Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network
Abstract
:1. Introduction
2. Research Background
2.1. Artificial Neural Network
2.2. ANN-Based Prediction of Concrete Properties
3. Establishment of A Database
4. Prediction Model for Compressive Strength and Elastic Modulus Using ANN
4.1. Input Parameters
4.2. Determination of the Optimal ANN Architecture
5. Evaluation of Prediction Accuracy
5.1. Prediction Results Using the ANN Model
5.2. Comparative Analysis
6. Conclusions
Author Contributions
Funding
Conflicts of Interest
Appendix A
Literatures | Mix Proportion [kg/m3] | Volume Fraction | Density [kg/m3] | σ28 [MPa] | E28 [GPa] | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
w/b | W | C | FA | SF | CNWA | CLWA | FNWA | FLWA | CNWA | CLWA | FNWA | FLWA | ||||
Kim et al., 2010. [8] | 0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 861 | 0 | 0.30 | 0 | 0.34 | 0 | 2300 | 47 | 37.0 |
0.38 | 175 | 460 | 0 | 0 | 608 | 117 | 861 | 0 | 0.22 | 0.07 | 0.34 | 0 | 2280 | 44 | 29.0 | |
0.38 | 175 | 460 | 0 | 0 | 405 | 234 | 861 | 0 | 0.15 | 0.15 | 0.34 | 0 | 2220 | 43 | 30.0 | |
0.38 | 175 | 460 | 0 | 0 | 203 | 352 | 861 | 0 | 0.07 | 0.22 | 0.34 | 0 | 2200 | 42 | 33.0 | |
0.38 | 175 | 460 | 0 | 0 | 0 | 469 | 861 | 0 | 0 | 0.30 | 0.34 | 0 | 2150 | 32 | 30.0 | |
0.38 | 175 | 460 | 0 | 0 | 604 | 154 | 861 | 0 | 0.22 | 0.07 | 0.34 | 0 | 2280 | 44 | 31.0 | |
0.38 | 175 | 460 | 0 | 0 | 402 | 308 | 861 | 0 | 0.15 | 0.15 | 0.34 | 0 | 2150 | 40 | 26.0 | |
0.38 | 175 | 460 | 0 | 0 | 201 | 463 | 861 | 0 | 0.07 | 0.22 | 0.34 | 0 | 2100 | 40 | 24.0 | |
0.38 | 175 | 460 | 0 | 0 | 0 | 617 | 861 | 0 | 0 | 0.30 | 0.34 | 0 | 2000 | 37 | 25.0 | |
Bogas and Gomes 2013. [30] | 0.50 | 225 | 450 | 0 | 0 | 0 | 374 | 676 | 0 | 0 | 0.35 | 0.26 | 0 | 1763 | 35 | - |
0.50 | 225 | 450 | 0 | 0 | 0 | 303 | 676 | 0 | 0 | 0.35 | 0.26 | 0 | 1686 | 27 | - | |
0.35 | 158 | 450 | 0 | 0 | 0 | 374 | 847 | 0 | 0 | 0.35 | 0.32 | 0 | 1897 | 49 | - | |
0.35 | 158 | 450 | 0 | 0 | 0 | 452 | 833 | 0 | 0 | 0.35 | 0.32 | 0 | 1942 | 66 | - | |
0.35 | 158 | 450 | 0 | 0 | 0 | 247 | 846 | 0 | 0 | 0.35 | 0.32 | 0 | 1776 | 31 | - | |
Bogas et al., 2015. [31] | 0.55 | 193 | 350 | 0 | 0 | 0 | 382 | 825 | 0 | 0 | 0.35 | 0.32 | 0 | 1897 | 38 | - |
0.55 | 193 | 350 | 0 | 0 | 0 | 208 | 825 | 0 | 0 | 0.35 | 0.32 | 0 | 1710 | 19 | - | |
Nguyen et al., 2014. [4] | 0.45 | 190 | 426 | 0 | 0 | 0 | 445 | 554 | 0 | 0 | 0.45 | 0.23 | 0 | 1440 | 38 | 19.3 |
0.45 | 190 | 426 | 0 | 0 | 0 | 445 | 277 | 213 | 0 | 0.45 | 0.11 | 0.11 | 1380 | 36 | 18.6 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 445 | 0 | 427 | 0 | 0.45 | 0 | 0.22 | 1320 | 34 | 17.3 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 626 | 554 | 0 | 0 | 0.45 | 0.23 | 0 | 1490 | 35 | 19.1 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 626 | 277 | 177 | 0 | 0.45 | 0.11 | 0.11 | 1410 | 33 | 17.0 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 626 | 0 | 354 | 0 | 0.45 | 0 | 0.22 | 1340 | 31 | 15.3 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 558 | 554 | 0 | 0 | 0.45 | 0.23 | 0 | 1410 | 31 | 16.3 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 558 | 277 | 189 | 0 | 0.45 | 0.11 | 0.11 | 1290 | 26 | 13.6 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 558 | 0 | 379 | 0 | 0.45 | 0 | 0.23 | 1170 | 22 | 11.1 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 673 | 554 | 0 | 0 | 0.45 | 0.23 | 0 | 1520 | 40 | 18.2 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 673 | 277 | 189 | 0 | 0.45 | 0.11 | 0.11 | 1400 | 35 | 15.7 | |
0.45 | 190 | 426 | 0 | 0 | 0 | 673 | 0 | 379 | 0 | 0.45 | 0 | 0.23 | 1280 | 31 | 13.6 | |
0.45 | 190 | 426 | 0 | 0 | 1105 | 0 | 554 | 0 | 0.45 | 0 | 0.23 | 0 | 2030 | 52 | 32.7 | |
Choi et al., 2006. [33] | 0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 861 | 0 | 0.31 | 0 | 0.34 | 0 | 2306 | 49 | 34.0 |
0.38 | 175 | 460 | 0 | 0 | 608 | 117 | 861 | 0 | 0.23 | 0.07 | 0.34 | 0 | 2221 | 46 | 27.0 | |
0.38 | 175 | 460 | 0 | 0 | 405 | 234 | 861 | 0 | 0.16 | 0.15 | 0.34 | 0 | 2135 | 45 | 24.0 | |
0.38 | 175 | 460 | 0 | 0 | 203 | 352 | 861 | 0 | 0.08 | 0.22 | 0.34 | 0 | 2051 | 46 | 25.0 | |
0.38 | 175 | 460 | 0 | 0 | 0 | 469 | 861 | 0 | 0 | 0.30 | 0.34 | 0 | 1965 | 34 | 28.0 | |
0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 645 | 158 | 0.31 | 0 | 0.25 | 0.10 | 2248 | 46 | 30.0 | |
0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 430 | 316 | 0.31 | 0 | 0.17 | 0.20 | 2191 | 46 | 33.0 | |
0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 215 | 473 | 0.31 | 0 | 0.08 | 0.29 | 2133 | 53 | 31.0 | |
0.38 | 175 | 460 | 0 | 0 | 810 | 0 | 0 | 631 | 0.31 | 0 | 0 | 0.39 | 2076 | 59 | 30.0 | |
Yang and Huang 1998. [34] | 0.28 | 178 | 626 | 0 | 0 | 0 | 292 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2192 | 41 | 23.0 |
0.28 | 178 | 626 | 0 | 0 | 0 | 299 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2199 | 44 | 23.8 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 311 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2211 | 50 | 24.7 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 389 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2132 | 37 | 20.6 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 399 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2142 | 41 | 21.5 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 415 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2158 | 47 | 22.6 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 486 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2073 | 35 | 18.2 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 498 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2085 | 38 | 19.0 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 519 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2106 | 45 | 20.3 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 583 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 2013 | 62 | 15.8 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 598 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 2028 | 36 | 17.2 | |
0.28 | 178 | 626 | 0 | 0 | 0 | 623 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 2053 | 42 | 18.7 | |
Kockal and Ozturan 2011. [10] | 0.26 | 158 | 551 | 0 | 55 | 0 | 592 | 636 | 0 | 0 | 0.37 | 0.24 | 0 | 1860 | 42 | 19.6 |
0.26 | 157 | 548 | 0 | 55 | 0 | 567 | 633 | 0 | 0 | 0.36 | 0.24 | 0 | 1915 | 54 | 26.0 | |
0.26 | 157 | 549 | 0 | 55 | 0 | 580 | 634 | 0 | 0 | 0.36 | 0.24 | 0 | 1943 | 56 | 25.7 | |
0.26 | 158 | 551 | 0 | 55 | 981 | 0 | 636 | 0 | 0.36 | 0 | 0.24 | 0 | 2316 | 63 | 36.8 | |
Gesoglu et al., 2007. [36] | 0.35 | 192 | 550 | 0 | 0 | 0 | 487 | 862 | 0 | 0 | 0.27 | 0.33 | 0 | 2101 | 36 | 20.0 |
0.35 | 192 | 547 | 0 | 0 | 0 | 646 | 624 | 0 | 0 | 0.36 | 0.24 | 0 | 2015 | 28 | 18.0 | |
0.35 | 191 | 547 | 0 | 0 | 0 | 465 | 858 | 0 | 0 | 0.27 | 0.33 | 0 | 2070 | 60 | 29.0 | |
0.35 | 193 | 550 | 0 | 0 | 0 | 624 | 628 | 0 | 0 | 0.36 | 0.24 | 0 | 2000 | 57 | 28.0 | |
0.35 | 193 | 550 | 0 | 0 | 0 | 506 | 863 | 0 | 0 | 0.28 | 0.33 | 0 | 2122 | 50 | 25.0 | |
0.35 | 193 | 550 | 0 | 0 | 0 | 675 | 627 | 0 | 0 | 0.38 | 0.24 | 0 | 2056 | 46 | 27.0 | |
0.55 | 220 | 399 | 0 | 0 | 0 | 509 | 902 | 0 | 0 | 0.29 | 0.35 | 0 | 2032 | 23 | 17.0 | |
0.55 | 220 | 401 | 0 | 0 | 0 | 681 | 658 | 0 | 0 | 0.38 | 0.25 | 0 | 1960 | 20 | 14.0 | |
0.55 | 221 | 403 | 0 | 0 | 0 | 475 | 908 | 0 | 0 | 0.28 | 0.35 | 0 | 2010 | 37 | 19.0 | |
0.55 | 220 | 399 | 0 | 0 | 0 | 631 | 657 | 0 | 0 | 0.37 | 0.25 | 0 | 1907 | 34 | 18.0 | |
0.55 | 218 | 397 | 0 | 0 | 0 | 525 | 895 | 0 | 0 | 0.29 | 0.34 | 0 | 2038 | 29 | 19.0 | |
0.55 | 219 | 399 | 0 | 0 | 0 | 706 | 657 | 0 | 0 | 0.39 | 0.25 | 0 | 1981 | 25 | 17.0 | |
Chi et al., 2003. [32] | 0.28 | 171 | 602 | 0 | 0 | 0 | 297 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2166 | 42 | 22.9 |
0.28 | 171 | 602 | 0 | 0 | 0 | 396 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2108 | 38 | 21.5 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 495 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2051 | 35 | 20.1 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 594 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1993 | 32 | 18.7 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 297 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2112 | 33 | 20.3 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 396 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2054 | 30 | 16.5 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 495 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1997 | 28 | 16.5 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 594 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1939 | 23 | 13.8 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 297 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2072 | 30 | 18.2 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 396 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2014 | 26 | 15.5 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 495 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1957 | 23 | 14.2 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 594 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1899 | 21 | 13.3 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 304 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2166 | 44 | 22.8 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 406 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2108 | 41 | 21.7 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 507 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2051 | 39 | 18.9 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 608 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1993 | 36 | 18.2 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 304 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2112 | 37 | 21.4 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 406 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2054 | 33 | 18.2 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 507 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1997 | 30 | 17.4 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 608 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1939 | 28 | 16.1 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 304 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2072 | 27 | 17.1 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 406 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2014 | 26 | 17.0 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 507 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1957 | 25 | 15.2 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 608 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1899 | 22 | 14.8 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 317 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2166 | 48 | 23.1 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 422 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2108 | 47 | 21.9 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 528 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 2051 | 46 | 20.9 | |
0.28 | 171 | 602 | 0 | 0 | 0 | 634 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1993 | 43 | 19.8 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 317 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2112 | 38 | 21.9 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 422 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2054 | 38 | 21.4 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 528 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1997 | 39 | 20.6 | |
0.39 | 202 | 517 | 0 | 0 | 0 | 634 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1939 | 38 | 18.0 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 317 | 1096 | 0 | 0 | 0.18 | 0.42 | 0 | 2072 | 31 | 19.3 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 422 | 939 | 0 | 0 | 0.24 | 0.36 | 0 | 2014 | 30 | 17.9 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 528 | 783 | 0 | 0 | 0.30 | 0.30 | 0 | 1957 | 28 | 16.3 | |
0.50 | 226 | 453 | 0 | 0 | 0 | 634 | 626 | 0 | 0 | 0.36 | 0.24 | 0 | 1899 | 30 | 15.4 | |
Kayali, 2008. [35] | 0.27 | 172 | 300 | 300 | 40 | 1001 | 0 | 288 | 0 | 0.37 | 0 | 0.12 | 0 | 2134 | 56 | 32.5 |
0.23 | 150 | 300 | 300 | 40 | 0 | 898 | 0 | 233 | 0 | 0.52 | 0 | 0.14 | 1540 | 45 | 16.7 | |
0.30 | 193 | 300 | 300 | 40 | 0 | 766 | 0 | 162 | 0 | 0.45 | 0 | 0.10 | 1747 | 63 | 23.7 | |
0.36 | 207 | 370 | 142 | 57 | 894 | 0 | 626 | 0 | 0.33 | 0 | 0.24 | 0 | 2260 | 58 | 32.5 | |
0.36 | 207 | 370 | 142 | 57 | 0 | 481 | 0 | 476 | 0 | 0.28 | 0 | 0.28 | 1770 | 53 | 19.0 | |
0.36 | 207 | 370 | 142 | 57 | 820 | 0 | 626 | 0 | 0.33 | 0 | 0.24 | 0 | 2280 | 56 | 31.5 | |
0.36 | 207 | 370 | 142 | 57 | 0 | 440 | 0 | 511 | 0 | 0.28 | 0 | 0.32 | 1780 | 67 | 25.5 | |
Guneyisi et al., 2012. [29] | 0.35 | 193 | 550 | 0 | 0 | 0 | 688 | 688 | 0 | 0 | 0.36 | 0.27 | 0 | 2124 | 48 | - |
0.35 | 193 | 468 | 83 | 0 | 0 | 677 | 677 | 0 | 0 | 0.35 | 0.26 | 0 | 2101 | 45 | - | |
0.35 | 193 | 385 | 165 | 0 | 0 | 665 | 665 | 0 | 0 | 0.35 | 0.26 | 0 | 2078 | 42 | - | |
0.35 | 193 | 523 | 0 | 28 | 0 | 684 | 684 | 0 | 0 | 0.36 | 0.26 | 0 | 2117 | 53 | - | |
0.35 | 193 | 495 | 0 | 55 | 0 | 680 | 680 | 0 | 0 | 0.35 | 0.26 | 0 | 2109 | 54 | - | |
0.35 | 193 | 440 | 83 | 28 | 0 | 670 | 670 | 0 | 0 | 0.35 | 0.26 | 0 | 2090 | 48 | - | |
0.35 | 193 | 413 | 83 | 55 | 0 | 669 | 668 | 0 | 0 | 0.35 | 0.26 | 0 | 2085 | 48 | - | |
0.35 | 193 | 358 | 165 | 28 | 0 | 661 | 661 | 0 | 0 | 0.34 | 0.26 | 0 | 2070 | 43 | - | |
0.35 | 193 | 330 | 165 | 55 | 0 | 657 | 657 | 0 | 0 | 0.34 | 0.25 | 0 | 2062 | 43 | - | |
Rossignolo et al., 2003. [2] | 0.34 | 263 | 710 | 0 | 71 | 0 | 447 | 192 | 0 | 0 | 0.34 | 0.07 | 0 | 1605 | 54 | 15.2 |
0.37 | 251 | 613 | 0 | 61 | 0 | 494 | 215 | 0 | 0 | 0.38 | 0.08 | 0 | 1573 | 50 | 13.5 | |
0.41 | 245 | 544 | 0 | 54 | 0 | 533 | 228 | 0 | 0 | 0.41 | 0.09 | 0 | 1532 | 46 | 12.9 | |
0.45 | 237 | 484 | 0 | 48 | 0 | 560 | 242 | 0 | 0 | 0.43 | 0.09 | 0 | 1482 | 43 | 12.3 | |
0.49 | 238 | 440 | 0 | 44 | 0 | 585 | 250.8 | 0 | 0 | 0.45 | 0.10 | 0 | 1460 | 40 | 12.0 | |
Aslam et al., 2016. [37] | 0.36 | 173 | 480 | 0 | 0 | 0 | 360 | 890 | 0 | 0 | 0.30 | 0.33 | 0 | 1790 | 36 | 7.9 |
0.36 | 173 | 480 | 0 | 0 | 0 | 375 | 890 | 0 | 0 | 0.30 | 0.33 | 0 | 1810 | 37 | 9.6 | |
0.36 | 173 | 480 | 0 | 0 | 0 | 390 | 890 | 0 | 0 | 0.30 | 0.33 | 0 | 1850 | 42 | 10.2 | |
0.36 | 173 | 480 | 0 | 0 | 0 | 405 | 890 | 0 | 0 | 0.29 | 0.33 | 0 | 1840 | 44 | 11.7 | |
0.36 | 173 | 480 | 0 | 0 | 0 | 421 | 890 | 0 | 0 | 0.29 | 0.33 | 0 | 1860 | 43 | 13.0 | |
0.36 | 173 | 480 | 0 | 0 | 0 | 436 | 890 | 0 | 0 | 0.29 | 0.33 | 0 | 1910 | 41 | 15.0 | |
Alengaram et al., 2011. [27] | 0.30 | 179 | 515 | 27 | 54 | 0 | 542 | 436 | 0 | 0 | 0.43 | 0.16 | 0 | 1677 | 30 | 7.1 |
0.32 | 187 | 510 | 25 | 50 | 0 | 535 | 430 | 0 | 0 | 0.42 | 0.16 | 0 | 1743 | 27 | 6.5 | |
0.35 | 201 | 501 | 24 | 48 | 0 | 525 | 422 | 0 | 0 | 0.41 | 0.16 | 0 | 1643 | 26 | 5.5 | |
0.35 | 189 | 465 | 25 | 50 | 0 | 392 | 784 | 0 | 0 | 0.31 | 0.29 | 0 | 1869 | 38 | 10.9 | |
0.35 | 205 | 504 | 27 | 54 | 0 | 424 | 637 | 0 | 0 | 0.33 | 0.24 | 0 | 1810 | 35 | 10.0 | |
0.35 | 216 | 532 | 28 | 56 | 0 | 448 | 560 | 0 | 0 | 0.35 | 0.21 | 0 | 1787 | 33 | 8.6 | |
0.35 | 229 | 564 | 30 | 60 | 0 | 475 | 475 | 0 | 0 | 0.37 | 0.18 | 0 | 1759 | 30 | 7.9 | |
Wee et al., 1996. [28] | 0.40 | 170 | 425 | 0 | 0 | 1083 | 0 | 722 | 0 | 0.42 | 0 | 0.28 | 0 | 2400 | 63 | 41.8 |
0.40 | 170 | 383 | 0 | 43 | 1083 | 0 | 722 | 0 | 0.42 | 0 | 0.28 | 0 | 2401 | 70 | 43.0 | |
0.40 | 170 | 298 | 128 | 0 | 1083 | 0 | 722 | 0 | 0.42 | 0 | 0.28 | 0 | 2401 | 65 | 41.5 | |
0.35 | 170 | 437 | 0 | 43 | 1046 | 0 | 698 | 0 | 0.40 | 0 | 0.27 | 0 | 2394 | 86 | 45.0 | |
0.35 | 170 | 389 | 0 | 96 | 1046 | 0 | 698 | 0 | 0.40 | 0 | 0.27 | 0 | 2399 | 90 | 44.4 | |
0.30 | 165 | 550 | 0 | 0 | 1045 | 0 | 640 | 0 | 0.40 | 0 | 0.25 | 0 | 2400 | 78 | 44.3 | |
0.30 | 165 | 495 | 0 | 55 | 1046 | 0 | 640 | 0 | 0.40 | 0 | 0.25 | 0 | 2401 | 86 | 44.3 | |
0.30 | 165 | 385 | 165 | 0 | 1045 | 0 | 640 | 0 | 0.40 | 0 | 0.25 | 0 | 2400 | 81 | 43.9 | |
0.25 | 160 | 640 | 0 | 0 | 1043 | 0 | 587 | 0 | 0.40 | 0 | 0.23 | 0 | 2430 | 86 | 45.6 | |
0.25 | 160 | 608 | 0 | 32 | 1043 | 0 | 587 | 0 | 0.40 | 0 | 0.23 | 0 | 2430 | 96 | 46.6 | |
0.25 | 160 | 576 | 0 | 64 | 1043 | 0 | 587 | 0 | 0.40 | 0 | 0.23 | 0 | 2430 | 103 | 46.7 | |
0.25 | 160 | 544 | 0 | 96 | 1043 | 0 | 587 | 0 | 0.40 | 0 | 0.23 | 0 | 2430 | 104 | 46.3 | |
0.25 | 160 | 448 | 192 | 0 | 1043 | 0 | 587 | 0 | 0.40 | 0 | 0.23 | 0 | 2430 | 93 | 45.8 |
References
- Ke, Y.; Ortola, S.; Beaucour, A.L.; Dumontet, H. Identification of microstructural characteristics in lightweight aggregate concretes by micromechanical modelling including the interfacial transition zone (ITZ). Cem. Concr. Res. 2010, 40, 1590–1600. [Google Scholar] [CrossRef]
- Rossignolo, J.A.; Agnesini, M.V.C.; Morais, J.A. Properties of high-performance LWAC for precast structures with Brazilian lightweight aggregates. Cem. Concr. Compos. 2003, 25, 77–82. [Google Scholar] [CrossRef]
- Elsharief, A.; Cohen, M.D.; Olek, J. Influence of lightweight aggregate on the microstructure and durability of mortar. Cem. Concr. Res. 2005, 35, 1368–1376. [Google Scholar] [CrossRef]
- Nguyen, L.H.; Beaucour, A.L.; Ortola, S.; Noumowé, A. Influence of the volume fraction and the nature of fine lightweight aggregates on the thermal and mechanical properties of structural concrete. Constr. Build. Mater. 2014, 51, 121–132. [Google Scholar] [CrossRef]
- Yoon, J.Y.; Lee, J.Y.; Kim, J.H. Use of raw-state bottom ash for aggregates in construction materials. J. Mater. Cycles Waste Manag. 2019, 21, 838–849. [Google Scholar] [CrossRef]
- ASTM C330/C330M-17a. Standard Specification for Lightweight Aggregates for Structural Concrete; ASTM International: West Conshohocken, PA, USA, 2017. [Google Scholar]
- Guide for Structural Lightweight-Aggregate Concrete; ACI 213R-14; American Concrete Institute: Farmington Hills, MI, USA, 2014.
- Kim, Y.J.; Choi, Y.W.; Lachemi, M. Characteristics of self-consolidating concrete using two types of lightweight coarse aggregates. Constr. Build. Mater. 2010, 24, 11–16. [Google Scholar] [CrossRef]
- Bogas, J.A.; Gomes, A.; Pereira, M.F.C. Self-compacting lightweight concrete produced with expanded clay aggregate. Constr. Build. Mater. 2012, 35, 1013–1022. [Google Scholar] [CrossRef]
- Kockal, N.U.; Ozturan, T. Strength and elastic properties of structural lightweight concretes. Mater. Des. 2011, 32, 2396–2403. [Google Scholar] [CrossRef]
- Kanadasan, J.; Razak, H.A. Mix design for self-compacting palm oil clinker concrete based on particle packing. Mater. Des. 2014, 56, 9–19. [Google Scholar] [CrossRef] [Green Version]
- Nepomuceno, M.C.S.; Pereira-de-Oliveira, L.A.; Pereira, S.F. Mix design of structural lightweight self-compacting concrete incorporating coarse lightweight expanded clay aggregates. Constr. Build. Mater. 2018, 166, 373–385. [Google Scholar] [CrossRef]
- Lippmann, R. An introduction to computing with neural nets. IEEE ASSP Mag. 1987, 4, 4–22. [Google Scholar] [CrossRef]
- Ni, H.G.; Wang, J.Z. Prediction of compressive strength of concrete by neural networks. Cem. Concr. Res. 2000, 30, 1245–1250. [Google Scholar] [CrossRef]
- Belalia Douma, O.; Boukhatem, B.; Ghrici, M.; Tagnit-Hamou, A. Prediction of properties of self-compacting concrete containing fly ash using artificial neural network. Neural Comput. Appl. 2017, 28, 707–718. [Google Scholar] [CrossRef]
- Öztaş, A.; Pala, M.; Özbay, E.; Kanca, E.; Çagˇlar, N.; Bhatti, M.A. Predicting the compressive strength and slump of high strength concrete using neural network. Constr. Build. Mater. 2006, 20, 769–775. [Google Scholar] [CrossRef]
- Alshihri, M.M.; Azmy, A.M.; El-Bisy, M.S. Neural networks for predicting compressive strength of structural light weight concrete. Constr. Build. Mater. 2009, 23, 2214–2219. [Google Scholar] [CrossRef]
- Tavakkol, S.; Alapour, F.; Kazemian, A.; Hasaninejad, A.; Ghanbari, A.; Ramezanianpour, A.A. Prediction of lightweight concrete strength by categorized regression, MLR and ANN. Comput. Concr. 2013, 12, 151–167. [Google Scholar] [CrossRef]
- Davraz, M.; Kilinçarslan, Ş.; Ceylan, H. Predicting the Poisson Ratio of Lightweight Concretes using Artificial Neural Network. Acta Phys. Pol. A 2015, 128, B-184–B-187. [Google Scholar] [CrossRef]
- Tenza-Abril, A.J.; Villacampa, Y.; Solak, A.M.; Baeza-Brotons, F. Prediction and sensitivity analysis of compressive strength in segregated lightweight concrete based on artificial neural network using ultrasonic pulse velocity. Constr. Build. Mater. 2018, 189, 1173–1183. [Google Scholar] [CrossRef]
- Kalman Šipoš, T.; Miličević, I.; Siddique, R. Model for mix design of brick aggregate concrete based on neural network modelling. Constr. Build. Mater. 2017, 148, 757–769. [Google Scholar] [CrossRef]
- Demir, F. Prediction of elastic modulus of normal and high strength concrete by artificial neural networks. Constr. Build. Mater. 2008, 22, 1428–1435. [Google Scholar] [CrossRef]
- Atici, U. Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network. Expert Syst. Appl. 2011, 38, 9609–9618. [Google Scholar] [CrossRef]
- Bal, L.; Buyle-Bodin, F. Artificial neural network for predicting drying shrinkage of concrete. Constr. Build. Mater. 2013, 38, 248–254. [Google Scholar] [CrossRef]
- Hossain, K.M.A.; Anwar, M.S.; Samani, S.G. Regression and artificial neural network models for strength properties of engineered cementitious composites. Neural Comput. Appl. 2018, 29, 631–645. [Google Scholar] [CrossRef]
- Khademi, F.; Jamal, S.M.; Deshpande, N.; Londhe, S. Predicting strength of recycled aggregate concrete using Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System and Multiple Linear Regression. Int. J. Sustain. Built Environ. 2016, 5, 355–369. [Google Scholar] [CrossRef] [Green Version]
- Alengaram, U.J.; Mahmud, H.; Jumaat, M.Z. Enhancement and prediction of modulus of elasticity of palm kernel shell concrete. Mater. Des. 2011, 32, 2143–2148. [Google Scholar] [CrossRef]
- Wee, T.H.; Chin, M.S.; Mansur, M.A. Stress-Strain Relationship of High-Strength Concrete in Compression. J. Mater. Civ. Eng. 1996, 8, 70–76. [Google Scholar] [CrossRef]
- Guneyisi, E.; Gesoglu, M.; Booya, E. Fresh properties of self-compacting cold bonded fly ash lightweight aggregate concrete with different mineral admixtures. Mater. Struct. 2012, 45, 1849–1859. [Google Scholar] [CrossRef]
- Bogas, J.A.; Gomes, A. A simple mix design method for structural lightweight aggregate concrete. Mater. Struct. 2013, 46, 1919–1932. [Google Scholar] [CrossRef]
- Bogas, J.A.; de Brito, J.; Figueiredo, J.M. Mechanical characterization of concrete produced with recycled lightweight expanded clay aggregate concrete. J. Clean. Prod. 2015, 89, 187–195. [Google Scholar] [CrossRef]
- Chi, J.M.; Huang, R.; Yang, C.C.; Chang, J.J. Effect of aggregate properties on the strength and stiffness of lightweight concrete. Cem. Concr. Compos. 2003, 25, 197–205. [Google Scholar] [CrossRef]
- Choi, Y.W.; Kim, Y.J.; Shin, H.C.; Moon, H.Y. An experimental research on the fluidity and mechanical properties of high-strength lightweight self-compacting concrete. Cem. Concr. Res. 2006, 36, 1595–1602. [Google Scholar] [CrossRef]
- Yang, C.C.; Huang, R. Approximate Strength of Lightweight Aggregate Using Micromechanics Method. Adv. Cem. Based Mater. 1998, 7, 133–138. [Google Scholar] [CrossRef]
- Kayali, O. Fly ash lightweight aggregates in high performance concrete. Constr. Build. Mater. 2008, 22, 2393–2399. [Google Scholar] [CrossRef]
- Gesoğlu, M.; Özturan, T.; Güneyisi, E. Effects of fly ash properties on characteristics of cold-bonded fly ash lightweight aggregates. Constr. Build. Mater. 2007, 21, 1869–1878. [Google Scholar] [CrossRef]
- Aslam, M.; Shafigh, P.; Jumaat, M.Z.; Lachemi, M. Benefits of using blended waste coarse lightweight aggregates in structural lightweight aggregate concrete. J. Clean. Prod. 2016, 119, 108–117. [Google Scholar] [CrossRef]
- Al-Sahawneh, E.I. Size effect and strength correction factors for normal weight concrete specimens under uniaxial compression stress. Contemp. Eng. Sci. 2013, 6, 57–68. [Google Scholar] [CrossRef]
- Li, M.; Hao, H.; Shi, Y.; Hao, Y. Specimen shape and size effects on the concrete compressive strength under static and dynamic tests. Constr. Build. Mater. 2018, 161, 84–93. [Google Scholar] [CrossRef]
- Mehta, P.K.; Monteiro, P.J.M. Concrete: Microstructure, Properties, and Materials; McGraw Hill Eduation: New York, NY, USA, 2013. [Google Scholar]
- Lee, B.J.; Kee, S.H.; Oh, T.; Kim, Y.Y. Effect of Cylinder Size on the Modulus of Elasticity and Compressive Strength of Concrete from Static and Dynamic Tests. Adv. Mater. Sci. Eng. 2015, 2015, 580638. [Google Scholar] [CrossRef]
- Hamad, A.J. Size and shape effect of specimen on the compressive strength of HPLWFC reinforced with glass fibres. J. King Saud Univ. Eng. Sci. 2017, 29, 373–380. [Google Scholar] [CrossRef] [Green Version]
- Vakhshouri, B.; Nejadi, S. Prediction of compressive strength of self-compacting concrete by ANFIS models. Neurocomputing 2018, 280, 13–22. [Google Scholar] [CrossRef]
- Jafari, S.; Mahini, S.S. Lightweight concrete design using gene expression programing. Constr. Build. Mater. 2017, 139, 93–100. [Google Scholar] [CrossRef]
- Younis, K.H.; Pilakoutas, K. Strength prediction model and methods for improving recycled aggregate concrete. Constr. Build. Mater. 2013, 49, 688–701. [Google Scholar] [CrossRef]
- Zain, M.F.M.; Abd, M.S. Multiple Regression Model for Compressive Strength Prediction of High Performance Concrete. J. Appl. Sci. 2009, 9, 155–160. [Google Scholar]
- Tamura, S.; Tateishi, M. Capabilities of a four-layered feedforward neural network: Four layers versus three. IEEE Trans. Neural Netw. 1997, 8, 251–255. [Google Scholar] [CrossRef] [PubMed]
- Li, J.Y.; Chow, T.W.S.; Yu, Y.L. The estimation theory and optimization algorithm for the number of hidden units in the higher-order feedforward neural network. In Proceedings of the IEEE International Conference on Neural Networks, Perth, Australia, 27 November–1 December 1995; IEEE: Piscataway, NJ, USA, 1995; Volume 3, pp. 1229–1233. [Google Scholar]
- Sheela, K.G.; Deepa, S.N. Review on Methods to Fix Number of Hidden Neurons in Neural Networks. Math. Probl. Eng. 2013, 2013, 1–11. [Google Scholar] [CrossRef] [Green Version]
- MATLAB and Deep Learning Toolbox Release 2018b; The MathWorks, Inc.: Natick, MA, USA, 2018.
- Kuhn, M.; Johnson, K. Applied Predictive Modeling; Springer: Berlin, Germany, 2013. [Google Scholar]
- DeRousseau, M.A.; Kasprzyk, J.R.; Srubar, W.V. Computational design optimization of concrete mixtures: A review. Cem. Concr. Res. 2018, 109, 42–53. [Google Scholar] [CrossRef]
- Nguyen, T.; Kashani, A.; Ngo, T.; Bordas, S. Deep neural network with high-order neuron for the prediction of foamed concrete strength. Comput. Civ. Infrastruct. Eng. 2019, 34, 316–332. [Google Scholar] [CrossRef]
Literature | Target | ANN Architecture (Number of Neurons in Input-Hidden-Output Layers) |
---|---|---|
Ni and Wang (2000) [14] | Compressive strength (65 data) | 11-7-1 |
Oztas et al. (2006) [16] | Compressive strength and fluidity (187 data) | 7-5-3-2 |
Demir (2008) [22] | Elastic modulus (159 data) | 1-3-1, 1-5-1, 1-3-3-1 |
Alshihri et al. (2009) [17] | Compressive strength (108 data) | 8-14-4, 8-14-6-4 |
Atici (2011) [23] | Compressive strength (27 data) | 3-5-1, 4-6-1, 4-6-1 3-5-1, 5-6-1, 2-4-1 |
Bal and Buyle-Bodin (2013) [24] | Drying shrinkage (176 data) | 11-8-4-1, 11-8-6-1 11-9-4-1, 11-9-6-1 |
Khademi et al. (2016) [26] | Compressive strength (257 data) | 14-29-1 |
Douma et al. (2017) [15] | Fluidity (114 data) | 6-17-1 |
Hossain et al. (2018) [25] | Compressive and tensile strength (180 data) | 12-8-1, 10-7-1 |
Mix Proportion and Material Properties | LWAC | NWAC | |
---|---|---|---|
Concrete density | 1170–2280 kg/m3 | 2030–2430 kg/m3 | |
w/b | 0.23–0.55 | 0.25–0.45 | |
Mass | Water | 150–263 kg/m3 | 158–207 kg/m3 |
Cement | 300–710 kg/m3 | 300–640 kg/m3 | |
Fly ash | 0–300 kg/m3 | 0–300 kg/m3 | |
Silica fume | 0–71 kg/m3 | 0–96 kg/m3 | |
CNWA | 0–810 kg/m3 | 810–1105 kg/m3 | |
FNWA | 0–1096 kg/m3 | 288–861 kg/m3 | |
CLWA | 0–898 kg/m3 | 0 | |
FLWA | 0–631 kg/m3 | 0 | |
Volume fraction | CNWA | 0–0.31 | 0.30–0.45 |
FNWA | 0–0.42 | 0.12–0.34 | |
CLWA | 0–0.52 | 0 | |
FLWA | 0–0.39 | 0 | |
Specific gravity | Cement | 3100–3160 kg/m3 | |
Fly ash | 2060–2470 kg/m3 | ||
Silica fume | 2000–2280 kg/m3 | ||
CNWA | 2460–2740 kg/m3 | ||
FNWA | 2460–2700 kg/m3 | ||
CLWA | 600–2070 kg/m3 | ||
FLWA | 1340–1790 kg/m3 |
Input Variables | |
---|---|
Oztas et al. [16] | w/b ratio, sand-to-aggregate ratio, replacement ratio of fly ash and silica fume, mass of water, chemical admixture |
Alshihri et al. [17] | w/c ratio, curing period, mass of FNWA, CLWA, FLWA, silica fume, chemical admixture |
Khademi et al. [26] | w/c ratio, aggregate-to-cement ratio, replacement ratio of recycled aggregate, water-to-total materials ratio, mass of water, cement, CNWA, FNWA, recycled aggregate, chemical admixture |
Douma et al. [15] | w/b ratio, replacement ratio of fly ash, content of binders, CNWA, FNWA, chemical admixture |
ANN model | w/b ratio, concrete density, mass of water, cement, fly ash, silica fume, volume fraction of CNWA, FNWA, CLWA, FLWA |
ANN Model | Prediction for Compressive Strength | Prediction for Elastic Modulus |
---|---|---|
Number of layers | 2 | 4 |
Number of neurons | 14 | 23 |
Training MSE | 48.7 | 7.8 |
Test MSE | 98.2 | 16.9 |
Error Configuration | Compressive Strength | Elastic Modulus | ||
---|---|---|---|---|
Training | Test | Training | Test | |
Square error | 1.3 × 10−3–6.2 × 102 | 3.6 × 10−2–2.9 × 102 | 1.5 × 10−4–8.5 × 10 | 6.5 × 10−5–4.4 × 10 |
MAE | 9.6% | 14.5% | 6.9% | 8.5% |
Correlation coefficient | 0.930 | 0.977 |
Prediction Accuracy (MAE) | Compressive Strength | Elastic Modulus | ||
---|---|---|---|---|
Training | Test | Training | Test | |
ANN model | 9.6% | 14.5% | 6.9% | 8.5% |
Linear regression | 17.0% | 19.7% | 19.0% | 21.4% |
Nonlinear regression | 14.3% | 19.9% | 13.7% | 20.1% |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yoon, J.Y.; Kim, H.; Lee, Y.-J.; Sim, S.-H. Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network. Materials 2019, 12, 2678. https://0-doi-org.brum.beds.ac.uk/10.3390/ma12172678
Yoon JY, Kim H, Lee Y-J, Sim S-H. Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network. Materials. 2019; 12(17):2678. https://0-doi-org.brum.beds.ac.uk/10.3390/ma12172678
Chicago/Turabian StyleYoon, Jin Young, Hyunjun Kim, Young-Joo Lee, and Sung-Han Sim. 2019. "Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network" Materials 12, no. 17: 2678. https://0-doi-org.brum.beds.ac.uk/10.3390/ma12172678