NSPACE
Welcome to NSBM Green University e-Repository!
One Platform for NSBM Publications

Communities in DSpace
Select a community to browse its collections.
Recent Submissions
Item type:Item, (#1) Evaluating Construction Cost Impacts of Building Parameters Using Artificial Neural Networks(NSBM Green University, 2024-08-23) Prasad, H.B.; Madushanka, T.H.; Guruge, R.N.D.; Rajapaksha, D.M.; Reza, T.S.The accurate estimation of construction costs is a critical, yet complex task influenced by numerous variables. Traditional methods often fail to provide reliable early-stage cost estimates, leading to budget overruns and project delays. This research addresses this gap by focusing on identifying and ranking the most significant factors affecting the construction costs of residential buildings with less than four stories. Specifically, the study leverages Artificial Neural Networks (ANN) to enhance the accuracy of cost predictions by considering multiple building parameters. This approach is aimed at improving budgeting processes and resource allocation in the construction industry.Item type:Item, (#57) Enhanced Object Localization via Neural Network Integration with Newton's Method(NSBM Green University, 2024-08-23) Balasooriya, T.N.; Dilpriya, H.Machine vision is crucial in autonomous vehicles and robotics, demanding precise object localization and environmental perception. Enhancing the baseline between cameras can improve accuracy and range but introduces challenges in stereo synchronization. This research presents a novel system that integrates neural networks with Newton's method to enhance object localization accuracy while reducing computational costs. Utilizing three cameras with known baselines, the system combines Convolutional Neural Network (CNN) models, such as YOLO, for critical component identification, with Newton's method for refining initial location estimates provided by machine learning algorithms. This integration ensures high accuracy by double-checking neural network outputs with mathematical models, avoiding local minima, and enhancing computational efficiency. Experimental results demonstrated successful camera calibration, accurate object detection, and significant improvements in point estimation accuracy using Newton's method. This approach promises advancements in 3D reconstruction and realtime object localization for autonomous systems.Item type:Item, (#52) Development of A Durable Cutting Technology for Enhanced Efficiency in Textile Manufacturing(NSBM Green University, 2024-08-23) Dulnath, N.K.S.C; Gunarathne, M.G.C.H.IThis study focuses on the development of durable cutting technology to improve efficiency in textile manufacturing, specifically for cutting thin fabric straps like shoulder straps for female undergarments. The research aims to design a cutting blade and mechanism actuated by a pneumatic actuator and controlled by an HMI-based system. It addresses the need for a durable cutting edge and proposes a method to model and design an effective cutting process. The study involves examining the mechanical properties of fabrics, frictional coefficients, and cutting mechanisms. It also explores the selection of actuation techniques and control systems, including the development of a ladder program to operate the mechanism. The methodology includes designing the blade using parametric curves, calculating cutting forces, and determining the wedge angle and blade thickness. Simulations ensure the blade’s strength meets the requirements for cutting force. The research identifies factors affecting cutting tool effectiveness, such as wedge angle, curvature of the edge, and blade thickness, which influence the cutting force needed for different fabric piles. The study contributes a solution that can be applied in the textile industry for productive and cost-effective cutting strategies.Item type:Item, (#51) Review: Obstacle Detection and Localization in an Autonomous Vehicle(NSBM Green University, 2024-08-23) Weerasinghe, K.M.R.; Lakmal, H.K.I.S.This paper analyses the revolutionary impact of artificial intelligence (AI) technologies on the fast-changing landscape of vehicle automation within the automobile industry. AI software for automobiles is expected to generate USD 6.6 billion by 2025, fuelling a revolutionary transformation, particularly in the realm of autonomous driving systems. Object detection, a cornerstone of selfdriving vehicles, is examined through the lenses of two-stage and single-stage approaches, stressing its vital role in allowing vehicles to observe and classify their surroundings. The analysis goes deeply into the complexities of obstacle avoidance, emphasizing its critical role in real-time path planning and assuring human and vehicle safety. Object localization, a critical component of this process, requires precise distance determination and justified coordinates to overcome obstacles given by changing environmental conditions. Current research highlights the dominance of deep learning algorithms, with the YOLO approach and several R-CNN variations taking the lead in object identification and avoidance systems. The problems of sensor integration are examined, with a focus on cameras and LIDARs, which are judged appropriate for 3D modeling. The review also addresses sensor position issues and provides an ideal solution that uses cameras for object recognition and LIDARs for depth perception. The literature study continues by identifying relevant studies with approaches that are closely matched with the suggested methodology, underlining the importance of continuous research to accelerate developments in autonomous driving capabilities.Item type:Item, (#40) In-Situ Pipeline Inspection with A Soft Robotic Manipulator Using PneuNet and SMA Springs(NSBM Green University, 2024-08-23) Alahakoon, G.A.; Gunarathna, M.G.C.H.L.Soft robotics has emerged as a trending field recently due to the traditional rigid robotics failure in their applications requiring flexibility and adaptability in constrained environments. One of the crucial parameters that defines a soft robot is its material and the redundant degrees of freedom. The use of soft materials allows for continuous deformation which in turn, enables structures with ranges of motion limited only by the properties of the material [1]. Such materials that are used for the fabrication of the soft manipulators are Silicone Rubber, Elastomers (PDMS), SMAs, Thermoplastic Elastomers, etc. Among the applications that require flexibility one significant scenario is the inspection of pipelines in water sprinkler systems, which often involves navigating through pipelines with diameters as narrow as 4-8 inches. This research aims to design and analyse a soft robotic manipulator specifically for in-situ operations within these confined spaces. The manipulator incorporates a Shape Memory Alloy (SMA) spring, actuated by voltage, and a pneumatically actuated PneuNet structure to facilitate precise and flexible movements. The main focus of this research is on detailing the design process of the manipulator and highlighting the customization of the SMA spring. The manufacturability and material selection for the PneuNet structure are also discussed, alongside simulations are also performed using Abaqus CAE to ensure the validity of the manipulator design.