Interpretable Machine Learning Method for Compressive Strength Prediction and Analysis of Pure Fly Ash-based Geopolymer Concrete

Abstract

In order to study the characteristics of pure fly ash-based geopolymer concrete (PFGC) conveniently, we used a machine learning method that can quantify the perception of characteristics to predict its compressive strength. In this study, 505 groups of data were collected, and a new database of compressive strength of PFGC was constructed. In order to establish an accurate prediction model of compressive strength, five different types of machine learning networks were used for comparative analysis. The five machine learning models all showed good compressive strength prediction performance on PFGC. Among them, R ², MSE, RMSE and MAE of decision tree model (DT) are 0.99, 1.58, 1.25, and 0.25, respectively. While R ², MSE, RMSE and MAE of random forest model (RF) are 0.97, 5.17, 2.27 and 1.38, respectively. The two models have high prediction accuracy and outstanding generalization ability. In order to enhance the interpretability of model decision-making, we used importance ranking to obtain the perception of machine learning model to 13 variables. These 13 variables include chemical composition of fly ash (SiO₂/Al₂O₃, Si/Al), the ratio of alkaline liquid to the binder, curing temperature, curing durations inside oven, fly ash dosage, fine aggregate dosage, coarse aggregate dosage, extra water dosage and sodium hydroxide dosage. Curing temperature, specimen ages and curing durations inside oven have the greatest influence on the prediction results, indicating that curing conditions have more prominent influence on the compressive strength of PFGC than ordinary Portland cement concrete. The importance of curing conditions of PFGC even exceeds that of the concrete mix proportion, due to the low reactivity of pure fly ash.

References

[1] Ahmad A, Ahmad W, Aslam F, et al.. Compressive Strength Prediction of Fly Ash-Based Geopolymer Concrete Via Advanced Machine Learning Techniques[J]. Case Studies in Construction Materials, 2022, 16(prepublish): e00 840

[2] Naveen Y K, Dean Kumar B, Swami B L P. Mechanical Properties of Geopolymer Concrete Reinforced with Steel and Glass Fibers with Various Mineral Admixtures[J]. Materials Today: Proceedings, 2022, 52(P3): 632-641

[3] Elzeadani M, Bompa D V, Elghazouli A Y. Preparation and Properties of Rubberised Geopolymer Concrete: A Review[J]. Construction and Building Materials, 2021, 313: 125 504

[4] Abdulrahman H, Muhamad R, Visintin P, et al.. Mechanical Properties and Bond Stress-Slip Behaviour of Fly Ash Geopolymer Concrete[J]. Construction and Building Materials, 2022, 327: 126 909

[5] Li W, Shumuye E D, Shiying T, et al.. Eco-Friendly Fibre Reinforced Geopolymer Concrete: A Critical Review on the Microstructure and Long-Term Durability Properties[J]. Case Studies in Construction Materials, 2022, 16: e00 894

[6] Peng Y, Unluer C. Analyzing the Mechanical Performance of Fly Ash-Based Geopolymer Concrete with Different Machine Learning Techniques[J]. Construction and Building Materials, 2022, 316: 125 785

[7] Wang X, Yang W, Liu H, et al.. Strength and Microstructural Analysis of Geopolymer Prepared with Recycled Geopolymer Powder[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2021, 36(3): 439-445

[8] Amin M, Elsakhawy Y, Abu el-hassan K, et al.. Behavior Evaluation of Sustainable High Strength Geopolymer Concrete Based on Fly Ash, Metakaolin, and Slag[J]. Case Studies in Construction Materials, 2022, 16: e00 976

[9] Lin W, Luo W, Zhang G, et al.. Preparation of Phlogopite-Based Geopolymer and Its Surface Nonpolar Modification[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2021, 36(3): 433-438

[10] Elzeadani M, Bompa D V, Elghazouli A Y. Preparation and Properties of Rubberised Geopolymer Concrete: A Review[J]. Construction and Building Materials, 2021, 313: 125 504

[11] Ahmed H U, Mohammed A A, Rafiq S, et al.. Compressive Strength of Sustainable Geopolymer Concrete Composites: A State-of-the-Art Review[J]. Sustainability, 2021, 13(24): 13 502

[12] Khalaf A A, Kopecskó K, Merta I. Prediction of the Compressive Strength of Fly Ash Geopolymer Concrete by An Optimised Neural Network Model[J]. Polymers, 2022, 14(7): 1 423

[13] Emarah D A. Compressive Strength Analysis of Fly Ash-based Geopolymer Concrete Using Machine Learning Approaches[J]. Results in Materials, 2022, 16: 100 347

[14] Liu Q, Zhang J, Su Y, et al.. Variation in Polymerization Degree of CASH Gels and Its Role in Strength Development of Alkali-activated Slag Binders[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2021, 36: 871-879

[15] Ahmad A, Ahmad W, Chaiyasarn K, et al.. Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms[J]. Polymers, 2021, 13(19): 3 389

[16] Shafiei A, Tatar A, Rayhani M, et al.. Artificial Neural Network, Support Vector Machine, Decision Tree, Random Forest, and Committee Machine Intelligent System Help to Improve Performance Prediction of Low Salinity Water Injection in Carbonate Oil Reservoirs[J]. Journal of Petroleum Science and Engineering, 2022, 219: 111 046

[17] Hardjito D, Wallah S E, Sumajouw D M J, et al.. Introducing Fly Ash-Based Geopolymer Concrete: Manufacture and Engineering Properties[C]. 30th Conference on Our World in Concrete & Structures, 2005 271-278

[18] Al-Azzawi M, Yu T, Hadi M N S. Factors Affecting the Bond Strength between the Fly Ash-Based Geopolymer Concrete and Steel Reinforcement[C]. Structures Elsevier, 2018, 14: 262-272

[19] Zhao R, Yuan Y, Cheng Z, et al.. Freeze-Thaw Resistance of Class F Fly Ash-based Geopolymer Concrete[J]. Construction and Building Materials, 2019, 222: 474-483

[20] Singhal D, Junaid M T, Jindal B B, et al.. Mechanical and Microstructural Properties of Fly Ash Based Geopolymer Concrete Incorporating Alccofine at Ambient Curing[J]. Construction and Building Materials, 2018, 180: 298-307

[21] Shehab H K, Eisa A S, Wahba A M. Mechanical Properties of Fly Ash Based Geopolymer Concrete with Full and Partial Cement Replacement[J]. Construction and Building Materials, 2016, 126: 560-565

[22] Chithambaram S J, Kumar S, Prasad M M, et al.. Effect of Parameters on the Compressive Strength of Fly Ash Based Geopolymer Concrete[J]. Structural Concrete, 2018, 19(4): 1 202-1 209

[23] Wardhono A, Gunasekara C, Law D W, et al.. Comparison of Long Term Performance between Alkali Activated Slag and Fly Ash Geopolymer Concretes[J]. Construction and Building Materials, 2017, 143: 272-279

[24] Ramujee K, PothaRaju M. Mechanical Properties of Geopolymer Concrete Composites[J]. Materials Today: Proceedings, 2017, 4(2): 2 937-2 945

[25] Wallah S E. Creep Behaviour of Fly Ash-Based Geopolymer Concrete[J]. Civil Engineering Dimension, 2010, 12(2): 73-78

[26] Aliabdo A A, Abd Elmoaty M, Salem H A. Effect of Water Addition, Plasticizer and Alkaline Solution Constitution on Fly Ash Based Geopolymer Concrete Performance[J]. Construction and Building Materials, 2016, 121: 694-703

[27] Xie T, Ozbakkaloglu T. Behavior of Low-Calcium Fly and Bottom Ash-Based Geopolymer Concrete Cured at Ambient Temperature[J]. Ceramics International, 2015, 41(4): 5 945-5 958

[28] Sarker P K. Bond Strength of Reinforcing Steel Embedded in Fly Ash-Based Geopolymer Concrete[J]. Materials and Structures, 2011, 44: 1 021-1 030

[29] Chindaprasirt P, Chalee W. Effect of Sodium Hydroxide Concentration on Chloride Penetration and Steel Corrosion of Fly Ash-Based Geopolymer Concrete under Marine Site[J]. Construction and Building Materials, 2014, 63: 303-310

[30] Shaikh F U A, Vimonsatit V. Compressive Strength of Fly-Ash-Based Geopolymer Concrete at Elevated Temperatures[J]. Fire and Materials, 2015, 39(2): 174-188

[31] Sastry K V S G K, Sahitya P, Ravitheja A. Influence of Nano TiO₂ on Strength and Durability Properties of Geopolymer Concrete[J]. Materials Today: Proceedings, 2021, 45: 1 017-1 025

[32] Çevik A, Alzeebaree R, Humur G, et al.. Effect of Nano-Silica on the Chemical Durability and Mechanical Performance of Fly Ash Based Geopolymer Concrete[J]. Ceramics International, 2018, 44(11): 12 253-12 264

[33] Embong R, Kusbiantoro A, Shafiq N, et al.. Strength and Microstructural Properties of Fly Ash Based Geopolymer Concrete Containing High-Calcium and Water-absorptive Aggregate[J]. Journal of Cleaner Production, 2016, 112: 816-822

[34] Sumajouw D M J, Hardjito D, Wallah S E, et al.. Fly Ash-Based Geopolymer Concrete: Study of Slender Reinforced Columns[J]. Journal of Materials Science, 2007, 42: 3 124-3 130

[35] Jaydeep S, Chakravarthy B J. Study on Fly Ash Based Geo-Polymer Concrete Using Admixtures[J]. International Journal of Engineering Trends and Technology, 2013, 4(10): 4 614-4 617

[36] Nuaklong P, Jongvivatsakul P, Pothisiri T, et al.. Influence of Rice Husk Ash on Mechanical Properties and Fire Resistance of Recycled Aggregate High-Calcium Fly Ash Geopolymer Concrete[J]. Journal of Cleaner Production, 2020, 252: 119 797

[37] Okoye F N, Durgaprasad J, Singh N B. Effect of Silica Fume on the Mechanical Properties of Fly Ash Based-Geopolymer Concrete[J]. Ceramics International, 2016, 42(2): 3 000-3 006

[38] Okoye F N, Prakash S, Singh N B. Durability of Fly Ash Based Geopolymer Concrete in the Presence of Silica Fume[J]. Journal of Cleaner Production, 2017, 149: 1 062-1 067

[39] Sarker P K, Haque R, Ramgolam K V. Fracture Behaviour of Heat Cured Fly Ash Based Geopolymer Concrete[J]. Materials & Design, 2013, 44: 580-586

[40] Talha Junaid M, Kayali O, Khennane A. Response of Alkali Activated Low Calcium Fly-Ash Based Geopolymer Concrete under Compressive Load at Elevated Temperatures[J]. Materials and Structures, 2017, 50: 1-10

[41] Olivia M, Sarker P, Nikraz H. Water Penetrability of Low Calcium Fly Ash Geopolymer Concrete[J]. Wahyu Sari Yeni, 2008, 46: 517-530

[42] Abhilash P, Sashidhar C, Reddy I R. Strength Properties of Fly Ash and GGBS Based Geo-Polymer Concrete[J]. Int. J. ChemTech Res., 2016, 9(3): 350-356

[43] Jindal B B, Parveen Singhal D, et al.. Predicting Relationship between Mechanical Properties of Low Calcium Fly Ash-Based Geopolymer Concrete[J]. Transactions of the Indian Ceramic Society, 2017, 76(4): 258-265

[44] Vignesh P, Vivek K. An Experimental Investigation on Strength Parameters of Flyash Based Geopolymer Concrete with GGBS[J]. Int. Res. J. Eng. Technol., 2015, 2(2): 135-142

[45] Joseph B, Mathew G. Influence of Aggregate Content on the Behavior of Fly Ash Based Geopolymer Concrete[J]. Scientia Iranica, 2012, 19(5): 1 188-1 194

[46] Nath P, Sarker P K. Effect of GGBFS on Setting, Workability and Early Strength Properties of Fly Ash Geopolymer Concrete Cured in Ambient Condition[J]. Construction and Building Materials, 2014, 66: 163-171

[47] Adak D, Sarkar M, Mandal S. Structural Performance of Nano-Silica Modified Fly-ash Based Geopolymer Concrete[J]. Construction and Building Materials, 2017, 135: 430-439

[48] Mehta A, Siddique R. Sulfuric Acid Resistance of Fly Ash Based Geopolymer Concrete[J]. Construction and Building Materials, 2017, 146: 136-143

[49] Cui Y, Gao K, Zhang P. Experimental and Statistical Study on Mechanical Characteristics of Geopolymer Concrete[J]. Materials, 2020, 13(7): 1 651

[50] Albitar M, Visintin P, Mohamed Ali M S, et al.. Assessing Behaviour of Fresh and Hardened Geopolymer Concrete Mixed with Class-F Fly Ash[J]. KSCE Journal of Civil Engineering, 2015, 19: 1 445-1 455

[51] Bhogayata A C, Arora N K. Utilization of Metalized Plastic Waste of Food Packaging Articles in Geopolymer Concrete[J]. Journal of Material Cycles and Waste Management, 2019, 21(4): 1 014-1 026

[52] Gomaa E, Sargon S, Kashosi C, et al.. Mechanical Properties of High Early Strength Class C Fly Ash-Based Alkali Activated Concrete[J]. Transportation Research Record, 2020, 2674(5): 430-443

[53] Hassan A, Arif M, Shariq M. Effect of Curing Condition on the Mechanical Properties of Fly Ash-Based Geopolymer Concrete[J]. SN Applied Sciences, 2019, 1: 1-9

[54] Kurtoglu A E, Alzeebaree R, Aljumaili O, et al.. Mechanical and Durability Properties of Fly Ash and Slag Based Geopolymer Concrete[J]. Advances in Concrete Construction, 2018, 6(4): 345

[55] Nath P, Sarker P K. Use of OPC to Improve Setting and Early Strength Properties of Low Calcium Fly Ash Geopolymer Concrete Cured at Room Temperature[J]. Cement and Concrete Composites, 2015, 55: 205-214

[56] Saravanan S, Elavenil S. Strength Properties of Geopolymer Concrete Using M Sand by Assessing their Mechanical Characteristics[J]. ARPN J. Eng. Appl., 2018, 13(13): 4 028-4 041

[57] Topark-Ngarm P, Chindaprasirt P, Sata V. Setting Time, Strength, and Bond of High-Calcium Fly Ash Geopolymer Concrete[J]. Journal of Materials in Civil Engineering, 2015, 27(7): 04 014 198

[58] Vijai K, Kumutha R, Vishnuram B G. Experimental Investigations on Mechanical Properties of Geopolymer Concrete Composites[J]. Asian Journal of Civil Engineering, 2012, 13(1): 89-96

[59] Vora P R, Dave U V. Parametric Studies on Compressive Strength of Geopolymer Concrete[J]. Procedia Engineering, 2013, 51: 210-219

[60] Wang Y, Hu S, He Z. Mechanical and Fracture Properties of Fly Ash Geopolymer Concrete Addictive with Calcium Aluminate Cement[J]. Materials, 2019, 12(18): 2 982

[61] Ibrahim M, Johari M A M, Maslehuddin M, et al.. Influence of Nano-SiO₂ on the Strength and Microstructure of Natural Pozzolan Based Alkali Activated Concrete[J]. Construction and Building Materials, 2018, 173: 573-585

[62] Ghafoor M T, Khan Q S, Qazi A U, et al.. Influence of Alkaline Activators on the Mechanical Properties of Fly Ash Based Geopolymer Concrete Cured at Ambient Temperature[J]. Construction and Building Materials, 2021, 273: 121 752

[63] Fang G, Ho W K, Tu W, et al.. Workability and Mechanical Properties of Alkali-Activated Fly Ash-Slag Concrete Cured at Ambient Temperature[J]. Construction and Building Materials, 2018, 172: 476-487

[64] Vijai K, Kumutha R, Vishnuram B G. Effect of Types of Curing on Strength of Geopolymer Concrete[J]. International Journal of the Physical Sciences, 2010, 5(9): 1 419-1 423

[65] Krishnaraja A R, Sathishkumar N P, Kumar T S, et al.. Mechanical Behaviour of Geopolymer Concrete under Ambient Curing[J]. International Journal of Scientific Engineering and Technology, 2014, 3(2): 130-132

[66] Kumaravel S. Development of Various Curing Effect of Nominal Strength Geopolymer Concrete[J]. Journal of Engineering Science and Technology Review, 2014, 7(1): 116-119

[67] Nagajothi S, Elavenil S. Effect of GGBS Addition on Reactivity and Microstructure Properties of Ambient Cured Fly Ash Based Geopolymer Concrete[J]. Silicon, 2021, 13(2): 507-516

[68] Muhammad N, Baharom S, Amirah N, et al.. Effect of Heat Curing Temperatures on Fly Ash-Based Geopolymer Concrete[J]. Int. J. Eng. Technol., 2019, 8(1.2): 15

[69] Das S K, Shrivastava S. Siliceous Fly Ash and Blast Furnace Slag Based Geopolymer Concrete under Ambient Temperature Curing Condition[J]. Structural Concrete, 2021, 22: E341-E351

[70] Nuruddin M F N, Kusbiantoro A K, Qazi S Q, et al.. Development of Geopolymer Concrete with Different Curing Conditions[J]. IPTEK the Journal for Technology and Science, 2011, 22(1): 24-28

[71] Kolli R, Potharaju M. Development of Low Calcium Flyash Based Geopolymer Concrete[J]. International Journal of Engineering and Technology, 2014, 6(1): 1-4

[72] Balogun A L, Tella A. Modelling and Investigating the Impacts of Climatic Variables on Ozone Concentration in Malaysia Using Correlation Analysis with Random Forest, Decision Tree Regression, Linear Regression, and Support Vector Regression[J]. Chemosphere, 2022, 299: 134 250

[73] Li J, Zhu D, Li C. Comparative Analysis of BPNN, SVR, LSTM, Random Forest, and LSTM-SVR for Conditional Simulation of Non-Gaussian Measured Fluctuating Wind Pressures[J]. Mechanical Systems and Signal Processing, 2022, 178: 109 285

[74] Elahi F, Muhammad K, Din S U, et al.. Lithological Mapping of Kohat Basin in Pakistan Using Multispectral Remote Sensing Data: A Comparison of Support Vector Machine (SVM) and Artificial Neural Network (ANN)[J]. Applied Sciences, 2022, 12(23): 12 147

[75] Singh R, Arora H C, Bahrami A, et al.. Enhancing Sustainability of Corroded RC Structures: Estimating Steel-to-Concrete Bond Strength with ANN and SVM Algorithms[J]. Materials, 2022, 15(23): 8 295

[76] Tejada A T Jr Ella V B, Lampayan R M, et al.. Modeling Reference Crop Evapotranspiration Using Support Vector Machine (SVM) and Extreme Learning Machine (ELM) in Region IV-A, Philippines[J]. Water, 2022, 14(5): 754

[77] Zhu L, Zhou X, Liu W, et al.. Total Organic Carbon Content Logging Prediction Based on Machine Learning:A Brief Review[J]. Energy Geoscience, 2023, 4(2): 100-107

[78] Guessoum S, Belda S, Ferrandiz J M, et al.. The Short-Term Prediction of Length of Day Using 1D Convolutional Neural Networks (1D CNN) [J]. Sensors, 2022, 22(23): 9 517

[79] Niu S, Srivastava V. Simulation Trained CNN for Accurate Embedded Crack Length, Location, and Orientation Prediction from Ultrasound Measurements[J]. International Journal of Solids and Structures, 2022, 242: 111 521

[80] Raja Sarobin M V, Panjanathan R. Diabetic Retinopathy Classification Using CNN and Hybrid Deep Convolutional Neural Networks[J]. Symmetry, 2022, 14(9): 1 932

[81] Kuang F, Long Z, Kuang D, et al.. Application of Back Propagation Neural Network to the Modeling of Slump and Compressive Strength of Composite Geopolymers[J]. Computational Materials Science, 2022, 206: 111 241

[82] Song J, Li Y, Liu S, et al.. Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case[J]. Energies, 2022, 15(18): 6 509

[83] Reza A, Chen L, Kruger K. Microwave Irradiated Ammonia Nitrogen Removal from Anaerobically Digested Liquid Dairy Manure: A Response Surface Methodology and Artificial Neural Network-Based Optimization and Modeling[J]. Journal of Environmental Chemical Engineering, 2022, 10(5): 108 279

[84] Shan X, Shen Y, Cai H, et al.. Convolutional Neural Network Optimization Via Channel Reassessment Attention Module[J]. Digital Signal Processing, 2022, 123: 103 408

[85] Ahmad A, Farooq F, Niewiadomski P, et al.. Prediction of Compressive Strength of Fly Ash Based Concrete Using Individual and Ensemble Algorithm[J]. Materials, 2021, 14(4): 794

[86] Wang Q, Ahmad W, Ahmad A, et al.. Application of Soft Computing Techniques to Predict the Strength of Geopolymer Composites[J]. Polymers, 2022, 14(6): 1 074

[87] Kastiukas G, Ruan S, Liang S, et al.. Development of Precast Geopolymer Concrete Via Oven and Microwave Radiation Curing with An Environmental Assessment[J]. Journal of Cleaner Production, 2020, 255: 120 290

[88] Rajmohan B, Nayaka R R, Kumar K R, et al.. Mechanical and Durability Performance Evaluation of Heat Cured Low Calcium Fly Ash Based Sustainable Geopolymer Concrete[J]. Materials Today: Proceedings, 2022, 58: 1 337-1 343

[89] Phavongkham V, Wattanasiriwech S, Wattanasiriwech D. Tailored Design of Properties of Hongsa Fly Ash-Based Geopolymer Paste Via An Adjustment of the Alkali Activator Composition[J]. Ceramics International, 2021, 47(10): 13 374-13 380

[90] Lim N G, Jeong S W, Her J W, et al.. Properties of Cement-Free Concrete Cast by Finely Grained Nanoslag with the NaOH-Based Alkali Activator[J]. Construction and Building Materials, 2012, 35: 557-563

[91] Wang Y, Liu X, Zhang W, et al.. Effects of Si/Al Ratio on the Efflorescence and Properties of Fly Ash Based Geopolymer[J]. Journal of Cleaner Production, 2020, 244: 118 852

RIGHTS & PERMISSIONS

Wuhan University of Technology and Springer-Verlag GmbH Germany, Part of Springer Nature