Neural network modeling of SBS modified bitumen produced with different methods

Kök, Baha Vural; Yılmaz, Mehmet; Çakiroğlu, Mehmet Alphan; Kuloğlu, Necati; Şengür, Abdulkadir

doi:10.1016/j.fuel.2012.12.073

Cited by 22 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The importance is constructing a new structure of an information processing system. ANN operates together through a great deal of highly interconnected processing neurons to work out issues [ 1 ].…”

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

“…With the dramatic increase in modern road traffic flow, frequency and axle weight of vehicles, more rigorous requirements have been placed on the performance and durability of pavement materials. Over decades of research, it has been found that polymer modifiers can effectively improve the performance of asphalt and enhance the durability of road materials [ 1 , 2 , 3 , 4 ]. Of which, SBS modifiers in particular are the best [ 5 , 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Network (ANN) Modeling for Predicting Performance of SBS Modified Asphalt

et al. 2022

View full text Add to dashboard Cite

Due to the superiorities of Styrene butadiene styrene (SBS) modified asphalt, it is widely used in civil engineering application. Meanwhile, accurately predicting and obtaining performance parameters of SBS modified asphalt in unison is difficult. At present, it is essential to discover an accurate and simple method between the input and output data. ANNs are used to model the performance and behavior of materials in place of conventional physical tests because of their adaptability and learning. The objective of this study discussed the application of ANNs in determining performance of SBS modified asphalt, based on attenuated total reflection Fourier transform infrared spectroscopy (ATR-FTIR) tests. A total of 150 asphalt mixtures were prepared from three matrix asphalt, two SBS modifiers and five modifier dosages. With the most suitable algorithm and number of neurons, an ANN model with seven hidden neurons was used to predict SBS content, needle penetration and softening point by using infrared spectral data of different modified asphalts as input. The results indicated that ANN-based models are valid for predicting the performance of SBS modified asphalt. The coefficient of determination (R2) of SBS content, softening point and penetration prediction models with the same grade of asphalt exceeded 99%, 98% and 96%, respectively. It can be concluded that ANNs can provide well-satisfied regression models between the SBS content and infrared spectrum statistics sets, and the precision of penetration and softening point model founded by the same grade of asphalt is high enough to can meet the forecast demand.

show abstract

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network (ANN) Modeling for Predicting Performance of SBS Modified Asphalt

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Based on several past researches, the base bitumen and the polymer are heated at such temperature to ensure that the base bitumen and polymer are above their softening points. Also, it is necessary to heat the bitumen at high temperatures to allow the polymer particles to become soluble during production [29][30][31][32]. The SBS was then added gradually to the base bitumen and the rotating speed was kept at 2000 rpm for 1 hour.…”

Section: Preparation Of Modified Bitumen Samplesmentioning

confidence: 99%

Investigation of Mixing and Compaction Temperatures of Modified Hot Asphalt and Warm Mix Asphalt

Almusawi

Şengöz

Topal

2020

Period. Polytech. Civil Eng.

View full text Add to dashboard Cite

The determination of mixing and compaction temperatures through the Equiviscous method has been defined as the standard method and it is designed for the base bitumen (unmodified bitumen) based on the viscosity measurements. The implementation of the Equiviscous method for the modified bitumen resulted in high mixing and compaction temperatures which may not be required during the construction of the asphalt mixtures. This study aims to investigate several alternative methods proposed in the literature named as high shear rate method, zero shear viscosity method, steady shear flow method, and phase angle method. Besides, the obtained mixing and compaction temperatures results are compared with the standard (equiviscous) method. For this purpose, 50/70 penetration grade bitumen modified with 5 % elastomeric type – Styrene Butadiene Styrene (SBS), and 1.5 % Reactive Elastomeric Terpolymer type – Elvaloy (RET) has been used. The study also aims to measure the applicability of the proposed alternative methods for the warm mix asphalt involving organic and chemical additives. The results have shown that for the polymer modified bitumen, the application of all proposed methods in the literature resulted in lower mixing and compaction temperatures compared to the Equiviscous method. While for the warm mix asphalt, the implementation of the steady shear flow method resulted in lesser temperatures compared to the Equiviscous method.

show abstract

“…Yapay zeka yöntemleri arasında hızlı sonuç alma, kullanım kolaylığı gibi sebeplerden dolayı Yapay Sinir Ağları (YSA) çokça tercih edilmektedir. Kök ve ekibi yaptıkları çalışmada YSA kullanarak farklı şartlarda Stiren -Butadien -Stiren (SBS) ile modifiye edilmiş bitümlü bağlayıcıların kompleks modül değerlerini yüksek doğrulukla elde etmişlerdir [32]. Özşahin ve Oruç, yapay sinir ağlarını kullanarak emülsifiye bitümün esneklik modülünü deneysel verilerle yüksek benzerlik elde ederek tahmin etmiştir.…”

Section: Introductionunclassified

Predicting The Complex Modulus of Magnetic Activated Carbon Modified Bitumen Using Artificial Neural Networks

Ozdemir

Yilmaz

Akgün

2021

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

View full text Add to dashboard Cite

Bu çalışmada Manyetik Aktif Karbon (MAK) ile modifiye edilmiş bitümlü bağlayıcının reolojik özellikleri araştırılmış ve sonuçlar yapar sinir ağları ile tahmin edilmiştir. Çalışma kapsamında B160/220 penetrasyon sınıfı bitümlü bağlayıcıya %5, %10 ve %15 oranlarında MAK ilave edilerek modifiye bitümler elde edilmiş, ardından bitümler üzerinde Dinamik Kayma Reometresi (DSR) cihazı ile on farklı frekansta (0.01-10Hz) ve dört farklı sıcaklıkta (40°,50°,60°,70°C) frekans taraması testi gerçekleştirilmiştir. Sonuçlar, MAK ilavesinin kompleks modül değerlerini artırıp, faz açısı değerlerini azaltarak bitümlü bağlayıcının elastik özelliklerini geliştirdiğini göstermiştir. Daha sonra frekans, katkı oranı ve sıcaklık değerlerine bağlı olarak değişen kompleks modül ve faz açısı değerleri yapay sinir ağları yöntemi ile tahmin edilmiştir. Sonuçlar, kompleks modül ve faz açısı değerlerinin oldukça yüksek doğrulukta düşük hata ile elde edilebileceğini göstermiştir.

show abstract

Neural network modeling of SBS modified bitumen produced with different methods

Cited by 22 publications

References 17 publications

Artificial Neural Network (ANN) Modeling for Predicting Performance of SBS Modified Asphalt

Artificial Neural Network (ANN) Modeling for Predicting Performance of SBS Modified Asphalt

Investigation of Mixing and Compaction Temperatures of Modified Hot Asphalt and Warm Mix Asphalt

Predicting The Complex Modulus of Magnetic Activated Carbon Modified Bitumen Using Artificial Neural Networks

Contact Info

Product

Resources

About