Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Assessment of compressive strength of high-performance concrete using soft computing approaches

  • Chukwuemeka Daniel (Pan African University Institute of Basic Sciences Technology and Innovation, Hosted at Jomo Kenyatta University of Agriculture and Technology) ;
  • Jitendra Khatti (Department of Civil Engineering, Rajasthan Technical University) ;
  • Kamaldeep Singh Grover (Department of Civil Engineering, Rajasthan Technical University)
  • Received : 2023.06.23
  • Accepted : 2023.08.21
  • Published : 2024.01.25
⟨ Previous Next ⟩

Abstract

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

Keywords

References

  1. Al-Jamimi, H.A., Al-Kutti, W.A., Alwahaishi, S. and Alotaibi, K.S. (2022), "Prediction of compressive strength in plain and blended cement concretes using a hybrid artificial intelligence model", Case Stud. Constr. Mater., 17, 01238. https://doi.org/10.1016/j.cscm.2022.e01238. 
  2. Alterary, S.S. and Marei, N.H. (2021), "Fly ash properties, characterization, and applications: A review", J. King Saud Univ. Sci., 33(6), 101536. https://doi.org/10.1016/j.jksus.2021.101536. 
  3. Amruthamol, N.A. and Kapoor, K. (2022), "Machine learning model to forecast concrete compressive strength", Advances in Data and Information Sciences: Proceedings of ICDIS 2022, Agra, India, June. 
  4. Andrews, D.F. (1974), "A robust method for multiple linear regression", Technometr., 16(4), 523-531.  https://doi.org/10.1080/00401706.1974.10489233
  5. Apostolopoulou, M., Asteris, P.G., Armaghani, D.J., Douvika, M.G., Lourenco, P.B., Cavaleri, L., Bakolas, A. and Moropoulou, A. (2020), "Mapping and holistic design of natural hydraulic lime mortars", Cement Concrete Res., 136, 106167. https://doi.org/10.1016/j.cemconres.2020.106167. 
  6. Armaghani, D.J. and Asteris, P.G. (2021), "A comparative study of ANN and ANFIS models for the prediction of cement-based mortar materials compressive strength", Neural Comput. Appl., 33(9), 4501-4532. https://doi.org/10.1007/s00521-020-05244-4. 
  7. Asteris, P.G., Apostolopoulou, M., Skentou, A.D. and Moropoulou, A. (2019b), "Application of artificial neural networks for the prediction of the compressive strength of cement-based mortars", Comput. Concrete, 24(4), 329-345. https://doi.org/10.12989/cac.2019.24.4.329. 
  8. Asteris, P.G., Armaghani, D.J., Hatzigeorgiou, G.D., Karayannis, C.G. and Pilakoutas, K. (2019a), "Predicting the shear strength of reinforced concrete beams using artificial neural networks", Comput. Concrete, 24(5), 469-488. https://doi.org/10.12989/cac.2019.24.5.469. 
  9. Asteris, P.G., Ashrafian, A. and Rezaie-Balf, M. (2019c), "Prediction of the compressive strength of self-compacting concrete using surrogate models", Comput. Concrete, 24(2), 137-150. https://doi.org/10.12989/cac.2019.24.2.137. 
  10. Asteris, P.G., Koopialipoor, M., Armaghani, D.J., Kotsonis, E.A. and Lourenco, P.B. (2021), "Prediction of cement-based mortars compressive strength using machine learning techniques", Neural Compu. Appl., 33(19), 13089-13121. https://doi.org/10.1007/s00521-021-06004-8. 
  11. Asteris, P.G., Lourenco, P.B., Hajihassani, M., Adami, C.E.N., Lemonis, M.E., Skentou, A.D., Marques, R., Nguyen, H., Rodrigues, H. and Varum, H. (2021b), "Soft computing-based models for the prediction of masonry compressive strength", Eng. Struct., 248, 113276. https://doi.org/10.1016/j.engstruct.2021.113276. 
  12. Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P. and Lourenco, P.B. (2021c), "Soft computing techniques for the prediction of concrete compressive strength using Non-Destructive tests", Constr. Build. Mater., 303, 124450. https://doi.org/10.1016/j.conbuildmat.2021.124450. 
  13. Bui, D.K., Nguyen, T., Chou, J.S., Nguyen-Xuan, H. and Ngo, T.D. (2018), "A modified firefly algorithm-artificial neural network expert system for predicting compressive and tensile strength of high-performance concrete", Constr. Build. Mater., 180, 320-333. https://doi.org/10.1016/j.conbuildmat.2018.05.201. 
  14. Cahyani, R.A.T. and Rusdianto, Y. (2020), "Concrete performance with ground granulated blast furnace slag as supplementary cementitious materials", IOP Conference Series: Materials Science and Engineering, Yogyakarta, Indonesia, November.
  15. Chen, L., (2022), "Hybrid structured artificial network for compressive strength prediction of HPC concrete", J. Appl. Sci. Eng., 26(7), 991-1001. https://doi.org/10.6180/jase.202307_26(7).0010. 
  16. Cheng, H., Kitchen, S. and Daniels, G. (2022), "Novel hybrid radial based neural network model on predicting the compressive strength of long-term HPC concrete", Adv. Eng. Intell. Syst., 1(2), 1. https://doi.org/10.22034/aeis.2022.340732.1012. 
  17. Cheng, M.Y, Cao, M.T. and Dao-Thi, N.M, (2023), "A novel artificial intelligence-aided system to mine historical high-performance concrete data for optimizing mixture design", Expert Syst. Appl., 212, 118605. https://doi.org/10.1016/j.eswa.2022.118605. 
  18. Dutta, S., Samui, P. and Kim, D. (2018), "Comparison of machine learning techniques to predict compressive strength of concrete", Comput. Concrete, 21(4), 463-470. https://doi.org/10.12989/cac.2018.21.4.463. 
  19. Emad, W., Mohammed, A.S., Bras, A., Asteris, P.G., Kurda, R., Muhammed, Z., Hassan, A.M.T., Qaidi, S.M. and Sihag, P. (2022), "Metamodel techniques to estimate the compressive strength of UHPFRC using various mix proportions and a high range of curing temperatures", Constr. Build. Mater., 349, 128737. https://doi.org/10.1016/j.conbuildmat.2022.128737. 
  20. Farooq, F., Ahmed, W., Akbar, A., Aslam, F. and Alyousef, R. (2021), "Predictive modeling for sustainable high-performance concrete from industrial wastes: A comparison and optimization of models using ensemble learners", J. Clean. Prod., 292, 126032. https://doi.org/10.1016/j.jclepro.2021.126032. 
  21. Golafshani, E.M., Behnood, A. and Arashpour, M. (2020), "Predicting the compressive strength of normal and high-performance concretes using ANN and ANFIS hybridized with grey wolf optimizer", Constr. Build. Mater., 232, 117266. https://doi.org/10.1016/j.conbuildmat.2019.117266. 
  22. Hameed, M.M. and AlOmar, M.K. (2019), "Prediction of compressive strength of high-performance concrete: Hybrid artificial intelligence technique", International Conference on Applied Computing to Support Industry: Innovation and Technology, Ramadi, Iraq, September. 
  23. Hameed, M.M., AlOmar, M.K., Baniya, W.J. and AlSaadi, M.A. (2021), "Incorporation of artificial neural network with principal component analysis and cross-validation technique to predict high-performance concrete compressive strength", Asian J. Civil Eng., 22, 1019-1031. https://doi.org/10.1007/s42107-021-00362-3. 
  24. Han, J., Pei, J. and Tong, H. (2022), Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, Burlington, MA, USA. 
  25. Han, Q., Gui, C., Xu, J. and Lacidogna, G. (2019), "A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm", Constr. Build. Mater., 226, 734-742. https://doi.org/10.1016/j.conbuildmat.2019.07.315. 
  26. Hu, X. (2023), "Evaluation of compressive strength of the HPC produced with admixtures by a novel hybrid SVR model", Multiscale Multidiscip. Model. Exp. Des., 2023, 1-14. https://doi.org/10.1007/s41939-023-00150-3. 
  27. Imran, H., Ibrahim, M., Al-Shoukry, S., Rustam, F. and Ashraf, I. (2022), "Latest concrete materials dataset and ensemble prediction model for concrete compressive strength containing RCA and GGBFS materials", Constr. Build. Mater., 325, 126525. https://doi.org/10.1016/j.conbuildmat.2022.126525. 
  28. Imran, M., Khushnood, R.A. and Fawad, M. (2023), "A hybrid data-driven and metaheuristic optimization approach for the compressive strength prediction of high-performance concrete", Case Stud. Constr. Mater., 18, 01890. https://doi.org/10.1016/j.cscm.2023.e01890. 
  29. Jin, R., Chen, Q. and Soboyejo, A.B. (2018), "Non-linear and mixed regression models in predicting sustainable concrete strength", Constr. Build. Mater., 170, 142-152. https://doi.org/10.1016/j.conbuildmat.2018.03.063. 
  30. Joy, R.A. (2021), "Fine tuning the prediction of the compressive strength of concrete: A bayesian optimization based approach", 2021 International Conference on Innovations in Intelligent Systems and Applications (INISTA), Kocaeli, Turkey, August. 
  31. Kablay, H. and Gumbo, V. (2021), "Comparison of multiple linear regression and neural network models in bank performance prediction in Botswana", J. Math. Stat., 17(1), 88-95. https://doi.org/10.3844/jmssp.2021.88.95. 
  32. Kaloop, M.R., Kumar, D., Samui, P., Hu, J.W. and Kim, D. (2020), "Compressive strength prediction of high-performance concrete using gradient tree boosting machine", Constr. Build. Mater., 264, 120198. https://doi.org/10.1016/j.conbuildmat.2020.120198. 
  33. Kamath, M.V., Prashanth, S., Kumar, M. and Tantri, A. (2022), "Machine-learning-algorithm to predict the high-performance concrete compressive strength using multiple data", J. Eng. Des. Technol., 2022, 1-29. https://doi.org/10.1108/JEDT-11-2021-0637. 
  34. Kapoor, H. (2020), Random Forest vs Extra Trees. https://www.kaggle.com/code/hkapoor/random-forest-vs-extra-trees
  35. Khan, K., Salami, B.A., Iqbal, M., Amin, M.N., Ahmed, F. and Jalal, F.E. (2022), "Compressive strength estimation of fly ash/slag based green concrete by deploying artificial intelligence models", Mater., 15(10), 3722. https://doi.org/10.3390/ma15103722. 
  36. Khatti, J. and Grover, K.S. (2023a), "Prediction of compaction parameters for fine-grained soil: Critical comparison of the deep learning and standalone models", J. Rock Mech. Geotech. Eng., 15(11), 3010-3038. https://doi.org/10.1016/j.jrmge.2022.12.034. 
  37. Khatti, J. and Grover, K.S. (2023b), "CBR prediction of pavement materials in unsoaked condition using LSSVM, LSTM-RNN, and ANN approaches", Int. J. Pavement Res. Technol., 2023, 1-37. https://doi.org/10.1007/s42947-022-00268-6. 
  38. Khatti, J. and Grover, K.S. (2023c), "Prediction of UCS of fine-grained soil based on machine learning part 1: multivariable regression analysis, gaussian process regression, and gene expression programming", Multiscale Multidiscip. Model. Exp. Des., 2023, 1-24. https://doi.org/10.1007/s41939-022-00137-6. 
  39. Khatti, J. and Grover, K.S. (2022), "Determination of the optimum performance AI model and methodology to predict the compaction parameters of soils", ICTACT J. Soft Comput., 12(3), http://doi.org/10.21917/ijsc.2022.0378. 
  40. Khatti, J. and Grover, K.S. (2023d), "Prediction of UCS of fine-grained soil based on machine learning part 2: Comparison between hybrid relevance vector machine and Gaussian process regression", Multiscale Multidiscip. Model. Exp. Des., 2023, 1-41. https://doi.org/10.1007/s41939-023-00191-8. 
  41. Khatti, J. and Grover, K.S. (2023e), "Assessment of fine-grained soil compaction parameters using advanced soft computing techniques", Arab. J. Geosci., 16(3), 208. https://doi.org/10.1007/s12517-023-11268-6. 
  42. Khatti, J. and Grover, K.S. (2023f), "Prediction of soaked CBR of fine-grained soils using soft computing techniques", Multiscale Multidiscip. Model. Exp. Des., 6(1), 97-121. https://doi.org/10.1007/s41939-022-00131-y 
  43. Latif, S.D. (2021), "Concrete compressive strength prediction modeling utilizing deep learning long short-term memory algorithm for a sustainable environment", Environ. Sci. Pollut. Res., 28(23), 30294-30302. https://doi.org/10.1007/s11356-021-12877-y. 
  44. Li, Q.F. and Song, Z.M. (2022), "High-performance concrete strength prediction based on ensemble learning", Constr. Build. Mater., 324, 126694. https://doi.org/10.1016/j.conbuildmat.2022.126694. 
  45. Ly, H.B., Nguyen, T.A. and Pham, B.T. (2022), "Investigation on factors affecting early strength of high-performance concrete by gaussian process regression", PloS one, 17(1), 0262930. https://doi.org/10.1371/journal.pone.0262930. 
  46. Mai, H.V.T., Nguyen, T.A., Ly, H.B. and Tran, V.Q. (2021), "Investigation of ANN model containing one hidden layer for predicting compressive strength of concrete with blast-furnace slag and fly ash", Adv. Mater. Sci. Eng., 2021, 1-17. https://doi.org/10.1155/2021/5540853. 
  47. Mai, H.V.T., Nguyen, T.A., Ly, H.B. and Tran, V.Q. (2021), "Prediction compressive strength of concrete containing GGBFS using random forest model", Adv. Civil Eng., 2021, 1-12. https://doi.org/10.1155/2021/6671448. 
  48. Mandal, S., Shilpa, M. and Rajeshwari, R. (2019), "Compressive strength prediction of high-strength concrete using regression and ANN models", Sustainable Construction and Building Materials: Select Proceedings of ICSCBM 2018, Springer, Singapore. 
  49. Mandal, S., Shilpa, M. and Rajeshwari, R. (2019), "Compressive strength prediction of high-strength concrete using regression and ANN models", Sustainable Construction and Building Materials: Select Proceedings of ICSCBM 2018, Springer, Singapore. 
  50. Mater, Y., Kamel, M., Karam, A. and Bakhoum, E. (2023), "ANN-Python prediction model for the compressive strength of green concrete", Constr. Innov., 23(2), 340-359. https://doi.org/10.1108/CI-08-2021-0145. 
  51. Mateus, M.S.R. (2023), "Prediction of high-performance concrete compressive strength through a comparison of machine learning techniques", MS Dissertation, Universidade Nova de Lisboa, Lisbon, Portugal. 
  52. Mentaschi, L., Besio, G., Cassola, F. and Mazzino, A. (2013), "Problems in RMSE-based wave model validations", Ocean Modell., 72, 53-58. https://doi.org/10.1016/j.ocemod.2013.08.003. 
  53. Min, H. and Luo, X. (2016), "Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method", Chin. J. Chem. Eng., 24(8), 1038-1046. https://doi.org/10.1016/j.cjche.2016.05.015. 
  54. Mohamed, O., Kewalramani, M., Ati, M. and Al Hawat, W. (2021), "Application of ANN for prediction of chloride penetration resistance and concrete compressive strength", Mater., 17, 101123. https://doi.org/10.1016/j.mtla.2021.101123. 
  55. Moradi, M.J., Khaleghi, M., Salimi, J,. Farhangi, V. and Ramezanianpour, A.M. (2021), "Predicting the compressive strength of concrete containing metakaolin with different properties using ANN", Measure., 183, 109790. https://doi.org/10.1016/j.measurement.2021.109790. 
  56. Nayak, D.K., Abhilash, P.P., Singh, R., Kumar, R. and Kumar, V. (2022), "Fly ash for sustainable construction: A review of fly ash concrete and its beneficial use case studies", Clean. Mater., 2022, 100143. https://doi.org/10.1016/j.clema.2022.100143. 
  57. Neville, A.M. and Brooks, J.J. (2010), Concrete Technology, 2nd Edition, Pearson Education Ltd., London, UK. 
  58. Nguyen, T.N., Yu, Y., Li, J., Gowripalan, N. and Sirivivatnanon, V. (2019), "Elastic modulus of ASR-affected concrete: An evaluation using artificial neural network", Comput. Concrete, 24(6), 541-553. https://doi.org/10.12989/cac.2019.24.6.541. 
  59. Ranjbar, I., Toufigh, V. and Boroushaki, M. (2022), "A combination of deep learning and genetic algorithm for predicting the compressive strength of high-performance concrete", Struct. Concrete, 23(4), 2405-2418. https://doi.org/10.1002/suco.202100199. 
  60. Ris, R.C., Holthuijsen, L.H. and Booij, N. (1999), "A third-generation wave model for coastal regions: 2. Verification", J. Geophys. Res.: Oceans, 104(C4), 7667-7681. https://doi.org/10.1029/1998JC900123. 
  61. Sadrossadat, E. and Basarir, H. (2019), "An evolutionary-based prediction model of the 28-day compressive strength of high-performance concrete containing cementitious materials", Adv. Civil Eng. Mater., 8(3), 484-497.  https://doi.org/10.1520/ACEM20190016
  62. Salami, B.A., Olayiwola, T., Oyehan, T.A. and Raji, I.A. (2021), "Data-driven model for ternary-blend concrete compressive strength prediction using machine learning approach", Constr. Build. Mater., 301, 124152. https://doi.org/10.1016/j.conbuildmat.2021.124152. 
  63. Shah, H.A., Yuan, Q., Akmal, U., Shah, S.A., Salmi, A., Awad, Y.A., Shah, L.A., Iftikhar, Y., Javed, M.H. and Khan, M.I. (2022), "Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin", Mater., 15(15), 5435. https://doi.org/10.3390/ma15155435. 
  64. Shaswat, K. (2021), "Hybrid-based deep belief network model for cement compressive strength prediction", Comput. J., 64(6), 909-920. https://doi.org/10.1093/comjnl/bxaa197. 
  65. Simsek, S., Gumus, M., Khalafalla, M. and Issa, T.B. (2020), "A hybrid data analytics approach for high-performance concrete compressive strength prediction", J. Business Anal., 3(2), 158-168. https://doi.org/10.1080/2573234X.2020.1760741. 
  66. Singh, U., Rizwan, M., Alaraj, M. and Alsaidan, I. (2021), "A machine learning-based gradient boosting regression approach for wind power production forecasting: A step towards smart grid environments", Energies, 14(16), 5196. https://doi.org/10.3390/en14165196. 
  67. Smith, G.N. (1986), Probability and Statistics in Civil Engineering - An Introduction, Collins, London, UK. 
  68. Song, H., Ahmad, A., Farooq, F., Ostrowski, K.A., Maslak, M., Czarnecki, S. and Aslam, F. (2021), "Predicting the compressive strength of concrete with fly ash admixture using machine learning algorithms", Constr. Build. Mater., 308, 125021. https://doi.org/10.1016/j.conbuildmat.2021.125021. 
  69. Strohmann, T. and Grudic, G. (2002), "A formulation for minimax probability machine regression", Adv. Neural Informat. Pr. Syst., 15, 1. 
  70. Tipu, R.K., Panchal, V.R. and Pandya, K.S. (2022), "An ensemble approach to improve BPNN model precision for predicting compressive strength of high-performance concrete", Struct., 45, 500-508. https://doi.org/10.1016/j.istruc.2022.09.046. 
  71. Vakharia, V. and Gujar, R. (2019), "Prediction of compressive strength and portland cement composition using cross-validation and feature ranking techniques", Constr. Build. Mater., 225, 292-301. https://doi.org/10.1016/j.conbuildmat.2019.07.224. 
  72. Vilane, B.R.T. and Sabelo, N. (2016), "The effect of aggregate size on the compressive strength of concrete", J. Agricult. Sci. Eng., 2(6), 66-69. 
  73. Wang, H. and Zhang, S. (2022), "Double hybridized artificial network for the prediction of HPC concrete compressive strength", J. Intell. Fuzzy Syst., 43(6), 7963-7974. https://doi.org/10.3233/JIFS-220736. 
  74. Waris, M.I., Plevris, V., Mir, J., Chairman, N. and Ahmad, A. (2022), "An alternative approach for measuring the mechanical properties of hybrid concrete through image processing and machine learning", Constr. Build. Mater., 328, 126899. https://doi.org/10.1016/j.conbuildmat.2022.126899. 
  75. Willmott, C.J., Robeson, S.M. and Matsuura, K. (2012), "A refined index of model performance", Int. J. Climatol., 32(13), 2088-2094. https://doi.org/10.1002/joc.2419. 
  76. Yu, Y., Li, W., Li, J. and Nguyen, T.N. (2018), "A novel optimised self-learning method for compressive strength prediction of high performance concrete", Constr. Build. Mater., 184, 229-247. https://doi.org/10.1016/j.conbuildmat.2018.06.219. 
  77. Yu, Y., Nguyen, T.N., Li, J., Sanchez, L.F. and Nguyen, A. (2021), "Predicting elastic modulus degradation of alkali silica reaction affected concrete using soft computing techniques: A comparative study", Constr. Build. Mater., 274, 122024. https://doi.org/10.1016/j.conbuildmat.2020.122024. 
  78. Yuan, Y., Wu, L. and Zhang, X. (2021), "Gini-Impurity index analysis", IEEE Trans. Informat. Forens. Secur., 16, 3154-3169. https://doi.org/10.1109/TIFS.2021.3076932. 
  79. Zhu, F., Wu, X., Zhou, M., Sabri, M.M.S. and Huang, J. (2022), "Intelligent design of building materials: Development of an ai-based method for cement-slag concrete design", Mater., 15(11), 3833. https://doi.org/10.3390/ma15113833.