1403/02/05
حبیب اکبرزاده بنگر

حبیب اکبرزاده بنگر

مرتبه علمی: دانشیار
ارکید:
تحصیلات: دکترای تخصصی
اسکاپوس:
دانشکده: دانشکده مهندسی و فناوری
نشانی:
تلفن: 09111165785

مشخصات پژوهش

عنوان
Artificial neural network model to predict the compressive strength of eco-friendly geopolymer concrete incorporating silica fume and natural zeolite
نوع پژوهش
JournalPaper
کلیدواژه‌ها
Geopolymer concrete, Ground granulated blast-furnace slag Silica fume, Natural zeolite, Compressive strength, Artificial neural network
سال
2021
مجله JOURNAL OF CLEANER PRODUCTION
شناسه DOI
پژوهشگران Amir Ali Shahmansouri ، Maziar Yazdani ، saeed Ghanbari ، Habib Akbarzadeh Bengar ، Abozar Jafari ، Hamid Farrokh Ghatte

چکیده

The growing concern about global climate change and its adverse impacts on societies is putting severe pressure on the construction industry as one of the largest producers of greenhouse gases. Given the environmental issues associated with cement production, Geopolymer Concrete (GPC) has emerged as a sustainable construction material. This research experimentally studied the effect of partially substituting ground granulated blast-furnace slag (GGBS) with silica fume (SF) and natural zeolite (NZ) (by 0e30% with 5% increments) in the GPC activated by sodium hydroxide (NaOH) solution with different concentrations (4, 6 and 8 M) and sodium silicate (water glass) solution on the compressive strength. Obtained results revealed that increasing the NaOH concentration reduced the concrete strength, while adding SF and NZ to the concrete yielded an improvement in the compressive strength. Moreover, this study proposed an Artificial Neural Network (ANN) to predict the compressive strength of pozzolanic GPC based on GGBS (i.e., at the ages of 7, 28, and 90 days). The compressive strength of GGBS-based GPC (i.e., 117 concrete specimens manufactured out of 39 various mixtures) obtained by experimental tests was used to develop the model. The specimen age, NaOH concentration, contents of NZ, SF, and GGBS were considered as inputs variables for developing the ANN model. The predicted results establish the accuracy and high prediction ability of the proposed model. The findings of this study can bring significant benefits for the range of organizations involved.