Search results for: dry-type transformers

Authors: Hossein Edrisi

Abstract:

To study the impact of the amount and volume of power of isolation transformer on the lamps in airfield Ground Lighting Systems. A test was conducted in Persian Gulf International Airport, This airport is situated in the south of Iran and it is one of the most cutting-edge airports, the same one that owns modern devices. Iran uses materials and auxiliary equipment which are made by ADB Company from Belgium. Airfield ground lighting (AGL) systems are responsible for providing visual issue to aircrafts and helicopters in the runways. In an AGL system a great deal of lamps are connected in serial circuits to each other and each ring has its individual constant current regulators (CCR), which through that provide energy to the lamps. Control of lamps is crucial for maintenance and operation in the AGL systems. Thanks to the Programmable Logic Controller (PLC) that is a cutting-edge technology can help the system to connect the elements from substations and ATC (TOWER). For this purpose, a test in real conditions of the airport done for all element that used in the airport such as isolation transformer in different power capacity and different consuming power and brightness of the lamps. The data were analyzed with Lux meter and Multimeter. The results had shown that the increase in the power of transformer caused a significant increase in brightness. According to the Ohm’s law and voltage division, without changing the characteristics of the light bulb, it is not possible to change the voltage, just need to change the amount of transformer with which it connects to the lamps. When the voltage is increased, the current through the bulb has to increase as well, because of Ohm's law: I=V/R and I=V/R which means that if V increases, so do I increase. The output voltage on the constant current regulator emerges between the lamps and the transformers.

Keywords: AGL, CCR, lamps, transformer, Ohm’s law

Procedia PDF Downloads 248

Authors: Aderonke Oluseun Akinwumi, Olusola A. Komolaf

Abstract:

This paper gives information about the wide array of challenges facing both the electric utilities and consumers in the distribution system in developing countries, using Obafemi Awolowo University, Ile-Ife Nigeria as a case study. It also proffers cost-effective solution through remote monitoring, diagnostic and operation of distribution networks without compromising the system reliability. As utilities move from manned and unintelligent networks to completely unmanned smart grids, switching activities at substations and feeders will be managed and controlled remotely by dedicated systems hence this design. The Substation Remote Diagnostic and Operation Solution (sRDOs) would remotely monitor the load on Medium Voltage (MV) and Low Voltage (LV) feeders as well as distribution transformers and allow the utility disconnect non-paying customers with absolutely no extra resource deployment and without interrupting supply to paying customers. The aftermath of the implementation of this design improved the lifetime of key distribution infrastructure by automatically isolating feeders during overload conditions and more importantly erring consumers. This increased the ratio of revenue generated on electricity bills to total network load.

Keywords: electric utility, consumers, remote monitoring, diagnostic, system reliability, manned and unintelligent networks, unmanned smart grids, switching activities, medium voltage, low voltage, distribution transformer

Procedia PDF Downloads 130

Authors: Nataša Stojić, Mira Pucarević, Nebojša Ralević, Vojislava Bursić, Gordan Stojić

Abstract:

Surface soil (0 – 10 cm) samples from 52 sampling sites along the length of railway tracks on the territory of Srem (the western part of the Autonomous Province of Vojvodina, itself part of Serbia) were collected and analyzed for 7 polychlorinated biphenyls (PCBs) in order to see how the distance from the railroad on the one hand and dump on the other hand, affect the concentration of PCBs (CPCBs) in the soil. Samples were taken at a distance of 0.03 to 4.19 km from the railway and 0.43 to 3.35 km from the landfills. For the soil extraction the Soxhlet extraction (USEPA 3540S) was used. The extracts were purified on a silica-gel column (USEPA 3630C). The analysis of the extracts was performed by gas chromatography with tandem mass spectrometry. PCBs were not detected only at two locations. Mean total concentration of PCBs for all other sampling locations was 0,0043 ppm dry weight (dw) with a range of 0,0005 to 0,0227 ppm dw. On the part of the data that were interesting for this research with statistical methods (PCA) were isolated factors that affect the concentration of PCBs. Data were also analyzed using the Pearson's chi-squared test which showed that the hypothesis of independence of CPCBs and distance from the railway can be rejected. Hypothesis of independence between CPCB and the percentage of humus in the soil can also be rejected, in contrast to dependence of CPCB and the distance from the landfill where the hypothesis of independence cannot be rejected. Based on these results can be said that railway transport is a potential source of PCBs. The next step in this research is to establish the position of transformers which are located near sampling sites as another important factor that affects the concentration of PCBs in the soil.

Keywords: GC/MS, landfill, PCB, railway, soil

Procedia PDF Downloads 335

Authors: Deepa S N, Srinivasan a D, Veeramanju K T

Abstract:

The power transformer is a critical equipment in the transmission and distribution network that must be managed to ensure uninterrupted power service. The liquid insulation is essential for the proper functioning of the transformer, as it serves as both coolant and insulating medium, which influences the transformer’s durability. Further, the insulating state of a power transformer has a significant impact on its reliability. Mineral oil derived from petroleum crude oil has been employed as liquid dielectrics for decades due to its superior functional characteristics, however as a resource for the same are getting depleted over the years. Research is undertaken across the globe to identify a viable substitute for mineral oil. Further, alternate insulating oils are being investigated for better environmental impact, biodegradability and economics. Several combinations of vegetable oil derived natural esters are being inspected by researchers across the globe in these domains. In this work, mineral oil is blended with soyabean oil with various proportions and dielectric properties such as dielectric breakdown voltage, relative permittivity, dissipation factor, viscosity, flash and fire point have been investigated according to international standards. A quantitative comparison is made among various samples and is observed that the blended oil sample of equal proportion of mineral oil and soyabean oil, MO50+SO50 exhibits superior dielectric properties such as breakdown voltage of 65kV, dissipation factor of 0.0044, relative permittivity of 3.1680 that are closer to the range of values recommended for power transformer applications. Also, Breakdown voltage values of all the investigated oil samples obeyed the Weibull and Normal probability distribution.

Keywords: blended oil, dielectric breakdown, liquid insulation, power transformer

Procedia PDF Downloads 89

Authors: Helena M. Wilhelm, Paulo O. Fernandes, Laís P. Dill, Kethlyn G. Moscon

Abstract:

The use of vegetable oil (or natural ester) as an insulating fluid in electrical transformers is a trend that aims to contribute to environmental preservation since it is biodegradable and non-toxic. Besides, vegetable oil has high flash and combustion points, being considered a fire safety fluid. However, vegetable oil is usually less stable towards oxidation than mineral oil. Both insulating fluids, mineral and vegetable oils, need to be tested periodically according to specific standards. Oxidation stability can be determined by the induction period measured by conductivity method (Rancimat) by monitoring the effectivity of oil’s antioxidant additives, a methodology already developed for food application and biodiesel but still not standardized for insulating fluids. Besides adequate oxidation stability, fluids must be compatible with transformer's construction materials under normal operating conditions to ensure that damage to the oil and parts of the transformer does not occur. ASTM standard and Brazilian normative differ in parameters evaluated, which reveals the need to regulate tests for each oil type. The aim of this study was to assess oxidation stability and compatibility of vegetable oils to suggest the best way to assure a viable performance of vegetable oil as transformer insulating fluid. The determination of the induction period for several vegetable insulating oils from the local market by using Rancimat was carried out according to BS EN 14112 standard, at different temperatures (110, 120, and 130 °C). Also, the compatibility of vegetable oil was assessed according to ASTM and ABNT NBR standards. The main results showed that the best temperature for use in the Rancimat test is 130 °C, which allows a better observation of conductivity change. The compatibility test results presented differences between vegetable and mineral oil standards that should be taken into account in oil testing since materials compatibility and oxidation stability are essential for equipment reliability.

Keywords: compatibility, Rancimat, natural ester, vegetable oil

Procedia PDF Downloads 210

Authors: K. N. Dinesh Babu

Abstract:

In this paper, the protection of a complicated bus arrangement with a dual bus coupler and bus sectionalizer using low impedance differential protection applicable for very high voltages like 220kV and 400kV is discussed. In many power generation stations, several operational procedures are implemented to utilize the transfer bus as the main bus and to facilitate the maintenance of circuit breakers and current transformers (in each section) without shutting down the bay(s). Owing to this fact, the complications in operational philosophy have thrown challenges for the bus bar protection implementation. Many bus topologies allow any one of the main buses available in the station to be used as an auxiliary bus. In such a system, pre-defined precautions and procedures are made as guidelines, which are followed before assigning any bus as an auxiliary bus. The procedure involves shifting of links, changing rotary switches, insertion of test block, and so on, thereby causing unreliable operation. This kind of unreliable operation or inadvertent procedural lapse may result in the isolation of the bus bar from the grid due to the unpredictable operation of the bus bar protection relay, which is a commonly occurring phenomenon due to manual mistakes. With the sophisticated configuration and implementation of logic in modern intelligent electronic devices, the operator is free to select the transfer arrangement without sacrificing the protection required by a bus differential system for a reliable operation, and labor-intensive processes are completely eliminated. This paper deals with the procedure to test the security logic for such special scenarios using Megger make SMRT, bus bar protection relay to assure system stability and get rid of all the specific operational precautions/procedure.

Keywords: bus bar protection, by-pass isolator, blind spot, breaker failure, intelligent electronic device, end fault, bus unification, directional principle, zones of protection, breaker re-trip, under voltage security, smart megger relay tester

Procedia PDF Downloads 68

Authors: Bonginkosi A. Thango, Jacobus A. Jordaan, Agha F. Nnachi

Abstract:

In this day and age, there is a proliferate concern from all governments across the globe to barricade the environment from greenhouse gases, which absorb infrared radiation. As a result, solar photovoltaic (PV) electricity has been an expeditiously growing renewable energy source and will eventually undertake a prominent role in the global energy generation. The selection and purchasing of energy-efficient transformers that meet the operational requirements of the solar photovoltaic energy generation plants then become a part of the Independent Power Producers (IPP’s) investment plan of action. Taking these into account, this paper proposes a procedure that put into effect the intricate financial analysis necessitated to precisely evaluate the transformer service lifetime no-load and load loss factors. This procedure correctly set forth the transformer service lifetime loss factors as a result of a solar PV plant’s sporadic generation profile and related levelized costs of electricity into the computation of the transformer’s total ownership cost. The results are then critically compared with the conventional transformer total ownership cost unaccompanied by the emission costs, and demonstrate the significance of the sporadic energy generation nature of the solar PV plant on the total ownership cost. The findings indicate that the latter play a crucial role for developers and Independent Power Producers (IPP’s) in making the purchase decision during a tender bid where competing offers from different transformer manufactures are evaluated. Additionally, the susceptibility analysis of different factors engrossed in the transformer service lifetime cost is carried out; factors including the levelized cost of electricity, solar PV plant’s generation modes, and the loading profile are examined.

Keywords: solar photovoltaic plant, transformer, total ownership cost, loss factors

Procedia PDF Downloads 130

Authors: M. R. Ahmad, I. Musirin, M. M. Othman, N. A. Rahmat

Abstract:

Plug-in Hybrid-Electric Vehicle (PHEV) has gained immense popularity in recent years. PHEV offers numerous advantages compared to the conventional internal-combustion engine (ICE) vehicle. Millions of PHEVs are estimated to be on the road in the USA by 2020. Uncoordinated PHEV charging is believed to cause severe impacts to the power grid; i.e. feeders, lines and transformers overload and voltage drop. Nevertheless, improper PHEV data model used in such studies may cause the findings of their works is in appropriated. Although smart charging is more attractive to researchers in recent years, its implementation is not yet attainable on the street due to its requirement for physical infrastructure readiness and technology advancement. As the first step, it is finest to study the impact of charging PHEV based on real vehicle travel data from National Household Travel Survey (NHTS) and at present charging rate. Due to the lack of charging station on the street at the moment, charging PHEV at home is the best option and has been considered in this work. This paper proposed a technique that comprehensively presents the impact of charging PHEV on power system networks considering huge numbers of PHEV samples with its traveling data pattern. Vehicles Charging Load Profile (VCLP) is developed and implemented in IEEE 30-bus test system that represents a portion of American Electric Power System (Midwestern US). Normalization technique is used to correspond to real time loads at all buses. Results from the study indicated that charging PHEV using opportunity charging will have significant impacts on power system networks, especially whereas bigger battery capacity (kWh) is used as well as for higher penetration level.

Keywords: plug-in hybrid electric vehicle, transportation electrification, impact of charging PHEV, electricity demand profile, load profile

Procedia PDF Downloads 287

Authors: Ma Cecilia Siva

Abstract:

This study introduces a Bidirectional Encoder Representations from Transformers (BERT)-based machine learning model aimed at improving educational counseling by automating the process of recommending academic strands for students. The framework is designed to streamline and enhance the strand selection process by analyzing students' profiles and suggesting suitable academic paths based on their interests, strengths, and goals. Data was gathered from a sample of 200 grade 10 students, which included personal essays and survey responses relevant to strand alignment. After thorough preprocessing, the text data was tokenized, label-encoded, and input into a fine-tuned BERT model set up for multi-label classification. The model was optimized for balanced accuracy and computational efficiency, featuring a multi-category classification layer with sigmoid activation for independent strand predictions. Performance metrics showed an F1 score of 88%, indicating a well-balanced model with precision at 80% and recall at 100%, demonstrating its effectiveness in providing reliable recommendations while reducing irrelevant strand suggestions. To facilitate practical use, the final deployment phase created a recommendation framework that processes new student data through the trained model and generates personalized academic strand suggestions. This automated recommendation system presents a scalable solution for academic guidance, potentially enhancing student satisfaction and alignment with educational objectives. The study's findings indicate that expanding the data set, integrating additional features, and refining the model iteratively could improve the framework's accuracy and broaden its applicability in various educational contexts.

Keywords: tokenized, sigmoid activation, transformer, multi category classification

Procedia PDF Downloads 8

Authors: Mubarak Suliman, Mohamed Hassan

Abstract:

Detection of downed conductors occurring with high fault resistance (reaching kilo-ohms) has always been a challenge, especially in countries like Saudi Arabia, on which earth resistivity is very high in general (reaching more than 1000 Ω-meter). The new approaches for the detection of resistive and high impedance faults are based on the analysis of the fault current waveform. These methods are still under research and development, and they are currently lacking security and dependability. The other approach is communication-based solutions which depends on voltage measurement at the end of overhead line branches and communicate the measured signals to substation feeder relay or a central control center. However, such a detection method is costly and depends on the availability of communication medium and infrastructure. The main objective of this research is to utilize the available standard protection schemes to increase the probability of detection of downed conductors occurring with a low magnitude of fault currents and at the same time avoiding unwanted tripping in healthy conditions and feeders. By specifying the operating region of the faulty feeder, use of tripping curve for discrimination between faulty and healthy feeders, and with proper selection of core balance current transformer (CBCT) and voltage transformers with fewer measurement errors, it is possible to set the pick-up of sensitive earth fault current to minimum values of few amps (i.e., Pick-up Settings = 3 A or 4 A, …) for the detection of earth faults with fault resistance more than (1 - 2 kΩ) for 13.8kV overhead network and more than (3-4) kΩ fault resistance in 33kV overhead network. By implementation of the outcomes of this study, the probability of detection of downed conductors is increased by the utilization of existing schemes (i.e., Directional Sensitive Earth Fault Protection).

Keywords: sensitive earth fault, zero sequence current, grounded system, resistive fault detection, healthy feeder

Procedia PDF Downloads 115

Authors: Othmane Touri, Sanaa El Filali, El Habib Benlahmar

Abstract:

Natural Language Processing (NLP) has gained significant attention lately. It has proved its ability to analyze and extract insights from unstructured text data in various languages. It is found that one of the most popular NLP applications is sentiment analysis which aims to identify the sentiment expressed in a piece of text, such as positive, negative, or neutral, in multiple languages. While there are several multilingual NLP models available for sentiment analysis, there is a need to investigate their effectiveness in different contexts and applications. In this study, we aim to investigate the effectiveness of different multilingual NLP models for sentiment analysis on a dataset of online product reviews in multiple languages. The performance of several NLP models, including Google Cloud Natural Language API, Microsoft Azure Cognitive Services, Amazon Comprehend, Stanford CoreNLP, spaCy, and Hugging Face Transformers are being compared. The models based on several metrics, including accuracy, precision, recall, and F1 score, are being evaluated and compared to their performance across different categories of product reviews. In order to run the study, preprocessing of the dataset has been performed by cleaning and tokenizing the text data in multiple languages. Then training and testing each model has been applied using a cross-validation approach where randomly dividing the dataset into training and testing sets and repeating the process multiple times has been used. A grid search approach to optimize the hyperparameters of each model and select the best-performing model for each category of product reviews and language has been applied. The findings of this study provide insights into the effectiveness of different multilingual NLP models for Multilingual Sentiment Analysis and their suitability for different languages and applications. The strengths and limitations of each model were identified, and recommendations for selecting the most performant model based on the specific requirements of a project were provided. This study contributes to the advancement of research methods in multilingual NLP and provides a practical guide for researchers and practitioners in the field.

Keywords: NLP, multilingual, sentiment analysis, texts

Procedia PDF Downloads 102

Authors: S. Mani, M. Kafil, E. Asadi

Abstract:

Condition Monitoring (CM) of electrical equipment has gained remarkable importance during the recent years; due to huge production losses, substantial imposed costs and increases in vulnerability, risk and uncertainty levels. Power cables feed numerous electrical equipment such as transformers, motors, and electric furnaces; thus their condition assessment is of a very great importance. This paper investigates electrical, structural and environmental failure sources, all of which influence cables' performances and limit their uptimes; and provides a comprehensive framework entailing practical CM guidelines for maintenance of cables in industries. The multilevel CM framework presented in this study covers performance indicative features of power cables; with a focus on both online and offline diagnosis and test scenarios, and covers short-term and long-term threats to the operation and longevity of power cables. The study, after concisely overviewing the concept of CM, thoroughly investigates five major areas of power quality, Insulation Quality features of partial discharges, tan delta and voltage withstand capabilities, together with sheath faults, shield currents and environmental features of temperature and humidity; and elaborates interconnections and mutual impacts between those areas; using mathematical formulation and practical guidelines. Detection, location, and severity identification methods for every threat or fault source are also elaborated. Finally, the comprehensive, practical guidelines presented in the study are presented for the specific case of Electric Arc Furnace (EAF) feeder MV power cables in Mobarakeh Steel Company (MSC), the largest steel company in MENA region, in Iran. Specific technical and industrial characteristics and limitations of a harsh industrial environment like MSC EAF feeder cable tunnels are imposed on the presented framework; making the suggested package more practical and tangible.

Keywords: condition monitoring, diagnostics, insulation, maintenance, partial discharge, power cables, power quality

Procedia PDF Downloads 228

Authors: Roghieh A. Biroon, Zoleikha Abdollahi

Abstract:

The recent growth of renewables, e.g., solar panels, batteries, and electric vehicles (EVs) in residential and small commercial sectors, has potential impacts on the stability and operation of power grids. Considering approximately 50 percent share of the residential and the commercial sectors in the electricity demand market, the significance of these impacts, and the necessity of addressing them are more highlighted. Utilities and power system operators should manage the renewable electricity sources integration with power systems in such a way to extract the most possible advantages for the power systems. The most common effect of high penetration level of the renewables is the reverse power flow in the distribution feeders when the customers generate more power than their needs. The reverse power flow causes voltage rise and thermal issues in the power grids. To overcome the voltage rise issues in the distribution system, several techniques have been proposed including reducing transformers short circuit resistance and feeder impedance, installing autotransformers/voltage regulators along the line, absorbing the reactive power by distributed generators (DGs), and limiting the PV and battery sizes. In this study, we consider a medium-scale battery energy storage to manage the power energy and address the aforementioned issues on voltage deviation and power loss increase. We propose an optimization algorithm to find the optimum size and location for the battery. The optimization for the battery location and size is so that the battery maintains the feeder voltage deviation and power loss at a certain desired level. Moreover, the proposed optimization algorithm controls the charging/discharging profile of the battery to absorb the negative power flow from residential and commercial customers in the feeder during the peak time and sell the power back to the system during the off-peak time. The proposed battery regulates the voltage problem in the distribution system while it also can play frequency regulation role in islanded microgrids. This battery can be regulated and controlled by the utilities or a third-party ancillary service provider for the utilities to reduce the power system loss and regulate the distribution feeder voltage and frequency in standard level.

Keywords: ancillary services, battery, distribution system and optimization

Procedia PDF Downloads 131

Authors: Pedro Esteban

Abstract:

Most installations nowadays are exposed to many power quality problems, and they also face numerous challenges to comply with grid code and energy efficiency requirements. The reason behind this is that they are not designed to support nonlinear, non-balanced, and variable loads and generators that make up a large percentage of modern electric power systems. These problems and challenges become especially critical when designing green buildings and smart cities. These problems and challenges are caused by equipment that can be typically found in these installations like variable speed drives (VSD), transformers, lighting, battery chargers, double-conversion UPS (uninterruptible power supply) systems, highly dynamic loads, single-phase loads, fossil fuel generators and renewable generation sources, to name a few. Moreover, events like capacitor switching (from existing capacitor banks or passive harmonic filters), auto-reclose operations of transmission and distribution lines, or the starting of large motors also contribute to these problems and challenges. Active power filters (APF) are one of the fastest-growing power electronics technologies for solving power quality problems and meeting grid code and energy efficiency requirements for a wide range of segments and applications. They are a high performance, flexible, compact, modular, and cost-effective type of power electronics solutions that provide an instantaneous and effective response in low or high voltage electric power systems. They enable longer equipment lifetime, higher process reliability, improved power system capacity and stability, and reduced energy losses, complying with most demanding power quality and energy efficiency standards and grid codes. There can be found several types of active power filters, including active harmonic filters (AHF), static var generators (SVG), active load balancers (ALB), hybrid var compensators (HVC), and low harmonic drives (LHD) nowadays. All these devices can be used in applications in Smart Cities bringing several technical and economic benefits.

Keywords: power quality improvement, energy efficiency, grid code compliance, green buildings, smart cities

Procedia PDF Downloads 112

Authors: M. Moyzykh, I. Klichuk, L. Sabirov, D. Kolomentseva, E. Magommedov

Abstract:

Modern city electrical grids are forced to increase their density due to the increasing number of customers and requirements for reliability and resiliency. However, progress in this direction is often limited by the capabilities of existing network equipment. New energy sources or grid connections increase the level of short-circuit currents in the adjacent network, which can exceed the maximum rating of equipment–breaking capacity of circuit breakers, thermal and dynamic current withstand qualities of disconnectors, cables, and transformers. Superconducting fault current limiter (SFCL) is a modern solution designed to deal with the increasing fault current levels in power grids. The key feature of this device is its instant (less than 2 ms) limitation of the current level due to the nature of the superconductor. In 2019 Moscow utilities installed SuperOx SFCL in the city power grid to test the capabilities of this novel technology. The SFCL became the first SFCL in the Russian energy system and is currently the most powerful SFCL in the world. Modern SFCL uses second-generation high-temperature superconductor (2G HTS). Despite its name, HTS still requires low temperatures of liquid nitrogen for operation. As a result, Moscow SFCL is built with a cryogenic system to provide cooling to the superconductor. The cryogenic system consists of three cryostats that contain a superconductor part and are filled with liquid nitrogen (three phases), three cryocoolers, one water chiller, three cryopumps, and pressure builders. All these components are controlled by an automatic control system. SFCL has been continuously operating on the city grid for over three years. During that period of operation, numerous faults occurred, including cryocooler failure, chiller failure, pump failure, and others (like a cryogenic system power outage). All these faults were eliminated without an SFCL shut down due to the specially designed cryogenic system backups and quick responses of grid operator utilities and the SuperOx crew. The paper will describe in detail the results of SFCL operation and cryogenic system maintenance and what measures were taken to solve and prevent similar faults in the future.

Keywords: superconductivity, current limiter, SFCL, HTS, utilities, cryogenics

Procedia PDF Downloads 80

Authors: Sheelagh Heugh, Michael Upton, Kriya Kalidas, Stephen Breen

Abstract:

This article aims to create awareness of the opportunities and issues the artificial intelligence (AI) tool GPT-3 (Generative Pre-trained Transformer-3) brings to higher education. Technological disruptors have featured in higher education (HE) since Konrad Klaus developed the first functional programmable automatic digital computer. The flurry of technological advances, such as personal computers, smartphones, the world wide web, search engines, and artificial intelligence (AI), have regularly caused disruption and discourse across the educational landscape around harnessing the change for the good. Accepting AI influences are inevitable; we took mixed methods through participatory action research and evaluation approach. Joining HE communities, reviewing the literature, and conducting our own research around Chat GPT-3, we reviewed our institutional approach to changing our current practices and developing policy linked to assessments and the use of Chat GPT-3. We review the impact of GPT-3, a high-powered natural language processing (NLP) system first seen in 2020 on HE. Historically HE has flexed and adapted with each technological advancement, and the latest debates for educationalists are focusing on the issues around this version of AI which creates natural human language text from prompts and other forms that can generate code and images. This paper explores how Chat GPT-3 affects the current educational landscape: we debate current views around plagiarism, research misconduct, and the credibility of assessment and determine the tool's value in developing skills for the workplace and enhancing critical analysis skills. These questions led us to review our institutional policy and explore the effects on our current assessments and the development of new assessments. Conclusions: After exploring the pros and cons of Chat GTP-3, it is evident that this form of AI cannot be un-invented. Technology needs to be harnessed for positive outcomes in higher education. We have observed that materials developed through AI and potential effects on our development of future assessments and teaching methods. Materials developed through Chat GPT-3 can still aid student learning but lead to redeveloping our institutional policy around plagiarism and academic integrity.

Keywords: artificial intelligence, Chat GPT-3, intellectual property, plagiarism, research misconduct

Procedia PDF Downloads 89

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 7

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 105

Authors: A. Maghoul, A. Rostampouryasouri, MR. Maghami

Abstract:

The development of an urban design and power network planning has been gaining momentum in recent years. The integration of renewable energy with urban design has been widely regarded as an increasingly important solution leading to climate change and energy security. Through the use of passive strategies and solar integration with Urban Building Energy Modeling (UBEM) tools, architects and designers can create high-quality designs that meet the needs of clients and stakeholders. To determine the most effective ways of combining renewable energy with urban development, we analyze the relationship between urban form and renewable energy production. The procedure involved in this practice include passive solar gain (in building design and urban design), solar integration, location strategy, and 3D models with a case study conducted in Tehran, Iran. The study emphasizes the importance of spatial and temporal considerations in the development of sector coupling strategies for solar power establishment in arid and semi-arid regions. The substation considered in the research consists of two parallel transformers, 13 lines, and 38 connection points. Each urban load connection point is equipped with 500 kW of solar PV capacity and 1 kWh of battery Energy Storage (BES) to store excess power generated from solar, injecting it into the urban network during peak periods. The simulations and analyses have occurred in EnergyPlus software. Passive solar gain involves maximizing the amount of sunlight that enters a building to reduce the need for artificial lighting and heating. Solar integration involves integrating solar photovoltaic (PV) power into smart grids to reduce emissions and increase energy efficiency. Location strategy is crucial to maximize the utilization of solar PV in an urban distribution feeder. Additionally, 3D models are made in Revit, and they are keys component of decision-making in areas including climate change mitigation, urban planning, and infrastructure. we applied these strategies in this research, and the results show that it is possible to create sustainable and energy-efficient urban environments. Furthermore, demand response programs can be used in conjunction with solar integration to optimize energy usage and reduce the strain on the power grid. This study highlights the influence of ancient Persian architecture on Iran's urban planning system, as well as the potential for reducing pollutants in building construction. Additionally, the paper explores the advances in eco-city planning and development and the emerging practices and strategies for integrating sustainability goals.

Keywords: energy-efficient urban planning, sustainable architecture, solar energy, sustainable urban design

Procedia PDF Downloads 76

Authors: Colin Schmidt, Adrien Lecossier, Pascal Crubleau, Philippe Blanchard, Simon Richir

Abstract:

Introduction:The widespread availability of artificial intelligence, exemplified by Generative Pre-trained Transformers (GPT) relying on large language models (LLM), has caused a seismic shift in the realm of knowledge. Everyone now has the capacity to swiftly learn how these models can either serve them well or not. Today, conversational AI like ChatGPT is grounded in neural transformer models, a significant advance in natural language processing facilitated by the emergence of renowned LLMs constructed using neural transformer architecture. Inventiveness of an LLM : OpenAI's GPT-3 stands as a premier LLM, capable of handling a broad spectrum of natural language processing tasks without requiring fine-tuning, reliably producing text that reads as if authored by humans. However, even with an understanding of how LLMs respond to questions asked, there may be lurking behind OpenAI’s seemingly endless responses an inventive model yet to be uncovered. There may be some unforeseen reasoning emerging from the interconnection of neural networks here. Just as a Soviet researcher in the 1940s questioned the existence of Common factors in inventions, enabling an Under standing of how and according to what principles humans create them, it is equally legitimate today to explore whether solutions provided by LLMs to complex problems also share common denominators. Theory of Inventive Problem Solving (TRIZ) : We will revisit some fundamentals of TRIZ and how Genrich ALTSHULLER was inspired by the idea that inventions and innovations are essential means to solve societal problems. It's crucial to note that traditional problem-solving methods often fall short in discovering innovative solutions. The design team is frequently hampered by psychological barriers stemming from confinement within a highly specialized knowledge domain that is difficult to question. We presume ChatGPT Utilizes TRIZ 40. Hence, the objective of this research is to decipher the inventive model of LLMs, particularly that of ChatGPT, through a comparative study. This will enhance the efficiency of sustainable innovation processes and shed light on how the construction of a solution to a complex problem was devised. Description of the Experimental Protocol : To confirm or reject our main hypothesis that is to determine whether ChatGPT uses TRIZ, we will follow a stringent protocol that we will detail, drawing on insights from a panel of two TRIZ experts. Conclusion and Future Directions : In this endeavor, we sought to comprehend how an LLM like GPT addresses complex challenges. Our goal was to analyze the inventive model of responses provided by an LLM, specifically ChatGPT, by comparing it to an existing standard model: TRIZ 40. Of course, problem solving is our main focus in our endeavours.

Keywords: artificial intelligence, Triz, ChatGPT, inventiveness, problem-solving

Procedia PDF Downloads 73

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 85

Authors: Edvard P. G. Bruun

Abstract:

One of the best ways of improving our understanding of reinforced concrete is through large-scale experimental testing. The gathered information is critical in making inferences about structural mechanics and deriving the mathematical models that are the basis for finite element analysis programs and design codes. An effective way of measuring the strains across a region of a specimen is by using a system of surface mounted Linear Variable Differential Transformers (LVDTs). While a single LVDT can only measure the linear strain in one direction, by combining several measurements at known angles a Mohr’s circle of strain can be derived for the whole region under investigation. This paper presents a method that can be used by researchers, which improves the accuracy and removes experimental bias in the calculation of the Mohr’s circle, using four rather than three independent strain measurements. Obtaining high quality strain data is essential, since knowing the angular deviation (shear strain) and the angle of principal strain in the region are important properties in characterizing the governing structural mechanics. For example, the Modified Compression Field Theory (MCFT) developed at the University of Toronto, is a rotating crack model that requires knowing the direction of the principal stress and strain, and then calculates the average secant stiffness in this direction. But since LVDTs can only measure average strains across a plane (i.e., between discrete points), localized cracking and spalling that typically occur in reinforced concrete, can lead to unrealistic results. To build in redundancy and improve the quality of the data gathered, the typical experimental setup for a large-scale shell specimen has four independent directions (X, Y, H, and V) that are instrumented. The question now becomes, which three should be used? The most common approach is to simply discard one of the measurements. The problem is that this can produce drastically different answers, depending on the three strain values that are chosen. To overcome this experimental bias, and to avoid simply discarding valuable data, a more rigorous approach would be to somehow make use of all four measurements. This paper presents the derivation of a method to draw what is effectively a Mohr’s circle of 'best-fit', which optimizes the circle by using all four independent strain values. The four-strain optimized Mohr’s circle approach has been utilized to process data from recent large-scale shell tests at the University of Toronto (Ruggiero, Proestos, and Bruun), where analysis of the test data has shown that the traditional three-strain method can lead to widely different results. This paper presents the derivation of the method and shows its application in the context of two reinforced concrete shells tested in pure torsion. In general, the constitutive models and relationships that characterize reinforced concrete are only as good as the experimental data that is gathered – ensuring that a rigorous and unbiased approach exists for calculating the Mohr’s circle of strain during an experiment, is of utmost importance to the structural research community.

Keywords: reinforced concrete, shell tests, Mohr’s circle, experimental research

Procedia PDF Downloads 235

Authors: Rahil Bahrami, Kaveh Ashenayi

Abstract:

This paper presents a systematic classification and comparative analysis of non-isolated bi-directional DC-DC converters. The increasing demand for efficient energy conversion in diverse applications has spurred the development of various converter topologies. In this study, we categorize bi-directional converters into three distinct classes: Inverting, Non-Inverting, and Interleaved. Each category is characterized by its unique operational characteristics and benefits. Furthermore, a practical comparison is conducted by evaluating the results of simulation of each bi-directional converter. BDCs can be classified into isolated and non-isolated topologies. Non-isolated converters share a common ground between input and output, making them suitable for applications with minimal voltage change. They are easy to integrate, lightweight, and cost-effective but have limitations like limited voltage gain, switching losses, and no protection against high voltages. Isolated converters use transformers to separate input and output, offering safety benefits, high voltage gain, and noise reduction. They are larger and more costly but are essential for automotive designs where safety is crucial. The paper focuses on non-isolated systems.The paper discusses the classification of non-isolated bidirectional converters based on several criteria. Common factors used for classification include topology, voltage conversion, control strategy, power capacity, voltage range, and application. These factors serve as a foundation for categorizing converters, although the specific scheme might vary depending on contextual, application, or system-specific requirements. The paper presents a three-category classification for non-isolated bi-directional DC-DC converters: inverting, non-inverting, and interleaved. In the inverting category, converters produce an output voltage with reversed polarity compared to the input voltage, achieved through specific circuit configurations and control strategies. This is valuable in applications such as motor control and grid-tied solar systems. The non-inverting category consists of converters maintaining the same voltage polarity, useful in scenarios like battery equalization. Lastly, the interleaved category employs parallel converter stages to enhance power delivery and reduce current ripple. This classification framework enhances comprehension and analysis of non-isolated bi-directional DC-DC converters. The findings contribute to a deeper understanding of the trade-offs and merits associated with different converter types. As a result, this work aids researchers, practitioners, and engineers in selecting appropriate bi-directional converter solutions for specific energy conversion requirements. The proposed classification framework and experimental assessment collectively enhance the comprehension of non-isolated bi-directional DC-DC converters, fostering advancements in efficient power management and utilization.The simulation process involves the utilization of PSIM to model and simulate non-isolated bi-directional converter from both inverted and non-inverted category. The aim is to conduct a comprehensive comparative analysis of these converters, considering key performance indicators such as rise time, efficiency, ripple factor, and maximum error. This systematic evaluation provides valuable insights into the dynamic response, energy efficiency, output stability, and overall precision of the converters. The results of this comparison facilitate informed decision-making and potential optimizations, ensuring that the chosen converter configuration aligns effectively with the designated operational criteria and performance goals.

Keywords: bi-directional, DC-DC converter, non-isolated, energy conversion

Procedia PDF Downloads 100

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 42