You are on page 1of 9

Proceedings of the International Conference

INTERNATIONAL JOURNAL on Emerging
OFTrends
CIVILin Engineering and ManagementAND
ENGINEERING (ICETEM14)
30 – 31, December 2014, Ernakulam, India
TECHNOLOGY (IJCIET)

ISSN 0976 – 6308 (Print) IJCIET
ISSN 0976 – 6316(Online)
Volume 5, Issue 12, December (2014), pp. 239-247
© IAEME: www.iaeme.com/Ijciet.asp
Journal Impact Factor (2014): 7.9290 (Calculated by GISI)
©IAEME
www.jifactor.com

PREDICTING THE STRENGTH OF SELF-COMPACTING
SELF-CURING CONCRETE USING ARTIFICIAL NEURAL
NETWORK

Mohanraj A1, Manoj Prabhakar S2, Rajendran M3
1,2,3
Department of Civil Engineering, Bannariamman Institute of Technology, Erode,
Tamil Nadu, India.

ABSTRACT

In recent years, self-compacting Self curing concrete (SCSCC) has gained wide use for concreting in congested
reinforced structures with difficult casting conditions. For such applications, the fresh concrete must possess high fluidity
and good cohesiveness. The use of fine materials such as Fly ash can ensure the required concrete properties. This
research work focuses on artificial neural networks (ANNs) for evaluating compressive strength of self compacting
concrete (SCC) at 28 days. To evaluate the strength seven input parameters that are the weight of cement, coarse and fine
aggregate, fly ash and three chemical admixtures were identified. Experimental works by casting 17 different trails of
cubes size 150mm was carried out and allowed for curing. All the cubes were tested and the compressive strength was
determined after 28 days of self curing. The experimental results of the tests carried out were used in training Artificial
Neural Network (ANN) model from which an optimum mix of SCSCC was obtained. It is concluded that 2% of super
plasticizers, 0.5% of Viscosity Modifying Agent and Poly-ethylene Glycol is optimum to use in SCSCC mix of M40
concrete. Exceeding which brings down the rate of setting time and strength.
The size of 1000x150x220 mm beam was also casted for the optimum mix and is tested. The experimental result
is compared with ANN result, which suits with minor negligible errors.

Keywords: Artificial Neural Network, Chemical Admixtures, Compressive Strength, Self-Compacting Self-Curing
Concrete

1. INTRODUCTION

There is no standard method for SCC mix design and many academic institutions, ready-mixed industries; precast
and contracting companies have developed their own mix proportioning methods. So in doing trial and error technique
requires a long time and needs more concrete material. To overcome the problems, need a tool for evaluating concrete mix
composition of SCC. This study uses Artificial Neural Network (ANN) as a tool to evaluate the workability test and the
compressive strength of SCC at 28 days. Good curing is not always practical in many cases due to the non-availability of
good quality water. The current trend is incorporating self-curing agents in Self Compacting Concrete. The current trend is
incorporating self-curing agents in Self Compacting Concrete. So, a study may be conducted on self-compacting self-
curing concrete using ANN tool. Abdul Raheman 2013 [1] concludes that, this study of Artificial Neural Network model
will provide an efficient and rapid means of obtaining optimal solutions to predict the optimum mix proportions for
specified strength and workability for sustainable SCC. C. Selvamony et al 2010 [2] Investigated on Self-compacted self-
curing concrete using Lime stone powder and clinkers indicated the use of silica fume in concrete significantly increased

239

565 3. -- 2.90 3.5 2. 15% and 20% by weight of cement.4 0.78 1.82 24 4.5 2 0.025 3.18 0.43 3 3 0.5 2 0. Poly Ethylene glycol (PEG) was used for internal curing (0. 1.024 1.5 770 8 0.5 2. December 2014. chemical admixtures of Viscosity Modifying Agent (VMA) Glenium Stream 2 of 0. Standard 150mm cube was produced.105 1 2 1 680 6 0.5 670 10 0. 1.024 1 1 0. The specific gravity of it is 2. 1. 1.5 2.18 0. 2.89 28 15. 1.45 1. The cement is replaced with 5%.59 0.33 2. 10%.64 0.9 0.91 28 5.105 0.99 22 6.34 2.25 2.18 0.5% by weight of cementitious material was used.17 2.5 1. 1.5 725 10 0. Typical Trail mix and workability property for Self-compacting Concrete are shown in TABLE 1.28 0.5 0.105 0.105 0. F.5 710 7 -.024 1.5 670 6 -.65 1. 1.5 2 0. 1. The initial and final setting times were found as 30 and 356 min respectively.5 630 9 0.5 575 11 1 25 7.025 3.36 3.025 3.083 2.65 2.5 2 0.45 0.73.50 0. 1. Ernakulam.50 0. 1.A.565 3.5% by weight of cement.28 0.45 2. To improve the workability of concrete Conplast SP430 (2% by weight of cementitious material had been used).5 630 10 0.5 500 10 0. passing ability and segregation resistance are the requirements for judging the workability criteria of fresh SCC.3 0. The size of coarse aggregate used was 12.75 1.75 mm.) Mix designs of Self compacting concretes were developed by means of trail mixes based on the guidance given in EFNARC. 1. Trails (Kg) (Kg) (Kg) (Kg) SP Slump V-funnel L-Box VMA PEG U-Box 337 (mm) (sec) H2/H1 1.82 15 13. 1. MATERIALS AND ITS PROPERTIES The cement used in this specimen is ordinary Portland cement of 53 grade and the specific gravity is 3.025 3.97 20 17.5 0.45 2.A.5 2.82 28 11.42 0.6 0.59 0.105 1 2 1 750 7 0.34 2. WORKABILITY OF SCC Filling ability. 1.2 0.9 20 9.34 0.35 0.565 3.63 2.5 660 12 0.36 2.89 25 18.024 1.5 670 8 0. 1.95 26 240 .025 3.5 630 12 0.21 3 3 0.76 27 12. These requirements are to be fulfilled at the time of placing of concrete.024 1.87 0.8 21 16.35 0. 1.65 1.17 2.2 1.86 22 14.5 2 0. To make the concrete as more workable with self compacting character. 1.025 3. -- 3. Silica fume can better reducing effect on total water absorption while quarry dust and lime powder will not have the same effect at 28 day. 1.083 2.105 0.7 1. Fine aggregate used was river sand passing through IS sieve 4.9 23 8.56 3.14. Table 1 Trail mixes and Workability tests for SCSCC concrete Admixtures (%) Workability Cement Flyash C.6 0.68 0. As mineral admixture Fly ash was used in this work.5 mm. India the dosage of Super plasticizer.024 1.5 2 0.5 680 9 0.5 790 11 0. Typical Trail mix for Self- compacting Concrete is shown in Table 1.5 780 10 0. 3.13 0.88 30 10.565 3. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31.5 2 0.565 3.024 1.5 2 0.18 0.5 700 9 0. 1.5 1.

Ernakulam. India Figure 1 Slump value for various trails Figure 2 V-Funnel tests for various trails Figure 3 L-Box tests for various trails Figure 4 U-Box tests for various trails Figure 5 Compressive strength results for various trails 241 . December 2014.Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31.

including cement. The process is given in fig 6 to 10. 0. fly ash. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31. the ANN investigated in the developing has seven units in the input layer and one unit in the output layer. Training function used is TRAINLM and adaption learning function is LEARNGDM. The data were randomly divided into a training phase (6 data sets). and validation phase (5 data set). and learning cycles (epochs) = 1000 which each cycle covers the entire database available for training. 2. 3.01. coarse aggregate. Ernakulam.25 and 0. For this compressive strength of SCC at 28 days modelling problem the obvious inputs are the component contents of concrete. 0.05. fine aggregate. Figure 6 Input and Output Figure 7 Neural Network creation Figure 8 Neural Network Training 242 . That is. December 2014. The values of ANN parameters considered in this approach are as follows: number of hidden layers = 1. number of hidden neurons = 1. The input and output (strength) details are feed in the ANN Tool box. testing phase (6 data set). It is trained and then is simulated. Transfer function is TANSIG. India 4. 0.01. learning rate = 0. and chemical admixture. ANN FOR EVALUATING DESIGN MIX The results of experimental data include 17 data sets.001. The compressive strength of SCC at 28 days was determined by the compressive strength machines. … and 20.5. which was collected experimentally. momentum factor = 0. 0.1.

fck = 35Mpa 5. Figure 11 Testing of Beam Figure 12 Tested Beam 243 .1. BEAM DETAILS The Beam is designed as a singly reinforced beam. India Figure 9 ANN Input Figure 10 ANN Output showing strength 5. The test results are given in TABLE 3. The two point load is applied at the distance of L/3. Deflecto- meter is said to measure the deflection value of the beam. Thus the beam details are given below: Beam Size = 1000 X 150 X 220 mm. The beam is designed as per Code IS 456: 2000. A. Load. deflection and crack measurement of RCC beam The beam as stated in V is tested as per the codal procedure. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31. The clear span of beam is adopted as 800mm & the concentric loading is given during the testing of the beam. Testing of beam is given in fig 11. Cover = 25 mm Main rod = 3 no’s of 10mm Ø rods Hanger rods = 2 no’s of 8mm Ø rods Stirrups = 2 legged stirrups of 8mm Ø rods @ 200 mm fy = Fe 415. December 2014. Ernakulam.

70 1. 20 0. India Table 3 Load & Deflection Test Results Loadings Deflection S. Consistency between ANN Modelling and Experiments The trained ANN models can be used to simulate the effects of some factors on the strength. 110 2. 80 1. Fig 6 respectively shows the amount of Cement. 30 0. 50 0.00 Ultimate crack load & 17. December 2014. 60 1. 100 2.No Remark (KN) (mm) 1.50 16. 10 0.02 3.65 10. VMA and PEG. 0 0 2.15 15.11 First Crack 8. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31.87 7. fine aggregate and percentage of Sp.66 6. 120 2. high strength (HS) self-compacting concrete samples have shown smaller physical interface micro-cracks than low strength (LS) self compacting concretes. 155 4.2. The following simulation results obtained are as shown in Fig. Fly ash. Ernakulam. 150 4.82 14. 10. 130 3. 140 3.52 Maximum deflection 5. and the obtained functional relations between strength.21 12.98 11.3. 40 0. 5.34 9.25 4. coarse aggregates.53 13.46 5. SEM and TEM Analysis From Fig 13 and Fig 14. 90 1. Fig 15 shows the TEM Images in which the particle size and its distributions are clearly pictured Figure 13 SEM Analysis of High Strength concrete Figure 14 SEM Analysis of Low Strength concrete 244 .

6% higher.9% lower.3% higher respectively to the workability results of trail 18. The slump value and L-Box value of trail 16 is about 8. L-Box and U-Box tests results as 3. Trail 4 and trail 6 does not satisfy the slump flow value as specified in EFNARC Specifications.2% and 2% respectively higher than the test results of trail 18. Trails 8 and Trail 15 has 20% lower slump value as compared with the slump value of trail 18. 6. 16. 10 and 12 is 13. trail 7 and trail 14 have the slump value 13% lower than the slump value of trail 18. Trail 13 and Trail 17 have slump value of about 6.e.3% lower than the trail 18. Similarly trail 8 and trail 16 has U-Box value of about 23% lower than trail 18.4% lower.5% lower than value of trail 18. For L-Box tests the trails 3. As it is raised the settling time also increases and thereby the hydration process slows down giving raise to decrease in compressive strength. The U-Box value of trail 4. The trail 7. The U-Box test result of trail 7 is about 11. 245 . About 4% higher L-Box test result than trail 18 and Trails 5.2% lower and trail 6 is 5% higher to the test results of trail 18. For the trail 6 and trail 17 have the same U-Box values and about 4% lower than the value of trail 18. V-Funnel. Trail 9 has slump value. 7. L-Box and U-Box tests results as 8. December 2014. SEM and TEM analysis were performed on the concrete specimen having High and Low strength i. V-Funnel result of trail 6 and trail 16 is 9% lower than trail 18. Trail 1. A trail 3. India Figure 15 TEM Analysis 6.2% lower respectively than the workability results of trail 18. 15.8% higher.3% lower than the trail 18.3% higher and 42. The beam was casted for the mix of trail 18 which gave the satisfactory load carrying capacity and deflection.2% lower than trail 18. But those satisfy the other workability test results.1. DISCUSSION ON RESULTS From the results we can able to retrieve the following conclusions: 6.2% lower and L-Box value of trail 13 is about 9..5% lower than trail 18. Trail 1 and trail 13 is about 40 % lower in V-Funnel tests comparing with trail 18.7% lower than trail 18. The L-Box test value of trail 4 is about 4. trail 9 and trail 17 has the same V-Funnel tests and about 10% lower than trail 18 and L-Box tests of trail 7 and trail 8 is about 5. 20% lower and 3. 13 has U-Box test results which are about 15. This is because of increasing the VMA and PEG to 1%. The value of U-Box test for trail 3 is 7.2. trail 10 and trail 14 is 7% higher than the value of trail 18. For the trail 3 the slump value is about 7% higher than the value of trail 18.5% lower than slump value of trail 18. Trail 15 has slump value.3 % lower respectively to the values of trail 18. Discussion on Chemical Admixtures Out of 18 Trails trail 12 and trail 13 gives the bad strength. on trail 12 and Trail 18.8% lower and 19. Trail 11 has slump value. L-Box and U-Box tests results as 5. The trail 5. Ernakulam.4% lower than trail 18. Discussion on Workability All the trails satisfy the recommendations of workability tests as per EFNARC Specifications.3% lower than trail 18. The Slump value and U-Box test results of Trail 12 is about 3. 4 and 5 has the same V-Funnel values as that of the values of trail 18.7% higher respectively than the workability results of trail 18. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31. Trail 14 and trail 17 have L-Box test value of about 6.3% lower and 13. The slump value and V-Funnel results of trail 2 gives about 10% and 36. trail 8 and trail 10 have satisfactory slump results which gives 7.

75% compared to trail 18. iii. To some extent. Trails 5. ii.5% lower than the strength achieved in trail 18. Trail 18 is our expected result which achieved the compressive strength of about 35N/mm2. CONCLUSION i. vi.5% lower than the strength achieved in trail 18. ANN’s model for evaluating the compressive strength of SCC was developed. Replacement of fly ash as admixture satisfies all the tests such as Slump flow test. Consequently. ix. In addition. Self-curing concrete is the answer to many problems faced due to lack of proper curing. The comparisons of results indicate good agreements. 11 and 17 has lower the compressive strength of about 27% compared to the compressive strength achieved in trail 18. December 2014. The deflection of beam is about 4. the application of ANN models to concrete strength prediction is practical and has a good future.3. Trails 8 and trail 15 has compressive strength of about 12. viii. The results of compressive strength of SCC at 28 days obtained from the developed computer program were compared with results from experimental studies. The application of ANN in the field of SCC mix design is very appropriate in order to preserve and disseminate valuable experience and innovation efficiently at reasonable cost. Trail 6 and trail 10 has compressive strength of about 22. From SEM and TEM analysis it is clear that the high strength of concrete is due to better bonding between the concrete ingredients. Discussion on Compressive strength The compressive strength of trail 1. As mentioned earlier. From the results. The optimum dosage of PEG400 for maximum strengths (compressive and flexural strength) was found to be 0. This explains the increase in tensile and compressive strength for the HS self-compacting concrete compared to the LS concrete. these reasonable results indicate that the trained ANN models exhibit good performance. trail 4 and trail 13 is about 50% lower than the target strength achieved in trail 18. v. V – Funnel. Conclusions drawn from the output conform to some rules on concrete mix proportioning. Ernakulam.52 mm which carries the load to about 155 KN. 6. The lower compressive strength achieved in trail 12 is about 68. between aggregate and cement. U – Box method and L – Box method. Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31. This study of Artificial Neural Network model will provide an efficient and rapid means of obtaining optimal solutions to predict the optimum mix proportions for specified strength and workability for sustainable SCC.5% respectively exceeding which gives low strength and higher setting time. 0. vii. The streams of PEG are also seen which is responsible for internal curing. Optimum percentage of chemical admixtures such as SP.5% and 0.5% lower than strength achieved in trail 18. In this research. Some effects of concrete compositions on strength are in accordance with the rules of mix proportioning. ANN models attain good prediction accuracy. Discussion on SEM and TEM Images From Fig 13 and Fig 14. The study suggests that the use of ANNs has several significant advantages over other conventional methods. The compressive strength of trail 2 and trail 16 is about 33% lower than strength achieved in trail 18.7% lower. 7. VMA and PEG was found as 2%. which meant that HS SCC had better bonds than LS concrete. Discussion on ANN The rules obtained by the ANN models are consistent with those by laboratory work. The compressive strength and flexural strength of analytical results satisfactorily matches with the experiment result. 246 . the ANN models prove reasonable and feasible.5. Fig 15 shows the TEM Images in which the particle size and its distributions are clearly pictured. 7. The compressive strength of trail 9 is nearly to the target compressive strength achieved in trail 18 which is about 8.5% for M40 grade of concrete. high strength (HS) self-compacting concrete samples have shown smaller physical interface micro-cracks than low strength (LS) self compacting concretes. India 6. The dark coloured particle is fly ash is closely arranged. Comparing the compressive strength. a better bonding due to the smaller physical interfaces in HS SCC increased the percentages of fractured aggregate compared to LS concrete. 6. iv. trail 3 and trail 14 is about 39.4.

2009. 33-42. [15] Sudarsana Rao H and Ramesh Babu B. 2012. 16(1). 33(2). 9(3).network applications in predicting moment curvature parameters from experimental data. Kannan S U and Basil Gnanappa S. Dynamics and strength analysis of a MK.2010. ISSN Online: 0976 – 6316. [5] Bai J. Investigation on self compacted self curing concrete using Lime stone. 2002. Predicting Density and Compressive Strength of Concrete Cement paste Containing Silica Fume Using Artificial Neural Networks. Maghsoudi. European Federation of Producers and Applicators of Specialist Products for Structures. A. Issue 2.249. 2013. 33-42. Volume 5. [11] Wang J Z. Issue 1. ISSN Print: 0976 – 6308. 1999. ISSN Print: 0976 – 6308. 429-442.34(12). Selvamony C. 1-6. 247 . 5(3). India REFERENCES [1] Abdul Raheman and Modani P. ARPN Journal of Engineering and Applied Sciences. 24-30 [3] Moosa Mazloom . The Indian Concrete Journal. ARPN Journal of Engineering and Applied Sciences. 13-20. Behaviour of self compacted self curing kiln ash concrete with various admixtures.M. 2013. J China Coal Soc. Sh. pp. 16(1). Journal of Scientific Research &Reports. Self – Compacting Concrete. 3(4). 60(6). Permeation properties of Self Compacting Concrete. Shrinkage behaviour of self-compacting concrete. [20] Santosh Patil and Shriniwas Valunjkar. Ernakulam. December 2014. [18] EFNARC. 5(3). 2008. 2 (1). Cement and Concrete research. 309-319. Volume 4. K. powder and Clinkers. Selvamony C. 663–9. 577-586 [16] Okamura Hajime and Ouchi Masahiro. International Journal of Civil Engineering. 441-454. 2009. [13] Yang. 2013. [9] Maghsoudi A. 2014. 2007. pp. [7] Jadid M N and Fairbairn D R (1996) Neural . Eng Appl Artif Intell. 5– 15.1996. International Journal of Engineering Research and Applications. 2003. Kannan S U and Basil Gnanappa S. Prediction of Properties of Self Compacting Concrete Using Artificial Neural Network. 2009. Magazine of Concrete Research. [17] Rasa E et al. Chattopadhyay. 244-251 [10] Rasa E et al. Ware JA and Sabir BB. 32(5). 13(6). [21] Bhavneet Singh.. Predicting Density and Compressive Strength of Concrete Cement paste Containing Silica Fume Using Artificial Neural Networks. Mohamadpour and M. [2] Ravikumar M S.II screen. Strength characteristics of self-curing concrete. Experiments for mix proportioning of self-compacting concrete. and Peter J. Hybrid Neural Network model for the design of beam subjected to bending and shear. 51-57. and Ashour. ISSN Online: 0976 – 6316. Mix design and mechanical properties of self compacting light weight concrete.Proceedings of the International Conference on Emerging Trends in Engineering and Management (ICETEM14) 30 – 31.. Huang Y X and Jiang. [6] Farhad Aslani and Shami Nejadi . 1(1). 247 . and D. 2011. Using neural networks to predict workability of concrete incorporating metakaolin and fly ash. Journal of advanced concrete technology. 333-339.2005. “Forecasting of Daily Runoff Using Artificial Neural Networks” International Journal of Civil Engineering & Technology (IJCIET). 24(2). S. Specification and guidelines for self-compacting concrete. [8] Jagannadha Kumar M V. Sadhana . Application of Neural Networks for Predicting the Workability of Self-Compacting Concrete.Science. 4(8). IJRET 1(1). Srikanth M and Jagannadha Rao K. Modelling of Reinforced Concrete Deep Beams. F.2012. 2003. 184-188 [12] Wenzhong Zhu. H. Journal of Zhejiang University . [14] Subramanian. Wen X M. Adv Eng Software. 13 . O. 2005. Wild S. 921-926.A. “Bleeding in Concrete” International Journal of Civil Engineering & Technology (IJCIET).Bartos.20. [4] Ravikumar M S. 407-419.