Research Papers - Department of Mechanical Engineering
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/604
Browse
31 results
Search Results
Publication Embargo Performance improvement of a cross-flow air turbine for oscillating water column wave energy converter by nozzle and blade optimization(Elsevier Ltd, 2025-01-15) Baddegamage B.H.B.P.D; Bae, S.J; Jang, S.H; Gunawardane S.D.G.S.P; Lee, Y.O; Kim, K; Yoon, MThe global pursuit of renewable energy solutions has highlighted the potential of wave energy converters (WECs), particularly oscillating water column (OWC) systems, as viable clean energy sources. This study focuses on optimizing a cross-flow air turbine (CFAT) through comprehensive numerical simulations, aimed at enhancing its performance as the power take-off system in OWC applications. The influences of various geometrical parameters, such as including nozzle entry arc angle, nozzle starting angle, and angle of attack, on the performance of the CFAT are investigated. The optimized turbine model achieves a peak efficiency (η) of 0.71 in unidirectional flow at a flow coefficient (Φ) of 0.41, representing a significant improvement over the reference model (η = 0.61 at Φ = 0.29). In addition, the performance of the optimized CFAT is evaluated under regular wave conditions, simulating the bidirectional flow typical of real-world OWC applications. Although the peak efficiency in reciprocating flow slightly decreases, shifting to 0.68 at Φ = 0.53, the turbine maintains a high mean efficiency throughout the operating cycle. The results demonstrate that the optimized CFAT model provides robust performance in both unidirectional and bidirectional flows, making it a promising candidate for enhancing the efficiency of OWC-based WECs.Publication Open Access Forecasting renewable energy for microgrids using machine learning(Springer Nature, 2025-05-03) Sudasinghe, P; Herath, D; Karunarathne, I; Weeratunge, H; Jayasuriya, LMicrogrids, comprised of interconnected loads and distributed energy resources, function as single controllable entities with respect to the main grid. However, the inherent variability of distributed wind and solar generation within microgrids presents operational stability challenges concerning voltage regulation and frequency stability. Accurate forecasting of renewable generation is crucial for mitigating these challenges. This work proposes a one-dimensional Convolutional Neural Network (1-D CNN) based approach to forecast photovoltaic (PV) generation and wind energy, using data from the University of California, San Diego microgrid and San Diego Airport weather records. The proposed method is evaluated against various forecasting methods using key metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared value. Results show that the 1-D CNN model achieves an improvement of up to 229.8 times in MSE and a 24.47 fold improvement in MAE compared to baseline models that use traditional statistical methods in forecasting. This demonstrates the potential of machine learning for enhancing microgrid management, particularly in short-term forecasting of renewable generation. © The Author(s) 2025. Evaluated ML-based renewable energy forecasting models by implementing 1-D CNN and LSTM models using real-world data. Proposed 1-D CNN performs better than LSTM and baseline models, achieving higher accuracy and computational efficiency. Accurate forecasting of PV and wind energy generation enhances grid stability, reduces backup power dependency, and supports sustainable energy integration.Publication Open Access Interpretable SHAP-bounded Bayesian optimization for underwater acoustic metamaterial coating design(Springer Science and Business Media Deutschland GmbH, 2025-09-08) Weeratunge, H; Robe, D. M; Hajizadeh, EWe present an interpretability-informed Bayesian optimization framework for the inverse design of underwater acoustic coatings composed of polyurethane elastomers with embedded metamaterial features. A data-driven model was used to capture the relationship between acoustic performance, specifically, sound absorption and the corresponding geometrical design variables. To interpret these relationships, we applied SHapley Additive exPlanations (SHAP), enabling the identification of key parameters influencing the objective function and providing both global and local insights into their effects. The insights from the SHAP analysis were used to automatically refine the bounds of the design space, guiding the optimization process toward more promising regions. This approach was tested on two polyurethane materials with different hardness levels and yielded improved optimal designs compared to standard Bayesian optimization without increasing the number of simulations. This work underscores the effectiveness of combining interpretability techniques with optimization for the efficient and cost-effective design of underwater acoustic metamaterials under strict computational constraints and can be generalized towards other materials and engineering optimization problemsPublication Open Access Sensitivity Analysis of Parameters Affecting Wetland Water Levels: A Study of Flood Detention Basin, Colombo, Sri Lanka(MDPI, 2023-04-02) Herath, M; Jayathilaka, T; Azamathulla, H.M; Mandala, V; Rathnayake, N; Rathnayake, UWetlands play a vital role in ecosystems. They help in flood accumulation, water purification, groundwater recharge, shoreline stabilization, provision of habitats for flora and fauna, and facilitation of recreation activities. Although wetlands are hot spots of biodiversity, they are one of the most endangered ecosystems on the Earth. This is not only due to anthropogenic activities but also due to changing climate. Many studies can be found in the literature to understand the water levels of wetlands with respect to the climate; however, there is a lack of identification of the major meteorological parameters affecting the water levels, which are much localized. Therefore, this study, for the first time in Sri Lanka, was carried out to understand the most important parameters affecting the water depth of the Colombo flood detention basin. The temporal behavior of water level fluctuations was tested among various combinations of hydro-meteorological parameters with the help of Artificial Neural Networks (ANN). As expected, rainfall was found to be the most impacting parameter; however, apart from that, some interesting combinations of meteorological parameters were found as the second layer of impacting parameters. The rainfall–nighttime relative humidity, rainfall–evaporation, daytime relative humidity–evaporation, and rainfall–nighttime relative humidity–evaporation combinations were highly impactful toward the water level fluctuations. The findings of this study help to sustainably manage the available wetlands in Colombo, Sri Lanka. In addition, the study emphasizes the importance of high-resolution on-site data availability for higher prediction accuracy.Publication Open Access Deep Machine Learning-Based Water Level Prediction Model for Colombo Flood Detention Area(MDPI, 2023-02-08) Herath, M; Jayathilaka, T; Hoshino, Y; Rathnayake, UMachine learning has already been proven as a powerful state-of-the-art technique for many non-linear applications, including environmental changes and climate predictions. Wetlands are among some of the most challenging and complex ecosystems for water level predictions. Wetland water level prediction is vital, as wetlands have their own permissible water levels. Exceeding these water levels can cause flooding and other severe environmental damage. On the other hand, the biodiversity of the wetlands is threatened by the sudden fluctuation of water levels. Hence, early prediction of water levels benefits in mitigating most of such environmental damage. However, monitoring and predicting the water levels in wetlands worldwide have been limited owing to various constraints. This study presents the first-ever application of deep machine-learning techniques (deep neural networks) to predict the water level in an urban wetland in Sri Lanka located in its capital. Moreover, for the first time in water level prediction, it investigates two types of relationships: the traditional relationship between water levels and environmental factors, including temperature, humidity, wind speed, and evaporation, and the temporal relationship between daily water levels. Two types of low load artificial neural networks (ANNs) were developed and employed to analyze two relationships which are feed forward neural networks (FFNN) and long short-term memory (LSTM) neural networks, to conduct the comparison on an unbiased common ground. The LSTM has outperformed FFNN and confirmed that the temporal relationship is much more robust in predicting wetland water levels than the traditional relationship. Further, the study identified interesting relationships between prediction accuracy, data volume, ANN type, and degree of information extraction embedded in wetland data. The LSTM neural networks (NN) has achieved substantial performance, including R2 of 0.8786, mean squared error (MSE) of 0.0004, and mean absolute error (MAE) of 0.0155 compared to existing studies.Publication Embargo Novel Image Based Method Using V-I Curves with Aggregate Energy Data for Non-Intrusive Load Monitoring Applications(IEEE, 2022-12-09) Liyanage, P.M.L.; Herath, G.M.; Thilakanayake, T.D.; Liyanage, M.H.The emerging energy crises allow consumers to be concerned with the energy consumption of their appliances. Consumption data of individual appliances as opposed to the entire house are therefore in high demand. Non-intrusive load monitoring (NILM) is a way of producing individual appliance consumption data without using meters at individual appliances. Most studies have used signal features in steady state for device identification. However, many studies have not explored transient state signal characteristics for NILM. The voltage-current (V-I) trajectories during the transient state provide a unique way of representing the energy consumption of appliances. Although appliance-vise V-I characteristics have been considered in past studies, none has used aggregate V-I characteristics for appliance classification. Hence, using the V-I features of the aggregate data in an innovative manner for appliance classification has been explored in this work. The publicly available Plug-Level Appliance Identification Dataset (PLAID) was used to conduct this work. A Convolutional Neural Network (CNN) has been designed for device identification with 3 convolutional layers, a flatten layer and 4 fully connected layers. The results confirmed the possibility of using aggregate V-I trajectories for appliance classification with accuracies of up to 92% while retaining the full non-intrusive flavor of the study.Publication Open Access Design and Fabrication of a Novel Hybrid Solar Dryer(SLIIT, 2022-02-11) Perera, C; Fernando, G; Liyanage, MA hybrid solar dryer was designed and tested for commercial dissemination of active and passive drying methods over traditional sun drying methods. The proposed dryer employs novel features such as user controllability of the drying parameters and includes sensors and controllers for active monitoring of drying parameters. The functionality of the dryer is broadened by using logic control whereby intermittent drying patterns are introduced to the system for more efficient operation. This paper documents the design calculations and fabrication process of the dryer as well as the results of drying obtained under a controlled environment. 10 experiments have been carried out to assess the limits and potential improvements to the system which yielded satisfactory conditions with a temperature fluctuation of ±1℃ and change in %RH of ±2% at any given temperature within the specified limits. The developed system has been used for drying apples which yielded dried products from an initial weight of 346 grams to a final weight of 55 grams in 5 hours in pure convection and the same initial weight was reduced to 52 grams in 3 hours when operating in solar hybrid mode. The average energy consumption of the dryer was obtained at 300 Watts at uninterrupted solar insolation operation and 224 Watts during pure convective operation, portraying the efficient operation of the system to be eligible to be powered by a solar-powered energy storagePublication Open Access Aeroacoustic Noise Produced from Novel Wind Turbine Rotor Design for Small-scale Applications in Sri Lanka(SLIIT, 2022-02-11) Perera, M; Bandara, U. HGrowing concerns regarding non-renewable energy sources have driven academic and industrial scholars as well as global superpowers to seek sustainable, greener power generation alternatives. One such prominent renewable substitute is wind power which was initially utilized in harnessing electricity towards the late nineteenth century though archaeological evidence has proved that wind power had been employed for various purposes since predynastic Egypt. Extensive research and development has enabled the efficient operation of multi megawatt wind farms at present though inherent drawbacks still persist, of which aerodynamic noise, also referred to as aeroacoustic noise, is of major concern. This paper details the simulative investigation of the aeroacoustic sound levels produced by an optimized novel wind turbine design intended for the use in small scale applications with medium wind speed conditions in Sri Lanka, using ANSYS Fluent. A transient analysis using the Shear Stress Transport turbulence model was used to obtain the converged pressure fluctuations which subsequently revealed the sound pressure levels via Fast Fourier Transforms at six predetermined locations of interest. The results revealed the presence of acoustic vibrations within the Infrasonic and Low Frequency Noise range with sound pressure levels exceeding one hundred decibels, particularly up to a frequency of twenty five Hertz. Prolonged exposure to elevated levels of low frequency noise has been identified to cause severe discomfort to humans though further conclusive research is required. Finer mesh controls which incorporate minute boundary layer variations during motion and precisely encapsulate the turbine geometry could further improve the accuracy of the results, however this would require adequate computational capacity. The results of this research primarily serve as a basis for identifying possible improvements for the novel rotor design in addition to providing a comparative study for future research, both simulative and empirical, on the aerodynamic noise emissions associated with wind turbines.Publication Embargo An Automated System for Estimating GSM Value of Fabrics using Beta Particle Absorption Characteristics(IEEE, 2021-11-22) Dias, S; Sandaruwan, K. G. D; Jayasekara, SGrams per square meter (GSM) or Grammage is an ISO-recommended term to express the mass per unit area of papers, metal sheets, plastic-made products, and fabric materials. GSM tests are widely used in the textile industry to measure GSM of knitted fabrics, and to ensure quality and other standard fabrics' specifications. Meanwhile, most textile organizations prefer the manual GSM measuring procedure, which leads to many disadvantages, including fabric wastage. An automated non-contact type fabric Grammage measuring method is proposed as an alternative solution for this industrial issue. This paper introduces mathematical models for determining GSM values based on beta particle absorption characteristics of three selected fabrics. Moreover, this study discusses a real-time GSM measuring system, which utilizes the generated mathematical models. Through this paper, developed mathematical models are investigated over the goodness of fit parameters. Developed models are appropriate for GSM value estimation with R2 values over 0.99, and lower Root Mean Square Error (RMSE) Values. Error percentages obtained during the validation of these mathematical models are less than 1% for all fabric types.Publication Embargo Machine learning based classification of ripening and decay stages of Mango (Mangifera indica L.) cv. Tom EJC(IEEE, 2022-06-21) Hippola, H. M. W. M; WaduMesthri, D. P; Rajakaruna, R. M. T. P; Yasakethu, L; Rajapaksha, Mom EJC is a variety of Mango grown in tropical countries like Sri Lanka and India which has a very large demand and hence expensive. From the early stage of ripening, until the senescence stage, the process takes around 10–14 days. The fruit shows a yellowish color starting from the very early stage of ripening, throughout the period until it reaches the senescence stage. Unlike the other Mango varieties, it is difficult for a regular customer to determine the stage of ripening of the Tom EJC fruit, by observation. This paper focuses towards developing a vision-based classifier to rapidly identify ripening and decay stages of Tom EJC mango using surface image captures. A dataset of Tom EJC mango images was collated at different maturity levels. A Convolutional Neural Network (CNN) is proposed and tested using over 6000 Tom EJC images. The proposed model is shown to have a 76% testing accuracy in identifying four stages of maturity.