PhD
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4219
Theses and Dissertations of the Sri Lanka Institute of Information Technology (SLIIT) are licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Browse
2 results
Search Results
Publication Open Access Development of Real-Time, Self-Learning Artificial Intelligence-Based Algorithms for Non-Intrusive Energy Disaggregation in a Multi-Appliance Environment(Faculty of Engineering Sri Lanka Institute of Information Technology, 2023-12) Herath, MElectricity serves as a cornerstone in modern economies, with demand in residential and commercial sectors rapidly increasing in recent years. Enabling real-time monitoring of individual appliance-wise energy consumption and delivering user feedback is essential for future energy conservation initiatives. Energy disaggregation becomes imperative in furnishing consumption statistics for individual appliances. The acquisition of appliance-specific energy consumption in a non-intrusive manner, without the need for sensors on each device but by utilizing readings from the main household energy meter, highlights Non-Intrusive Load Monitoring (NILM) as a promising solution. NILM, leveraging the capabilities of smart meters and advancements in computational power, gains popularity for its effectiveness in disaggregating and analyzing energy consumption patterns. This study introduces an Artificial Intelligence (AI)-based NILM solution capable of disaggregating the energy consumption of multiple appliances while adapting to new appliances and their evolving behaviors. Among various NILM approaches, Neural Network (NN)-based models demonstrate promising disaggregation capabilities. However, the selection of the most suitable NN type or architecture poses a challenge due to the multitude of approaches in literature. To address this issue, the study standardizes and compares different NNs, with results showing that the Convolutional Neural Network (CNN) exhibits superior prediction accuracy and speed. This study also investigates the impact of different appliances and their consumption profiles on disaggregation performance, rigorously testing parameters such as NN architecture, input-output mapping topologies, data preprocessing, and hyperparameters. This leads to the development of guidelines for future NILM studies. Additionally, the study introduces a hierarchical plug-and-play modular-based model for appliance anomaly detection, extending the application of NILM and overcoming limitations in anomaly detection literature. This study investigates two-dimensional (2D) input-based NILM solutions for predicting appliance energy consumption profiles and classifying appliances. Unlike conventional NN-based models using 1D signals, representing the aggregate energy signal as a 2D image improves performance by leveraging feature extraction capabilities of NNs and preserving vital temporal information and signal amplitude relationships. Various TSS to 2D image conversion methods for NILM were tested, including Gramin Angular Summation Field (GASF), Gramin Angular Difference Field (GADF), Recurrent Plot (RP), and Markov Transition Field (MTF), with GADF outperforming other methods. In addition, the study introduces a simple yet powerful 2D input mechanism for time series data, specifically energy consumption data. This mechanism will be integrated into a CNN-based energy disaggregation model for the first time in the NILM domain, with the aim of improving overall performance. While the proposed method excels over 1D input-based models in training, it is observed that the novel 2D input method requires augmentation in training data volume, data mixing, NN depth, and hyperparameter tuning to achieve superior generalization capabilities. Furthermore, aggregate energy signal-based Voltage-Current (V-I) trajectory plots were investigated for fully non-intrusive appliance classification, demonstrating high accuracy. v The study proposes a single NN architecture named "One-Shot." This model exhibits the capability to simultaneously disaggregate multiple appliances, offering a more efficient alternative to the intricate and computationally demanding existing NN-based NILM models that necessitate separate NNs for each appliance. The efficacy of this approach is evaluated across multiple input-output mapping configurations, with the multi-point multi-bin model proving superior. To address challenges associated with manual model re-training for new appliances and adapting to evolving consumption patterns, a self-learning module is incorporated, enhancing the performance of the OneShot model. To overcome issues related to excessive hyperparameter tuning and insufficient training data, the study presents an unsupervised model based on Blind Source Separation (BSS), utilizing Independent Component Analysis (ICA) to separate appliance energy signals from the aggregate signal. Developing more reliable disaggregation models in local environments requires a local energy dataset. For this purpose, the study creates a local energy dataset from households using a custom-designed data logger, capturing both low and high-frequency energy data at appliance, circuit, and main energy meter levels. This dataset is verified using the One-Shot model developed in this study. In summary, this study advances the field of NILM by introducing AI-based solutions, innovative approaches, and comprehensive guidelines. Ultimately, these contributions aim to foster energy conservation and enhance efficiency in residential and commercial settings globally.Publication Open Access Development and testing of a high speed hydraulic manipulator with single time scale visual servoing(Memorial University of Newfoundland, 2014) Liyanage, M. HAutomation of production processes has enabled to meet the dramatic demand for manufactured products that has grown out of the increase in world population. In existing industries greater production requirements and improvement in product quality call for faster industrial robots. This study details the design and development of a high-speed visual servoing system for industrial applications. The proposed visual servoing system consists of a high speed robotic manipulator, a high-speed camera system and an embedded controller. The proposed robotic manipulator has the configuration of a Selective Compliant Assembly Robotic Arm (SCARA). It uses two custom-designed double vane rotary hydraulic actuators for driving the links of the robot. The SCARA system was mathematically modeled and simulated. Based on the simulation results, the hydraulic actuators were sized for optimal performance. A prototype actuator was subsequently designed, manufactured and experimentally evaluated. The test results show that the proposed actuator is capable of reaching torques of up to 460 Nm in 30 ms with a payload of 12 kg. This is not possible with electric motors of similar size. Then the proposed SCARA was designed and fabricated using the proposed actuators. The end effector of this manipulator was capable of reaching velocities of up to 2.7 ms⁻¹ with a payload of 5.3 kg. Comparable performance is not feasible with contemporary SCARA type robots. The proposed robot was designed for handling payloads up to 15 kg with speeds of up to 2 ms⁻¹. This often results in flexing of the links and twisting of the support column, adding external disturbances to the system. A high-speed camera system was designed and built to obtain the position of the end effector as feedback for the controller. It uses a two dimensional Position Sensitive Detector as the image sensor. An electronic circuit was designed and built for signal conditioning and data acquisition from the Position Sensitive Detector. It was then calibrated to account for non-linearities on the image sensor. The camera was constructed using this Position Sensitive Detector circuit, a lens and an infra red filter.It was then calibrated to estimate the extrinsic and intrinsic parameters. This camera was capable of carrying out measurements at frequencies of up to 1350 Hz. The measurements made by this camera produced an average absolute accuracy of 0.31 mm and 0.37 mm in x and y directions, respectively. A Field Programmable Gate Array was used in this study as the platform for developing an embedded controller for the robot. Using contemporary Field Programmable Gate Array technology, a powerful virtual processor can be synthesized and integrated with custom hardware to create a dedicated controller that out performs some of the conventional microcontroller and microprocessor based designs. The Field Programmable Gate Array based controller takes advantage of both hardware features and virtual processor technology. The input, output interfaces for this controller were implemented using hardware. Complex functions that are difficult to be implemented in hardware were implemented using a virtual soft processor. Four different types of controllers were implemented and tested. These include hardware proportional-derivative, software proportional-derivative, single time scale visual servoing and set point modification type controllers. The proposed implementation carried out single time scale visual servoing at frequencies of up to 330 Hz.