KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 19

Some of the metrics are blocked by your
consent settings
Photothermal solar assisted Madhuca diethyl ether fuel processing for LHR engines with AI-based performance and yield prediction
(2026-12-01)
Dubey, Rakesh
;
Prajapati, Ajeet Kumar
;
Bharadwaj, Shruti
;
Kamchoom, Viroon
;
Onyelowe, Kennedy C.
This study investigates the combustion, performance, and emission characteristics of biodiesel blends derived from Madhuca longifolia oil with diethyl ether (DEE) as an oxygenated additive in a diesel engine. Prior to fuel preparation, Fourier Transform Infrared (FTIR) analysis was conducted to verify the chemical composition of the extracted oil, confirming the presence of triglyceride structures and long-chain fatty acids characteristic of Madhuca longifolia oil. A solar-assisted preheating mechanism was incorporated during oil extraction to reduce energy consumption and improve yield consistency. The system was further integrated with a 250 Wp solar photovoltaic (PV) panel (efficiency ~ 17%, Voc = 37 V, Isc = 8.5 A, MPPT = 30 V/8 A) to power auxiliary loads such as the fuel metering unit, sensors, and control panel. This renewable integration enabled 100% solar contribution for auxiliary components, saving approximately 1.04 kWh/day of grid electricity and achieving an estimated reduction of about 151 kg of CO<inf>2</inf> emissions annually. Four fuel types were evaluated: Diesel, MB100 (pure biodiesel), MB20D80 (20% biodiesel, 80% diesel), and MB5DEE5D90 (5% biodiesel, 5% DEE, 90% diesel). Among these, MB5DEE5D90 demonstrated comparatively improved performance, showing an 8% increase in Brake Thermal Efficiency (BTE) and a 10% reduction in Brake-Specific Fuel Consumption (BSFC) compared with diesel. Emission analysis indicated reductions of approximately 20% in CO and 18% in HC emissions, while life-cycle assessment suggested around 40% lower combustion-phase CO<inf>2</inf> emissions. Heat release rate analysis indicated earlier and more efficient combustion behavior. Additionally, LSTM-based predictive modeling showed lower error margins compared with RNN, demonstrating improved prediction accuracy for engine performance parameters.
Some of the metrics are blocked by your
consent settings
Investigation of long-term performance monitoring of cementitious mixes modified with healing agents and polymeric additives of self-healing polymer modified mortar (SHPMM)
(2026-03-01)
Kanwal, Humaira
;
Wang, Ziping
;
Hao, Wenfeng
;
Javed, Kamran
;
Asim, Muhammad
Concrete and mortar exhibit durability limitations in aggressive environments due to cracking, high permeability, and construction defects. Polymer-modified and self-healing cementitious materials have emerged as sustainable solutions; however, the synergistic use of polymer modifiers with chemical–biological healing agents remains underexplored. This study investigates self-healing polymer-modified mortar (SHPMM) incorporating styrene butadiene rubber (SBR) and ethylene vinyl acetate (EVA) as partial cement replacements at 0%,4%,8%,12% & 16%. A healing system consisting of 5% calcium lactate, 5% sodium silicate, 1% sodium carbonate. Also 1% effective microorganisms was added to all mixes. Workability, mechanical performance, durability, and microstructural characteristics were evaluated through slump, ultrasonic pulse velocity, strength tests, rapid chloride permeability, SEM, and EDX analyses. The results indicate that polymer addition significantly improves workability, strength, and durability. Slump values increased steadily with increasing polymer content. Optimum performance was observed at 4% and 8% polymer replacement, where permeability was markedly reduced. Compared to the control mix, compressive strength increased by 7–11%, split tensile strength by 12–17%, and flexural strength by 31–33%. RCPT values decreased substantially, with reductions of 32% and 45% for 4% and 8% SBR, and 22% and 58% for 4% and 8% EVA, respectively. Microstructural analysis confirmed improved matrix densification and crack-healing efficiency. EVA demonstrated superior performance compared to SBR, attributed to its powdered form and enhanced bonding characteristics. Overall, the combined application of polymer modifiers and healing agents effectively improves the mechanical performance, durability, and self-healing efficiency of cementitious composites, offering a viable solution for sustainable infrastructure in aggressive environments.
Some of the metrics are blocked by your
consent settings
Development of data-driven framework for the geotechnical behavior of xanthan gum-treated clay reinforced with polypropylene fibers
(2026-01-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Baldovino, Jair De Jesús Arrieta
;
Kumar, S. Anandha
;
Ebid, Ahmed M.
This study develops a robust data-driven modeling framework to predict the unconfined compressive strength (UCS) and stiffness (Go) of low-plasticity clay soils stabilized with Xanthan Gum (XG) and Polypropylene Fiber (PPF), aiming to advance sustainable geotechnical design. A total of 108 soil specimens were prepared with varying XG dosages and cured over different periods, and predictive models were constructed using a Decision Table algorithm optimized with six bio-inspired optimization techniques. Among these, the Firefly-optimized model consistently provided the highest accuracy, demonstrating reliable agreement between predicted and measured values. Sensitivity analysis identified XG dosage, curing time, and dry density as the most influential factors governing UCS and Go. These findings highlight the strong potential of the proposed machine learning framework to guide field engineers in optimizing mix design parameters for improved mechanical behavior of bio-treated soils, reducing reliance on time-consuming and costly laboratory tests while promoting environmentally sustainable foundation practices. The need for this study arises from the growing demand for green soil stabilization techniques that minimize the use of cement and lime while still ensuring reliable performance in construction. Its applicability extends to real-world geotechnical projects such as embankments, road subgrades, and shallow foundations, where predictive modeling can significantly streamline design decisions and improve long-term sustainability.
Some of the metrics are blocked by your
consent settings
Mechanical properties of self compacting concrete reinforced with hybrid fibers and industrial wastes under elevated heat treatment
(2025-12-01)
Onyelowe, Kennedy C.
;
Hanandeh, Shadi
;
Kamchoom, Viroon
;
Ebid, Ahmed M.
;
Zurita Polo, Susana Monserrat
Machine learning prediction of the mechanical properties of self-compacting concrete (SCC) reinforced with hybrid fibers, incorporating industrial wastes like fly ash and blast furnace slag, and cured under elevated heat provides a reliable and efficient alternative to traditional laboratory experiments. In this work, extensive literature review leading to the collection, sorting and curation of a global database representative of the mechanical properties of self-compacting concrete reinforced with hybrid fiber mixed with industrial wastes for sustainable construction was conducted. The collected database constituted traditional concrete components and admixtures such as Cement (C), Fly ash (FA), Slag (BFS), Fine Aggregate (FAg), Coarse Aggregate (CAg), Water (W), Superplasticizer (PL), Fiber (Fi), and Temperature (Temp.) studied under the mechanical properties such as the Compressive Strength (Fc), Tensile Strength (Fsp), and Flexural Strength (Ff). The collected 114 records were divided into training set (90 records = 80%) and validation set (24 records = 20%) following the guidelines for data partitioning for optimal performance in machine learning predictions. Different advanced machine learning methods created using “Weka Data Mining” software version 3.8.6 were applied such as “Semi-supervised classifier (Kstar)”, “M5 classifier (M5Rules), “Elastic net classifier (ElasticNet), “Correlated Nystrom Views (XNV)”, and “Decision Table (DT)” to predict the output. The Hoffman/Gardener and SHAP techniques are used to estimate the sensitivity of the input parameter on the output. Finally, various performance metrics are used to evaluate the reliability of the models. The results show that the machine learning models show varying degrees of predictive accuracy, with the Kstar and XNV models consistently outperforming others across all mechanical properties. However, Kstar with accuracies of 96.5%, 96.0%, and 97.0% for Fc, Fsp, and Ff predictions, respectively proposed the most decisive model. Also, the Hoffman and Gardener method highlights the role of the binders, chemical additives, and curing, whereas SHAP attributes greater importance to aggregates and binder interactions.
Some of the metrics are blocked by your
consent settings
Modeling the compressive strength behavior of concrete reinforced with basalt fiber
(2025-12-01)
Onyelowe, Kennedy C.
;
Ebid, Ahmed M.
;
Hanandeh, Shadi
;
Kamchoom, Viroon
;
Awoyera, Paul
This research investigates the compressive strength behavior of basalt fiber-reinforced concrete (BFRC) using machine learning models to optimize predictions and enhance its practical applications. The study incorporates various modeling techniques, including Artificial Neural Networks (ANN), k-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees, and Random Forest (RF), to evaluate their predictive capabilities. Basalt Fiber Reinforced Concrete (BFRC) is a composite material that incorporates basalt fibers into traditional concrete to enhance its mechanical and durability properties. The use of basalt fibers, derived from natural volcanic rocks, aligns with sustainability goals due to their eco-friendliness, cost-effectiveness, and high performance. BFRC combines structural excellence with sustainability, making it an ideal material for modern construction practices. Its ability to enhance performance, reduce environmental impact, and ensure long-term durability positions it as a pivotal solution for sustainable infrastructure development. The developed models were used to predict compressive strength of basalt fiber concrete (Cs_bf) using the concrete mixture contents, age, and fiber dimensions. All the developed models were created using “Orange Data Mining” software version 3.36. A total of three hundred and nine (309) records were collected from literature for compressive strength for different mixing ratios of basalt fiber concrete with concrete at different ages. Each record contains the following data: C-Cement content (Kg/m3), FA-Fly ash content (Kg/m3), W-Water content (Kg/m3), SP-Super-plasticizer content (Kg/m3), CAg-Coarse aggregates content (Kg/m3), FAg-Fine aggregates content (Kg/m3), Age-The concrete age at testing (days), L_b-length of basalt fibers (mm), d_bf-Diameter of basalt fibers (µm), V_bf-Volume content of basalt fibers (%) and Cs_bf-Compressive strength of basalt fibre concrete (MPa). The collected records were divided into training set (249 records≈80%) and validation set (60 records≈ 20%). At the end of the process, it can be shown that the present research work outclassed other ML techniques applied in the previous research paper, which reported the utilization of the same size of data entries and basalt reinforced concrete constituents. Taylor chart for measured compressive strength of basalt fiber reinforced concrete predicted with ANN, KNN, SVM, Tree and RF is presented for comparing the performance of predictive models by illustrating three key statistical measures simultaneously: the correlation coefficient (R), the normalized standard deviation (σ), and the root-mean-square error (RMSE). Finally, it can be deduced that after considering the performance indices of the selected ensemble and classification models utilized in this present research paper, all the developed modes have almost the same excellent level of accuracy 95%, but ANN, KNN, and SVR produced R2 of 0.98 each with KNN producing MAE of 1.4 MPa, and MSE of 2.5 MPa to outperform ANN and SVR which produced MAE of 1.55 MPa/MSE of 4.1 MPa and MAE of 1.6 MPa/MSE of 3.85 MPa, respectively. Three techniques were used to estimate the impact of each input on the compressive strength, namely correlation matrix, sensitivity analysis and relative importance chart.
Some of the metrics are blocked by your
consent settings
Developing advanced datadriven framework to predict the bearing capacity of piles on rock
(2025-12-01)
Onyelowe, Kennedy C.
;
Hanandeh, Shadi
;
Kamchoom, Viroon
;
Ebid, Ahmed M.
;
Reyes Silva, Fabián Danilo
Developing accurate predictive models for pile bearing capacity on rock is crucial for optimizing foundation design and ensuring structural stability. This research presents an advanced data-driven framework that integrates multiple machine learning algorithms to predict the bearing capacity of piles based on geotechnical and in-situ test parameters. A comprehensive dataset comprising key influencing factors such as pile dimensions, geological characteristics, and penetration resistance was utilized to train and validate various models, including Kstar, M5Rules, ElasticNet, XNV, and Decision Trees. The Taylor diagram and statistical evaluations demonstrated the superiority of the proposed models in capturing complex nonlinear relationships, with high correlation coefficients and low root mean square errors indicating robust predictive capabilities. Sensitivity analyses using Hoffman and Gardener’s approach and SHAP values identified the most influential parameters, revealing that penetration resistance, pile embedment depth, and geological conditions significantly impact pile capacity. The findings underscore the effectiveness of machine learning in geotechnical engineering applications, offering a reliable and efficient alternative to traditional empirical and analytical methods. The developed framework provides engineers and practitioners with a powerful tool for improving pile design accuracy, reducing uncertainties, and optimizing construction practices. Future research should focus on expanding the dataset with diverse geological conditions and exploring hybrid modeling techniques to enhance prediction accuracy further.
Some of the metrics are blocked by your
consent settings
Evaluating the impact of waste marble on the compressive strength of traditional concrete using machine learning
(2025-12-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Ebid, Ahmed M.
;
Hanandeh, Shadi
;
Zurita Polo, Susana Monserrat
Waste marble, an industrial byproduct generated from marble cutting and polishing processes, can be effectively utilized as a partial replacement in concrete mixtures. Incorporating waste marble in concrete not only addresses environmental concerns related to marble waste disposal but also contributes to the sustainability of construction materials. Using machine learning (ML) to predict the impact of waste marble on the compressive strength of traditional concrete offers several advantages over repeated laboratory experiments. ML offers a powerful alternative to costly and time-consuming laboratory experiments, enabling faster and more sustainable exploration of the potential of waste marble in improving concrete’s compressive strength. This research has focused on evaluating the impact of waste marble on the compressive strength of traditional concrete using machine learning (ML). Advanced ML techniques such as the Group Methods Data Handling Neural Network (GMDH-NN), Support Vector Regression (SVR), K-Nearest Neighbors (kNN) and Adaptive Boosting (AdaBoost) have been applied in this research work. The GMDH-NN model was created using GMDH Shell 3.0 software, while AdaBoost, SVR and kNN models were created using “Orange Data Mining” software version 3.36. Error indices such as the sum of squared error (SSE), mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and Error (%), and performance metrics such as Accuracy % and the R2 between predicted and calculated compressive strength parameters were used to evaluate the overall behavior of the models. Finally, the Hoffman sensitivity analysis procedure was applied to determine the individual relative impact of the input variables on the output. At the end of the processes, a total of 1135 waste marble concrete entries were collected containing constituents such as the cement density (C), waste marble (WM), fine aggregate (FAg), coarse aggregate (CAg), water (W), superplasticizer (PL) and curing age (Age) used as input variables of the waste marble concrete model. The records were divided into training set (900 records = 80%) and validation set (235 records = 20%) following standard partitioning pattern reported in the literature. The kNN and AdaBoost, with SSE of 1408.5 MPa2 and 1397 MPa2 respectively and a tie Accuracy of 95.5% and R2 of 0.985 showed the best models suggesting excellent model performance while GMDH-NN showed the worst. Conversely, RF balances accuracy and model complexity, making it a practical alternative to kNN and AdaBoost. And lastly, Age, Coarse Aggregates, Water, and Plasticizer play the most significant roles in determining the compressive strength, while Cement, Waste Marble, and Fine Aggregates have comparatively smaller impacts. However, considering the standard proportion required for waste marble powder to replace cement, it showed a remarkable influence on the behavior of the concrete thus a recommended potential for its used as replacement for cement.
Some of the metrics are blocked by your
consent settings
Predicting the strengths of basalt fiber reinforced concrete mixed with fly ash using AML and Hoffman and Gardener techniques
(2025-12-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Hanandeh, Shadi
;
Ebid, Ahmed M.
;
Llamuca Llamuca, José Luis
Basalt fiber-reinforced concrete (BFRC) mixed with fly ash, combined with advanced machine learning techniques, offers a practical, cost-effective, and less time-consuming alternative to traditional experimental methods. Conventional approaches to evaluating mechanical properties, such as compressive and splitting tensile strengths, typically require sophisticated equipment, meticulous sample preparation, and extended testing periods. These methods demand substantial financial resources, specialized labor, and considerable time for data collection and analysis. The integration of machine learning provides a transformative solution by enabling accurate prediction of concrete properties with minimal experimental data. The methods of data collection from literature and analysis were used and 121 records were collected from experimentally tested basalt fiber reinforced concrete samples measuring the compressive and splitting tensile strengths of the concrete. Eleven (11) critical factors have been considered as constituents of the studied concrete to predict the Fc-Compressive strength (MPa) and Fsp-Splitting tensile strength (MPa), which are the output parameters. The collected records were divided into training set (96 records = 80%) and validation set (25 records = 20%) following the requirements for data partitioning for sustainable machine learning application. Seven (7) selected machine learning techniques are applied in the prediction. Further, performance evaluation indices were used to compare the models’ abilities and lastly, the Hoffman and Gardener’s technique was used to evaluate the sensitivity of the parameters on the concrete strengths. At the end of the exercise, results were collated. In predicting the compressive strength (Fc), AdaBoost similarly excels, matching XGBoosting’s validation performance with R2 of 0.98 and the same MAE values. This shows the effectiveness of boosting techniques for predictive modeling in concrete strength estimation. For splitting tensile strength (Fsp), AdaBoost also outperforms most models, achieving an R2 of 0.96 for training and validation phases. Its exceptionally low validation MAE of 0.124 MPa underscores its excellent generalization capabilities. Overall, XGBoosting and AdaBoost consistently demonstrate superior performance for both compressive and splitting tensile strength predictions, followed closely by KNN. These models benefit from advanced ensemble techniques that efficiently handle non-linear patterns and noise. SVR also performs admirably, whereas GEP and GMDHNN exhibit weaker predictive capabilities due to limitations in handling complex data dynamics. For the sensitivity analysis, the Hoffman and Gardener’s method of sensitivity analysis proves instrumental in identifying key drivers of strength in fiber-reinforced concrete, guiding informed decision-making for material optimization and sustainable construction practices.
Some of the metrics are blocked by your
consent settings
Impact of lightweight clay aggregate with slag and biomedical waste ash on self-compacting concrete using machine learning approach
(2025-12-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Hanandeh, Shadi
;
Ebid, Ahmed M.
;
Viñan Villagran, Janneth Alejandra
The self-compacting concrete (SCC) mixes were developed using lightweight expandable clay aggregate (LECA) as a partial substitute for coarse aggregate, ground granulated blast-furnace slag (GGBS) as a partial replacement for cement, and combusted bio-medical waste ash (BMWA) as a partial replacement for fine aggregate. The substitution levels for LECA, GGBS, and BMWA were set at 10%, 20%, and 30% of coarse aggregate, cement, and fine aggregate, respectively. M30-grade SCC mixes were designed with two different water-to-binder ratios—0.40 and 0.45—and their compressive strength (CS) was experimentally evaluated. The data entries from the above mix designs and experiments were collected in this research which deals with evaluating the impact of lightweight expandable clay aggregate, metallurgical slag, and combusted bio-medical waste ash on self-compacting concrete. An extensive literature search was used in this project and this produced a global representative database collected from literature. The collected 384 records were divided into training set (300 records = 80%) and validation set (84 records = 20%) in line with the requirements of a more reliable data partitioning. Six advanced machine learning methods such as the Artificial Neural Network (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGB), Random Forest (RF), and Adaptive Boosting (AdaBoost) were used to model the concrete behavior. All models were created using “Orange Data Mining” software version 3.36. A combination of error metrics, efficiency metrics and determination/correlation metrics were used to test the models performance and accuracy. Also, the Hoffman and Gardener’s method was used to evaluate the sensitivity analysis of the model variables. At the end of the model work, AdaBoost and KNN excel in predictive accuracy with 97.5%, reducing the margin of error and ensuring precise mix designs for SCC. SVR, XGB, and RF also exhibit strong accuracy (96.5–97%), supporting reliable material selection and proportions. AdaBoost and KNN demonstrate the lowest errors (MAE: 0.65 MPa, RMSE: 0.75 MPa), indicating precise performance, minimizing overdesign or underperformance risks, and optimizing material usage. The Hoffman/Gardener’s sensitivity analysis produced produced GGBS of 31% and Dens of 26% as the highest impact and this is followed by LECA of 21% and BMWA of 20%. This research enables the optimization of self-compacting concrete mix designs using machine learning, reducing experimental trials, enhancing material efficiency, lowering environmental impact, and promoting sustainable construction through the effective reuse of industrial by-products.
Some of the metrics are blocked by your
consent settings
Developing data driven framework to model earthquake induced liquefaction potential of granular terrain by machine learning classification models
(2025-12-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Gnananandarao, Tammineni
;
Arunachalam, Krishna P.
Earthquake-inducedliquefaction of soils poses a serious georisk in geotechnical designs, construction and the application of geotechnical structures around the world. In this study, the applicability of three soft computing models for liquefaction classification, a topic of significant importance within the fields of geotechnical and earthquake engineering has been evaluated. Twelve input parameters are used to classify the liquefaction potential for 234 data sets collected from an earthquake-induced liquefaction prone granular material environment. For developing the SVM_Poly, SVM_RBK models, an extensive number of trials were conducted using various combinations of C and d for polynomial kernels and C and ∂ for radial basis function kernel-based support vector machines (SVMs) utilizing user-defined parameters. In the same way, several experiments were conducted with a fixed value of C and ∂ kernel specific parameters in order to determine an appropriate value of error-insensitive zone (∋).Similarly, for the random forest classifier (RFC) model, the number of variables used (m) and the number of trees to be grown (k) are two user-defined parameters. These optimum values of m and k parameters are fixed using trial and error process and the same fixed values. The best model was developed as evidence from the confusion matrixes and statistical indicators. The calculated values of confusion matrixes and statistical indicators for training and testing shows that an accuracy of 0.89 indicates the model is correct in its predictions 89% of the time. A sensitivity of 0.85 signifies the model correctly identifies 85% of actual positive instances, while a specificity of 0.94 implies correct identification of 94% of actual negative instances. A precision of 0.94 suggests that when the model predicts a positive instance, it is correct 94% of the time. The Phi Correlation Coefficient, with a value of 0.82, indicates a strong positive correlation between predicted and actual values.Furthermore, the model exhibits a Mean Absolute Error (MAE) of 0.2351, reflecting a relatively low average error in predictions. The Root Mean Squared Error (RMSE) value of 0.3115 indicates better accuracy in predicting the target variable.Finally, all the developed models exhibit promising performance across various evaluation metrics, with low error measures (MAE and RMSE), high accuracy, and strong performance in correctly identifying both positive and negative instances, as evidenced by sensitivity and specificity. The high precision and Phi Correlation Coefficient further affirm the reliability and accuracy of the model’s predictions. However, among the three models FRC model is the best for classifying the liquefaction. The novelty of this research lies in its comparative evaluation and optimization of SVM_Poly, SVM_RBK, and RFC models using a comprehensive set of seismic and soil parameters to accurately classify earthquake-induced liquefaction potential, with the RFC model demonstrating superior predictive performance.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results