Research Papers - Department of Civil Engineering

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/598

Browse

Filters

2025 - 20262

Advanced Search

Filter by

Settings

Author: search.filters.author.Meddage D.P.P.

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen 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.
  • Thumbnail Image
    PublicationEmbargo
    Machine learning prediction of web-crippling strength in cold-formed steel beams with staggered slotted perforations
    (Elsevier Ltd, 2025-01) Gatheeshgar, P; Ranasinghe R.S.S; Simwanda, L; Meddage D.P.P.; Mohotti, D
    The application of staggered slotted perforations in cold-formed steel (CFS) members is increasingly prominent in modern construction. Understanding the web-crippling strength of CFS beams, especially those with staggered slotted perforations, is crucial in structural engineering. This study employs machine learning (ML) models to predict the web-crippling strength of these beams under one-flange loading conditions, specifically interior-one-flange and end-one-flange loading. The research utilises a comprehensive dataset comprising 576 web-crippling strength results obtained through numerical modelling. The dataset includes parameters such as yield strength, thickness, corner radius, slot length, slot width, and bearing plate length. Four different ML algorithms—k-nearest neighbour (KNN), random forest (RF), support vector regression (SVR), and artificial neural network (ANN)—are developed and evaluated. Performance metrics, including coefficient of determination (R²), mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE) and mean normalised bias (MNB) are used to assess model accuracy. The random forest model outperforms others in both the training and testing phases. Shapley additive explanation (SHAP) and partial dependence plots further analyse the influence of input features on web crippling strength. This study presents a robust ML-based approach for predicting web crippling strength, providing engineers with a time-efficient alternate method.