Research Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194
This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.
Browse
8 results
Search Results
Publication Embargo Uniaxial compressive response of cement mortar with waste aluminium fibre sourced from electrical distribution cables(Springer Science and Business Media, 2025-01) Perera K.D.Y.G.; Ahamed Y.L.F; Somarathna H.M.C.C; Jayasekara D.A.B.P.M; Mohotti D; Raman S.NElectrical distribution and communication cables cease to function for transmission when their length is insufficient, and it is considered as it approaches the end of their useful lives. Further, the disposal techniques are not eco-friendly. This study aimed to evaluate the feasibility of cement mortar systems with the inclusion of aluminium fibre extracted from electrical distribution cables. Two diameters of 1.35 mm and 1.70 mm and two lengths of 10 mm and 15 mm fibres were used while incorporating four volume ratios, particularly 0.5%, 1.0%, 1.5%, and 2.0% to evaluate the effect of the length, diameter and volume ratios. The compression test and density test were performed to study the behaviour of Metal Fibre Reinforced Mortar (MFRM) systems under both dry and wet states. Compared to conventional mortar, the ultimate compressive strength of MFRM systems was increased up to 39.4% in 1.5% of fibre addition under the 28-day dry state, where the 1.5% volume ratio showed the best performance under compressive loads. Strain at ultimate strength, modulus of elasticity and strain energy also showed improvements with the fibre inclusion up to 74.4%, 87.3%, and 106.6% respectively. Fibres with higher aspect ratios showed significant effectiveness among the aforementioned fibre variations. The overall results highlighted that the MFRM with 1.5% of fibres performed expertly with 15 mm length and 1.35 mm diameter under compression loadsPublication Embargo Mechanical and durability analysis of eco-friendly light weight cement blocks using raw rice husk as a partial replacement for manufactured sand(Elsevier Ltd, 2025-03-08) Thavarajah, L; Sundaralingam, K; Tharmarajah, GThe study investigates the mechanical and durability properties of cement blocks made by partially replacing manufactured sand (M-sand) with raw rice husk (RRH). The rising demand for sand in construction, coupled with the environmental impact of its extraction, has prompted the exploration of alternative materials. RRH, a byproduct of rice milling, offers an eco-friendly substitute for sand. The research examines blocks containing varying proportions of RRH (20 %, 40 %, and 60 %) and compares treated and untreated husks. Key parameters, including compressive strength, tensile strength, density, performance when exposed to heat, and water absorption, were analyzed. The results show that up to 40 % of RRH can be used to replace sand without compromising the blocks' structural integrity. Treated RRH blocks demonstrated better bonding with cement, leading to higher compressive and tensile strengths compared to untreated ones. A 40 % RRH replacement achieved an average compressive strength of 3.57 MPa, surpassing the minimum requirements for non-load-bearing masonry units as per Sri Lankan and Australian standards. However, increasing RRH content to 60 % significantly reduced strength and durability. Additionally, RRH blocks exhibited a decrease in density, offering advantages in terms of transportation and handling. Water absorption increased with higher RRH content due to its porous nature yet remained within acceptable limits for treated blocks. These findings suggest that RRH can be a sustainable alternative to sand in masonry applications, especially in rural and eco-conscious construction.Publication Embargo Correlation of compressive strength and flexural tensile strength of blended cement concrete(SLIIT, Faculty of Engineering, 2024-10) Kulathilaka, U. G. D. U.; Somaratna, N.Eurocodes for structural designs have been adopted for Sri Lanka. Hence in Sri Lanka, concrete designs need to be in compliance with the relevant Eurocodes – mainly EN1992 (EC2). In EC2, concrete is categorized by its compressive strength. The other strength parameters are derived from the compressive strength using correlations based on empirical data. A recent trend has been the increasing use of blended cement for concrete in certain applications. But the correlations specified in EC2 are based on data probably related to Ordinary Portland Cement (OPC) concrete. It is important to examine whether the correlations listed in EC2 are applicable to blended cement concrete too. The present study was performed to experimentally examine the correlation of compressive strength and flexural tensile strength of blended cement concrete. A parallel study was conducted for OPC concrete to serve as a baseline reference. Standard beam and cylinder specimens of concrete were cast, cured, and tested for flexural tensile strength and compressive strength. Three different mix ratios were used. Each mix was tested twice. The same series of tests were conducted for blended cement (Portland Composite Cement – PCC) and for OPC. Experimentally measured values of flexural tensile strength were compared against their estimated values derived from the experimentally measured compressive strengths, using EC2 listed relationships. The analysis showed that in the case of both OPC as well as PCC, the measured values of the flexural tensile strength exceeded their estimated values based on EC2 relationships. But the testing conducted has been limited in the number of tests performed, the range of mix ratios, and the types of aggregate used. In order to affirm the general applicability of Eurocode 2 relationships for blended cement concrete also, additional more comprehensive testing is warranted across a wider span of mix ratios and aggregate types.Publication Embargo Experimental Investigation of Some Strength Parameter Correlation in Blended Cement Concrete(SLIIT, Faculty of Engineering, 2024-10) Chularathna, P. K. G. O. T.; Somaratna, N.Sri Lanka has adopted Eurocodes for structural designs. Accordingly, the design of concrete structures should adhere to EN1992 (Eurocode 2). The strength parameters of concrete essential for designs are classified in Eurocode 2 based on the compressive strength of concrete. Most of the other relevant strength parameters are derived using correlations with compressive strength. These correlations based on past empirical test results would typically be valid for concrete made using ordinary Portland cement (OPC). Recently there has been a tendency to use blended cements for concrete. To develop economical and safe designs in such cases the correlations among strength parameters used in EN 1992 should be verified as being applicable to blended cement concrete too. The study presented here was aimed at investigating the applicability of EN 1992 correlation between compressive strength and split cylinder tensile strength to blended cement concretes. Test specimens of concrete made using a blended cement – Portland Composite Cement (PCC) – were cast, cured, and tested under standard conditions for their compressive strength and split cylinder tensile strength. These tests were repeated for greater reliability. For comparison, similar tests were performed on concrete made using OPC also. The measured compressive strengths were used to produce estimated values of corresponding tensile strengths following the EN1992 correlations. Comparisons were made, in graphical form, between the measured tensile strengths and the estimated tensile strengths. Separately for each cement type. They revealed that the test results for OPC concrete, as expected, aligned with EN1992 correlations with a significant margin of safety while those related to blended cement, though complying with EN1992 correlations, provided only a narrow margin of safety. This indicates a need for a higher level of quality assurance for blended cement concrete. As these observations are based on a limited number of tests it is recommended to conduct further comprehensive studies.Publication Open Access Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning(Elsevier, 2024-09) Ranasinghe, R.S.S.; Kulasooriya, W.K.V.J.B; Perera, U.S; Ekanayake, I.U.; Meddage, D.P.P.; Mohotti, D; Rathanayake, UGeopolymer concrete is a sustainable and eco-friendly substitute for traditional OPC (Ordinary Portland Cement) based concrete, as it reduces greenhouse gas emissions. With various supplementary cementitious materials, the compressive strength of geopolymer concrete should be accurately predicted. Recent studies have applied deep learning techniques to predict the compressive strength of geopolymer concrete yet its hidden decision-making criteria diminish the end-users’ trust in predictions. To bridge this gap, the authors first developed three deep learning models: an artificial neural network (ANN), a deep neural network (DNN), and a 1D convolution neural network (CNN) to predict the compressive strength of slag ash-based geopolymer concrete. The performance indices for accuracy revealed that the DNN model outperforms the other two models. Subsequently, Shapley additive explanations (SHAP) were used to explain the best-performed deep learning model, DNN, and its compressive strength predictions. SHAP exhibited how the importance of each feature and its relationship contributes to the compressive strength prediction of the DNN model. Finally, the authors developed a novel DNN-based open-source software interface to predict the mix design proportions for a given target compressive strength (using inverse modeling technique) for slag ash-based geopolymer concrete. Additionally, the software calculates the Global Warming Potential (kg CO2 equivalent) for each mix design to select the mix designs with low greenhouse emissions.Publication Open Access Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning(Elsevier, 2024-09) Ranasinghe, R.S.S.; Kulasooriya, W.K.V.J.B.; Perera, U S; Ekanayake, I.U.; Meddage, D.P.P.; Mohotti, D; Rathanayake, UGeopolymer concrete is a sustainable and eco-friendly substitute for traditional OPC (Ordinary Portland Cement) based concrete, as it reduces greenhouse gas emissions. With various supplementary cementitious materials, the compressive strength of geopolymer concrete should be accurately predicted. Recent studies have applied deep learning techniques to predict the compressive strength of geopolymer concrete yet its hidden decision-making criteria diminish the end-users’ trust in predictions. To bridge this gap, the authors first developed three deep learning models: an artificial neural network (ANN), a deep neural network (DNN), and a 1D convolution neural network (CNN) to predict the compressive strength of slag ash-based geopolymer concrete. The performance indices for accuracy revealed that the DNN model outperforms the other two models. Subsequently, Shapley additive explanations (SHAP) were used to explain the best-performed deep learning model, DNN, and its compressive strength predictions. SHAP exhibited how the importance of each feature and its relationship contributes to the compressive strength prediction of the DNN model. Finally, the authors developed a novel DNN-based open-source software interface to predict the mix design proportions for a given target compressive strength (using inverse modeling technique) for slag ash-based geopolymer concrete. Additionally, the software calculates the Global Warming Potential (kg CO2 equivalent) for each mix design to select the mix designs with low greenhouse emissions.Publication Open Access The Properties of Lime/Soil Concrete(SLIIT, 2022-02-11) Perera, J; Chandrasiri, JThe investigation of materials for replacing cement in concrete manufacturing has garnered steady interest from experts in recent years. However, the majority of past researches have only focused on the use of lime as a cement substitute in producing Lime Concrete. The reason for this is that lime concrete can be made easily and cheaply while still providing a durable material that can minimize negative environmental impacts. Even though lime is used as an alternative material the integration of a new material as a replacement for conventional aggregates has been limited. As a result, this study will attempt to examine the various compositions of hydraulic lime as a partial replacement of cement while completely replacing the coarse and fine aggregate with a soil to find the influence on the physical characteristics of Lime/Soil concrete. This will also help in decreasing the ecological imbalance caused due to the excess use of conventional aggregates. Locally available reddish-brown laterite soil was used in this study without any modifications. C30 concrete mixes containing 0%, 10%, 15% of hydraulic lime replaced with OPC and complete replacement of aggregate with laterite soil were casted before subjected to water curing. Workability, compressive strength, splitting tensile strength and water absorption test were conducted in accordance with the existing standard. Based on the results obtained from the study it has shown that even with complete replacement of aggregate with laterite soil it was able to produce workable concrete with satisfactory strength that can be employed for ground improvements in pavement design and to manufacture economical non-load bearing concrete blocks. The targeted strength still can be achieved with replacement of 15% hydraulic lime for a lower cost. With the accomplishment from the composition, future studies will be able to better assess the long-term effects of construction operations on the environment.Publication Open Access A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP)(Elsevier, 2022-04) Ekanayake, I.U; Meddage, D. P. P; Rathnayake, UMachine learning (ML) techniques are often employed for the accurate prediction of the compressive strength of concrete. Despite higher accuracy, previous ML models failed to interpret the rationale behind predictions. Model interpretability is essential to appeal to the interest of domain experts. Therefore, overcoming research gaps identified, this research study proposes a way to predict the compressive strength of concrete using supervised ML algorithms (Decision tree, Extra tree, Adaptive boost (AdaBoost), Extreme gradient boost (XGBoost), Light gradient boosting method (LGBM), and Laplacian Kernel Ridge Regression (LKRR). Alternatively, SHapley Additive exPlainations (SHAP) – a novel black-box interpretation approach - was employed to elucidate the predictions. The comparison revealed that tree-based algorithms and LKRR provide acceptable accuracy for compressive strength predictions. Moreover, XGBoost and LKRR algorithms evinced superior performance (R ¼ 0.98). According to SHAP interpretation, XGBoost predictions capture complex relationships among the constituents. On the other hand, SHAP provides unified measures on feature importance and the impact of a variable for a prediction. Interestingly, SHAP interpretations were in accordance with what is generally observed in the compressive behavior of concrete, thus validating the causality of ML predictions.