RETRACTED ARTICLE: Predicting the effects of nanoparticles on early age compressive strength of ash-based geopolymers by
- PDF / 478,828 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 18 Downloads / 217 Views
ORIGINAL ARTICLE
Predicting the effects of nanoparticles on early age compressive strength of ash-based geopolymers by artificial neural networks Shadi Riahi • Ali Nazari
Received: 20 April 2012 / Accepted: 7 July 2012 Ó Springer-Verlag London Limited 2012
Abstract In the present work, compressive strength of ash-based geopolymers with different mixtures of rice husk ash, fly ash, nano alumina, and nano silica has been predicted by artificial neural networks. The neural network models were constructed by 12 input parameters including the water curing time, the rice husk ash content, the fly ash content, the water glass content, NaOH content, the water content, the aggregate content, SiO2 nanoparticles content, Al2O3 nanoparticles content, oven curing temperature, oven curing time, and test trial number. The value for the output layer was the compressive strength. According to the input parameters in feed-forward back-propagation algorithm, the constructed networks were trained, validated, and tested. The results indicate that artificial neural networks model is a powerful tool for predicting the compressive strength of the geopolymers in the considered range. Keywords Geopolymer Compressive strength Nanoparticles mixture Artificial neural networks
1 Introduction Geopolymer is an amorphous aluminosilicate network formed by the polycondensation of individual [SiO4]4- and [AlO4]5- tetrahedral. This material has been received considerable attention due to its excellent mechanical properties, low shrinkage, fire resistance, low energy
S. Riahi A. Nazari (&) Department of Materials Science and Engineering, Saveh Branch, Islamic Azad University, Saveh, Iran e-mail: [email protected]
consumption for the purposes of building industry and engineering field [1]. In this work, artificial neural networks (ANNs) have been utilized to predict the compressive behavior of ashbased geopolymers. ANNs are a family of massively parallel architectures that solve difficult problems via the cooperation of highly interconnected but simple computing elements (or artificial neurons). Basically, the processing elements of a neural network are analogous to the neurons in the brain, which consist of many simple computational elements arranged in several layers [2, 3]. ANNs has lately been used widely to model some of the human-interesting activities in many areas of science and engineering. Especially, many of studies were made for the prediction compressive strength of concrete specimens. Yeh [4] applied the ANN for predicting properties of high-performance concretes. Lai and Serra [5] predicted the strength of concrete by using the neural network. Lee [6] used single and multiple ANNs architecture for predicting concrete strength. Hong-Guang and Ji-Zong [7] proposed a method to predict 28-day compressive strength of concrete by using multilayer feed-forward neural networks. Dias and Pooliyadda [8] utilized back-propagation neural networks to predict the strength and slump of ready-mixed concrete and high-strength concrete in
Data Loading...
