This research aims to optimize the mixing proportion of recycled aggregate concrete (RAC) using neural networks (NNs) based on genetic algorithms (GAs) for increasing the use of recycled aggregate (RA). NN and GA were used to predict the compressive strength of the concrete at 28 days. And sensitivity analysis of the NN based on GA was used to find the mixing ratio of RAC. The mixing criteria for RAC were determined and the replacement ratio of RAs was identified. This research reveal that the proposed method, which is NN based on GA, is proper for optimizing appropriate mixing proportion of RAC. Also, this method would help the construction engineers to utilize the recycled aggregate and reduce the concrete waste in construction process.
Recycled aggregate concrete (RAC) has been widely studied in Korea as part of the effort to preserve natural resources and prevent environmental disruption. Currently, many researchers have studied about application of recycled aggregates (RAs) as the base or subbase material in road construction [
Therefore, it should be more effective to determine the mixing proportion for RAC than to attempt to improve the quality of the RAs. The quality of concrete, as determined by its compressive strength and durability, depends on the mixing proportions of the concrete and the mixing preparation technique, as well as on the quality of the concrete components [
Therefore, it applied a neural network (NN) and a genetic algorithm (GA) to the mixing of RAC as a tool for the solution of those problems. This research proposes criteria for optimal mixing design of a RAC by sensitivity analysis of NN. Also, with designed mixing proportion, it is able to estimate the compressive strength of RAC. Changes in the quality of the RAC according to the mixing ratio of its components were verified by experimental research in the laboratory, and the quality of RAC predicted by the applied NN was compared with the experimental data.
This research was divided into three main phases (Figure
The three steps of this study for RAC mixing. (a) Each factor and
Generally, the NN is designed for the specific set of input as well as output. The number of inputs and outputs is not restricted, which is one advantage of NN [
The constituents of the concrete used in this study included ASTM C 150 Type I Portland cement, the specific gravity of which is 3.16, recycled coarse aggregates (RCA), and recycled fine aggregates (RFA), made using first-class aggregates produced from a RAs manufacturing corporation, which is BLUESTONE Corporation in South Korea (water absorption ratios: RFA ≤ 5%, RCA ≤ 3%; specific gravity: RFA
Physical properties of RAs (1st class) and NAs.
Source of aggregate | Fineness modulus | Specific gravity | Water absorption (%) |
---|---|---|---|
NCA | 6.52 | 2.64 | 1.24 |
NFA | 2.52 | 2.55 | 1.53 |
RCA | 6.65 | 2.53 | 2.86 |
RFA | 3.89 | 2.43 | 4.95 |
The American Concrete Institute (ACI) Standard 211.1, “Recommended Practice for Selecting Proportions for Normal-Weight Concrete,” was used to proportion the concrete mixtures. The RFA was replaced at 0%, 10%, 30%, 50%, 70%, and 100% (by weight), and the RCA was replaced at 0%, 30%, 50%, and 100% (by weight). Table
Sample of specified concrete mixing proportions used for NN training.
S/a (%) | Unit content (kg/m3) | Admixtures (g) | Air (%) | Slump (cm) | Compressive strength (MPa) | ||||||
---|---|---|---|---|---|---|---|---|---|---|---|
NCA | RCA | NFA | RFA | AE-reducing | AE agent | ||||||
42 | 1008.68 | 0 | 724.81 | 0 | 196 | 4.9 | 4.3 | 21.5 | 33.71 | 33.79 | 33.87 |
1008.68 | 0 | 652.33 | 72.48 | 196 | 4.9 | 3.9 | 22 | 30.45 | 28.43 | 30.43 | |
706.08 | 302.60 | 507.37 | 217.44 | 196 | 2.45 | 5.8 | 22 | 33.64 | 32.65 | 33.74 | |
706.08 | 302.60 | 362.405 | 361.405 | 196 | 2.45 | 2.0 | 23 | 35.79 | 32.80 | 37.02 | |
504.34 | 504.34 | 362.405 | 361.405 | 196 | 2.45 | 2.8 | 25 | 33.71 | 36.13 | 34.38 | |
504.34 | 504.34 | 0 | 724.81 | 196 | 2.45 | 2.3 | 20 | 31.67 | 31.68 | 26.35 | |
0 | 1008.68 | 724.81 | 0 | 196 | 2.45 | 4.5 | 17 | 32.22 | 28.39 | 28.58 | |
0 | 1008.68 | 652.33 | 72.48 | 196 | 2.45 | 4.5 | 20 | 30.42 | 28.90 | 32.34 | |
| |||||||||||
47 | 921.73 | 0 | 567.77 | 229.19 | 196 | 1.225 | 6.0 | 22.5 | 35.83 | 36.01 | 35.44 |
921.73 | 0 | 405.55 | 381.97 | 196 | 1.225 | 3.3 | 10 | 38.16 | 38.23 | 36.16 | |
645.21 | 270.14 | 729.99 | 76.39 | 196 | 1.225 | 5.6 | 11 | 34.91 | 35.30 | 33.52 | |
645.21 | 270.14 | 567.77 | 229.19 | 196 | 1.225 | 4.7 | 17 | 35.94 | 35.03 | 34.66 | |
460.86 | 450.23 | 567.77 | 229.19 | 196 | 1.225 | 3.8 | 22.5 | 33.70 | 29.98 | 35.30 | |
460.86 | 450.23 | 405.55 | 381.97 | 196 | 1.225 | 3.3 | 19 | 32.35 | 35.48 | 35.23 | |
0 | 900.46 | 243.33 | 534.76 | 196 | 1.225 | 2.5 | 21 | 34.15 | 34.11 | 34.92 | |
0 | 900.46 | 0 | 763.94 | 196 | 1.225 | 3.5 | 17 | 30.52 | 31.34 | 33.15 | |
| |||||||||||
52 | 834.77 | 0 | 807.64 | 84.52 | 196 | 0 | 7.2 | 22.5 | 29.08 | 30.27 | 29.99 |
834.77 | 0 | 628.17 | 253.26 | 196 | 0 | 6.8 | 23 | 27.64 | 29.29 | 30.61 | |
584.34 | 244.65 | 897.38 | 0 | 196 | 0 | 2.1 | 25 | 30.65 | 33.06 | 34.66 | |
584.34 | 244.65 | 448.69 | 422.6 | 196 | 0 | 2.8 | 21 | 32.87 | 30.62 | 29.82 | |
417.39 | 407.75 | 807.64 | 84.52 | 196 | 0 | 3.4 | 16.5 | 32.78 | 33.13 | 31.87 | |
417.39 | 407.75 | 628.17 | 253.26 | 196 | 0 | 3.4 | 16 | 33.09 | 34.03 | 33.48 | |
0 | 815.51 | 897.38 | 0 | 196 | 0 | 3.0 | 14.5 | 35.60 | 31.52 | 32.64 | |
0 | 815.51 | 807.64 | 84.52 | 196 | 0 | 3.4 | 15 | 35.63 | 29.06 | 29.97 |
Admixtures, unit water content, unit cement content, and designed compressive strength are as follows: water/cement ratio (W/C): 50%; unit water content: 175 kg/m3; unit cement content: 350 kg/m3; designed compressive strength: 35 MPa.
All test procedures in sieve analysis, specific gravities, and the absorptions of aggregates conformed to ASTM Standards C 136, C 127, and C 128, respectively. Making and curing the concrete and the compressive strength of the cylindrical concrete specimens conformed to ASTM C 192 and ASTM C 39, respectively.
Seventy-two casts, for each of which five cylindrical (28-day) concrete specimens were cast (i.e., a total of 360), were prepared for mechanical testing. A cylindrical concrete specimen with a diameter of 100 mm and a depth of 200 mm (
Figure
Histogram of compressive strengths of
In this section, the construction of a compressive strength prediction model based on NN and GA is described. The NN architecture was composed of three layers (Figure
Backpropagation of NN.
The learning of NN is accomplished by a backpropagation algorithm (BPN), and the BPN has one of the following transfer functions sigmoid, linear, and exponential functions, that are used to calculate the output for each neuron, except for the input neuron. Among those transfer functions, sigmoid function is used most extensively and has many advantages:
The NN is inspired by the neuronal structure and operation of the biological brain. Figure
(i) At early, NN does connection weights
(ii) Delta (
(iii) NN calculates for backward from output layer again. Do a connection weights (
(iv) Also, it calculates for backward from hidden layer again. The hidden layer, by the same formula that is calculated for backward in output layer, is calculated toward input layer from the nearest layer to output layer, and the delta of output layer is as follows:
(v) Repeat all learning data from (i) to (iv) steps. Uniting MSE (mean squared error) value of all learning data that get by repeating, learning of once is completed
(vi) If the MSE is not satisfied target error value from (i) step and reached in target error value, this circulation operation is repeated continuously.
The GA employs Darwinian selection and Mendelian crossover principles. Because GAs are robust and guided random search methods, they have found a niche in the nonlinear programming field. GA is based on the collective learning of a population, the individuals of which represent the potential solutions for the problem to be solved. GA transfers a group of genetic individuals from one generation to the next. A set of individuals from the same generation is known as a population. Each population goes through a series of genetic operators, that is, selection, recombination, or variation, to produce the next generation. An in-depth analysis is given in [
NN is commonly used for difficult tasks involving intuitive judgment or requiring the detection of data patterns that elude conventional analytic techniques. The performance of NN, however, is affected by the network architecture and its parameter settings. In NN models, these factors have been determined by heuristic and trial-and-error methods, which are time-consuming and tedious [ If the number of input variables is “ Each individual corresponded with input variable of NN, and corresponded input variable is applied to NN and the NN learn. The learned MSE of NN gets fitness value of each chromosome. Individuals which the fitness valued pass hybridization (crossover) or mutation process. At this process, individuals that have excellent fitness value exist, and individuals that are not so disappear. Until reaching optimum result, process of (ii) and (iii) as established number of households is repeated. Passing through this process, chromosomes that have a bad influence upon result value of NN disappears, and individuals whose fitness is superior exist. As this, combination of input variable whose estimation correctness of NN is high is decided. A more in-depth content is given in [
The GA application process for optimizing the number of input variables in the input layer, the number of neurons in the hidden layer, and the coefficient of learning rates of NN was as follows. First, the numbers of hidden layers and output neurons in the NN were set to 1 (2 and 3) and 1, respectively. All chromosomes were automatically set in NN so that they consisted of the numbers of input variables, of hidden neurons, and of learning rates. NN also automatically produced their initial values. The values for these input variables were set in a range with a lower limit of
After the parameter values (number of input variables, hidden neurons, step size, and momentum for each chromosome) were translated into the predefined NN, the network of NN was trained on the training data set. A cross-validation data set was used to test whether the stopping criteria were satisfied. The training process for the BPN stopped after a maximum of 1,000 epochs or until there was no improvement in mean squared error (MSE) for 1,000 epochs on the cross-validation data set. The fitness of every chromosome was evaluated by measuring the MSE, which is the estimated result on a cross-validation data set.
The number of data sets used to train the NN was 176, and the average training error was 5.26% (lowest training error 0.06%, highest training error 9.94%). As can be seen in Figure
Results of training with 176 data sets.
The test results given in Figure
Results of testing the trained model (40 data sets).
The sensitivity of the input variables of the NN (such as RCA, RFA, and air content) to the compressive strength of the RAC was also analysed using the constructed NN model.
Because properties of RAs are different from those of NAs, shape, surface, impurity content, agent usage, and others, it is required to research how much those properties of NAs have an effect on the compressive strength of RAC. And based on the sensitivity analysis, a mixing design of RAC will be made. Sensitivity analysis evaluates the changes in training error resulting from a change in an input value. The 216 data points obtained by experimentation were used to analyse the sensitivity of the input variables. In this study, NN with 2 hidden layers optimized by GA was used for the sensitivity analysis and to map the inputs and outputs.
The sensitivity of RCA/NCA, which represents the change in compressive strength according to the replacement ratio of RCA, shows a relatively higher value in Figures
Sensitivity about the mean showing the dependence on the input parameters.
Sensitivity of the input parameters to the compressive strength, showing the effect of varying the input value on the parameters.
In Figure
In Figure
Sensitivity analysis shows that compressive strength was more affected by the replacement ratio of RCA than by the replacement ratio of RFA. The deflection of compressive strength by the cross-matches of RCA and RFA is shown in Figure
Deflection of compressive strength with RCA and RFA replacing ratios.
Range of AE admixture.
Range of slump and air content.
It acquired criteria (Table
Summary of results (approximate range of each parameter).
Required strength (MPa) | S/a (%) | Air (%) | Slump (cm) | Replacement ratio (%) | Admixtures (g) | ||
---|---|---|---|---|---|---|---|
RCA (1st Class) | RFA (1st Class) | AE-water reducing agent | AE agent | ||||
33~34 | 42 |
|
|
0~30% | 0~50% | 196 | 5~10 |
47 | 0~50% | 0~50% | 196 | 5~10 | |||
52 | 0~50% | 0~30% | 196 | — |
The replacement ratio of RAs applied the maximum value (RCA 30% and RFA 50% at S/a 42%; RCA 50% and RFA 50% at S/a 47%; RCA 50% and RFA 30% at S/a 52%) that is registered in Table
Criteria evaluation.
S/a (%) | Unit content (kg/m3) | Admixtures (g) | Target value | Test value | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Cement | Water | NCA | RCA | NFA | RFA | AE-water reducing agent | AE agent | Air (%) | Slump (cm) | Strength (MPa) | Air (%) | Slump (cm) | Strength (MPa) | |
42 | 350 | 175 | 719.7 | 291 | 368.9 | 350.2 | 202 | 4.9 |
|
|
33 | 4.2 | 18.4 | 34.4 |
47 | 469.7 | 443.1 | 412.9 | 391.9 | 205 | 1.225 | 4.1 | 21.7 | 31.7 | |||||
52 | 425.4 | 401.3 | 632.9 | 257.5 | 203 | 1.014 | 4.2 | 20.1 | 31.5 |
This study presents an appropriate quality range for RAs and the other components of RAC using sensitivity analysis with neural networks, for use in the production of RAs and RAC, and ultimately to promote the use of RAs in concrete. In this study, the mixing criteria of the basic concrete for RAC were determined. RCA content and the AE admixture content are the most important to the compressive strength of RAC. Finally, the results of this study will be applied to use in various mixing proportions of recycled concrete. This research will contribute to improve the usage of the recycled aggregate in construction industry and to reduce the waste in construction process.