Browsing by Author "Herath, S"

Now showing 1 - 6 of 6

Open Access
Automated design of reinforced concrete dapped-end connections using hybrid deep learning and generative AI augmentation
(Elsevier Ltd, 2026-04-15) Dharmawansha, S; Herath, S; Fernando P.L.N; Meddage D.P.P.; Rajapakse, C
Dapped-end connections, also known as half-joints or Gerber beams, are widely used yet structurally vulnerable elements in precast concrete structures due to high stress concentrations near the re-entrant corner. Therefore, a comprehensive assessment of the load-bearing capacity of dapped-end connections is important to ensure structural integrity and mitigate the risk of failure. Although prior studies have explored their behaviour through analytical and experimental methods, the application of data-driven approaches remains limited due to the availability of limited experimental data, which constrains the predictive accuracy and generalisation of Machine Learning (ML) models. This study presents a novel approach that integrates numerical simulation with Conditional Tabular Generative Adversarial Network (CTGAN)-based data augmentation to enhance prediction accuracy and model generalisation. A numerical database containing 720 results was developed, which was expanded with 680 augmented data using CTGAN. The combined dataset of 1400 instances was used to train Artificial Neural Network (ANN), Genetic Algorithm-ANN (GA-ANN), and Particle Swarm Optimisation-ANN (PSO-ANN) models. The hybrid models outperformed the standalone ANN, with GA-ANN achieving the highest accuracy (testing R2 = 0.961). The trained models were separately validated using 64 unseen experimental datasets, which shows the improved generalisation of the models through augmentation. Shapley Additive Explanations analysis reveals that the GA-ANN model predictions aligned with the principles underlying the compatibility of deformations of dapped-ends. Further, a novel ML-assisted design model was developed, which predicts multiple solutions for a given design problem, assisting in the optimisation of connection design.
Embargo
Graph Neural Network Based Surrogate Model for Design Informed Structural Optimization
(Springer Science and Business Media Deutschland GmbH, 2025) Ariyasinghe, N; Weeratunga, H; Mallikarachchi, C; Herath, S
Structural optimization of skeletal forms is crucial in weight-sensitive applications. Optimizing such structures often involves iterative, computationally intensive methods, which are inefficient under varying design parameters and constraints. This paper introduces a novel surrogate model based on Graph Neural Network (GNN) for real-time structural optimization, aimed at significantly reducing computational costs. In our approach, trusses composed of pin joints and connecting members are represented as graphs, where joints correspond to vertices and members to edges. This correspondence forms the use of Graph Neural Networks (GNNs) to predict topology and size-optimized truss structures. The GNN models the truss as a graph, with edges denoting member cross-sectional areas and nodes representing truss joints, based on input parameters such as geometry, load combinations, and boundary conditions. The resulting predicted structure reflects the optimized topology and member sizes. The proposed model bypasses the need for iterative computations by learning from a dataset comprising various problem definitions and their corresponding optimized results. This GNN-based optimization holds substantial promise for design scenarios requiring rapid and reliable optimization, demonstrating the potential for significant computational time savings while maintaining high accuracy in predicting near-optimal truss layouts. This is particularly significant in the context of sustainability, where industrial users can produce optimally designed structures with minimal material usage within a fraction of the computational power and time required for different applications. Testing results indicate that the model effectively generalizes across various design scenarios, providing near-optimal solutions with minimal computational effort. Specifically, the predicted structures exhibited a normalized root mean square error (NRMSE) of less than 10−3 and R2 values approaching unity. Additionally, predictions were made in under 0.01 s, demonstrating both accuracy and efficiency.
Open Access
Hybrid neural network methods to model the external wind pressure on a low-rise flat-roofed building in an irregularly shaped urban environment
(Elsevier Ltd, 2025-06-23) Sajindra, H; Dharmawansha, S; Wijesundara, H; Herath, S; Rathnayake, U; Meddage D.P.P
The present study used hybrid artificial neural networks to model the wind pressure (mean and fluctuating) on a flat-roofed, low-rise building in an irregularly shaped urban environment. Four neural networks, each combined with an artificial bee colony (ABC), genetic algorithm (GA), particle swarm optimisation (PSO), and independent component analysis (ICA), along with an individual artificial neural network (ANN) model and a convolutional neural network (CNN), were used for the wind pressure predictions. The data was obtained from Tokyo Polytechnic University’s boundary layer wind tunnel and was used to train the neural network models. The results revealed that all models accurately captured the wind pressure on the low-rise building in a dense urban environment. Specifically, the genetic algorithm-artificial neural network (GA-ANN) model outperformed the remaining models, achieving good prediction accuracy for test data (coefficient of determination (R²) = 0.96 for mean pressure R² = 0.84 for fluctuation pressure). The use of machine learning explainability methods confirmed the consistency of GA-ANN with the fundamentals of wind engineering. Notably, the GA-ANN approach accurately modeled the special flow features on the building surface, such as flow separation, vortex formation, and pressure gradients, to a greater extent compared to the wind tunnel results. Therefore, the authors propose this method as an complementary approach for predicting wind pressure on low-rise buildings in complex urban environments
Open Access
Mini Market: Information Technology Based Support Tool for Small and Medium Scale Enterprises in Sri Lanka
(ICRD Publicatio, 2019-07) Thilakarathne, S; Herath, S; Rajapaksha, A; Karunasena, A
Small and medium enterprises (SMEs) play a crucial role in developing countries such as Sri Lanka in growth of an economy. Recently online platforms are being extensively used by SMEs for both marketing and selling items. In a context of keen competition among the online selling platforms, sellers are increasingly feeling the pressure for improving their sales and marketing strategies. When investigating existing problems of SMEs, we were able to find they do not have proper guidance to improve their own business. Simply, the SMEs cannot identify their own marketing level among the other competitors, they haven't any suitable guidelines to identify how they can improve their own market and they have to use manual reports to get their own sales details for visualizing their marketing level where they waste their valuable time and money for visualizing sales market outcomes. In consideration of this, we propose a web system, that examines the effects of three categories in this system, i.e. Seller trustworthiness, analyze customer's emotions, feelings, thoughts, and opinions through Social media (Facebook) and sales prediction component. This system facilitates a multiple seller platform, where they can dynamically manage virtual shop inside this platform. It increases their stability and it will provide directions to overcome economic and unemployment barriers in our country. The results support our research hypotheses partially. The findings of this study are expected to provide some suggestions for sellers on promote and improve of their sales
Open Access
Predicting Bulk Average Velocity with Rigid Vegetation in Open Channels Using Tree-Based Machine Learning: A Novel Approach Using Explainable Artificial Intelligence
(MDPI, 2022-06-10) Meddage, D. P. P; Ekanayake, I. U; Herath, S; Gobirahavan, R; Muttil, N; Rathnayake, U
Predicting the bulk-average velocity (UB) in open channels with rigid vegetation is complicated due to the non-linear nature of the parameters. Despite their higher accuracy, existing regression models fail to highlight the feature importance or causality of the respective predictions. Therefore, we propose a method to predict UB and the friction factor in the surface layer (fS) using tree-based machine learning (ML) models (decision tree, extra tree, and XGBoost). Further, Shapley Additive exPlanation (SHAP) was used to interpret the ML predictions. The comparison emphasized that the XGBoost model is superior in predicting UB (R = 0.984) and fS (R = 0.92) relative to the existing regression models. SHAP revealed the underlying reasoning behind predictions, the dependence of predictions, and feature importance. Interestingly, SHAP adheres to what is generally observed in complex flow behavior, thus, improving trust in predictions
Open Access
Topology and size optimization of trusses using graph neural networks: Towards efficient surrogate modeling
(Elsevier Ltd, 2026-06) Ariyasinghe, N; Wickremasinghe, T; Weeratunge, H; Mallikarachchi, C; Herath, S
Real-time structural optimization of trusses using machine learning techniques, incorporating both topology and size optimization, is more effective in discrete domains than in continuous ones, with Graph Neural Networks (GNNs) showing strong potential. However, the impact of convolutions in GNNs is not yet fully understood, limiting their full applicability. This paper presents a GNN-based surrogate model for real-time structural optimization and identifies the most suitable convolution type for this task. The study assesses the predictive performance of models trained on a dataset of optimized structures spanning a range of loads, boundary conditions, and design domain sizes. The resulting model effectively predicts both optimal topology and member sizes once the design parameters are provided. Eight graph convolution types are investigated to identify the most suitable method, alongside an evaluation of optimal network architectures. Among the tested approaches, Generalised Graph Convolution achieves the highest accuracy, followed by Topology Adaptive Graph Convolution, producing near-ideal topology predictions for most test cases and maintaining section size prediction errors within ±2% across all test data points. This framework demonstrates strong potential for broader applications.