Research Papers - Department of Mechanical Engineering
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/604
Browse
12 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo An Image Based Approach of Energy Signal Disaggregation Using Artificial Intelligence(IEEE, 2021-12-09) Senarathna, M; Herath, M; Thilakanayake, H. D; Liyanage, M. H; Angammana, C. JNon-Intrusive Load Monitoring (NILM) is the real-time monitoring of energy consumption data of individual appliances through the decomposition of composite energy signal captured at the household smart energy meter. Most of the existing NILM techniques utilize one-dimensional (1D) time-series signal analysis to predict the individual appliance energy signals. The utilization of image-based methods for the disaggregation of energy signals is a relatively new approach in the NILM domain. This paper presents a study of a novel computer vision-based Artificial Intelligence (AI) approach when compared to the traditional time series-based NILM methods. Gramian Angular Fields (GAF) and Recurrence Plots (RP) have been widely used in recent literature to encode time series signals as images. Novel image classification techniques with the use of Convolutional Neural Networks (CNN) simplify the extraction of nuclear load features from encoded two-dimensional (2D) images. The results considered the indices validation accuracy and validation loss in comparing the performance of different vision-based AI approaches. The results reveal that Gramian Angular Difference Field (GADF) outperforms both Gramian Angular Summation Field (GASF) and RP with a training accuracy of 97.9% and a validation accuracy of 94.2%. A comprehensive analysis and comparison are presented with an in-depth evaluation using multi-state appliances and it was concluded that GADF is the most suitable 1D to 2D conversion method for the representation of time series energy data for disaggregation purposes.Publication Open Access A QUADCOPTER WITH AUTOMATED TAKE-OFF AND LANDING ON MOBILE ROBOT PLATFORM(SHEFFIELD HALLAM UNIVERSITY ENGINEERING PROGRAM, 2016-12) Sandaruwan, B. A. S; Mithun, S; Rathnayake, R. M. K. M; Liyanage, M. HIn this thesis, a controller is designed for an off the shelf quadcopter to give it the ability to autonomously takeoff, hover at a given altitude, follow and land on a mobile robot platform. This is a small part of a much bigger system which is a quadcopter and a mobile robot combined fully autonomous surveillance system. This system has the ability to navigate and complete a given task without any human interaction. Different types of sensor are used to determine the position of the quadcopter in 3D space. A PID controller is implemented to keep the quadcopter at a given altitude. Different types of sensors and technologies were used to achieve our target. A discrete PID controller will be used to hold the altitude of the quadcopter. Real-time image processing is used to determine the position of the quadcopter relative to the mobile robot platform. An ideal quadcopter simulation and a 3D simulation of the task is done to understand in detail how a quadcopter works and how to controller it the way we desire. Kalman filter is used to produce accurate and precious angular data of the quadcopter. The project is separated into several parts and divided among all the members of the group. The simulation of the complete system and the implementation of the takeoff, altitude holding and landing algorithms for the test system are done by me. Determining the position of the quadcopter using image processing and design and implementation of the Mobile robot platform is done by Rathnayake R.M.K.M. Implementation of Kalman filter to be used with Gyro and accelerometer sensors and the simulation of an ideal quadcopter model in Matlab is done by S. Mithun.Publication Embargo The Potential Role of Carbon Tax in Achieving the Paris Agreement Targets for a Developing Country: A Case Study of Sri Lanka(IEEE, 2020-10-20) Fernando, G. L; Liyanage, M. HThis study assess the effect of carbon taxes on energy and emissions of the Sri Lankan energy sector during 2015-2050. Along with a Business As Usual (BAU) scenario, three alternative carbon price trajectories were considered. These scenarios have been proposed based on fifth Shared Socioeconomic Pathway (SSP5) to achieve the 2°C Paris target for Asia. The Carbon Price trajectories proposed by AIM/CGA, REMIND-MAgPIE and GCAM were considered. The energy-economic-environmental system was modelled using the AIM/Enduse model. It considered both energy supply and demand sectors. The results show that in the BAU scenario the GHG emissions are expected to increase from 19.8MtCO 2e in 2015to 106.2MtCO 2e in 2050. Out of three carbon tax scenarios the prices proposed by AIM/CGA has been the most efficient for reduction of GHG emissions as it could reduce final energy consumption by 26% and GHG emissions by 24% in 2050 as compared to BAU scenario.Publication Embargo An Embedded System for a High-Speed Manipulator With Single Time Scale Visual Servoing(American Society of Mechanical Engineers, 2017-07-01) Liyanage, M. H; Krouglicof, NThis study presents the development of an embedded system for controlling a high-speed robotic manipulator. Three different types of controllers including hardware proportional derivative (PD), software PD, and single time scale visual servoing are considered in this study. Novel field programmable gate array (FPGA) technology was used for implementing the embedded system for faster execution speeds and parallelism. It is comprised of dedicated hardware and software modules for obtaining sensor feedback and control signal (CT) estimation, providing the control signal to the servovalves. A NIOS II virtual soft processor system was configured in the FPGA for implementing functions that are computationally expensive and difficult to implement in hardware. Quadrature decoding, serial peripheral interface (SPI) input and output modules, and control signal estimation in some cases was carried out using the dedicated hardware modules. The experiments show that the proposed controller performed satisfactory control of the end effector position. It performed single time scale visual servoing with control signal updates at 330 Hz to control the end effector trajectory at speeds of up to 0.8 ms1 . The FPGA technology also provided a more compact single chip implementation of the controller.Publication Open Access Sustainable Energy Options for Sri Lankan Transport sector(National Energy Symposium 2019, 2019) Fernando, G. L; Ruzaik, M. A; Liyanage, M. HTransport sector of Sri Lanka accounts for 29% of total energy consumption and almost half of greenhouse gas (GHG) emissions in Sri Lanka. This study is to investigate the possible sustainable energy options for the transport sector. Sri Lankan transport sector is modelled using the Asia Pacific Integrated/Endues (AIM Endues) model for the planning horizon from 2015 to 2045. This study analyses four countermeasures along with the business as usual (BAU) scenario. The first countermeasure scenario is promoting residential solar electricity for electric vehicles. Other three scenarios modelled with 20%, 30% and 40% subsidy for electric and hybrid vehicles. Out of the four scenarios, promoting residential solar electricity for electric vehicles is the most effective countermeasure as it could reduce the transport sector energy consumption by 16.4 Mtoe and CO2 emissions by 35% in 2045. At the current vehicle and electricity prices, providing 20% subsidy will not be effective as 30% and 40% subsidies in achieving significant reduction in energy consumption and CO2 mitigation Sri Lankan transport sector.Publication Embargo Economic Viability of Solar PV for Domestic Applications in a Middle-Income Country: A case Study of Sri Lanka(IEEE, 2020-10-20) Wijesinghe, J. K; Najim, M. Y. M; Fernando, G. L; Liyanage, M. HThis study focuses on the economics of using solar Photovoltaics for residential in a middle-income country like Sri Lanka. It considers solar irradiance in the Colombo district to estimate the power generation potential by a selected 2.16kWp solar PV system throughout the year. It used solar irradiance data by NASA Surface Meteorology and Solar Energy (SSE), satellite solar insolation values for Sri Lanka and used the Liu and Jordan (LJ) method. Furthermore, it considered the economics of four different scenarios as model houses depending on appliance usage with net accounting. It was seen that without net accounting the Levelized cost of electricity could be as high as US0.69/kWh.However,withmechanismslikenetaccounting,itcouldbereducedtoUS 0.12 /kWh with full owners' contribution. Under the net accounting scheme houses that consume above 300 kWh/month will have the lowest payback period of 2 years and 9 months.Publication Embargo Optimization of controller gains for FPGA-based multivariable motion controller using response surface methodology(IEEE, 2015-05-03) Sekaran, H. P; Liyanage, M. H; Krouglicof, NField Programmable Gate Arrays (FPGA) have become increasingly popular in recent years for control applications. Using contemporary FPGA technology, a powerful virtual processor can be synthesized and integrated with custom hardware to create a dedicated controller that outperforms conventional microcontroller and microprocessor based designs. The FPGA based controller takes advantage of both hardware features and virtual processor technology. This study details the development of a cascaded type PD controller for an inverted pendulum system implemented on a single FPGA device. The controller includes a hardware based implementation of the IO modules including quadrature decoders/counters and a Pulse Width Modulation (PWM) controller for the motor driver. The NIOS II processor was synthesized to implement the cascaded PID controller algorithm. This study also proposes a novel method for obtaining the optimal controller gains for the system. It uses the Central Composite Design (CCD) in Response Surface Methodology (RSM) for obtaining these gains. A classic inverted pendulum system was selected to demonstrate the applicability of the proposed approach. The gains provided by the RSM were verified experimentally to validate the proposed controller tuning method.Publication Embargo Energy and Environmental Implications of Green House Gas Mitigation Policies in the Transport Sector of Sri Lanka(IEEE, 2018-10-24) Fernando, G. L; Liyanage, M. H; Samarasekara, G. NThis study analyzes the greenhouse gas mitigation policy options for the transport sector in Sri Lanka. It was carried out through the Asia-Pacific Integrated Assessment Model (AIM/Enduse), which is a bottom up type least cost optimization framework. A business as usual scenario and four alternative mitigation policy options were considered in this study. These policy options include two scenarios with 100 $/tonCO 2 , 500 $/tonCO 2 carbon tax, a subsidy scenario with tax rebates for electric, hybrid vehicles and a scenario which promotes pubic transport. The results show that the transport sector energy consumption is expected to increase from 5 Mtoe in 2015 to 19.5 Mtoe in 2045. The CO 2 emissions are expected to increase from 15 Mton in 2015 to 58 Mton in 2045. Out of the four scenarios, promoting public transport was most effective as it could reduce energy consumption by 52% and reduce CO 2 emissions by almost 36% in 2045. At current electricity prices and other costs, electric vehicles are not found to be economical in the analysis.Publication Embargo Comprehensive Analysis of Convolutional Neural Network Models for Non-Instructive Load Monitoring(IEEE, 2020-10-20) Herath, G. M; Thilakanayake, T. D; Liyanage, M. H; Angammana, C. JNon-Instructive Load Monitoring (NILM) schemes have become more popular in recent years with the availability of smart meters. It provides energy use data to utilities and per-appliance energy consumption details to end users. This study carries out a comprehensive analysis of existing Convolutional Neural Network (CNN) architectures that have been used for NILM. Nevertheless, it provides an unbiased comparison of the existing architectures thereby helping to select the best performing model for NILM applications. The commonly used CNN disaggregation models were categorized into distinctive groups based on their architectures which considered structure of the Neural Network (NN) and outputs. It considers regression-based sequence to sequence and sequence to point mapping, classification-based sequence to point hard association and soft association-based mapping. The CNN models are improved and modified to bring them onto a common platform for comparison. Thereafter, a rigorous comparison was performed using indices which included accuracy, precision, F-measure and recall. The results reveal interesting relationships between architectures, appliances and measures.Publication Embargo A single time scale visual servoing system for a high speed SCARA type robotic arm(IEEE, 2014-05-31) Liyanage, M. H; Krouglicof, NA high speed image based visual servoing (VS) technique is developed in this study for a Selective Compliant Assembly Robotic Arm (SCARA) manipulator with rotary hydraulic actuators. This study has developed a 2D position measuring system which comprise a high speed camera with a position sensitive detector as the image sensor. The input output interface and the controller for the VS system was implemented using a field programmable gate array (FPGA) providing a single chip solution for the embedded system. This camera was capable of providing position measurements of the end effector (EE) with an accuracy of up to 0.95 mm at a frequency of 1340 Hz. The proposed control strategy produced a better tracking performance with an EE payload of 12 kg with speeds of up to 1.3 m/s.