties of Al–Si alloys synthesized by stir casting // Journal of Petroleum and Mining Engineering. 2019. Vol. 21. P. 97–103. DOI: 10.21608/jpme.2019.13857.1004.Alamri F., Maalouf M., Barsoum I. Prediction of Porosity, Hardness and Surface Roughness in Additive Manufactured AlSi10Mg Samples: preprint. 2023. DOI: 10.21203/rs.3.rs-3186551/v1.Lawal A.I., Aladejari A.E., Onifade M., Bada S., Idris M.A. Predictions of elemental composition of coal and biomass from their proximate analyses using ANFIS, ANN and MLR. International Journal of Coal Science and Technology, 2024, vol. 8, pp. 124–140. DOI: 10.1007/s40789-020-00346-9.Lawal A.I., Aladejari A.E., Onifade M., Bada S., Idris M.A. Predictions of elemental composition of coal and biomass from their proximate analyses using ANFIS, ANN and MLR // International Journal of Coal Science and Technology. 2024. Vol. 8. P. 124–140. DOI: 10.1007/s40789-020-00346-9.Owunna I., Ikpe A.E. Modelling and prediction of the mechanical properties of TIG welded joint for AISI 4130 low carbon steel plates using artificial neural network (ANN) approach. Nigerian Journal of Technology (NIJOTECH), 2019, vol. 38, no. 1, pp. 117–126. DOI: 10.4314/njt.v38i1.16.Owunna I., Ikpe A.E. Modelling and prediction of the mechanical properties of TIG welded joint for AISI 4130 low carbon steel plates using artificial neural network (ANN) approach // Nigerian Journal of Technology (NIJOTECH). 2019. Vol. 38. № 1. P. 117–126. DOI: 10.4314/njt.v38i1.16.Mahmoodi-Babolan N., Heydari A., Nematollahzadeh A. Removal of methylene blue via bioinspired catecholamine/starch superadsorbent and the efficiency prediction by response surface methodology and artificial neural network-particle swarm optimization. Bioresource Technology, 2019, vol. 294, article number 122084. DOI: 10.1016/j.biortech.2019.122084.Mahmoodi-Babolan N., Heydari A., Nematollahzadeh A. Removal of methylene blue via bioinspired catecholamine/starch superadsorbent and the efficiency prediction by response surface methodology and artificial neural network-particle swarm optimization // Bioresource Technology. 2019. Vol. 294. Article number 122084. DOI: 10.1016/j.biortech.2019.122084.Prasad M., Kempaiah U.N., Mohan R.M., Nagaral M. Microstructure, Tensile and Compression Behavior of AlSi10Mg Alloy Developed by Direct Metal Laser Sintering. Indian Journal of Science and Technology, 2021, vol. 14, no. 45, pp. 3346–3353. DOI: 10.17485/IJST/v14i45.1705.Prasad M., Kempaiah U.N., Mohan R.M., Nagaral M. Microstructure, Tensile and Compression Behavior of AlSi10Mg Alloy Developed by Direct Metal Laser Sintering // Indian Journal of Science and Technology. 2021. Vol. 14. № 45. P. 3346–3353. DOI: 10.17485/IJST/v14i45.1705.Zhuo Longchao, Wang Zeyu, Zhang Hongjia, Yin Enhuai, Wang Yanlin, Xu Tao, Li Chao. Effect of post-process heat treatment on microstructure and properties of selective laser melted AlSi10Mg alloy. Materials Letters, 2019, vol. 234, pp. 196–200. DOI: 10.1016/j.matlet.2018.09.109.Zhuo Longchao, Wang Zeyu, Zhang Hongjia, Yin Enhuai, Wang Yanlin, Xu Tao, Li Chao. Effect of post-process heat treatment on microstructure and properties of selective laser melted AlSi10Mg alloy // Materials Letters. 2019. Vol. 234. P. 196–200. DOI: 10.1016/j.matlet.2018.09.109.Mei Jiahe, Han Ying, Zu Guoqing, Zhu Weiwei, Zhao Yu, Chen Hua, Ran Xu. Achieving Superior Strength and Ductility of AlSi10Mg Alloy Fabricated by Selective Laser Melting with Large Laser Power and High Scanning Speed. Acta Metallurgica Sinica (English Letters), 2022, vol. 35, pp. 1665–1672. DOI: 10.1007/s40195-022-01410-w.Mei Jiahe, Han Ying, Zu Guoqing, Zhu Weiwei, Zhao Yu, Chen Hua, Ran Xu. Achieving Superior Strength and Ductility of AlSi10Mg Alloy Fabricated by Selective Laser Melting with Large Laser Power and High Scanning Speed // Acta Metallurgica Sinica (English Letters). 2022. Vol. 35. P. 1665–1672. DOI: 10.1007/s40195-022-01410-w.Zhou Suyuan, Su Yang, Gu Rui, Wang Zhenyu, Zhou Yinghao, Ma Qian, Yan Ming. Impacts of Defocusing Amount and Molten Pool Boundaries on Mechanical Properties and Microstructure of Selective Laser Melted AlSi10Mg. Materials, 2019, vol. 12, no. 1, article number 73. DOI: 10.3390/ma12010073.Zhou Suyuan, Su Yang, Gu Rui, Wang Zhenyu, Zhou Yinghao, Ma Qian, Yan Ming. Impacts of Defocusing Amount and Molten Pool Boundaries on Mechanical Properties and Microstructure of Selective Laser Melted AlSi10Mg // Materials. 2019. Vol. 12. № 1. Article number 73. DOI: 10.3390/ma12010073.Zhang Shuzhe, Wei Pei, Chen Zhen, Li Bobo, Huang Ke, Zou Yatong, Lu Bingheng. Graphene/ZrO2/aluminum alloy composite with enhanced strength and ductility fabricated by laser powder bed fusion. Journal of Alloys and Compounds, 2022, vol. 910, article number 164941. DOI: 10.1016/j.jallcom.2022.164941.Zhang Shuzhe, Wei Pei, Chen Zhen, Li Bobo, Huang Ke, Zou Yatong, Lu Bingheng. Graphene/ZrO2/aluminum alloy composite with enhanced strength and ductility fabricated by laser powder bed fusion // Journal of Alloys and Compounds. 2022. Vol. 910. Article number 164941. DOI: 10.1016/j.jallcom.2022.164941.Wei Pei, Chen Zhen, Zhang Shuzhe, Li Bobo, Han Jiang, Lu Bingheng. Microstructure and mechanical properties of graphene and nano-zirconia reinforced AlSi10Mg composite fabricated by laser powder bed fusion. Materials Science and Engineering: A, 2023, vol. 864, article number 144574. DOI: 10.1016/j.msea.2022.144574.Wei Pei, Chen Zhen, Zhang Shuzhe, Li Bobo, Han Jiang, Lu Bingheng. Microstructure and mechanical properties of graphene and nano-zirconia reinforced AlSi10Mg composite fabricated by laser powder bed fusion // Materials Science and Engineering: A. 2023. Vol. 864. Article number 144574. DOI: 10.1016/j.msea.2022.144574.Amor N., Noman M.T., Ismail A., Petru M., Sebastian N. Use of an Artificial Neural Network for Tensile Strength Prediction of Nano Titanium Dioxide Coated Cotton. Polymers, 2022, vol. 14, no. 5, article number 937. DOI: 10.3390/polym14050937.Amor N., Noman M.T., Ismail A., Petru M., Sebastian N. Use of an Artificial Neural Network for Tensile Strength Prediction of Nano Titanium Dioxide Coated Cotton // Polymers. 2022. Vol. 14. № 5. Article number 937. DOI: 10.3390/polym14050937.Khan A.Q., Awan H.A., Rasul M., Siddiqi Z.A., Pimanmas A. Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete. Cleaner Materials, 2023, vol. 10, article number 100211. DOI: 10.1016/j.clema.2023.100211.Khan A.Q., Awan H.A., Rasul M., Siddiqi Z.A., Pimanmas A. Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete // Cleaner Materials. 2023. Vol. 10. Article number 100211. DOI: 10.1016/j.clema.2023.100211.