Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models

Sobhani, Jafar; Najimi, Meysam; Pourkhorshidi, A.R.; Parhizkar, T

doi:10.1016/j.conbuildmat.2009.10.037

Cited by 282 publications

(131 citation statements)

References 17 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…Pored navednih konvencionalnih modela i vešta kih neuronskih mreža, neretko se koriste i drugi modeli procene vrsto e betona pri pritisku, koji se zasnivaju na razmatranju efekta razli itih proporcija vode, cementa i agregata [17][18], odnosno koji koriste sisteme na bazi adaptivne mreže [19][20][21] ili fazi logike [22][23][24].…”

Section: Introductionunclassified

Estimation of concrete compressive strength using artificial neural network

Kostic¹,

Vasović²

2015

Gra mat konstru

View full text Add to dashboard Cite

Analiza vrsto e betona pri pritisku predstavlja jedan od primarnih zadataka laboratorijskih ispitivanja za razli ite potrebe inženjerske prakse, pre svega u zgradarstvu, tunelogradnji, putarstvu, pri izgradnji brana i mostova, kao i pri izvo enju razli itih podzemnih i površinskih konstrukcija u rudarstvu. Zavisno od zahteva projekta, ispitivanje vrsto e betona izvodi se za uzorke razli ite starosti s promenljivim vodocementnim faktorom, raznim tipovima i koli inom aditiva (lete i pepeo, silikatna prašina, metakaolin i mlevena granulisana zgura iz visokih pe i kao mineralni aditivi, odnosno plastifikatori, razli iti akceleratori i retarderi, kao hemijski aditivi), te u razli itim spoljašnjim uslovima ugradnje betona (s naglaskom na otpornost betona pri izlaganju mrazu). Pri tome, pouzdanost dobijenih rezultata naj eš e predstavlja direktnu funkciju broja ispitanih uzoraka, tj. ve i broj ispitanih uzoraka betona doprinosi pouzdanijem odre ivanju njegovih svojstava. Me utim, sredstva predvi ena programom istraživanja, u najveem broju slu ajeva, nisu dovoljna za analizu brojnih uzoraka, ve se naj eš e pristupa interpolaciji malog, vrlo esto i nedovoljnog broja podataka ispitivanja. U tom smislu, modeli za procenu vrsto e betona predstavljaju posebno važnu tehniku koja omogu ava utvr ivanje relacije izme u zrelosti betona i njegove vrsto e, Sr an Kosti , Departman za geologiju, Univerzitet u Beogradu, Rudarsko-geološki fakultet, Srbija, srdjan.kostic@rgf.bg.ac.rs Dejan Vasovi Departman za arhitektonske tehnologije, Univerzitet u Beogradu, Arhitektonski fakultet, Srbija,

show abstract

Section: Introductionunclassified

Estimation of concrete compressive strength using artificial neural network

Kostic¹,

Vasović²

2015

Gra mat konstru

View full text Add to dashboard Cite

show abstract

“…Three neuron models namely, 'tansig', 'logsig' and 'purelin', have been used in the architecture of the network with the back propagation algorithm implemented in originally developed MATLAB routines. In the back propagation algorithm, the feed-forward (FFBP), cascade-forward (CFBP) and Elman back propagation (EBP) type network were considered [3,11,12,16,18,23]. Each input is weighted with an appropriate weight and the sum of the weighted inputs and the bias forms the input to the transfer function.…”

Section: Neural Network Modelmentioning

confidence: 99%

“…Analysis of the accumulated test data employing the neural network technique has been performed in order to develop a new procedure for predicting the effective strength of the slabcolumn joint. A neural network has the capability of realizing a greater variety of nonlinear relationship of considerable complexity [3,23]. In neural networking the data is presented to the network in the form of input and output parameters, and the optimum nonlinear relationship is found by minimizing a penalized likelihood.…”

Section: Introductionmentioning

confidence: 99%

Estimation of RC slab-column joints effective strength using neural networks

Shah

Ribakov

2011

Lat. Am. j. solids struct.

View full text Add to dashboard Cite

The nominal strength of slab-column joints made of highstrength concrete (HSC) columns and normal strength concrete (NSC) slabs is of great importance in structural design and construction of concrete buildings. This topic has been intensively studied during the last decades. Different types of column-slab joints have been investigated experimentally providing a basis for developing design provisions. However, available data does not cover all classes of concretes, reinforcements, and possible loading cases for the proper calculation of joint stresses necessary for design purposes. New numerical methods based on modern software seem to be effective and may allow reliable prediction of column-slab joint strength. The current research is focused on analysis of available experimental data on different slab-to-column joints with the aim of predicting the nominal strength of slabcolumn joint. Neural networks technique is proposed herein using MATLAB routines developed to analyze available experimental data. The obtained results allow prediction of the effective strength of column-slab joints with accuracy and good correlation coefficients when compared to regression based models. The proposed method enables the user to predict the effective design of column-slab joints without the need for conservative safety coefficients generally promoted and used by most construction codes.

show abstract

“…But CCS is usually tested three days after production, and sometimes even after 28 days, this makes it impossible for enterprises to take effective measures in the presence of the quality risk [7]. In order to deal with these problems, scholars and engineers have been studying the online and real-time CCS estimation methods [8][9][10][11][12][13], the maximum error was reduced to 8%. Madandoust.et al found that the hybrid algorithms were better than the single algorithms, and the models with input layers being closer to the actual production crafts were more conducive to improve the prediction accuracy, the mean relative error was about 4% [14][15], which was an almost acceptable error value considering the characteristics of concrete production.…”

Section: Introductionmentioning

confidence: 99%

Predictions of concrete compressive strength based a hybrid algorithm of GA-BP

Shi¹,

Zhong²,

Zhang³

et al. 2018

Proceedings of the 4th Annual International Conference on Material Engineering and Application (ICMEA 2017)

View full text Add to dashboard Cite

Abstract-The concrete quality is of great significance for the safety of buildings. This paper conducted the research on this subject in the actual concrete mixing plant, with concrete compressive strength (CCS) being the indicator of concrete quality. Firstly, in order to make the quality evaluation models feasible, the rough set theory method based attribute reduction rule (ARR) was introduced to build the equivalent quality evaluation models with fewer measurable factors. Then, along with the consumptions of raw materials, the correlation coefficients of the consumption amounts, including sand ratio, water-cement ratio, and water-binder ratio,were determined as the input parameters of GA-BP. The prediction accuracy, stability and reliability (RMSE:1.39; : 3.20%; S:2.18%) were better than those of the contrast schemes. Furtherly, the research shew that the rules of some factors, such as personnel, material properties, equipment status, and environment, are step functions of time, so the time threshold was introduced into GA-BP models to reduce the influence of these factors on the model, the algorithm of determining the optimal time threshold was given. In the case study, the appropriate time threshold improved the accuracy of GA-BP. Finally, the proposed models and the algorithms were applied in the actual plant operations to estimate CCS on line, the satisfied results were achieved.

show abstract

Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models

Cited by 282 publications

References 17 publications

Estimation of concrete compressive strength using artificial neural network

Estimation of concrete compressive strength using artificial neural network

Estimation of RC slab-column joints effective strength using neural networks

Predictions of concrete compressive strength based a hybrid algorithm of GA-BP

Contact Info

Product

Resources

About