Abstract
In the present paper, we propose a prediction model for concrete compressive strength using artificial neural networks. In experimental part of the research, 75 concrete samples with various w/c ratios were exposed to freezing and thawing, after which their compressive strength was determined at different age, viz. 7, 20 and 32 days. In computational phase of the research, different prediction models for concrete compressive strength were developed using artificial neural networks with w/c ratio, age and number of freeze/thaw cycles as three input nodes. We examined three-layer feed-forward back-propagation neural networks with 2, 6 and 9 hidden nodes using four different learning algorithms. The most accurate prediction models, with the highest coefficient of determination (R 2 > 0.87), and with all of the predicted data falling within the 95 % prediction interval, were obtained with six hidden nodes using Levenberg–Marquardt, scaled conjugate gradient and one-step secant algorithms, and with nine hidden nodes using Broyden–Fletcher–Goldfarb–Shannon algorithm. Further analysis showed that relative error between the predicted and experimental data increases up to acceptable ≈15 %, which confirms that proposed ANN models are robust to the consistency of training and validation output data. Accuracy of the proposed models was further verified by low values of standard statistical errors. In the final phase of the research, individual effect of each input parameter was examined using the global sensitivity analysis, whose results indicated that w/c ratio has the strongest impact on concrete compressive strength.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
1 Introduction
Rapid development of new technologies, as well as the increase in production of synthetic ingredients, enables the constructors to create and use different types of concrete, depending on the type of object, possible external static and dynamic forces and surrounding environment. Increasing demands for higher and stronger buildings, together with more complicated architectural designs, seek concrete mixtures of higher quality, which are typically obtained by including a certain amount of the appropriate additive. Depending on the property which is to be improved, concrete is usually mixed with different plasticizers and superplasticizers, ground granulated blast furnace slag, pozzolanic ash, as well as fly ash or silica fume. Hence, as it could be seen, there is a variety of factors that could affect the ultimate characteristic of the concrete. Nevertheless, its physical and mechanical properties are still predetermined by the three main ingredients: water, cement, and aggregates, which are typically represented by the w/c ratio, physical, mechanical and chemical properties of cement and by the aggregate granulometric structure. It is this basic concrete mixture, without additives, that is examined in present paper, in order to obtain a reliable model for prediction of concrete compressive strength. Prediction models are very useful in laboratory testing, since they optimize experimental process by providing an optimal minimum number of probes for analyzing a specific property of concrete mixture. Several different prediction models have been developed, which are frequently used for estimating the compressive strength, as the most important engineering property of the concrete. First of them is based on linear and nonlinear regression analysis, commonly using the maturity concept [1–4], as well as the combination of input variables, water, cement and aggregates [5, 6]. Second approach uses the adaptive network-based fuzzy inference system [7, 8], while third approach relies on fuzzy logic techniques [9–12].
Apart from the aforementioned models, in recent years, artificial neural networks (ANN) have been used for estimating different concrete properties, such as drying shrinkage [13], concrete durability [14], ready mixed concrete delivery [15], compressive strength of normal and high-performance concrete [16–23], workability of concrete with metakaolin and fly ash [24], mechanical behavior of concrete at high temperatures [25] and long-term effect of fly ash and silica fume on concrete compressive strength [26]. The main advantage of ANN approach over the other computational methods lies in the fact that ANN automatically manages to detect the multivariable interrelationships. From an engineering point of view, this modeling method results in a concrete mix proportion with the lesser number of trials, cost and time.
In the present paper, we develop ANN models for prediction of concrete compressive strength based on the results of a series of experiments. The obtained model would be able to reproduce the experimental results and to approximate the results in other experiments through its generalization capability. The present research is focused on compressive strength of basic concrete mixture, depending on three main factors: w/c ratio, age and exposure to freezing and thawing.
The paper is organized as follows. Material properties and testing procedure are described in Sect. 2, while experimental results are provided in Sect. 3. The obtained results of ANN modeling are presented and compared with experimental data in Sect. 4, while their performance is further evaluated in Sect. 5. Results of global sensitivity analysis are presented and discussed in Sect. 6. A brief review on the obtained results is given in the final section, together with suggestions for further research.
2 Laboratory testing
2.1 Properties of cement
The examined concrete specimens were made of CEM I normal Portland cement (PC 42.5 N/mm2), manufactured by Lafarge BFC (Serbia), with specific gravity ρ = 3.10 g/cm3, and with the initial and final setting times of 2 h and 30 min and 3 h and 30 min, respectively. Blaine specific surface area of cement was 3,450 cm2/g. Physical and mechanical properties of cement and its chemical composition were determined by Institute for testing of materials—IMS Serbia (Tables 1, 2).
2.2 Properties of aggregate
Concrete mixture included natural river aggregate. Maximum nominal size of gravel was 16 mm with 5 % of the oversized particles (Table 3). The water absorption was 1.5 %, and its relative density at saturated surface dry condition (SSD) was 2.72 g/cm3. The water absorption value of sand was 2.0 %, and its relative density at SSD condition was 2.69 g/cm3.
2.3 Preparation of concrete specimens
Concrete was made in a laboratory counter-current concrete mixer of “‘Eiric” type. Cubic concrete samples (100 × 100 mm) were made and examined according to the national standard SRPS [27, 28]. Mixing period was 3 min for all mixtures. Casting was performed at a vibrating table until a complete consolidation was achieved. Consistency of the fresh concrete was measured by applying the slump test [29], Vebe test [30] and flow test [31] (Table 4).
2.4 Test procedure
After the concrete was casted in metal moulds, samples were left at room temperature (20 ± 2 °C) with relative humidity of 90–95 %. Concrete samples were demoulded after 24 h and soaked in water at the same temperature (20 °C) for the next 6 days. At the seventh day, four out of eight series of the concrete samples were exposed to freezing and thawing. Compressive strength was determined after 50 and 100 cycles (one cycle lasted for 4 h in environmental chamber at −20 ± 2 °C and 4 h soaked in water at 20 ± 2 °C) after 7, 20 and 32 days. Measured strength was compared with the strength of the control group of specimens, continuously cured in water at 20 ± 2 °C, which were not exposed to freezing and thawing, also after 7, 20 and 32 days [32]. These ages were chosen so as to fall on a working day. Moreover, it is a common practice to observe a development of concrete strength after 1, 3, 5, 7, 14, 21 and 28 days, in order to capture the relative gain of strength in time [33]. Differences between the observed strength after 20 and 21 days, or after 28 and 32 days, are not higher than few percentages [33]. The compressive strength and bulk density of the hardened concrete were tested according to the national SRPS standard [34]. Compressive strength measurements were carried out using “Amsler” hydraulic press with capacity of 2,000 kN and with loading rate of 0.4 MPa/s.
3 Experimental results
Results of the performed testing of 75 concrete samples are given in Table 5. For each composition of concrete mixture, compressive strength of specimens was determined after three probes, in order to reduce the measurement error. Testing results imply that the maximum difference between the largest and smallest value of compressive strength for samples of the same composition (and exposed to the equal number of freezing/thawing cycles) is in the range of 10 %, except for the following group of specimens: A5-4 → A5-6, A3-7 → A3-9, A1-10 → A1-12, A2-10 → A2-12, A1-13 → A1-15, A2-13 → A2-15, A5-13 → A5-15, where the difference between the measured strengths increases even up to >20 %. However, despite such relatively high contrasts, all the experimental results were used for ANN modeling, in order to examine the robustness of the prediction models to the consistency of training and validation output data.
Regarding the impact of particular concrete ingredients, the obtained results clearly indicate the strong influence of w/c ratio on concrete compressive strength. Samples of concrete with lower w/c ratio show higher compressive strength, determined by the aggregate grading and amount of cement in the mixture. On the other hand, exposure to freeze and thawing decreases the concrete strength, especially at higher w/c ratios.
4 Development of prediction model
Prediction model for concrete compressive strength was developed using three-layer back-propagation feed-forward artificial neural networks, with w/c ratio, age and the number of freeze/thaw cycles as input parameters, whereas compressive strength was considered as a single output unit (Table 6). Similar approach was already used in [6, 35–37].
Following the suggestion of Rumelhart et al. [38], Lippmann [39] and Sonmez et al. [40], we chose ANN model with one hidden layer, while the number of hidden nodes was determined using heuristics summarized by Sonmez et al. [40]. As it is clear from Table 7, the number of nodes that may be used in hidden layer varies between 1 and 9. In the present study, we examined ANN models with 2, 6 and 9 hidden neurons in order to establish the most effective ANN architecture.
In all the examined cases, the total data set has been divided as following: 60 % for training (45 recordings), 15 % for validation (11 recordings) and 25 % for testing (19 recordings), which corresponds well with the suggestion of Looney [41], who proposed 25 % for testing, and with recommendation made by Nelson and Illingworth [42] who supported the idea of 20–30 % of data for testing. ANN training was performed using the Matlab Neural Network toolbox [43], with four different learning algorithms: Levenberg–Marquardt, scaled conjugate gradient, one-step-secant back-propagation and Broyden–Fletcher–Goldfarb–Shannon (BFGS) quasi-Newton back-propagation. Results were obtained for random initial conditions and sampling.
The proposed ANN architectures were trained using combinations of the number of hidden nodes defined above. Since input parameters have different units of measure, scaling of their values was necessary, using the following relation:
In this way, values of all the input and output units were scaled in the range [0, 1].
4.1 Levenberg–Marquardt (LM) learning algorithm
LM learning algorithm is commonly considered as the fastest method for training moderate-sized feed-forward neural networks [44, 45], and it is the first choice for solving the problems of supervised learning, which is the case in the present analysis. As an activation function, we use sigmoid function which has been typically implemented in previous studies [39].
In order to create a prediction model with most accurate response, we developed three artificial neural networks with 2, 6 and 9 hidden neurons. The possibility of overfitting was excluded by confirming that any increase in accuracy over the training data set yields rise in accuracy over a validation data set. In the present study, mean-squared error (MSE) saturates with the increase of epochs for training and validation data for all three examined cases with different number of hidden neurons (Fig. 1).
Comparison of prediction results with experimental data for training, validation and testing sets, using ANNs with 2, 6 and 9 hidden nodes, is given in Fig. 2. It is clear that the ANN model with six hidden nodes has the highest coefficient of determination (R 2 ≈ 0.941) for testing set, approximately the same value of R 2 for training and validation sets and with statistically small value of standard error, SE = 2.260, meaning that the average distance of the data points from the fitted line is 2.26 MPa. In other words, this means that all of predicted data fall within the 95 % prediction interval, which confirms the precision of the proposed model. A review of the experimental and predicted values of concrete compressive strength, including the absolute and relative prediction errors for ANN with six hidden nodes, is given in Table 8. Analysis of the error distribution for testing set shows that relative prediction errors are within the acceptable range of measurement results, up to ≈15 %.
4.2 Scaled conjugate gradient (SCG) learning algorithm
SCG learning algorithm belongs to the class of conjugate gradient optimization methods which are well suited to handle the large-scale problems in an effective way [46]. This method represents one of the four most commonly used algorithms of this group, besides Fletcher–Reeves Update, Polak–Ribiére Update and Powell–Beale Restarts algorithm. Each of these conjugate gradient algorithms requires a line search at every iteration step, which is computationally expensive, since the network response to all training inputs has to be computed several times for each search. The SCG algorithm was designed to avoid this time-consuming procedure, by combining the model-trust region approach (used in LM algorithm) with the conjugate gradient algorithm [47].
As in the previous case of LM algorithm, change of MSE with the increase of number of epochs was examined for training, validation and testing sets, using different number of hidden nodes (Fig. 3). The analysis showed that training set errors and validation set errors have similar properties, confirming the absence of overfitting.
Comparison of prediction results with experimental data for training, validation and testing sets, using ANNs with 2, 6 and 9 hidden nodes, is given in Fig. 4. ANN model with six hidden nodes has the highest coefficient of determination (R 2 ≈ 0.877) for testing set, approximately the same value of R 2 for validation set and with statistically small value of standard error, SE = 2.495, meaning that all of the predicted data fall within the 95 % prediction interval, which confirms the precision of the proposed model. A slight decrease of R 2 between the training and validation sets does not affect the obtained results significantly, since standard error indicates that predicted data fall within the 95 % prediction interval in both cases (SE = 2.062 and 2.756, respectively). Analysis of the error distribution for training set (for ANN with six hidden nodes) shows that relative prediction errors are in the range up to ≈15 % (Table 9).
4.3 Broyden–Fletcher–Goldfarb–Shannon (BFGS) quasi-Newton back-propagation learning algorithm
BFGS algorithm is considered as one of the best quasi-Newton’s techniques that uses a local quadratic approximation of the error function and employs an approximation of the inverse of the Hessian matrix to update the weights, thus getting the lowest computational cost. This algorithm is error tolerant, yields good solutions and converges in a small number of iterations [48]. The computational advantage of BFGS especially holds for small- to moderate-sized problems, which is the case in the present analysis. The ANN model with BFGS learning algorithm and different number of hidden nodes is developed for the step length in the range [10−6, 102], while change in step size takes values from the realm [0.1, 0.5]. Initial step size in interval location step is set to 0.01, while scale factor that determines sufficiently large step size is assumed to be 0.1. Parameter to avoid small reductions in performance is set to 0.1.
As in the previous two models, decrease of MSE with the increase of epochs for training, validation and testing data using different number of hidden nodes excludes the possibility of overfitting (Fig. 5).
Comparison of prediction results with experimental data for training, validation and testing sets, using ANNs with 2, 6, and 9 hidden nodes, is given in Fig. 6. ANN model with nine hidden nodes has the highest coefficient of determination (R 2 ≈ 0.951) for testing set, approximately the same value of R 2 for training and validation sets and with statistically small value of standard error, SE = 2.028, meaning that all of the predicted data fall within the 95 % prediction interval, which confirms the precision of the proposed model. Analysis of the error distribution for training, validation and testing sets (for ANN with nine hidden nodes) shows that all of the predicted values for testing set have relative errors smaller than 10 % (Table 10).
4.4 One-step-secant (OSS) back-propagation learning algorithm
OSS learning algorithm represents an attempt to bridge the gap between the conjugate gradient and the quasi-Newton secant algorithms. The OSS method does not require the choice of critical parameters, is guaranteed to converge to a point with zero gradient, and has been shown to accelerate the learning phase by many orders of magnitude with respect to standard back-propagation algorithms if high precision in the output values is desired [49]. In the present study, parameters for OSS learning algorithm are the same as for the previous BFGS method.
MSE versus the number of epochs for training, validation and testing data, using different number of hidden nodes, is shown in Fig. 7. The results of all three models are reasonable, since the training set errors and the validation set errors have similar properties. Consequently, it does not appear that any significant overfitting has occurred.
Comparison of prediction results with experimental data for training, validation and testing sets, using ANNs with 2, 6, and 9 hidden nodes, is given in Fig. 8. ANN model with six hidden nodes has the highest coefficient of determination (R 2 ≈ 0.951) for testing set, approximately the same value of R 2 for training set and with statistically small value of standard error, SE = 2.028, meaning that all of the predicted data fall within the 95 % prediction interval, which confirms the precision of the proposed model. Slightly lower value of R 2 for validation set does not affect the obtained results significantly, since standard error indicates that predicted data fall within the 95 % prediction interval (SE = 3.193). Analysis of the error distribution for training, validation and testing sets (for ANN with six hidden nodes) shows that relative prediction errors are up to ≈10 % (Table 11).
5 Performance evaluation of the proposed models
Performances of the developed prediction models could be further evaluated using different standard statistical criteria given in Table 12 [50].
Calculated statistical errors are shown in Table 13. ANN model with OSS learning algorithm and six hidden nodes has the lowest values of MAPE (Mean Absolute Percentage Error) and VARE (Variance Absolute Relative Error), while model with LM learning algorithm and six hidden nodes has the lowest value of and MEDAE (MEDian Absolute Error), in comparison with other proposed ANN models.
6 Sensitivity analysis
Sensitivity analysis represents a method which enables us to determine the relative strength of effect (RSE) for each input unit on the concrete compressive strength [51]. In this case, it was carried out by the hierarchical analysis [52], where the RSE parameter is determined in the following way:
where C is normalized constant which controls the maximum absolute values of RSE ki , W is a connected weight and \(G\left( {e_{k} } \right) = \exp ( - e_{k} )/(1 + \exp ( - e_{k} ))^{2}\) denotes the hidden units in the n, n − 1, n − 2,…,1 hidden layers [52].
Global sensitivity analysis, which was carried out for all the input parameters and for all the ANN models with different learning algorithms and different number of hidden nodes, indicated that the w/c ratio has the strongest impact on the compressive strength of concrete (Fig. 9).
7 Conclusion
In the present study, we develop four ANN models with different learning algorithms for prediction of concrete compressive strength. For this purpose, 75 specimens of basic concrete mixture were exposed to different cycles of freezing and thawing, after which their compressive strength was measured at different ages (7, 20 and 32 days). Afterward, these results were used for ANN modeling with different number of hidden nodes in order to exclude the possibility of overfitting. In all the examined cases, a three-layer feed-forward back-propagation artificial neural network was used. The obtained results showed that ANN models with six hidden nodes (using LM, SCG and OSS learning algorithms) and nine hidden nodes (using BFGS learning algorithm) have the best predictive power comparable to the experimental results. Moreover, in all the examined cases, analysis of standard error indicated that each predicted value falls within the 95 % prediction interval. As for the error distribution, further inquiry implied that relative prediction error increases up to the acceptable value of ≈15 %, which suggests that the proposed ANN models are robust to the consistency of the training and validation data. Additional analysis indicated that ANN model with OSS learning algorithm and six hidden nodes has the lowest values of MAPE and VARE, while the model with LM algorithm and six nodes has the lowest value of MEDAE.
Regarding the separate impact of each input unit on the final value of concrete compressive strength, the sensitivity analysis indicated that w/c ratio has the strongest influence on the experimental results in all the examined cases with various learning algorithms and different number of hidden nodes.
It should be noted that one of the main outcome of the performed analysis lies in the fact that the results of ANN modeling seem to be almost independent on the choice of learning algorithm and number of hidden nodes (as long as this number is in the acceptable range determined by the widely used heuristics). This claim follows the results of ANN training in all the examined cases, with high coefficient of determination for every training, validation and testing sets (R 2 > 0.81). This fact is further supported by the low values of SE and favorable change of MSE with the number of training epochs.
However, despite the high predictive power of the proposed ANN models, one of the main limitations of the analysis is certainly simple composition of the concrete specimens. Future analyzes should include concrete samples with different additives (superplasticizer, fly ash, zeolite, etc.), in order to expand the proposed models and make them more usable in daily practice.
References
Saul AGA (1951) Principles underlying the steam curing of concrete at atmospheric pressure. Mag Concr Res 2:127–140
Plowman JM (1956) Maturity and the strength of concrete. Mag Concr Res 22:13–22
Bernhardt CJ (1956) Hardening of concrete at different temperatures. In: RILEM symposium on winter concreting, Copenhagen, Danish Institute for Building Research, Session B-II
Yi S-T, Moon Y-H, Kim J-K (2005) Long-term strength prediction of concrete with curing temperature. Cem Concr Res 35:1961–1969
Popovics S, Ujhelyi J (2008) Contribution to the concrete strength versus water-cement ratio relationship. J Mater Civ Eng 20:459–463
Sobhani J, Najimi M, Pourkhorshidi AR, Parhizkar T (2010) Prediction of the compressive strength of no-slump concrete: a comparative study of regression, neural network and ANFIS models. Constr Build Mater 24:709–718
Ramezanianpour AA, Sobhani M, Sobhani J (2004) Application of network based neuro-fuzzy system for prediction of the strength of high strength concrete. AMIRKABIR 15:78–93
Saridemir M (2009) Predicting the compressive strength of mortars containing metakaolin by artificial neural networks and fuzzy logic. Adv Eng Softw 40:920–927
Topcu IB, Saridemir M (2008) Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic. Comput Mater Sci 41:305–311
Singh R, Vishal V, Singh TN, Ranjith PG (2012) A comparative study of generalized regression neural network approach and adaptive neuro-fuzzy inference systems for prediction of unconfined compressive strength of rocks. Neural Comp Appl 23:499–506
Singh R, Vishal V, Singh TN (2012) Soft computing method for assessment of compressional wave velocity. Sci Iran 19:1018–1024
Basyigit C, Akkurt I, Kilincarslan S, Beycioglu A (2010) Prediction of compressive strength of heavyweight concrete by ANN and FL models. Neural Comp Appl 19:507–513
Basma AA, Barakat S, Oraimi SA (1999) Prediction of cement degree of hydration using artificial neural networks. Mater J 96:166–172
Jepsen MT (2002) Predicting concrete durability by using artificial neural network. Special NCR-publication; ID 5268
Graham LD, Forbes DR, Smith SD (2006) Modeling the ready mixed concrete delivery system with neural network. Autom Constr 15:656–663
Lai S, Serra M (1997) Concrete strength prediction by means of neural network. Constr Build Mater 11:93–98
Yeh I (1998) Modeling of strength of high-performance concrete using artificial neural networks. Cem Concr Res 28:1797–1808
Oh J-W, Lee I-W, Kim J-T, Lee G-W (1999) Application of neural networks for proportioning of concrete. Mater J 96:352–356
Dias W, Pooliyadda S (2001) Neural network for predicting properties of concretes with admixtures. Constr Build Mater 15:371–379
Lee S-C (2003) Prediction of concrete strength using artificial neural networks. Eng Struct 25:849–857
Kim JI, Kim DK, Feng MQ, Yazdani F (2004) Application of neural networks for estimation of concrete strength. J Mater Civ Eng 16:257–264
Gupta R, Kewalramani MA, Goel A (2006) Prediction of concrete strength using neural-expert system. ASCE J Mater Civ Eng 18:462–466
Oztas A, Pala M, Ozbay E, Kanca E, Caglar N, Bhatti MA (2006) Predicting the compressive strength and slump of high strength concrete using neural network. Constr Build Mater 20:769–775
Bai J, Wild S, Ware JA, Sabir BB (2003) Using neural networks to predict workability of concrete. Adv Eng Softw 34:663–669
Mukherjee A, Biswas SN (1997) Artificial neural networks in prediction of mechanical behavior of concrete at high temperature. Nucl Eng Des 178:1–11
Pala M, Ozbay E, Oztas A, Yuce MI (2007) Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks. Constr Build Mater 21:384–394
SRPS ISO 2736-1:1997. Concrete tests—test specimens—part 1: sampling of fresh concrete
SRPS ISO 2736-2:1997. Concrete tests—test specimens—part 2: making and curing of test specimens for strength tests
SRPS ISO 4109:1997. Fresh concrete—determination of the consistency—slump test
SRPS ISO 4110:1997. Fresh concrete—determination of the consistency—Vebe test
SRPS U.M8.052:1996. Fresh concrete—determination of the consistency—flow test
SRPS CEN/TR 15177:2009. Testing the freeze–thaw resistance of concrete—internal structural damage
Neville A (2002) Properties of concrete, 4th edn. Wiley, New York
SRPS EN 12390-3:2010. Testing hardened concrete—part 3: compressive strength of test specimens
Yaprak H, Karaci A, Demir I (2013) Prediction of the effect of varying cure conditions and w/c ratio on the compressive strength of concrete using artificial neural networks. Neural Comp Appl 22:133–141
Sarkar K, Tiwary A, Singh TN (2010) Estimation of strength parameters of rock using artificial neural networks. Bull Eng Geol Environ 69:599–606
Monjezi M, Singh TN, Khandelwal M, Sinha S, Singh V, Hosseini I (2006) Prediction and analysis of blast parameters using artificial neural network. Noise Vib Control Worldw 37:8–16
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representation by error propagation. In: Rumelhart DE, McCleland JL (eds) Parallel distribution processing: explorations in the microstructure of cognition, vol 1. MIT Press, Cambridge, pp 318–362
Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4:4–22
Sonmez H, Gokceoglu C, Nefeslioglu HA, Kayabasi A (2006) Estimation of rock modulus: for intact rocks with an artificial neural network and for rock masses with a new empirical equation. Int J Rock Mech Min 43:224–235
Looney CG (1996) Advances in feed-forward neural networks: demystifying knowledge acquiring black boxes. IEEE Trans Knowl Data Eng 8:211–226
Nelson M, Illingworth WT (1990) A practical guide to neural nets. Addison-Wesley, Reading
MATLAB Neural Network Toolbox (2014). www.mathworks.com/products/neural-network
Khandelwal M, Singh TN (2010) Prediction of macerals contents of Indian coals from proximate and ultimate analyses using artificial neural networks. Fuel 89:1101–1109
Singh TN, Kanchan R, Verma AK, Saigal K (2005) A comparative study of ANN and Neuro-fuzzy for the prediction of dynamic constant of rockmass. J Earth Syst Sci 114:75–86
Fletcher R (2000) Practical methods of optimization. Wiley, New York
Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533
Dennis JE, Schnabel RB (1987) Numerical methods for unconstrained optimization and nonlinear equations. Society for industrial and applied mathematics
Battiti R (1992) First- and second-order methods for learning: between steepest descent and Newton’s method. Neural Comput 4:141–166
Monjezi M, Hasanipanah M, Khandelwal M (2013) Evaluation and prediction of blast-induced ground vibration at Shur River Dam, Iran, by artificial neural network. Neural Comput Appl 22:1637–1643
Khandelwal M, Singh TN (2009) Prediction of blast-induced ground vibration using artificial neural network. Int J Rock Mech Min 46:1214–1222
Yang Y, Zang O (1997) A hierarchical analysis for rock engineering using artificial neural networks. Rock Mech Rock Eng 30:207–222
Acknowledgments
This research was partly supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia (No. 176016). Special thanks go to Tomislav Vasović for thorough participation in the experimental part of the performed research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kostić, S., Vasović, D. Prediction model for compressive strength of basic concrete mixture using artificial neural networks. Neural Comput & Applic 26, 1005–1024 (2015). https://doi.org/10.1007/s00521-014-1763-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1763-1