Comparative study of corrosion-based service life prediction of reinforced concrete structures using traditional and machine learning approach Amgoth Rajender, Amiya K. Samanta, Animesh Paral International Journal of Structural Integrity, 2025 PurposeAccurate predictions of the steady-state corrosion phase and service life to achieve specific safety limits are crucial for assessing the service of reinforced concrete (RC) structures. Forecasting the service life (SL) of structures is imperative for devising maintenance and repair strategy plans. The optimization of maintenance strategies serves to prolong asset life, mitigate asset failures, minimize repair costs and enhance health and safety standards for society.Design/methodology/approachThe well-known empirical conventional (traditional) approaches and machine learning (ML)-based SL prediction models were presented and compared. A comprehensive parametric study was conducted on existing models, considering real-world conditions as reported in the literature. The analysis of traditional and ML models underscored their respective limitations.FindingsEmpirical models have been developed by considering simplified assumptions and relying on factors such as corrosion rate, steel reinforcement diameter and concrete cover depth, utilizing fundamental mathematical formulas. The growth of ML in the structural domain has been identified and highlighted. The ML can capture complex relationships between input and output variables. The performance of ML in corrosion and service life evaluation has been satisfactory. The limitations of ML techniques are discussed, and its open challenges are identified, along with insights into the future direction to develop more accurate and reliable models.Practical implicationsTo enhance the traditional modeling of service life, key areas for future research have been highlighted. These include addressing the heterogeneous properties of concrete, the permeability of concrete and incorporating the interaction between temperature and bond-slip effect, which has been overlooked in existing models. Though the performance of the ML model in service life assessment is satisfactory, models overlooked some parameters, such as the material characterization and chemical composition of individual parameters, which play a significant role. As a recommendation, further research should take these factors into account as input parameters and strive to develop models with superior predictive capabilities.Originality/valueRecent deployment has revealed that ML algorithms can grasp complex relationships among key factors impacting deterioration and offer precise evaluations of remaining SL without relying on traditional models. Incorporation of more comprehensive and diverse data sources toward potential future directions in the RC structural domain can provide valuable insights to decision-makers, guiding their efforts toward the creation of even more resilient, reliable, cost-efficient and eco-friendly RC structures.
Performance evaluation on corrosion resistance of concrete blended with microsilica under chloride-laden conditions: an experimental and ANN-based approach Amgoth Rajender, Amiya K. Samanta Engineering Computations Swansea Wales, 2025 PurposeAccurate and premature prediction of corrosion onset in reinforced concrete structures is crucial for designing sustainable and resilient structures, which will have a lesser carbon footprints, reduced diminution of natural resources and effective utilization of waste materials.Design/methodology/approachThis study envisages the corrosion resistance and corrosion initiation across seven distinct phases at 15, 30, 45, 60, 75, 90 and 105 days in concrete blended with Portland Slag Cement (PSC) and microsilica. Concrete cube specimens with variable microsilica content (0, 5, 10, 15 and 20%), each containing a centrally sited rebar, were subjected to accelerated corrosion under severe chloride circumstances (5% NaCl) for 105 days, following ASTM C876-91 stipulation.FindingsExperimental results and scanning electron microscope investigation revealed that samples with 10% microsilica exhibited the superior corrosion resistance, attributed to the enhanced development of calcium silicate hydrate gel. Additionally, the experimental findings have also been validated using an artificial neural network (ANN). The ANN model predictions closely align with experimental predictions, by achieving higher correlation coefficients (“R” values of 0.99935, 0.99835, 0.99906 and 0.99917 for training, testing, validation and the overall model, respectively). Experimental findings and model predictions suggest that PSC partially replaced with 10% microsilica holds noteworthy potential for developing concrete mixes suited for extreme environments.Originality/valueAccurate and timely prediction of corrosion initiation minimizes potential hazards, ensuring structural longevity and reliability. Furthermore, the partial replacement of cement with microsilica enhances corrosion resistance, reducing cement consumption and promoting the effective utilization of waste materials for sustainable construction.
Analyzing compressive strength of sustainable concrete with recycled refractory brick fine aggregate: an experimental and ANN approach Sudipta Ghosh, Amgoth Rajender, Amiya K. Samanta World Journal of Engineering, 2025 Purpose The growing trend of infrastructure development leads to the depletion of natural resources. Researchers are continually seeking suitable substitutes to mitigate the depletion of natural resources and conserve them. In view of this, this study aims to develop a few innovative concrete mixes with recycled refractory brick (RRB), which is a key by-product from different steel, refractory and other ancillary industries, as a partial to total replacement for fine aggregate. Design/methodology/approach In this investigation, M25-grade concrete with two different types of design mix ratios with 1:1.98:3.78 and 1:2.17:3.74 were produced with a w/c ratio of 0.45. The RRB has been used as a substitute for fine aggregate by weight at 00%, 10%, 20%, 30%, 40%, 50%, 70% and 100% levels. The compressive strength of different concrete mixes has been evaluated after 7 and 28 days of curing periods with potable water having an approximate temperature of 23 ± 2°C. Particle size gradation (mm), fineness modulus, consistency (%), specific gravity and water absorption (%) tests for the raw materials and compression test after 7 and 28 days for the concrete specimens have been conducted. Moreover, the experimental outcomes have also been confirmed through an artificial neural network (ANN). Findings Experimental investigation reveals that, after a seven-day curing period, the sample with 40% and 50% RRB, and after 28 days, samples with 20% replacement of RRB yielded the highest compressive strength, which are 33%, 39% and 15%, respectively. Based on the microstructural analysis, it has been evident that the development of CH and CSH gels fills up the micro pores and results in an improvement in compressive strength. Similar to the experimental output, the proposed ANN model confirmed similar output with the least error percentage of ± 2%–4%. Originality/value The residual mechanical strength and potential of RRB incorporated concrete may be considered appropriate for a wide range of applications under harsh climatic conditions, in particular under high temperature gradients. Deployed ANN to offer specific evaluations of compressive strength short of relying on traditional models, considering complex relationships. The sustainable concrete with recycled refractory brick fine aggregate suits eco-friendly construction, structural and/or nonstructural uses in compliance with IS 10262, IS 516, IS 456. The ANN model complements IS design, accurately predicting strength and optimizing mixes for sustainable construction practices.
Compressive strength prediction of metakaolin based high-performance concrete with machine learning Amgoth Rajender, Amiya K. Samanta Materials Today Proceedings, 2023 The demands of the building sector have significantly intensified the search for the development of high-strength and high-performance concretes due to its conspicuous advantage of high strength and performance, which increases the service life of reinforced concrete structures . The requirement for cement in the construction industry is progressively increasing with the recent trend. The cement industry is one of the world's leading producers of carbon dioxide (CO 2 ). To improve the mechanical properties of the concrete and reduce the liberation of CO 2 during manufacturing, cement is partially replaced with various cementitious materials . In the present work, the cement is partially replaced with metakaolin in high-performance concrete, while the tool of machine learning application has also been utilized. The present work focuses on developing ML-based models to assess the characteristic compressive strength of metakaolin-based high-performance concrete (M60) based on the mix proportions. Four Machine learning algorithms Backpropagation Neural Networks (BPNN), Linear Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) are employed using this dataset. Cement, metakaolin , water content, admixtures, fine aggregate, and coarse aggregate quantities are used as input variables, and the characteristic compressive strength achieved at 28 days of curing is used as the output variable. Employed ‘Coefficient of Correlation’ (R 2 ), ‘Mean Absolute Error (MAE)’, and Root Mean Square Error (RMSE) to validate the experimental data. A value of R 2 equal to or more than 0.9 is considered a good correlation among the input variables. The value of coefficient correlation R2 value achieved about 0.8944 For the Random Forest (RF) algorithm-based model, which shows the higher efficiency among the proposed machine learning algorithms for an optimum 10% percentage of metakaolin as a partial replacement for cement in high-performance concrete.
