scholarly journals Model-Based Adaptive Machine Learning Approach in Concrete Mix Design

Materials ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1661
Author(s):  
Patryk Ziolkowski ◽  
Maciej Niedostatkiewicz ◽  
Shao-Bo Kang

Concrete mix design is one of the most critical issues in concrete technology. This process aims to create a concrete mix which helps deliver concrete with desired features and quality. Contemporary requirements for concrete concern not only its structural properties, but also increasingly its production process and environmental friendliness, forcing concrete producers to use both chemically and technologically complex concrete mixtures. The concrete mix design methods currently used in engineering practice are joint analytical and laboratory procedures derived from the Three Equation Method and do not perform well enough for the needs of modern concrete technology. This often causes difficulties in predicting the final properties of the designed mix and leads to precautionary oversizing of concrete properties for fear of not providing the required parameters. A new approach that would make it possible to predict the newly designed concrete mix properties is highly desirable. The answer to this challenge can be methods based on machine learning, which have been intensively developed in recent years, especially in predicting concrete compressive strength. Machine learning-based methods have been more or less successful in predicting concrete compressive strength, but they do not reflect well the variability that characterises the currently used concrete mixes. A new adaptive solution that allows estimating concrete compressive strength on the basis of the concrete mix main ingredient composition by including two observations for a given batch of concrete is proposed herein. In presented study, a machine learning model was built with a deep neural network architecture, trained on an extensive database of concrete recipes, and translated into a mathematical formula. Testing on four concrete mix recipes was performed, which were calculated according to contemporary design methods (Bolomey and Fuller method), and a comparative analysis was conducted. It was found out that the new algorithm performs significantly better than that without adaptive features trained on the same dataset. The presented algorithm can be used as a concrete strength checking tool for the concrete mix design process.

2020 ◽  
Vol 14 (1) ◽  
Author(s):  
Julia Widia Nika ◽  
Anisah Anisah ◽  
Rosmawita Saleh

This research aims to utilize green mussel shell waste as a partial replacement for cement by establishing the best temperature that should be used to obtain the chemical substance if the sehell ashes to optimize the chemical substance for replacement of cement. This research replaces 10% of total weight cement with shell ash which has been combusted with a temperature of 700 ° C, 800 ° C and 900 ° C and control concrete. The compressive strength of the concrete plan is 20 MPa. Concrete mix design is 1:2:3. The results of this study indicate with subtitutes 10% semen with green shell ash with temperature 700 ° C, 800 ° C and 900 ° C is 20,53MPa; 16,76 MPa and 19,74 MPa and for control concrete has compressive strength 20,18 MPa. The maximum concrete compressive strength was obtained on the concrete of green shell ash with a combustion temperature of 700 ° C which is 20.53 MPa. In the concrete the green shells ash with a burning temperature above 700 ° C experience a decrease in compressive strength and cannot meet the compressive strength of the plan.


Materials ◽  
2019 ◽  
Vol 12 (8) ◽  
pp. 1256 ◽  
Author(s):  
Patryk Ziolkowski ◽  
Maciej Niedostatkiewicz

Concrete mix design is a complex and multistage process in which we try to find the best composition of ingredients to create good performing concrete. In contemporary literature, as well as in state-of-the-art corporate practice, there are some methods of concrete mix design, from which the most popular are methods derived from The Three Equation Method. One of the most important features of concrete is compressive strength, which determines the concrete class. Predictable compressive strength of concrete is essential for concrete structure utilisation and is the main feature of its safety and durability. Recently, machine learning is gaining significant attention and future predictions for this technology are even more promising. Data mining on large sets of data attracts attention since machine learning algorithms have achieved a level in which they can recognise patterns which are difficult to recognise by human cognitive skills. In our paper, we would like to utilise state-of-the-art achievements in machine learning techniques for concrete mix design. In our research, we prepared an extensive database of concrete recipes with the according destructive laboratory tests, which we used to feed the selected optimal architecture of an artificial neural network. We have translated the architecture of the artificial neural network into a mathematical equation that can be used in practical applications.


2018 ◽  
Vol 149 ◽  
pp. 01054
Author(s):  
Nadia Tebbal ◽  
Zine El Abidine Rahmouni ◽  
Lamis Rabiaa Chadi

The objective of this study is to analyze the effect of the air entrainment on the fresh rheological properties as well as on the compressive mechanical resistances of the mortars. The hardened concrete contains a certain amount of randomly spread air, coming either from a drive during kneading or from the evaporation of the mixing water. The air quantity is in the order of 20 l / m3, ie 2% of the volume. However, the presence of a large volume of air bubbles causes the mechanical resistances to fall in compression. On the other hand, the use of air entrainment could improve the rheological properties of fresh concrete. Experimental studies have been carried out to study the effect of air entrainment on compressive strength, density and ingredients of fresh concrete mix. During all the study, water cement ratio (w/c) was maintained constant at 0.5. The results have shown substantial decreasing in water and mortar density followed with decreasing in compressive strength of mortar. The results of this study has given more promising to use it as a guide for mortar mix design to choose the most appropriate concrete mix design economically.


2013 ◽  
Vol 423-426 ◽  
pp. 1072-1075
Author(s):  
Xin Hua Zhang ◽  
Sai Tian ◽  
Huai Ru Dai ◽  
Wei Lin ◽  
Zhi Chun Yao ◽  
...  

This paper discusses waste production of recycled aggregate concrete is used as the recycled concrete, experiment with different recycled aggregate instead of natural aggregate, the ratio of recycled concrete workability and compressive strength etc performance compared with ordinary concrete, analyzing the change of the recycled aggregate replacement rate on the influence of concrete strength.


2019 ◽  
Vol 1 (2) ◽  
pp. 124-132
Author(s):  
Hermansyah ◽  
Moh Ihsan Sibgotuloh

The more widespread use of concrete construction and the increasing scale of construction, the higher the demand for materials used in concrete mixes. One of the innovations of concrete is fiber concrete. Hope the addition of fiber in concrete mixes such as wire fiber to increase the compressive strength value of normal concrete that is often used, so the purpose of this study is to determine the effect of adding wire fiber to the ease of working (workability) of the concrete mixture and to determine the effect of adding wire fiber to concrete compressive strength. In this study, the fiber used is the type of wire fiber with a diameter of 1 mm and a length of 60 mm. Fiber variations used are 0%, 0.4%, 0.6% and 0.8% based on the weight of fresh concrete. Concrete mix (mix design) using SNI 03-2834-2000 about concrete mix planning with a test life of 28 days. The test results showed that the lowest average compressive strength of 12,291 MPa occurred at 0% variation and the highest average compressive strength value of 20,656 MPa at 0.8% fiber variation. The increase is caused by the even distribution of fibers in the concrete produced, the higher the variation that is given by the fiber, the better the fiber spread, from these fibers provide a fairly good contribution to the fiber concrete


Materials ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 5637
Author(s):  
Sofija Kekez ◽  
Jan Kubica

Prominence of concrete is characterized by its high mechanical properties and durability, combined with multifunctionality and aesthetic appeal. Development of alternative eco-friendly or multipurpose materials has conditioned improvements in concrete mix design to optimize concrete production speed and price, as well as carbon footprint. Artificial neural networks represent a new and efficient tool in achieving optimal concrete mixtures according to its intended function. This paper addresses concrete mix design and the application of artificial neural networks (ANNs) for self-sensing concrete. The authors review concrete mix design methods and the development of ANNs for prediction of properties for various types of concrete. Furthermore, the authors present developments and applications of ANNs for prediction of compressive strength and flexural strength of carbon nanotubes/carbon nanofibers (CNT/CNF) reinforced concrete using experimental results for the learning process. The goal is to bring the ANN approach closer to a variety of concrete researchers and possibly propose the implementation of ANNs in the civil engineering practice.


Author(s):  
Nanang Budi Setyawan ◽  
Fredy Kurniawan

Development era of globalization has resulted in increasing number of second-hand goods / waste that its existence can be a problem for life in the future. Many things are done in order to recycle paper cement in order to overcome this problem the existence of waste. One way is to use waste paper to be a part of the building. The purpose of this study, to determine the compressive strength and optimum density. Laboratory experimental method uses a variation of 10%, 20%, 30% and testing conducted in the form of compressive strength and density. From the test results obtained by the result of decrease in the compressive strength and density. In addition cellulose concrete mix design with variations determined that 10%, 20%, 30% resulted in a decrease in the compressive strength of concrete,


The present research work analysis the conceptual concrete mix design regarding the packing unit density concept for multi initial trial and error perfect shaped methodologies. In initial, a high strength based concrete with desired target compressive strength of M40 Graded concrete was shaped for various mixing proportion and Also, a stabilized standard chart has been developed for the various packing constituents (percentage) in various parameters, where the aggregates (F/c) ratio 0.5 to 0.8, Binder-Total aggregate (B/Ta) ratio 0.27 to 0.24 and water-binder content (w/b) ratio 0.30. The laboratory experimental research work results contain fly ash percentage replacement level at 25 and 50% in Portland cement and inclusion of both ends hooked type of steel fibers along with 1.50% of superplasticizers by weight of binder content for the various mix produced for the good tracking of the UPV values by using fabricating Plexiglas moulds, Pozzolanic Activity Index (PAI), if the compressive strength increases automatically less volumetric shrinkage takes place.


2019 ◽  
Vol 9 (2) ◽  
pp. 47-54
Author(s):  
Fepy Supriani ◽  
Mukhlis Islam

Concrete strength is influenced by several variables, among others by its constituent material, mix design, workmanship, and curing. The objective of concrete curing is to maintain the concrete in certain conditions after the dismantling of the formwork hence the optimization of concrete strength can be achieved close to the designed strength. This study aims to determine the effect of concrete curing on its compressive strength. Designed concrete compressivestrength of 20 MPa with slump values of 60-100 mm to be used. The specimens are cube-shaped with 15 cm dimension. Concrete compressive strength tests were conducted at 28 days and 56 days of concrete age. The types of concrete curing consist of 9 variations, i.e., not treated, water immersed and water sprinkling. Optimum 28 days age of compressive strength of concrete obtained from specimens that immersed in fresh water, which was 31,3 MPa. The concretespecimens that were put outdoor without any curing and treatment generates second highest compressive strength value of 28.6 MPa. The 28 days age of concrete compressive strength values cured with water sprinkling with addition of burlap wrapping are still under the compressive strength of uncured concrete. Significant changes to the strength of cured concrete occurred at age of 56 days and uncured concrete strength decreased up to 19%. The optimum increase occurred in concrete cured with burlap sack wrapping and water sprinkling that was conducted routinely for 3 days by 27,84%. With increasing age (durability) the treated concrete has better strength.


2013 ◽  
Vol 701 ◽  
pp. 12-16 ◽  
Author(s):  
Mohd Irwan Juki ◽  
Khairunnisa Muhamad ◽  
Mahamad Mohd Khairil Annas ◽  
Koh Heng Boon ◽  
Norzila Othman ◽  
...  

This paper describes the experimental investigation to develop the concrete mix design Nomograph for concrete containing PET as fine aggregate. The physical and mechanical properties were determined by using mix proportion containing 25%, 50% and 75% of PET with water cement ratio (w/c) 0.45, 0.55 and 0.65. The data obtained showed that the inclusion of PET aggregate reduce the strength performances of concrete. All the data obtained were combined into one single graph to develop a preliminary mix design nomograph for PET concrete. The nomograph consist of ; relationship between compressive strength and water cement ratio; relationship between splitting tensile strength water cement ratio; relationship between splitting tensile strength and PET percentage and relationship between compressive strength and PET percentage. The mix design nomograph can be used to assists in selecting the proper mix proportion parameters based on the criteria required.


Sign in / Sign up

Export Citation Format

Share Document