@article{nokey,

title = {A novel Pareto Front Symbiotic Organism Search (PF-SOS) combined with metaheuristic-optimized machine learning for optimal recycled aggregate concrete mixtures},

author = {Hanna Chintya Febriani Gunawan and John Thedy and Bagus Hario Setiadji and Ay Lie Han and Marc Ottele },

url = {https://www.sciencedirect.com/science/article/abs/pii/S2352710225012288},

doi = {10.1016/j.jobe.2025.112991},

year  = {2025},

date = {2025-08-15},

journal = {Journal of Building Engineering},

volume = {108},

abstract = {Recycled Aggregate Concrete (RAC) represents a significant innovation aimed at reducing the carbon footprint in the construction industry. Over the past few decades, numerous investigations and experiments have confirmed the viability of RAC as a construction material when the optimal combination of recycled and natural aggregates is used. This study seeks to further enhance the application of RAC by providing a robust framework for determining the optimal RAC mixture. To achieve this, machine learning is developed to predict the compressive strength of RAC by considering various mixture properties. To improve the accuracy of these predictions, the Symbiotic Organism Search (SOS) metaheuristic algorithm is employed, not only to fine-tune the machine learning hyperparameters but also to select the most suitable model. In this study, the SOS algorithm is tasked with choosing between Artificial Neural Networks (ANN), Support Vector Machines (SVM), or Random Forests (RF), based on predefined upper and lower bounds for their hyperparameters. The resulting machine learning model is then integrated with the novel Pareto Front Symbiotic Organism Search (PF-SOS) to generate a Pareto front of optimal mixtures, with compressive strength and production cost as the objectives. To validate the efficiency of the proposed method, the PF-SOS results are compared with those from other well-known multi-objective optimization algorithms. The findings demonstrate that PF-SOS offers faster convergence and a broader range of mixture options within the same function evaluation limit. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Tensile behavior of self-compacting geopolymer concrete considering tension stiffening Author links open overlay panel},

author = {Bobby Rio Indriyantho and Blinka Hernawan Prasetya and Banu Ardi Hidayat and Herry Puguh Prasetya and Ay Lie Han and Michael Kaliske},

url = {https://www.sciencedirect.com/science/article/abs/pii/S2352710225006394},

doi = {10.1016/j.jobe.2025.112402},

year  = {2025},

date = {2025-07-01},

journal = {Journal of Building Engineering},

volume = {105},

abstract = {When it comes to lowering carbon emissions due to the production of cement, geopolymer concrete holds great promise as an environmentally friendly alternative to conventional cement-based concrete. Due to the variation in its material constituents, building codes do not yet mandate any specific norm for its mechanical properties. In the meantime, since reinforced concrete with steel reinforcements has taken up the tensile contribution, the behavior of concrete under tension has little bearing on construction designs. However, it might not be accurate to disregard concrete’s tensile strength for analyses meant to identify structural responses. With reference to the tension stiffening phenomenon of reinforcing steel embedded in a cylindrical self-compacting geopolymer concrete (SCGC) with certain dimensions, the goal of this work is to examine the tensile behavior of SCGC. The behavior of this specimen under tension, including its strength and the relationship between stress and strain, as well as its crack pattern and failure mechanism, is determined via uniaxial tensile testing, considering tension stiffening phenomena. Following normalization, the results are compared to the tensile performance of conventional concrete under identical circumstances and evaluated against the standard building code.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Artificial Intelligence in Geopolymer Concrete Mix Design: A Comprehensive Review of Techniques and Applications},

author = {Malik Mushthofa and John Thedy and Mochamad Teguh and Purwanto and Adjie Gemilang Pratama and Ay Lie Han },

url = {https://link.springer.com/article/10.1007/s40996-025-01873-8},

year  = {2025},

date = {2025-05-13},

journal = { Iranian Journal of Science and Technology, Transactions of Civil Engineering },

abstract = {This systematic review explores the application of Artificial Intelligence (AI) in optimizing the mix design of fly ash-based geopolymer concrete (FABGC). Analyzing studies published between 2014 and 2025, it examines key methodologies, including machine learning models, optimization algorithms, and multi-criteria decision-making approaches. Critical aspects such as data preprocessing, AI model selection, hyperparameter tuning, explainable AI (XAI), and optimization strategies are synthesized to provide a comprehensive perspective on AI-driven FABGC research. The review identifies Deep Residual Networks (ResNet) and Extreme Gradient Boosting (XGB) as the most accurate models for predicting FABGC strength, consistently outperforming others due to their lower error metrics. Backpropagation Neural Networks (BPNN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) also demonstrate competitive performance, while Random Forest (RF) and Decision Tree (DT) models excel in computational efficiency with shorter training times. Despite being the most widely implemented, Artificial Neural Networks (ANN) rarely achieve the highest predictive accuracy. Traditional regression methods, though straightforward, lag behind in performance. These findings underscore the need for standardized datasets, enhanced collaboration, and innovative AI-driven approaches to improve FABGC mix design optimization. Addressing these challenges will facilitate more reliable and efficient AI applications in sustainable concrete technology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Stress–strain behavior of CFRP-bond to steel in tension},

author = {Dinar Gumilang Jati and Mhd Rony Asshidiqie and Bobby Rio Indriyantho and Viktor Mechtcherine and Buntara Sthenly Gan and Ay Lie Han },

url = {https://link.springer.com/article/10.1617/s11527-025-02666-1},

year  = {2025},

date = {2025-04-24},

journal = {Materials and Structures },

volume = {58},

number = {123},

abstract = {Carbon fiber reinforced polymer (CFRP) sheets are used to externally reinforce structural elements. Compatibility is of major importance to transfer stresses and strains from the reinforced member to the CFRP through the bond. This bond is a contribution of three layers: the adhesive-to-structure, the adhesive-to-CFRP bond, and the properties of the adhesive-impregnated CFRP. While in modeling, the CFRP is assumed to be fully bonded; test results suggested that this assumption overestimated post-peak responses in particular. Defining accurate CFRP bond behavior is therefore obligatory in modeling. This research aimed to construct accurate stress–strain responses of CFRP bond layers. The study acquired this by investigating the strain-gauge responses at each layer as a function of incremental loading. CFRP sheets with a variation in length ranging from 40 to 120 mm were attached to a 300 mm steel plate subjected to flexural stresses. The CFRP was situated in the tensile zone. The steel plate was favored to ensure the failure mode occurred in the CFRP layer. It was concluded that bond length significantly influenced the transfer mechanism, concluding a minimum effective CFRP length of 100 mm. All stress–strain bond relationships are characterized by bilinear responses, with almost identical adhesive-to-CFRP and impregnated CFRP behavior. The adhesive-to-structural layer had a lower ultimate stress and post-peak response; initial stiffnesses were undifferentiated. An implementation of the obtained stress–strain response into a finite element analysis (FEA) demonstrated the accuracy of the results and the significant deviation when a full bond is assumed through the toughness of the strengthened member.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {RC T-beams with flexural strengthening in the negative moment region under different configurations of NSM CFRP rods},

author = {Yanuar Haryanto and Nanang Gunawan Wariyatno and Fu-Pei Hsiao and Hsuan-Teh Hu and Ay Lie Han and Laurencius Nugroho and Hioe Hartono },

url = {https://www.sciencedirect.com/science/article/abs/pii/S1350630725001992?via%3Dihub},

doi = {10.1016/j.engfailanal.2025.109458},

year  = {2025},

date = {2025-02-27},

journal = {Engineering Failure Analysis},

volume = {173},

abstract = {This study employed a near-surface mounted (NSM) technique to enhance the flexural performance of reinforced concrete (RC) T-beams in the negative moment region, using carbon fiber reinforced polymer (CFRP) rods embedded at varying depths. An experimental investigation was conducted, supported by analytical calculations and finite element (FE) simulations, to validate the results. The experiments revealed that beams with half-embedded CFRP rods experienced partial debonding at significant crack locations, a problem potentially mitigated by fully embedded rods. Strengthening with NSM-CFRP rods increased cracking, yield, and ultimate loads by 10–21%, 36–38%, and 30–40%, respectively, compared to control beams, while also enhancing stiffness. However, these methods may have a twofold impact on the specimen by decreasing its ductility and energy absorption capacity. The analytical approach provided accurate and conservative predictions, with a coefficient of variation of 4.5%, while the FE model demonstrated high accuracy, achieving a coefficient of variation of 3.5% when compared to experimental flexural load capacity results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}