Journal of Concrete Structures and Materials

Journal of Concrete Structures and Materials

An Intelligent Data-Driven Framework for Optimizing HPFRCC Mix Designs Using a Hybrid ANN-EO-Taguchi Approach

Document Type : Original Article

Authors
Peyman Farhadi Yeganeh 1
Maryam Firoozi Nezamabadi
Ata Hojatkashani 2
Abbas Akbarpour NikghalbRashti 2
Hassan Abbasi 2
1 Ph.D. candidate in Structural Engineering at Islamic Azad University, South Tehran Branch
2 Assistant Professor , Department of civil engineering, Islamic Azad University, South Tehran Branch, Tehran, Iran
10.30478/jcsm.2025.529988.1392
Abstract
performance fiber-reinforced cementitious composites (HPFRCC). Using the Taguchi method, an initial set of 16 physical mix designs was prepared, and their results were collected. Subsequently, synthetic data were generated through simulation, increasing the total number of mix designs to 44, and the additional designs were also fabricated and tested. The results from all 44 mixes were employed to train and optimize an artificial neural network (ANN) model. The model inputs included cement, pozzolans, fibers, water-to-cement ratio, sand, and superplasticizer contents. After optimizing the ANN architecture using the Equilibrium Optimizer (EO) algorithm, the model demonstrated high accuracy in predicting both the workability index and energy absorption capacity, with a mean squared error (MSE) of 0.0049 and a coefficient of determination (R²) exceeding 0.98. Experimental validation of the optimal mix design confirmed the model’s accuracy with an error of less than 0.3%. The results indicated that the workability index of the proposed framework was, on average, approximately 40% higher than that of the reference sample obtained by the independent Taguchi method. Overall, the proposed data-driven framework provides an efficient tool for the precise and cost-effective design of advanced concretes.
Keywords
High-Performance Fiber-Reinforced Cementitious Composites (HPFRCC)
Taguchi Method
Artificial Neural Network (ANN)
Flexural Toughness
Equilibrium Optimization Algorithm (EO)

Subjects

[1]. Almeida, J.A., Bandelt, M.J., (2024), Plastic hinge length in reinforced HPFRCC beams and columns, Engineering Structures, 315: 118345.
[2] Lu, T., (2025), Mechanical Analysis of HPFRCC Precast Composite Column, Materials, 18(7): 1567.
[3] Guo, P., (2025), Applications of machine learning methods for design and characterization of high-performance fiber-reinforced cementitious composite (HPFRCC): a review, Journal of Sustainable Cement-Based Materials : 1-24.
[4] Dai, L., (2022), Using machine learning algorithms to estimate the compressive property of high strength fiber reinforced concrete, Materials, 15(13): 4450.
[5] Hasanzadeh, A., (2022), Prediction of the mechanical properties of basalt fiber reinforced high-performance concrete using machine learning techniques, Materials, 15(20): 7165.
[6] Jiao, P., (2019), High-performance fiber reinforced concrete as a repairing material to normal concrete structures: Experiments, numerical simulations and a machine learning-based prediction model, Construction and Building Materials, 223: 1167-1181.
[7] Kontoni, D.-P.N., Ahmadi, M., (2024), Practical prediction of ultimate axial strain and peak axial stress of FRP-confined concrete using hybrid ANFIS-PSO models, in Artificial intelligence applications for sustainable construction, Elsevier, : 225-255.
[8] Shariati, M., (2022), A novel hybrid extreme learning machine–grey wolf optimizer (ELM-GWO) model to predict compressive strength of concrete with partial replacements for cement, Engineering with Computers, 38(1): 757-779.
[9] Ahmadi, M., (2024), Hybrid bio-inspired metaheuristic approach for design compressive strength of high-strength concrete-filled high-strength steel tube columns, Neural Computing and Applications, 36(14): 7953-7969.
[10] Shariati, M., (2020), Prediction of concrete strength in presence of furnace slag and fly ash using Hybrid ANN-GA (Artificial Neural Network-Genetic Algorithm), Smart Structures and Systems, 25(2): 183-195.
[11] Faramarzi, A., (2020), Equilibrium optimizer: A novel optimization algorithm, Knowledge-based systems, 191: 105190.
[12]Natalli, J.F., (2021), A review on the evolution of Portland cement and chemical admixtures in Brazil, Revista IBRACON de Estruturas e Materiais, 14: e14603.
 [13] Feng, Z., (2022), Optimal design of a low-cost high-performance hybrid fiber engineered cementitious composites, Construction and Building Materials, 345: 128372.
[14] Naseri, M., (1402), Investigation of the effect of calcination temperature of clay on compressive strength and durability of LC3 concrete, Journal of Concrete Structures and Materials, 8(2): 95-111
[15] Abdolahzade, S., Nili, M., (2022), Evaluation of engineering properties of self-compacting geopolymer concrete using Taguchi method, Journal of Concrete Structures and Materials, 7(2): 213-228
 [16] Rai, R., Dhal, K.G., (2023), Recent developments in equilibrium optimizer algorithm: its variants and applications, Archives of Computational Methods in Engineering, 30(6): 3791-3844.
[17] Emani, D.M., (1403), Optimization of mixture design of cementitious concrete containing various percentages of recycled and waste materials: Crumb rubber and reclaimed asphalt pavement (RAP), Journal of Transportation Infrastructure Engineering, 11(1): 11-20.
[18] Rahmani, K., Naserlazade, K., Rostami Golehdar, M., (1402), Experimental study on the effect of aggregate and fiber content on the mechanical properties of single-component slag-based alkali-activated concrete, Journal of Concrete Structures and Materials, 8(2): 146-162.
[19] Ling, J.H., Lim, Y.T., Euniza, J., (2023), Methods to determine ductility of structural members: a review, Journal of the Civil Engineering Forum.
[20] Temesi, O.K., (2024), Ductility Index for Refractory High Entropy Alloys, Crystals, 14(10): 838.
[21] Cong, S., Zhou, Y., (2023), A review of convolutional neural network architectures and their optimizations, Artificial Intelligence Review, 56(3): 1905-1969.
[22] Hossen, M.S., (2020), Data preprocess, Machine Learning and Big Data: Concepts, Algorithms, Tools and Applications : 71-103.
[23] Hematibahar, M., (2024), Analysis of models to predict mechanical properties of high-performance and ultra-high-performance concrete using machine learning, Journal of Composites Science, 8(8): 287.
[24] Dehghani, M., Trojovská, E., Trojovský, P., (2022), Driving training-based optimization: a new human-based metaheuristic algorithm for solving optimization problems.

  • Receive Date 24 June 2025
  • Revise Date 16 August 2025
  • Accept Date 25 October 2025