Ultrases dalga hızının tahmininde farklı makine öğrenimi yöntemlerinin karşılaştırılması

Year 2024, , 510 - 525, 15.06.2024

Serhat Demirhan , Necim Kaya , Selahattin Akalp

https://doi.org/10.17714/gumusfenbil.1362940

Abstract

Deneysel sonuçlardan elde edilen basınç dayanımı sonuçlarına bağlı olarak ultrases dalgası hızı sonuçlarının tahmin edilmesi amacıyla, farklı oranlarda mineral katkı içeren on iki (12) farklı çimento harcı üretilmiştir. Üretilen harç numunelerinin 1, 3, 7, 28 ve 90 günlük kür yaşları için hem basınç dayanımı hem de ultrases dalgası hızı sonuçları deneysel olarak elde edilmiştir. Farklı kür koşulları için harç numunelerinden elde edilen basınç dayanımı deneysel verileri Aşırı Öğrenme Makinesi, Destek Vektör Makinesi ve Grup Veri İşleme Yöntemi olmak üzere üç farklı regresyon yöntemi kullanılarak ultrases dalgası hızı değerlerinin tahmininde kullanılmıştır. Regresyon yöntemlerinin uygulanmasında iki farklı yaklaşım izlenmiştir. İlk yaklaşımda, farklı kür yaşları için ultrases dalgası hızı sonuçları, basınç dayanımı değerleri göz ardı edilerek tahmin edilmiştir. Diğer yaklaşımda ise ultrases dalgası hızı sonuçlarını tahmin etmek için basınç dayanımı değerleri dikkate alınmıştır. Böylece hem basınç dayanımı hem de ultrases dalgası hızı değerleri ile regresyon modelleri ile elde edilen başarı sonuçları arasındaki ilişki belirlenip, karşılaştırılmıştır. Bu çalışmada, Yöntem 1'deki Grup Veri İşleme Yöntemi modeli ile en iyi test performansları (yani R2 ve MSE için) sırasıyla 0.856 ve 0.037; Yöntem 2'de ise Grup Veri İşleme Yöntemi modeli ile en iyi test performansları sırasıyla 0.977 ve 0.003 olarak bulunmuştur. Elde edilen sonuçlar dikkate alındığında, ultrases dalgası hızı değerleri seçilen regresyon modelleri ile yüksek başarı oranlarıyla elde edilmiştir.

Keywords

Basınç dayanımı, Regresyon, Ultrases dalga hızı

Ethical Statement

Bu çalışmada, “Yükseköğretim Kurumları Bilimsel Araştırma ve Yayın Etiği Yönergesi” kapsamında uyulması gerekli tüm kurallara uyulduğunu, bahsi geçen yönergenin “Bilimsel Araştırma ve Yayın Etiğine Aykırı Eylemler” başlığı altında belirtilen eylemlerden hiçbirinin gerçekleştirilmediğini taahhüt ederiz.

Comparison of different machine learning methods for prediction of ultrasonic pulse velocity

Abstract

In order to predict the ultrasonic pulse velocity results based on the compressive strength results obtained from the experimental results, twelve (12) different cement mortars including mineral admixtures with different proportions were cast. Five curing ages of 1, 3, 7, 28, and 90 days were chosen in order to obtain experimental testing results of compressive strength and ultrasonic pulse velocity. Ultrasonic pulse velocity values have been estimated with regression methods developed via the experimental results of Compressive strength by using Extreme Learning Machine, Support Vector Machine and Group Method of Data Handling. Two distinct approaches were employed for each regression method. In Method 1, ultrasonic pulse velocity values were estimated without compressive strength test results. In Method 2, ultrasonic pulse velocity values were estimated using the compressive strength results. Hereby, first experimental test results of compressive strength and ultrasonic pulse velocity were determined and then estimated results of compressive strength and ultrasonic pulse velocity via regression models were compared in terms of success rate of regression models. When evaluating the performance, the Group Method of Data Handling model achieved the highest test performance among the approaches used in Method 1 and the results for R2 and MSE were 0.856 and 0.037, respectively. In Method 2, the best test performance was achieved with the Group Method of Data Handling model, while the results for R2 and MSE were 0.977 and 0.003, respectively. It has been revealed that the selected regression models have achieved high success in estimating ultrasonic pulse velocity (with/without considering compressive strength).

Keywords

Compressive strength, Regression, Ultrasonic pulse velocity

References

• Atici, U. (2011). Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network. Expert Systems with applications, 38(8), 9609-9618. https://doi.org/1016/j.eswa.2011.01.156
• Ciftci, M., & Demirhan, S. (2021). Effect of nano type and slag replacement level on cement mortars. Gumushane University Journal of Science Institute, 11(2), 482-496. https://doi.org/10.17714/gumusfenbil.867858
• Çalışkan, A., Demirhan, S., & Tekin, R. (2022). Comparison of different machine learning methods for estimating compressive strength of mortars. Construction and Building Materials, 335, 127490. https://doi.org/10.1016/j.conbuildmat.2022.127490
• Ding, S., Zhao, H., Zhang, Y., Xu, X., & Nie, R. (2015). Extreme learning machine: algorithm, theory and applications. Artificial Intelligence Review, 44(1), 103-115. https://doi.org/10.1007/s10462-013-9405-z
• Demirhan, S. (2020). Combined Effects of Nano-Sized Calcite and Fly Ash on Hydration and Microstructural Properties of Mortars. Afyon Kocatepe University Journal of Science and Engineering Sciences, 20(6), 1051-1067. https://doi.org/10.35414/akufemubid.825862
• Fung, G. M., & Mangasarian, O. L. (2005). Multicategory proximal support vector machine classifiers. Machine learning, 59(1-2), 77-97. https://doi.org/10.1007/s10994-005-0463-6
• GÜLTEKİN, N., & DOĞAN, A. (2023). Makine Öğrenimi Yöntemleriyle Bazaltlarda Tek Eksenli Sıkışma Dayanımının Değerlendirilmesi ve Performanslarının Karşılaştırılması. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11(2), 1059-1074. https://doi.org/10.29130/dubited.1173624 Gültekin, N., & Doğan, A. (2022). Kohezyonlu zeminlerde net limit basınç ve deformasyon modülünün makine öğrenimi temelli modeller kullanılarak tahmin edilmesi. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 11(4), 1025-1033. https://doi.org/10.28948/ngumuh.1155568
• Ghosh, R., Sagar, S. P., Kumar, A., Gupta, S. K., & Kumar, S. (2018). Estimation of geopolymer concrete strength from ultrasonic pulse velocity (UPV) using high power pulser. Journal of building engineering, 16, 39-44. https://doi.org/10.1016/j.jobe.2017.12.009
• Hamidian, M., Shariati, A., Khanouki, M. A., Sinaei, H., Toghroli, A., & Nouri, K. (2012). Application of Schmidt rebound hammer and ultrasonic pulse velocity techniques for structural health monitoring. Scientific Research and Essays, 7(21), 1997-2001. https://doi.org/10.5897/SRE11.1387
• Hammoudi, A., Moussaceb, K., Belebchouche, C., & Dahmoune, F. (2019). Comparison of artificial neural network (YSA) and response surface methodology (RSM) prediction in compressive strength of recycled concrete aggregates. Construction and Building Materials, 209, 425-436. https://doi.org/10.1016/j.conbuildmat.2019.03.119
• Hong, G., Oh, S., Choi, S., Chin, W. J., Kim, Y. J., & Song, C. (2021). Correlation between the Compressive Strength and Ultrasonic Pulse Velocity of Cement Mortars Blended with Silica Fume: An Analysis of Microstructure and Hydration Kinetics. Materials, 14(10), 2476. https://doi.org/10.3390/ma14102476
• Hosseinpour, M., Sharifi, H., & Sharifi, Y. (2018). Stepwise regression modeling for compressive strength assessment of mortar containing metakaolin. International Journal of Modelling and Simulation, 38(4), 207-215. https://doi.org/10.1080/02286203.2017.1422096
• Kostić, S., & Vasović, D. (2015). Prediction model for compressive strength of basic concrete mixture using artificial neural networks. Neural Computing and Applications, 26(5), 1005-1024. https://doi.org/10.1007/s00521-014-1763-1
• Lee, S., Nguyen, N. H., Karamanli, A., Lee, J., & Vo, T. P. (2023). Super learner machine‐learning algorithms for compressive strength prediction of high performance concrete. Structural Concrete, 24(2), 2208-2228.
• Li, D., Tang, Z., Kang, Q., Zhang, X., & Li, Y. (2023). Machine Learning-Based Method for Predicting Compressive Strength of Concrete. Processes, 11(2), 390. https://doi.org/10.3390/pr11020390
• Ling, H., Qian, C., Kang, W., Liang, C., & Chen, H. (2019). Combination of support vector machine and K-fold cross validation to predict compressive strength of concrete in marine environment. Construction and Building Materials, 206, 355-363. https://doi.org/10.1016/j.conbuildmat.2019.02.071
• Madandoust, R., Ghavidel, R., & Nariman-Zadeh, N. (2010). Evolutionary design of generalized GMDH-type neural network for prediction of concrete compressive strength using UPV. Computational Materials Science, 49(3), 556-567. https://doi.org/10.1016/j.commatsci.2010.05.050
• Revilla-Cuesta, V., Skaf, M., Serrano-López, R., & Ortega-López, V. (2021). Models for compressive strength estimation through non-destructive testing of highly self-compacting concrete containing recycled concrete aggregate and slag-based binder. Construction and Building Materials, 280, 122454. https://doi.org/10.1016/j.conbuildmat.2021.122454
• Rodríguez-Pérez, R., Vogt, M., & Bajorath, J. (2017). Support vector machine classification and regression prioritize different structural features for binary compound activity and potency value prediction. ACS omega, 2(10), 6371-6379. https://doi.org/10.1021/acsomega.7b01079
• Sajid, S. H., Ali, S. M., Saeed, S., Sajid, H. U., & Naeem, A. (2016). Non-destructive testing for in-place strength estimation of concrete masonry units. Insight-Non-Destructive Testing and Condition Monitoring, 58(3), 152-156. https://doi.org/10.1784/insi.2016.58.3.152
• Shahmansouri, A. A., Yazdani, M., Ghanbari, S., Bengar, H. A., Jafari, A., & Ghatte, H. F. (2021). Artificial neural network model to predict the compressive strength of eco-friendly geopolymer concrete incorporating silica fume and natural zeolite. Journal of Cleaner Production, 279, 123697. https://doi.org/10.1016/j.jclepro.2020.123697
• Sharma, D., & Chandra, P. (2020). Linear regression with factor analysis in fault prediction of software. Journal of Interdisciplinary Mathematics, 23(1), 11-19. https://doi.org/10.1080/09720502.2020.1721641
• Sun, J., Zhang, J., Gu, Y., Huang, Y., Sun, Y., & Ma, G. (2019). Prediction of permeability and unconfined compressive strength of pervious concrete using evolved support vector regression. Construction and Building Materials, 207, 440-449. https://doi.org/10.1016/j.conbuildmat.2019.02.117
• Tang, J., Deng, C., & Huang, G. B. (2015). Extreme learning machine for multilayer perceptron. IEEE transactions on neural networks and learning systems, 27(4), 809-821. https://doi.org/10.1109/TNNLS.2015.2424995
• TS EN 196-1, 2002, Methods of testing cement - Part 1: Determination of strength
• TS EN 197-1, 2012, Cement- Part 1: Compositions and conformity criteria for common cements
• TS EN 12504-4, 2012, Testing concrete - Part 4: Determination of ultrasonic pulse velocity
• Turgut, P. (2004). Research into the correlation between concrete strength and UPV values. NDT. net, 12(12), 1-9.
• Yaprak, H., Karacı, A., & Demir, I. (2013). Prediction of the effect of varying cure conditions and w/c ratio on the compressive strength of concrete using artificial neural networks. Neural Computing and Applications, 22(1), 133-141. https://doi.org/10.1007/s00521-011-0671-x
• Zengin, S., Demirhan, S., Gözkeser, M. Y., Başaran, E., & Çalışkan, A. (2023). Monitoring consumption of calcium hydroxide via a new approach. Materials Today Communications, 36, 106672. https://doi.org/10.1016/j.mtcomm.2023.106672