Skip to main content

Babatunde A B I O D U N Salami

Cardiff Metropolitan University, Cardiff School of Management, Faculty Member

Followers

277

Following

198

Co-authors

3

Mentions

330

Public Views

I am a Senior Lecturer at Cardiff Metropolitan University, where I teach project management, and research on construction and project management, artificial intelligence, and circular economy. I have a PhD and an MSc in Structural Engineering, and I hold PMP, Fully Registered Engineer, and LEED AP certifications. I have over 15 years of experience in interdisciplinary and multidisciplinary research, industry practice, and academic teaching in the construction sector.

My research interests include construction materials and management, digital construction, machine learning, project management, and project analytics. I aim to solve problems and improve the status quo in the construction industry, by applying innovative and sustainable solutions. I have published nearly 60 peer-reviewed articles, received 13 patents, and worked on various projects as a Construction Project Manager, Structural Design Engineer, and Research Assistant. I am a team player, self-motivated, goal-oriented, and passionate about advancing the knowledge and practice of construction.
Address: Cardiff, Wales

less

InterestsView All (6)

Uploads

Papers by Babatunde A B I O D U N Salami

Estimating Flexural Strength of FRP Reinforced Beam Using Artificial Neural Network and Random Forest Prediction Models

Polymers

An accurate calculation of the flexural capacity of flexural members is vital for the safe and ec... more An accurate calculation of the flexural capacity of flexural members is vital for the safe and economical design of FRP reinforced structures. The existing empirical models are not accurately calculating the flexural capacity of beams and columns. This study investigated the estimation of the flexural capacity of beams using non-linear capabilities of two Artificial Intelligence (AI) models, namely Artificial neural network (ANN) and Random Forest (RF) Regression. The models were trained using optimized hyperparameters obtained from the trial-and-error method. The coefficient of correlation (R), Mean Absolute Error, and Root Mean Square Error (RMSE) were observed as 0.99, 5.67 kN-m, and 7.37 kN-m, for ANN, while 0.97, 7.63 kN-m, and 8.02 kN-m for RF regression model, respectively. Both models showed close agreement between experimental and predicted results; however, the ANN model showed superior accuracy and flexural strength performance. The parametric and sensitivity analysis of ...

Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Measurement, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Data-driven model for ternary-blend concrete compressive strength prediction using machine learning approach

Ternary-blend concrete is a complex composite material, and the nonlinearity in its compressive s... more Ternary-blend concrete is a complex composite material, and the nonlinearity in its compressive strength behavior is unquestionable. Entirely many models have been developed to accurately predict the ternary-blend concrete compressive strength, such as ANN, SVM, random forest, decision tree, to mention but a few. This study underscores the better predictive performance and successful application of the least square support vector machine (LSSVM), a machine learning model for predicting the compressive strength of ternary-blend concrete. Coupled simulated annealing (CSA) was applied to the LSSVM model as an optimization algorithm. In addition, the genetic programming (GP) model was used as a benchmark model to compare the performance of the LSSVM-CSA model. The predictive performance of the LSSVM-CSA was compared with that of some of the proposed models in well-known studies where the same datasets were used. The model proposed in this study outperformed other studies, yielding an R 2 value of 0.954.

A risk assessment approach for enhancing construction safety performance

The construction industry is one of the most dangerous industries worldwide due to deadly fatalit... more The construction industry is one of the most dangerous industries worldwide due to deadly fatalities and accidents recorded yearly. Though many countries have established and implemented safety programs, the situation does not seem to have been mitigated. This study aims at developing a risk assessment approach that can be used to enhance the safety performance of construction projects. The study has employed pair-wise comparisons and weighting-by-ranking surveys to establish risk scores and weights for the various construction accidents, and their potential causes. Data has been collected from safety professionals in 15 large construction sites across the Eastern Province of Saudi Arabia. The study revealed that the type of accident with the highest risk score is "falling objects", while the most significant cause is excessive winds on the project site. The developed approach was applied on an ongoing car park construction project. Results showed that slips, trips and falls had the best safety performance. Furthermore, based on six sigma evaluation, the average project safety performance was at 2.33-sigma which implies that 228,739 accidents may occur in every million opportunities. The paper also provided recommendations to improve the safety performance of the case study.

Predicting the compressive strength of a quaternary blend concrete using Bayesian regularized neural network

Concrete produced with ordinary Portland cement (OPC) along with insertion of supplementary mater... more Concrete produced with ordinary Portland cement (OPC) along with insertion of supplementary materials increases the level of nonlinearity. Due to this increased non-linearity and difficulty in modeling numerically, the focus has increased on the exploration of computational intelligent models like artificial neural network (ANN) to estimate different concrete properties. In this study, a quaternary blend concrete was developed with OPC, fly ash (FA), metakaolin (MK) and rice husk ash (RHA). The experimental data were further used in training the proposed ANN models to approximate its compressive strength. The proposed neural network models were trained and optimized using three different regularization algorithms; the scaled conjugate gradient "trainsc" (SCG), Levenberg-Marquardt "trainlm" (LM) and Bayesian regularized "trainbr" (BR) algorithms. The percent proportion of OPC, FA, MK and RHA making up the quaternary blends and curing days are the five features used as input variables, while the compressive strength of each of the individual concrete mixture is the output variable (target). It was found out that ANN optimized with Bayesian regularization function performed best with the highest correlation coefficient, and lowest MAE, MSE and RMSE. The results obtained from the ANN approach show significant improvement with the experimental observations.

Effect of Common Salt on Some Engineering Properties of Eggshell Stabilized Lateritic Soil

This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR)... more This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR) properties of eggshell stabilized lateritic soils with a view of obtaining a good compliment for eggshell as a useful stabilizer for road works. Classification and consistency tests were performed on the soil samples which were also subjected to compaction and CBR tests. Stabilization was performed at optimum eggshell and with 2, 4, 6, 8, and 10% of common salt. The addition of common salt reduced the Plastic Indices (PI) of the samples. The values reduced from 14.82, 11.11 and 7.99% to 8.03, 1.25 and 1.23% in samples A, B and C respectively. Maximum Dry Density (MDD) increased from 1995 to 2140 kg/m 3 and 2000 to 2110 kg/m 3 in samples B and C respectively. The unsoaked CBR values also increased from 34.78 to 50.99 kN/m 2 , 15.64 to 28.89 kN/m 2 and 27.31 to 34.20 kN/m 2 at optimum stabilization in samples A, B and C respectively. The result showed that the addition of common salt impr...

A Risk Assessment Approach for Enhancing Construction Safety Performance

by Babatunde A B I O D U N Salami and Muizz O Sanni-Anibire

Safety Science, 2020

The construction industry is one of the most dangerous industries worldwide due to deadly fatalit... more The construction industry is one of the most dangerous industries worldwide due to deadly fatalities and accidents recorded yearly. Though many countries have established and implemented safety programs, the situation does not seem to have been mitigated. This study aims at developing a risk assessment approach that can be used to enhance the safety performance of construction projects. The study has employed pair-wise comparisons and weighting-by-ranking surveys to establish risk scores and weights for the various construction accidents, and their potential causes. Data has been collected from safety professionals in 15 large construction sites across the Eastern Province of Saudi Arabia. The study revealed that the type of accident with the highest risk score is "falling objects", while the most significant cause is excessive winds on the project site. The developed approach was applied on an ongoing car park construction project. Results showed that slips, trips and falls had the best safety performance. Furthermore, based on six sigma evaluation, the average project safety performance was at 2.33-sigma which implies that 228,739 accidents may occur in every million opportunities. The paper also provided recommendations to improve the safety performance of the case study.

Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Measurement , 2020

Corrosion initiation time of embedded steel is an important service life parameter, which depends... more Corrosion initiation time of embedded steel is an important service life parameter, which depends on concrete material make-up, exposure environment, and duration of exposure. Early and accurate determination of corrosion initiation time will aid in designing durable reinforced concrete, saves cost and time. This study leveraged on the power of ensemble machine learning by combining the performances of different models in estimating the corrosion initiation time of steel embedded in self compacted concrete using corrosion potential measurement. The concrete specimens were prepared with limestone powder as supplementary addition to Portland cement and was exposed to 5% sodium chloride in accordance with the requirements of ASTM C876-15 for 8 months. During the exposure, corrosion potential of the embedded steel was measured, and the recorded datasets were used in training five different machine learning models. With cement, limestone powder, coarse aggregate, fine aggregate, water and exposure period.as input variables, five different models were developed to estimate the corrosion initiation time (determined from the corrosion potential measurements) of the embedded steel. With respect to model predictive performance, the acquired results demonstrated that the random forest (RF) ensemble model amongst other trained models performed best with 85/15 dataset percentage split for the training and testing. RF ensemble performed best with CC and RMSE of 99.01% and 18.2747 mV for training, and 98.67% and 25.0298 mV for testing respectively. Hence, due to its superior and robust performance, this study proposes RF ensemble model in the estimation of corrosion initiation time of embedded steel in reinforced limestone-cement blend concrete.

Influence of composition and concentration of alkaline activator on the properties of natural-pozzolan based green concrete

The chemical constituents of precursor materials, the composition and concentration of alkaline a... more The chemical constituents of precursor materials, the composition and concentration of alkaline activators, volume of free water, and curing conditions are some of the mix design variables that influence the fresh and hardened properties of alkali-activated binders (AABs). To achieve desirable engineering properties and long-term performance of an AAB under various exposure conditions, each of these variables has to be carefully controlled. The reported research focused on the influence of concentration and composition of alkaline activators on the properties of natural pozzolan (NP)-based AAB. Since the molarity of sodium hydroxide (SH) and the ratio of sodium silicate (SS) to sodium hydroxide (SH) influence the properties of an AAB, the NP-based AABs were prepared by varying the SS to SH ratio from 2.0 to 2.75, at an increment of 0.25, and the molarity of SH from 8 to 14. The developed AAC specimens were tested to evaluate the strength development and the binder was characterized using SEM, XRD and FTIR techniques. A SS/SH ratio of 2.5 and 14 M SH solution were required to obtain maximum strength and dense microstructure. In addition, it was established that there exists an optimum silica modulus of the combined activator that results in faster polymerization of the precursor material.

EFFECT OF COMMON SALT ON SOME ENGINEERING PROPERTIES OF EGGSHELL STABILIZED LATERITIC SOIL

This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR)... more This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR) properties of eggshell stabilized lateritic soils with a view of obtaining a good compliment for eggshell as a useful stabilizer for road works. Classification and consistency tests were performed on the soil samples which were also subjected to compaction and CBR tests. Stabilization was performed at optimum eggshell and with 2, 4, 6, 8, and 10% of common salt. The addition of common salt reduced the Plastic Indices (PI) of the samples. The values reduced from 14.82, 11.11 and 7.99% to 8.03, 1.25 and 1.23% in samples A, B and C respectively. Maximum Dry Density (MDD) increased from 1995 to 2140 kg/m 3 and 2000 to 2110 kg/m 3 in samples B and C respectively. The unsoaked CBR values also increased from 34.78 to 50.99 kN/m 2 , 15.64 to 28.89 kN/m 2 and 27.31 to 34.20 kN/m 2 at optimum stabilization in samples A, B and C respectively. The result showed that the addition of common salt improved the compaction and CBR characteristics of eggshell stabilized soils.

Performance of POFA-Based Alkali-Activated Mortar Exposed to Elevated Temperatures

This research work was conducted to investigate the residual strength performance of POFA alkali-... more This research work was conducted to investigate the residual strength performance of POFA alkali-activated mortar when subjected to different levels of elevated temperature. 100% POFA, sand and (Na2SiO3(aq)/NaOH(aq)) ratios of 2.5, 2, 1 and 0.5 were used in the preparation of POFA alkali-activated mortar mixtures. 50 mm x 50 mm x 50 mm cube specimens were tested after 60±5 o C heat curing to study the effect of exposure to 3 levels of elevated temperature; 300, 600 and 900 o C. The performance metrics used to assess the impact of exposure to elevated temperatures were the residual compressive strength, weight loss and visual appearance. The alkaline activator ratio and the elevated temperature have induced specific impact on the residual compressive strength of the POFA alkali-activated mortar specimens. For all alkaline-activator ratios, increased strength was recorded for the specimens exposed to 600 o C temperature, however for mortar specimens exposed to 300 o C and 900 o C temperatures strength reduction was recorded. Microstructural changes of the POFA-alkali activated binder was investigated using scanning electron microscope (SEM) equipped with energy dispersive spectrometry (EDS) as a result of the elevated temperature exposure. Superior performance of the 600 o C specimens was also revealed as a result of the post-heating solidification of molten POFA alkali-activated binder.

POFA Engineered Alkali activated Cementitious Comp

The durability performance of palm oil fuel ash engineered alkali-activated cementitious composit... more The durability performance of palm oil fuel ash engineered alkali-activated cementitious composite (POFA-EACC) mortar exposed to different acid solutions is assessed in this study. 50 mm cubic specimens used for the study were prepared from 100% POFA, alkali-activator (Na 2 SiO 3(aq) /NaOH (aq)) ratios of 2.5, different molarities (10, 12 and 14 M) of NaOH (aq) and 2% volume fraction of polyvinyl alcohol (PVA) fibres. Specimens were exposed to 10% H 2 SO 4(aq) , 10% HNO 3(aq) and 10% HCl (aq) at pH of 0.56, 0.52 and 0.42 respectively for 3, 6 and 9 months, with unexposed specimens as control. Small changes in compressive strength were identified with POFA mortar specimens during exposure to H 2 SO 4(aq) , while exposure to HNO 3(aq) and HCl (aq) greatly reduced the strength of the POFA mortar specimens. The results were supported through microstructural examinations using SEM, while the characterization was done using XRD and FTIR. The high resistance of POFA-EACC mortar to H 2 SO 4(aq) is the contribution received through the formation of gypsum, which hinders the infiltration of more acids into the matrix microstructure.

Mechanical properties and durability characteristics of SCC incorporating crushed limestone powder

by Babatunde A B I O D U N Salami and Mohammed Ibrahim

This study assessed the flow criteria, compressive strength, and durability (chloride permeabilit... more This study assessed the flow criteria, compressive strength, and durability (chloride permeability, corrosion and sulfate resistance) characteristics of self-compacting concrete (SCC) prepared utilizing crushed limestone powder (CLSP). The test samples were prepared by partially replacing CLSP with cement and aggregate such that CLSP/ (CLSP + Cement) and CLSP/(CLSP + aggregate) tagged CLSP Cx and CLSP Ax , respectively, varied between 10 and 40% at the interval of 10%. The finding showed that CLSP-aggregate replacement contributed better than CLSP-cement substitution in terms of compressive strength, delay in corrosion initiation and propagation rate, better strength retention in sulfate exposure, and microstructural density through microfilling and matrix core reinforcement. The presence of widely distributed hydration products and unhydrated cement core (filler) characterized the CLSP-cement microstructure. CLSP Cx in the excess of 20% was detrimental, but the CLSP Ax up to 40% was found to contribute positively to the mechanical and durability characteristics of SCC.

Modelling the early strength of alkali-activated cement composites containing palm oil fuel ash

Proceedings of the Institution of Civil Engineers - Construction Materials

Palm oil fuel ash (Pofa) and polyvinyl alcohol fibres were used to make an alkali-activated cemen... more Palm oil fuel ash (Pofa) and polyvinyl alcohol fibres were used to make an alkali-activated cementitious composite mortar, which was then tested. Based on the test results, a support vector regression model was developed to estimate the effect of the alkaline activator/Pofa ratio on early compressive strength at different added water contents. The results from the model show that the mortar strength increased as the sodium silicate+sodium hydroxide/Pofa ratio increased up to an optimum, after which the strength declined considerably. The sodium hydroxide molarity and added water were also found to have a significant effect on strength. Excellent agreement was found between the model results and test results. The precision and accuracy of the developed model show its potential for reducing the challenges of acquiring experimental data.

Durability performance of Palm Oil Fuel Ash-based Engineered Alkaline-activated Cementitious Composite (POFA-EACC) mortar in sulfate environment

Construction and Building Materials, 2017

Self compacting concrete utilizing local materials

Impact of added water and superplasticizer on early compressive strength of selected mixtures of palm oil fuel ash-based engineered geopolymer composites

by Babatunde A B I O D U N Salami and Salami Abiodun

Construction and Building Materials, 2016

h i g h l i g h t s Engineered geopolymer composites (EGC) was developed using 100% POFA. H 2 O a... more h i g h l i g h t s Engineered geopolymer composites (EGC) was developed using 100% POFA. H 2 O and naphthalene-based superplasticizer effect on POFA-EGC strength was studied. POFA-EGC performed better with added water than naphthalene-based superplasticizer. (B.A. Salami), cemamj@usm. my (M.A. Megat Johari), [email protected] (Z.A. Ahmad), [email protected] (M. Maslehuddin).

Impact of Al(OH) 3 addition to POFA on the compressive strength of POFA alkali-activated mortar

Estimating Flexural Strength of FRP Reinforced Beam Using Artificial Neural Network and Random Forest Prediction Models

Polymers

An accurate calculation of the flexural capacity of flexural members is vital for the safe and ec... more An accurate calculation of the flexural capacity of flexural members is vital for the safe and economical design of FRP reinforced structures. The existing empirical models are not accurately calculating the flexural capacity of beams and columns. This study investigated the estimation of the flexural capacity of beams using non-linear capabilities of two Artificial Intelligence (AI) models, namely Artificial neural network (ANN) and Random Forest (RF) Regression. The models were trained using optimized hyperparameters obtained from the trial-and-error method. The coefficient of correlation (R), Mean Absolute Error, and Root Mean Square Error (RMSE) were observed as 0.99, 5.67 kN-m, and 7.37 kN-m, for ANN, while 0.97, 7.63 kN-m, and 8.02 kN-m for RF regression model, respectively. Both models showed close agreement between experimental and predicted results; however, the ANN model showed superior accuracy and flexural strength performance. The parametric and sensitivity analysis of ...

Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Measurement, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Data-driven model for ternary-blend concrete compressive strength prediction using machine learning approach

Ternary-blend concrete is a complex composite material, and the nonlinearity in its compressive s... more Ternary-blend concrete is a complex composite material, and the nonlinearity in its compressive strength behavior is unquestionable. Entirely many models have been developed to accurately predict the ternary-blend concrete compressive strength, such as ANN, SVM, random forest, decision tree, to mention but a few. This study underscores the better predictive performance and successful application of the least square support vector machine (LSSVM), a machine learning model for predicting the compressive strength of ternary-blend concrete. Coupled simulated annealing (CSA) was applied to the LSSVM model as an optimization algorithm. In addition, the genetic programming (GP) model was used as a benchmark model to compare the performance of the LSSVM-CSA model. The predictive performance of the LSSVM-CSA was compared with that of some of the proposed models in well-known studies where the same datasets were used. The model proposed in this study outperformed other studies, yielding an R 2 value of 0.954.

A risk assessment approach for enhancing construction safety performance

The construction industry is one of the most dangerous industries worldwide due to deadly fatalit... more The construction industry is one of the most dangerous industries worldwide due to deadly fatalities and accidents recorded yearly. Though many countries have established and implemented safety programs, the situation does not seem to have been mitigated. This study aims at developing a risk assessment approach that can be used to enhance the safety performance of construction projects. The study has employed pair-wise comparisons and weighting-by-ranking surveys to establish risk scores and weights for the various construction accidents, and their potential causes. Data has been collected from safety professionals in 15 large construction sites across the Eastern Province of Saudi Arabia. The study revealed that the type of accident with the highest risk score is "falling objects", while the most significant cause is excessive winds on the project site. The developed approach was applied on an ongoing car park construction project. Results showed that slips, trips and falls had the best safety performance. Furthermore, based on six sigma evaluation, the average project safety performance was at 2.33-sigma which implies that 228,739 accidents may occur in every million opportunities. The paper also provided recommendations to improve the safety performance of the case study.

Predicting the compressive strength of a quaternary blend concrete using Bayesian regularized neural network

Concrete produced with ordinary Portland cement (OPC) along with insertion of supplementary mater... more Concrete produced with ordinary Portland cement (OPC) along with insertion of supplementary materials increases the level of nonlinearity. Due to this increased non-linearity and difficulty in modeling numerically, the focus has increased on the exploration of computational intelligent models like artificial neural network (ANN) to estimate different concrete properties. In this study, a quaternary blend concrete was developed with OPC, fly ash (FA), metakaolin (MK) and rice husk ash (RHA). The experimental data were further used in training the proposed ANN models to approximate its compressive strength. The proposed neural network models were trained and optimized using three different regularization algorithms; the scaled conjugate gradient "trainsc" (SCG), Levenberg-Marquardt "trainlm" (LM) and Bayesian regularized "trainbr" (BR) algorithms. The percent proportion of OPC, FA, MK and RHA making up the quaternary blends and curing days are the five features used as input variables, while the compressive strength of each of the individual concrete mixture is the output variable (target). It was found out that ANN optimized with Bayesian regularization function performed best with the highest correlation coefficient, and lowest MAE, MSE and RMSE. The results obtained from the ANN approach show significant improvement with the experimental observations.

Effect of Common Salt on Some Engineering Properties of Eggshell Stabilized Lateritic Soil

This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR)... more This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR) properties of eggshell stabilized lateritic soils with a view of obtaining a good compliment for eggshell as a useful stabilizer for road works. Classification and consistency tests were performed on the soil samples which were also subjected to compaction and CBR tests. Stabilization was performed at optimum eggshell and with 2, 4, 6, 8, and 10% of common salt. The addition of common salt reduced the Plastic Indices (PI) of the samples. The values reduced from 14.82, 11.11 and 7.99% to 8.03, 1.25 and 1.23% in samples A, B and C respectively. Maximum Dry Density (MDD) increased from 1995 to 2140 kg/m 3 and 2000 to 2110 kg/m 3 in samples B and C respectively. The unsoaked CBR values also increased from 34.78 to 50.99 kN/m 2 , 15.64 to 28.89 kN/m 2 and 27.31 to 34.20 kN/m 2 at optimum stabilization in samples A, B and C respectively. The result showed that the addition of common salt impr...

A Risk Assessment Approach for Enhancing Construction Safety Performance

by Babatunde A B I O D U N Salami and Muizz O Sanni-Anibire

Safety Science, 2020

The construction industry is one of the most dangerous industries worldwide due to deadly fatalit... more The construction industry is one of the most dangerous industries worldwide due to deadly fatalities and accidents recorded yearly. Though many countries have established and implemented safety programs, the situation does not seem to have been mitigated. This study aims at developing a risk assessment approach that can be used to enhance the safety performance of construction projects. The study has employed pair-wise comparisons and weighting-by-ranking surveys to establish risk scores and weights for the various construction accidents, and their potential causes. Data has been collected from safety professionals in 15 large construction sites across the Eastern Province of Saudi Arabia. The study revealed that the type of accident with the highest risk score is "falling objects", while the most significant cause is excessive winds on the project site. The developed approach was applied on an ongoing car park construction project. Results showed that slips, trips and falls had the best safety performance. Furthermore, based on six sigma evaluation, the average project safety performance was at 2.33-sigma which implies that 228,739 accidents may occur in every million opportunities. The paper also provided recommendations to improve the safety performance of the case study.

Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Measurement , 2020

Corrosion initiation time of embedded steel is an important service life parameter, which depends... more Corrosion initiation time of embedded steel is an important service life parameter, which depends on concrete material make-up, exposure environment, and duration of exposure. Early and accurate determination of corrosion initiation time will aid in designing durable reinforced concrete, saves cost and time. This study leveraged on the power of ensemble machine learning by combining the performances of different models in estimating the corrosion initiation time of steel embedded in self compacted concrete using corrosion potential measurement. The concrete specimens were prepared with limestone powder as supplementary addition to Portland cement and was exposed to 5% sodium chloride in accordance with the requirements of ASTM C876-15 for 8 months. During the exposure, corrosion potential of the embedded steel was measured, and the recorded datasets were used in training five different machine learning models. With cement, limestone powder, coarse aggregate, fine aggregate, water and exposure period.as input variables, five different models were developed to estimate the corrosion initiation time (determined from the corrosion potential measurements) of the embedded steel. With respect to model predictive performance, the acquired results demonstrated that the random forest (RF) ensemble model amongst other trained models performed best with 85/15 dataset percentage split for the training and testing. RF ensemble performed best with CC and RMSE of 99.01% and 18.2747 mV for training, and 98.67% and 25.0298 mV for testing respectively. Hence, due to its superior and robust performance, this study proposes RF ensemble model in the estimation of corrosion initiation time of embedded steel in reinforced limestone-cement blend concrete.

Influence of composition and concentration of alkaline activator on the properties of natural-pozzolan based green concrete

The chemical constituents of precursor materials, the composition and concentration of alkaline a... more The chemical constituents of precursor materials, the composition and concentration of alkaline activators, volume of free water, and curing conditions are some of the mix design variables that influence the fresh and hardened properties of alkali-activated binders (AABs). To achieve desirable engineering properties and long-term performance of an AAB under various exposure conditions, each of these variables has to be carefully controlled. The reported research focused on the influence of concentration and composition of alkaline activators on the properties of natural pozzolan (NP)-based AAB. Since the molarity of sodium hydroxide (SH) and the ratio of sodium silicate (SS) to sodium hydroxide (SH) influence the properties of an AAB, the NP-based AABs were prepared by varying the SS to SH ratio from 2.0 to 2.75, at an increment of 0.25, and the molarity of SH from 8 to 14. The developed AAC specimens were tested to evaluate the strength development and the binder was characterized using SEM, XRD and FTIR techniques. A SS/SH ratio of 2.5 and 14 M SH solution were required to obtain maximum strength and dense microstructure. In addition, it was established that there exists an optimum silica modulus of the combined activator that results in faster polymerization of the precursor material.

EFFECT OF COMMON SALT ON SOME ENGINEERING PROPERTIES OF EGGSHELL STABILIZED LATERITIC SOIL

This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR)... more This paper studied the effect of common salt on the compaction and California Bearing Ratio (CBR) properties of eggshell stabilized lateritic soils with a view of obtaining a good compliment for eggshell as a useful stabilizer for road works. Classification and consistency tests were performed on the soil samples which were also subjected to compaction and CBR tests. Stabilization was performed at optimum eggshell and with 2, 4, 6, 8, and 10% of common salt. The addition of common salt reduced the Plastic Indices (PI) of the samples. The values reduced from 14.82, 11.11 and 7.99% to 8.03, 1.25 and 1.23% in samples A, B and C respectively. Maximum Dry Density (MDD) increased from 1995 to 2140 kg/m 3 and 2000 to 2110 kg/m 3 in samples B and C respectively. The unsoaked CBR values also increased from 34.78 to 50.99 kN/m 2 , 15.64 to 28.89 kN/m 2 and 27.31 to 34.20 kN/m 2 at optimum stabilization in samples A, B and C respectively. The result showed that the addition of common salt improved the compaction and CBR characteristics of eggshell stabilized soils.

Performance of POFA-Based Alkali-Activated Mortar Exposed to Elevated Temperatures

This research work was conducted to investigate the residual strength performance of POFA alkali-... more This research work was conducted to investigate the residual strength performance of POFA alkali-activated mortar when subjected to different levels of elevated temperature. 100% POFA, sand and (Na2SiO3(aq)/NaOH(aq)) ratios of 2.5, 2, 1 and 0.5 were used in the preparation of POFA alkali-activated mortar mixtures. 50 mm x 50 mm x 50 mm cube specimens were tested after 60±5 o C heat curing to study the effect of exposure to 3 levels of elevated temperature; 300, 600 and 900 o C. The performance metrics used to assess the impact of exposure to elevated temperatures were the residual compressive strength, weight loss and visual appearance. The alkaline activator ratio and the elevated temperature have induced specific impact on the residual compressive strength of the POFA alkali-activated mortar specimens. For all alkaline-activator ratios, increased strength was recorded for the specimens exposed to 600 o C temperature, however for mortar specimens exposed to 300 o C and 900 o C temperatures strength reduction was recorded. Microstructural changes of the POFA-alkali activated binder was investigated using scanning electron microscope (SEM) equipped with energy dispersive spectrometry (EDS) as a result of the elevated temperature exposure. Superior performance of the 600 o C specimens was also revealed as a result of the post-heating solidification of molten POFA alkali-activated binder.

POFA Engineered Alkali activated Cementitious Comp

The durability performance of palm oil fuel ash engineered alkali-activated cementitious composit... more The durability performance of palm oil fuel ash engineered alkali-activated cementitious composite (POFA-EACC) mortar exposed to different acid solutions is assessed in this study. 50 mm cubic specimens used for the study were prepared from 100% POFA, alkali-activator (Na 2 SiO 3(aq) /NaOH (aq)) ratios of 2.5, different molarities (10, 12 and 14 M) of NaOH (aq) and 2% volume fraction of polyvinyl alcohol (PVA) fibres. Specimens were exposed to 10% H 2 SO 4(aq) , 10% HNO 3(aq) and 10% HCl (aq) at pH of 0.56, 0.52 and 0.42 respectively for 3, 6 and 9 months, with unexposed specimens as control. Small changes in compressive strength were identified with POFA mortar specimens during exposure to H 2 SO 4(aq) , while exposure to HNO 3(aq) and HCl (aq) greatly reduced the strength of the POFA mortar specimens. The results were supported through microstructural examinations using SEM, while the characterization was done using XRD and FTIR. The high resistance of POFA-EACC mortar to H 2 SO 4(aq) is the contribution received through the formation of gypsum, which hinders the infiltration of more acids into the matrix microstructure.

Mechanical properties and durability characteristics of SCC incorporating crushed limestone powder

by Babatunde A B I O D U N Salami and Mohammed Ibrahim

This study assessed the flow criteria, compressive strength, and durability (chloride permeabilit... more This study assessed the flow criteria, compressive strength, and durability (chloride permeability, corrosion and sulfate resistance) characteristics of self-compacting concrete (SCC) prepared utilizing crushed limestone powder (CLSP). The test samples were prepared by partially replacing CLSP with cement and aggregate such that CLSP/ (CLSP + Cement) and CLSP/(CLSP + aggregate) tagged CLSP Cx and CLSP Ax , respectively, varied between 10 and 40% at the interval of 10%. The finding showed that CLSP-aggregate replacement contributed better than CLSP-cement substitution in terms of compressive strength, delay in corrosion initiation and propagation rate, better strength retention in sulfate exposure, and microstructural density through microfilling and matrix core reinforcement. The presence of widely distributed hydration products and unhydrated cement core (filler) characterized the CLSP-cement microstructure. CLSP Cx in the excess of 20% was detrimental, but the CLSP Ax up to 40% was found to contribute positively to the mechanical and durability characteristics of SCC.

Modelling the early strength of alkali-activated cement composites containing palm oil fuel ash

Proceedings of the Institution of Civil Engineers - Construction Materials

Palm oil fuel ash (Pofa) and polyvinyl alcohol fibres were used to make an alkali-activated cemen... more Palm oil fuel ash (Pofa) and polyvinyl alcohol fibres were used to make an alkali-activated cementitious composite mortar, which was then tested. Based on the test results, a support vector regression model was developed to estimate the effect of the alkaline activator/Pofa ratio on early compressive strength at different added water contents. The results from the model show that the mortar strength increased as the sodium silicate+sodium hydroxide/Pofa ratio increased up to an optimum, after which the strength declined considerably. The sodium hydroxide molarity and added water were also found to have a significant effect on strength. Excellent agreement was found between the model results and test results. The precision and accuracy of the developed model show its potential for reducing the challenges of acquiring experimental data.

Durability performance of Palm Oil Fuel Ash-based Engineered Alkaline-activated Cementitious Composite (POFA-EACC) mortar in sulfate environment

Construction and Building Materials, 2017

Self compacting concrete utilizing local materials

Impact of added water and superplasticizer on early compressive strength of selected mixtures of palm oil fuel ash-based engineered geopolymer composites

by Babatunde A B I O D U N Salami and Salami Abiodun

Construction and Building Materials, 2016

h i g h l i g h t s Engineered geopolymer composites (EGC) was developed using 100% POFA. H 2 O a... more h i g h l i g h t s Engineered geopolymer composites (EGC) was developed using 100% POFA. H 2 O and naphthalene-based superplasticizer effect on POFA-EGC strength was studied. POFA-EGC performed better with added water than naphthalene-based superplasticizer. (B.A. Salami), cemamj@usm. my (M.A. Megat Johari), [email protected] (Z.A. Ahmad), [email protected] (M. Maslehuddin).

Impact of Al(OH) 3 addition to POFA on the compressive strength of POFA alkali-activated mortar