Search results for: electrical equivalent circuit analogy

Authors: Wei Hu, Wenguang Chen, Chong Dong

Abstract:

In order to improve the efficiency and safety of photovoltaic power generation devices, this photovoltaic power generation system combines Artificial Intelligence (AI) and the Internet of Things (IoT) to control the chasing photovoltaic power generation device to track the sun to improve power generation efficiency and then convert energy management. The system uses artificial intelligence as the control terminal, the power generation device executive end uses the Linux system, and Exynos4412 is the CPU. The power generating device collects the sun image information through Sony CCD. After several power generating devices feedback the data to the CPU for processing, several CPUs send the data to the artificial intelligence control terminal through the Internet. The control terminal integrates the executive terminal information, time information, and environmental information to decide whether to generate electricity normally and then whether to convert the converted electrical energy into the grid or store it in the battery pack. When the power generation environment is abnormal, the control terminal authorizes the protection strategy, the power generation device executive terminal stops power generation and enters a self-protection posture, and at the same time, the control terminal synchronizes the data with the cloud. At the same time, the system is more intelligent, more adaptive, and longer life.

Keywords: photo-voltaic power generation, the pursuit of light, artificial intelligence, internet of things, photovoltaic array, power management

Procedia PDF Downloads 123

Authors: Seongcheol Kwon, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

We assume an IoT-based smart-home environment where the on-off status of each of the electrical appliances including the room lights can be recognized in a real time by monitoring and analyzing the smart meter data. At any moment in such an environment, we can recognize what the household or the user is doing by referring to the status data of the appliances. In this paper, we focus on a smart-home service that is to activate a robot vacuum cleaner at right time by recognizing the user situation, which requires a situation-aware model that can distinguish the situations that allow vacuum cleaning (Yes) from those that do not (No). We learn as our candidate models a few classifiers such as naïve Bayes, decision tree, and logistic regression that can map the appliance-status data into Yes and No situations. Our training and test data are obtained from simulations of user behaviors, in which a sequence of user situations such as cooking, eating, dish washing, and so on is generated with the status of the relevant appliances changed in accordance with the situation changes. During the simulation, both the situation transition and the resulting appliance status are determined stochastically. To compare the performances of the aforementioned classifiers we obtain their learning curves for different types of users through simulations. The result of our empirical study reveals that naïve Bayes achieves a slightly better classification accuracy than the other compared classifiers.

Keywords: situation-awareness, smart home, IoT, machine learning, classifier

Procedia PDF Downloads 422

Authors: H. M. Mohammad, A. Martin, N. Brown, N. Hodson, P. Hill, E. Roberts

Abstract:

Graphite intercalation compound (GIC) has been demonstrated to be a useful, low capacity and rapid adsorbent for the removal of organic micropollutants from water. The high electrical conductivity and low capacity of the material lends itself to electrochemical regeneration. Following electrochemical regeneration, equilibrium loading under similar conditions is reported to exceed that achieved by the fresh adsorbent. This behavior is reported in terms of the regeneration efficiency being greater than 100%. In this work, surface analysis techniques are employed to investigate the material in three states: ‘Fresh’, ‘Loaded’ and ‘Regenerated’. ‘Fresh’ GIC is shown to exhibit a hydrogen and oxygen rich surface layer approximately 150 nm thick. ‘Loaded’ GIC shows a similar but slightly thicker surface layer (approximately 370 nm thick) and significant enhancement in the hydrogen and oxygen abundance extending beyond 600 nm from the surface. 'Regenerated’ GIC shows an oxygen rich layer, slightly thicker than the fresh case at approximately 220 nm while showing a very much lower hydrogen enrichment at the surface. Results demonstrate that while the electrochemical regeneration effectively removes the phenol model pollutant, it also oxidizes the exposed carbon surface. These results may have a significant impact on the estimation of adsorbent life.

Keywords: graphite, adsorbent, electrochemical, regeneration, phenol

Procedia PDF Downloads 139

Authors: Roya Moradifar, Bijan Honarvar, Masoumeh Zabihi

Abstract:

The personal residential camps of South Pars gas complex are one of the few places where electric energy is used for the bath water heating. The widespread use of these devices is mainly responsible for the high peak of the electricity demand in the residential sector. In an attempt to deal with this issue, to reduce the electricity usage of the hot water, as an option, solar hot water systems have been proposed. However, despite the high incidence of solar radiation on the Assaloyeh about 20 MJ/m²/day, currently, there is no technical assessment quantifying the economic benefits on the region. The present study estimates the economic impacts resulting by the deployment of solar hot water systems in residential camp. Hence, the feasibility study allows assessing the potential of solar water heating as an alternative to reduce the peak on the electricity demand. In order to examine the potential of using solar energy in Bidkhoon residential camp two solar water heater packages as pilots were installed for restaurant and building. Restaurant package was damaged due to maintenance problems, but for the building package, we achieved the result of the solar fraction total 83percent and max energy saving 2895 kWh, the maximum reduction in CO₂ emissions calculated as 1634.5 kg. The results of this study can be used as a support tool to spread the use solar water heaters and create policies for South Pars Gas Complex.

Keywords: electrical energy, hot water, solar, South Pars Gas complex

Procedia PDF Downloads 202

Authors: Serzhan Ashirov, Dana Nour, Rafat Rob, Khaled Alotaibi

Abstract:

There has been a fast growth in the introduction and use of communications, information, monitoring, and sensing technologies. The new technologies are making their way to the Industrial Control Systems as embedded in products, software applications, IT services, or commissioned to enable integration and automation of increasingly global supply chains. As a result, the lines that separated the physical, digital, and cyber world have diminished due to the vast implementation of the new, disruptive digital technologies. The variety and increased use of these technologies introduce many cybersecurity risks affecting cyber-resilience of the supply chain, both in terms of the product or service delivered to a customer and members of the supply chain operation. US department of energy considers supply chain in the IR4 space to be the weakest link in cybersecurity. The IR4 identified the digitization of the field devices, followed by digitalization that eventually moved through the digital transformation space with little care for the new introduced cybersecurity risks. This paper will examine the best methodologies for securing the electrical substations from cybersecurity attacks due to supply chain risks, and due to digitization effort. SCADA systems are the most vulnerable part of the power system infrastructure due to digitization and due to the weakness and vulnerabilities in the supply chain security. The paper will discuss in details how create a secure supply chain methodology, secure substations, and mitigate the risks due to digitization

Keywords: cybersecurity, supply chain methodology, secure substation, digitization

Procedia PDF Downloads 64

Authors: Livinus A. Obasi, Augustine N. Ajah

Abstract:

Biotechnology in recent times has tried to develop a mechanism whereby sustainable electricity can be generated by the activity of microorganisms on waste and renewable biomass (often regarded as “negative value”) in a device called microbial fuel cell, MFC. In this paper, we established how the biocatalytic activities of bacteria on organic matter (substrates) produced some electrons with the associated removal of some water pollution parameters; Biochemical oxygen demand (BOD), chemical oxygen demand (COD) to the tune of 77.2% and 88.3% respectively from a petrochemical sanitary wastewater. The electricity generation was possible by conditioning the bacteria to operate anaerobically in one chamber referred to as the anode while the electrons are transferred to the fully aerated counter chamber containing the cathode. Power densities ranging from 12.83 mW/m² to 966.66 mW/m² were achieved using a dual-chamber starch membrane MFC experimental set-up. The maximum power density obtained in this research shows an improvement in the use of low cost MFC set up to achieve power production. Also, the level of organic matter removal from the sanitary waste water by the operation of this device clearly demonstrates its potential benefit in achieving an improved benign environment. The beauty of the MFCs is their potential utility in areas lacking electrical infrastructures like in most developing countries.

Keywords: bioelectricity, COD, microbial fuel cell, sanitary wastewater, wheat starch

Procedia PDF Downloads 256

Authors: Sergey A. Lurie, Yury O. Solyaev, Dmitry B. Volkov-Bogorodsky, Alexander V. Volkov

Abstract:

The media with voids is considered and the method of the analytical estimation of the effective mechanical properties in the theory of elastic materials with voids is proposed. The variational model of the porous media is discussed, which is based on the model of the media with fields of conserved dislocations. It is shown that this model is fully consistent with the known model of the linear elastic materials with voids. In the present work, the generalized model of the porous media is proposed in which the specific surface properties are associated with the field of defects-pores in the volume of the deformed body. Unlike typical surface elasticity model, the strain energy density of the considered model includes the special part of the surface energy with the quadratic form of the free distortion tensor. In the result, the non-classical boundary conditions take modified form of the balance equations of volume and surface stresses. The analytical approach is proposed in the present work which allows to receive the simple enough engineering estimations for effective characteristics of the media with free dilatation. In particular, the effective flexural modulus and Poisson's ratio are determined for the problem of a beam pure bending. Here, the known voids elasticity solution was expanded on the generalized model with the surface effects. Received results allow us to compare the deformed state of the porous beam with the equivalent classic beam to introduce effective bending rigidity. Obtained analytical expressions for the effective properties depend on the thickness of the beam as a parameter. It is shown that the flexural modulus of the porous beam is decreased with an increasing of its thickness and the effective Poisson's ratio of the porous beams can take negative values for the certain values of the model parameters. On the other hand, the effective shear modulus is constant under variation of all values of the non-classical model parameters. Solutions received for a beam pure bending and the hydrostatic loading of the porous media are compared. It is shown that an analytical estimation for the bulk modulus of the porous material under hydrostatic compression gives an asymptotic value for the effective bulk modulus of the porous beam in the case of beam thickness increasing. Additionally, it is shown that the scale effects appear due to the surface properties of the porous media. Obtained results allow us to offer the procedure of an experimental identification of the non-classical parameters in the theory of the linear elastic materials with voids based on the bending tests for samples with different thickness. Finally, the problem of implementation of the Saint-Venant hypothesis for the transverse stresses in the porous beam are discussed. These stresses are different from zero in the solution of the voids elasticity theory, but satisfy the integral equilibrium equations. In this work, the exact value of the introduced surface parameter was found, which provides the vanishing of the transverse stresses on the free surfaces of a beam.

Keywords: effective properties, scale effects, surface defects, voids elasticity

Procedia PDF Downloads 417

Authors: Zwalnan Selfa Johnson, Caleb Nanchen Nimyel, Gideon Duvuna Ayuba

Abstract:

Air conditioning accounts for a significant share of the overall energy consumed in residential buildings. Solar thermal gains in buildings account for a significant component of the air conditioning load in buildings. This study compares the solar thermal gain and air conditioning load of a proposed building design with a typical conventional building in the climatic conditions of Jos, Nigeria, using a combined experimental and computational method using TRNSYS software. According to the findings of this study, the proposed design building's annual average solar thermal gains are lower compared to the reference building's average solar heat gains. The study case building's decreased solar heat gain is mostly attributable to the lower temperature of the building zones because of the greater building volume and lower fenestration ratio (ratio external opening area to the area of the external walls). This result shows that the proposed building design adjusts to the local climate better than the standard conventional construction in Jos to maintain a suitable temperature within the building. This finding means that the air-conditioning electrical energy consumption per volume of the proposed building design will be lower than that of a conventional building design.

Keywords: solar heat gain, building zone, cooling energy, air conditioning, zone temperature

Procedia PDF Downloads 93

Authors: Om Prakash Bharti, Aanchal Verma, R. K. Saket

Abstract:

The Doubly-Fed Induction Generator (DFIG) is suggested for Wind Energy Conversion System (WECS) to extract wind power. DFIG is preferably employed due to its robustness towards variable wind and rotor speed. DFIG has the adaptable property because the system parameters are smoothly dealt with, including real power, reactive power, DC-link voltage, and the transient and dynamic responses, which are needed to analyze constantly. The analysis becomes more prominent during any unusual condition in the electrical power system. Hence, the study and improvement in the system parameters and transient response performance of DFIG are required to be accomplished using some controlling techniques. For fulfilling the task, the present work implements and compares the optimization methods for the design of the DFIG controller for WECS. The bio-inspired optimization techniques are applied to get the optimal controller design parameters for DFIG-based WECS. The optimized DFIG controllers are then used to retrieve the transient response performance of the six-order DFIG model with a step input. The results using MATLAB/Simulink show the betterment of the Firefly algorithm (FFA) over other control techniques when compared with the other controller design methods.

Keywords: doubly-fed induction generator, wind turbine, wind energy conversion system, induction generator, transfer function, proportional, integral, derivatives

Procedia PDF Downloads 93

Authors: Chien-kuo Chang, Bo-wei Wu, Yi-yun Tang, Min-chiu Wu

Abstract:

This paper proposes a power equipment diagnosis system based on partial discharge (PD), which is characterized by increasing the readability of experimental data and the convenience of operation. This system integrates a variety of analysis programs of different data formats and different programming languages and then establishes a set of interfaces that can follow and expand the structure, which is also helpful for subsequent maintenance and innovation. This study shows a case of using the developed Convolutional Neural Networks (CNN) to integrate with this system, using the designed model architecture to simplify the complex training process. It is expected that the simplified training process can be used to establish an adaptive deep learning experimental structure. By selecting different test data for repeated training, the accuracy of the identification system can be enhanced. On this platform, the measurement status and partial discharge pattern of each equipment can be checked in real time, and the function of real-time identification can be set, and various training models can be used to carry out real-time partial discharge insulation defect identification and insulation state diagnosis. When the electric power equipment entering the dangerous period, replace equipment early to avoid unexpected electrical accidents.

Keywords: partial discharge, convolutional neural network, partial discharge analysis platform, adaptive deep learning

Procedia PDF Downloads 78

Authors: Hyunjoo Park, Taehyun Kim, Taehyun Kim

Abstract:

Human life, activity, and culture depend on the wider environment. Cities offer economic opportunities for goods and services, but cannot exist in environments without food, energy, and water supply. Technological innovation in energy supply and transport speeds up the expansion of urban areas and the physical separation from agricultural land. As a result, division of urban agricultural areas causes more energy demand for food and goods transport between the regions. As the energy resources are leaking all over the world, the impact on the environment crossing the boundaries of cities is also growing. While advances in energy and other technologies can reduce the environmental impact of consumption, there is still a gap between energy supply and demand by current technology, even in technically advanced countries. Therefore, reducing energy demand is more realistic than relying solely on the development of technology for sustainable development. The purpose of this study is to introduce the application of carbon footprint assessment in fields of urban planning and geography. In urban studies, carbon footprint has been assessed at different geographical scales, such as nation, city, region, household, and individual. Carbon footprint assessment for a nation and a city is available by using national or city level statistics of energy consumption categories. By means of carbon footprint calculation, it is possible to compare the ecological capacity and deficit among nations and cities. Carbon footprint also offers great insight on the geographical distribution of carbon intensity at a regional level in the agricultural field. The study shows the background of carbon footprint applications in urban planning and geography by case studies such as figuring out sustainable land-use measures in urban planning and geography. For micro level, footprint quiz or survey can be adapted to measure household and individual carbon footprint. For example, first case study collected carbon footprint data from the survey measuring home energy use and travel behavior of 2,064 households in eight cities in Gyeonggi-do, Korea. Second case study analyzed the effects of the net and gross population densities on carbon footprint of residents at an intra-urban scale in the capital city of Seoul, Korea. In this study, the individual carbon footprint of residents was calculated by converting the carbon intensities of home and travel fossil fuel use of respondents to the unit of metric ton of carbon dioxide (tCO₂) by multiplying the conversion factors equivalent to the carbon intensities of each energy source, such as electricity, natural gas, and gasoline. Carbon footprint is an important concept not only for reducing climate change but also for sustainable development. As seen in case studies carbon footprint may be measured and applied in various spatial units, including but not limited to countries and regions. These examples may provide new perspectives on carbon footprint application in planning and geography. In addition, additional concerns for consumption of food, goods, and services can be included in carbon footprint calculation in the area of urban planning and geography.

Keywords: carbon footprint, case study, geography, urban planning

Procedia PDF Downloads 288

Authors: M. Zafar, S. Rasheed, Imran Hashmi

Abstract:

Very little is concerned about the bacterial contamination in drinking water biofilm which provide a potential source for bacteria to grow and increase rapidly. So as to understand the microbial density in DWDs, a three-month study was carried out. The aim of this study was to examine biofilm in three different pipe materials including PVC, PPR and GI. A set of all these pipe materials was installed in DWDs at nine different locations and assessed on monthly basis. Drinking water quality was evaluated by different parameters and characterization of biofilm. Among various parameters are Temperature, pH, turbidity, TDS, electrical conductivity, BOD, COD, total phosphates, total nitrates, total organic carbon (TOC) free chlorine and total chlorine, coliforms and spread plate counts (SPC) according to standard methods. Predominant species were Bacillus thuringiensis, Pseudomonas fluorescens , Staphylococcus haemolyticus, Bacillus safensis and significant increase in bacterial population was observed in PVC pipes while least in cement pipes. The quantity of DWDs bacteria was directly depended on biofilm bacteria and its increase was correlated with growth and detachment of bacteria from biofilms. Pipe material also affected the microbial community in drinking water distribution network biofilm while Similarity in bacterial species was observed between systems due to same disinfectant dose, time period and plumbing pipes.

Keywords: biofilm, DWDs, pipe material, bacterial population

Procedia PDF Downloads 347

Authors: Elham Allahmoradi, Bahman Allahmoradi, Ali Bonyadi Naeini

Abstract:

Complex systems have many aspects. A variety of methods have been developed to analyze these systems. The most efficient of these methods should not only be simple, but also provide useful and comprehensive information about many aspects of the system. Matrix methods are considered the most commonly methods used to analyze and design systems. Each matrix method can examine a particular aspect of the system. If these methods are combined, managers can access to more comprehensive and broader information about the system. This study was conducted in four steps. In the first step, a process model of a real project has been extracted through IDEF3. In the second step, activity levels have been attained by writing a process model in the form of a design structure matrix (DSM) and sorting it through triangulation algorithm (TA). In the third step, sub-processes have been obtained by writing the process model in the form of an interface structure matrix (ISM) and clustering it through cluster identification algorithm (CIA). In the fourth step, a mixed model has been developed to provide a unified picture of the project structure through the simultaneous presentation of activities and sub-processes. Finally, the paper is completed with a conclusion.

Keywords: integrated definition for process description capture (IDEF3) method, design structure matrix (DSM), interface structure matrix (ism), mixed matrix model, activity level, sub-process

Procedia PDF Downloads 494

Authors: S. Neelima, P. S. Subramanyam

Abstract:

A distribution system is an interface between the bulk power system and the consumers. Among these systems, radial distributions system is popular because of low cost and simple design. In distribution systems, the voltages at buses reduces when moved away from the substation, also the losses are high. The reason for a decrease in voltage and high losses is the insufficient amount of reactive power, which can be provided by the shunt capacitors. But the placement of the capacitor with an appropriate size is always a challenge. Thus, the optimal capacitor placement problem is to determine the location and size of capacitors to be placed in distribution networks in an efficient way to reduce the power losses and improve the voltage profile of the system. For this purpose, in this paper, two stage methodologies are used. In the first stage, the load flow of pre-compensated distribution system is carried out using ‘dimension reducing distribution load flow algorithm (DRDLFA)’. On the basis of this load flow the potential locations of compensation are computed. In the second stage, Genetic Algorithm (GA) technique is used to determine the optimal location and size of the capacitors such that the cost of the energy loss and capacitor cost to be a minimum. The above method is tested on IEEE 9 and 34 bus system and compared with other methods in the literature.

Keywords: dimension reducing distribution load flow algorithm, DRDLFA, genetic algorithm, electrical distribution network, optimal capacitors placement, voltage profile improvement, loss reduction

Procedia PDF Downloads 390

Authors: Sandeep Santosh, O. P. Sahu

Abstract:

In this paper, performance comparison of wideband covariance matrix sparse representation (W-CMSR) method with other existing wideband Direction of Arrival (DOA) estimation methods has been made.W-CMSR relies less on a priori information of the incident signal number than the ordinary subspace based methods.Consider the perturbation free covariance matrix of the wideband array output. The diagonal covariance elements are contaminated by unknown noise variance. The covariance matrix of array output is conjugate symmetric i.e its upper right triangular elements can be represented by lower left triangular ones.As the main diagonal elements are contaminated by unknown noise variance,slide over them and align the lower left triangular elements column by column to obtain a measurement vector.Simulation results for W-CMSR are compared with simulation results of other wideband DOA estimation methods like Coherent signal subspace method (CSSM), Capon, l1-SVD, and JLZA-DOA. W-CMSR separate two signals very clearly and CSSM, Capon, L1-SVD and JLZA-DOA fail to separate two signals clearly and an amount of pseudo peaks exist in the spectrum of L1-SVD.

Keywords: W-CMSR, wideband direction of arrival (DOA), covariance matrix, electrical and computer engineering

Procedia PDF Downloads 471

Authors: MD Mashiur Rahman, Muhammad Arshadul Haque

Abstract:

Emerging conservation agriculture (CA) is an option for improving soil health and maintaining environmental sustainability for intensive agriculture, especially in the tropical climate. Three years lengthy research experiment was performed in arid climate from 2018 to 2020 at research field of Bangladesh Agricultural Research Station (RARS)F, Jamalpur (soil texture belongs to Agro-Ecological Zone (AEZ)-8/9, 24˚56'11''N latitude and 89˚55'54''E longitude and an altitude of 16.46m) to evaluate the effect of CA approaches on energy use efficiency and a streamlined life cycle greenhouse gas (GHG) emission of wheat production. For this, the conservation tillage practices (strip tillage (ST) and minimum tillage (MT)) were adopted in comparison to the conventional farmers' tillage (CT), with retained a fixed level (30 cm) of residue retention. This study examined the relationship between energy consumption and life cycle greenhouse gas (GHG) emission of wheat cultivation in Jamalpur region of Bangladesh. Standard energy equivalents megajoules (MJ) were used to measure energy from different inputs and output, similarly, the global warming potential values for the 100-year timescale and a standard unit kilogram of carbon dioxide equivalent (kg CO₂eq) was used to estimate direct and indirect GHG emissions from the use of on-farm and off-farm inputs. Farm efficiency analysis tool (FEAT) was used to analyze GHG emission and its intensity. A non-parametric data envelopment (DEA) analysis was used to estimate the optimum energy requirement of wheat production. The results showed that the treatment combination having MT with optimum energy inputs is the best suit for cost-effective, sustainable CA practice in wheat cultivation without compromising with the yield during the dry season. A total of 22045.86 MJ ha⁻¹, 22158.82 MJ ha⁻¹, and 23656.63 MJ ha⁻¹ input energy for the practice of ST, MT, and CT was used in wheat production, and output energy was calculated as 158657.40 MJ ha⁻¹, 162070.55 MJ ha⁻¹, and 149501.58 MJ ha⁻¹, respectively; where energy use efficiency/net energy ratio was found to be 7.20, 7.31 and 6.32. Among these, MT is the most effective practice option taken into account in the wheat production process. The optimum energy requirement was found to be 18236.71 MJ ha⁻¹ demonstrating for the practice of MT that if recommendations are followed, 18.7% of input energy can be saved. The total greenhouse gas (GHG) emission was calculated to be 2288 kgCO₂eq ha⁻¹, 2293 kgCO₂eq ha⁻¹ and 2331 kgCO₂eq ha⁻¹, where GHG intensity is the ratio of kg CO₂eq emission per MJ of output energy produced was estimated to be 0.014 kg CO₂/MJ, 0.014 kg CO₂/MJ and 0.015 kg CO₂/MJ in wheat production. Therefore, CA approaches ST practice with 30 cm residue retention was the most effective GHG mitigation option when the net life cycle GHG emission was considered in wheat production in the silt clay loam soil of Bangladesh. In conclusion, the CA approaches being implemented for wheat production involving MT practice have the potential to mitigate global warming potential in Bangladesh to achieve soil carbon footprint, where the life cycle assessment approach needs to be applied to a more diverse range of wheat-based cropping systems.

Keywords: conservation agriculture and tillage, energy use efficiency, life cycle GHG, Bangladesh

Procedia PDF Downloads 102

Authors: Opeyemi Atiba-Oyewo, Taile Y. Leswfi, Maurice S. Onyango, Christian Wolkersdorfer

Abstract:

This paper describes the preparation of surface modified montmorillonite using hexadecyltrimethylammonium bromide (HDTMA-Br) for the removal of vanadium from mine water. The adsorbent before and after adsorption was characterised by Fourier transform infra-red (FT-IR), X-ray diffraction (XRD) and scanning electron microscopy (SEM), while the amount of vanadium adsorbed was determined by ICP-OES. The batch adsorption method was employed using vanadium concentrations in solution ranging from 50 to 320 mg/L and vanadium tailings seepage water from a South African mine. Also, solution pH, temperature and sorbent mass were varied. Results show that the adsorption capacity was affected by solution pH, temperature, sorbent mass and the initial concentration. Electrical conductivity of the mine water before and after adsorption was measured to estimate the total dissolved solids in the mine water. Equilibrium isotherm results revealed that vanadium sorption follows the Freundlich isotherm, indicating that the surface of the sorbent was heterogeneous. The pseudo-second order kinetic model gave the best fit to the kinetic experimental data compared to the first order and Elovich models. The results of this study may be used to predict the uptake efficiency of South Africa montmorillonite in view of its application for the removal of vanadium from mine water. However, the choice of this adsorbent for the uptake of vanadium or other contaminants will depend on the composition of the effluent to be treated.

Keywords: adsorption, vanadium, modified montmorillonite, equilibrium, kinetics, mine water

Procedia PDF Downloads 433

Authors: Nabil Mezhoud

Abstract:

The economic operation of electric energy generating systems is one of the predominant problems in energy systems. Due to the need for better reliability, high energy quality, lower losses, lower cost and a clean environment, the application of renewable and sustainable energy sources, such as wind energy, solar energy, etc., in recent years has become more widespread. In this work, one of a bio-inspired meta-heuristic algorithm inspired by the flashing behavior of fireflies at night called the Firefly Algorithm (FFA) is applied to solve the Optimal Energy Management (OEM) and the environmental index (EI) problems of a micro-grid (MG) operating by Renewable and Sustainable Generation Systems (RSGS). Our main goal is to minimize the nonlinear objective function of an electrical microgrid, taking into account equality and inequality constraints. The FFA approach was examined and tested on a standard MG system composed of different types of RSGS, such as wind turbines (WT), photovoltaic systems (PV), and non-renewable energy, such as fuel cells (FC), micro turbine (MT), diesel generator (DEG) and loads with energy storage systems (ESS). The results are promising and show the effectiveness and robustness of the proposed approach to solve the OEM and the EI problems. The results of the proposed method have been compared and validated with those known references published recently.

Keywords: renewable energy sources, energy management, distributed generator, micro-grids, firefly algorithm

Procedia PDF Downloads 76

Authors: Amany Mohamed, Alaa Balbaa, Magdoline Mishel

Abstract:

Background: Pain in the neck or scapular region is one of the most frequent symptoms in cervical radiculopathy, which is commonly caused by degenerative process in the spine. Purpose: To determine the effect of scapular stabilization exercises in the treatment of chronic neck pain regarding pain and disability and limitation in the range of motion. Patients and Methods: Thirty male and female patients with chronic neck pain were involved. Aged between 30-50 years old. They were randomly assigned into two groups. In group (A), patients received physical therapy program in the form of infrared, transcutaneous electrical nerve stimulation (TENS), Stretching and cervical stabilization exercises. In group (B), patients received scapular stabilization exercises in addition to the same physical therapy program. Treatment was given 3 times a week for 4 weeks. Range of motion of the cervical spine, range of motion of the scapula, neck pain and disability were assessed before and after treatment. Results: There was significant improvement in both groups (A and B) in cervical range of motion, pain and disability. Group (B) showed more significant improvement than group (A) in cervical range of motion and pain and disability. There was no significant improvement in both groups in scapular range of motion. Conclusion: Scapular stabilization exercises should be used as an integral part in the rehabilitation program

Keywords: Neck pain, neck stabilization exercise, scapular stabilization exercise, chronic neck pain

Procedia PDF Downloads 301

Authors: Ramesh P., Aby Joseph

Abstract:

Micro Inverters provide Module Embedded Solution for harvesting energy from small-scale solar photovoltaic (PV) panels. In addition to higher modularity & reliability (25 years of life), the MicroInverter has inherent advantages such as avoidance of long DC cables, eliminates module mismatch losses, minimizes partial shading effect, improves safety and flexibility in installations etc. Due to the above-stated benefits, the renewable energy technology with Solar Photovoltaic (PV) Micro Inverter becomes more widespread in Village Nano Grid application ensuring grid independence for rural communities and areas without access to electricity. While the primary objective of this paper is to discuss the problems related to rural electrification, this concept can also be extended to urban installation with grid connectivity. This work presents a comprehensive analysis of the power circuit design, control methodologies and prototyping of 300Wₚ Single Phase PV Micro Inverter. This paper investigates two different topologies for PV Micro Inverters, based on the first hand on Single Stage Flyback/ Forward PV Micro-Inverter configuration and the other hand on the Double stage configuration including DC-DC converter, H bridge DC-AC Inverter. This work covers Power Decoupling techniques to reduce the input filter capacitor size to buffer double line (100 Hz) ripple energy and eliminates the use of electrolytic capacitors. The propagation of the double line oscillation reflected back to PV module will affect the Maximum Power Point Tracking (MPPT) performance. Also, the grid current will be distorted. To mitigate this issue, an independent MPPT control algorithm is developed in this work to reject the propagation of this double line ripple oscillation to PV side to improve the MPPT performance and grid side to improve current quality. Here, the power hardware topology accepts wide input voltage variation and consists of suitably rated MOSFET switches, Galvanically Isolated gate drivers, high-frequency magnetics and Film capacitors with a long lifespan. The digital controller hardware platform inbuilt with the external peripheral interface is developed using floating point microcontroller TMS320F2806x from Texas Instruments. The firmware governing the operation of the PV Micro Inverter is written in C language and was developed using code composer studio Integrated Development Environment (IDE). In this work, the prototype hardware for the Single Phase Photovoltaic Micro Inverter with Double stage configuration was developed and the comparative analysis between the above mentioned configurations with experimental results will be presented.

Keywords: double line oscillation, micro inverter, MPPT, nano grid, power decoupling

Procedia PDF Downloads 133

Authors: N. Hatraf, l. Merabeti, M. Abbas

Abstract:

The interest in air conditioning using renewable energies is increasing. The Thermal energy produced from the solar energy can be transformed to useful cooling and heating through the thermo chemical or thermo physical processes by using thermally activated energy conversion system. Solid desiccant conditioning systems can represent a reliable alternative solution compared with other thermal cooling technologies. Their basic characteristics refer to the capability to regulate both temperature and humidity of the conditioned space in one side and to its potential in electrical energy saving in the other side. The ambient air contains so much water that very high dehumidification rates are required. For a continuous dehumidification of the process air the water adsorbed on the desiccant material has to be removed, which is done by allowing hot air to flow through the desiccant material (regeneration). Basically, solid desiccant cooling system transfers moisture from the inlet air to the silica gel by using two processes: absorption process and the regeneration process; The silica gel in the desiccant wheel which is the most important device in the system absorbs the moisture from the incoming air to the desiccant material in this case the silica gel, then it changes the heat with an rotary heat exchanger, after that the air passes through an humidifier to have the humidity required before entering to the local. The main aim of this paper is to study how the dehumidification rate, the generation temperature and many other factors influence the efficiency of a solid desiccant system by using TRNSYS software.

Keywords: desiccation, dehumidification, TRNSYS, efficiency

Procedia PDF Downloads 419

Authors: El Mehdi Haily, Lahcen Bih, Mohammed Azrour, Bouchaib Manoun

Abstract:

The effects of xBi₂O₃-yBaO-zP₂O₅ (BBP) glass addition on the sintering, structural, and dielectric properties of BaTiO₃ ceramic (BT) are studied. The BT ceramic was synthesized by the conventional solid-state reaction method while the glasses BaO-Bi₂O₃-P₂O₅ (BBP) were elaborated by melting and quenching process. Different composites BT-xBBP were formed by mixing the BBP glasses with BT ceramic. For each glass composition, where the ratio (x:y:z) is maintained constant, we have developed three composites with different glass weight percentage (x = 2.5, 5, and 7.5 wt %). Addition of the glass helps in better sintering at lower temperatures with the presence of liquid phase at the respective sintering temperatures. The results showed that the sintering temperature decreased from more than 1300°C to 900°C. Density measurements of the composites are performed using the standard Archimedean method with water as medium liquid. It is found that their density and molar volume decrease and increase with glass content, respectively. Raman spectroscopy is used to characterize their structural approach. This technique has allowed the identification of different structural units of phosphate and the characteristic vibration modes of the BT. The electrical properties of the composite samples are carried out by impedance spectroscopy in the frequency range of 10 Hz to 1 MHz under various temperatures from 300 to 473 K. The obtained results show that their dielectric properties depend both on the content of the glass in the composite and the Bi/P ratio in the glasses.

Keywords: phosphate, glasses, composite, Raman spectroscopy, dielectric properties

Procedia PDF Downloads 163

Authors: Sanaz Seraj, Shohre Rouhani

Abstract:

Recently, graphene has gained much attention because of its unique optical, mechanical, electrical, and thermal properties. Graphene has been used as a key material in the technological applications in various areas such as sensors, drug delivery, super capacitors, transparent conductor, and solar cell. It has a superior quenching efficiency for various fluorophores. Based on these unique properties, the optical sensors with graphene materials as the energy acceptors have demonstrated great success in recent years. During quenching, the emission of a fluorophore is perturbed by a quencher which can be a substrate or biomolecule, and due to this phenomenon, fluorophore-quencher has been used for selective detection of target molecules. Among fluorescence dyes, 1,8-naphthalimide is well known for its typical intramolecular charge transfer (ICT) and photo-induced charge transfer (PET) fluorophore, strong absorption and emission in the visible region, high photo stability, and large Stokes shift. Derivatives of 1,8-naphthalimides have found applications in some areas, especially fluorescence sensors. Herein, the fluorescence quenching of graphene oxide has been carried out on a naphthalimide dye as a fluorescent probe model. The quenching ability of graphene oxide on naphthalimide dye was studied by UV-VIS and fluorescence spectroscopy. This study showed that graphene is an efficient quencher for fluorescent dyes. Therefore, it can be used as a suitable candidate sensing platform. To the best of our knowledge, studies on the quenching and absorption of naphthalimide dyes by graphene oxide are rare.

Keywords: fluorescence, graphene oxide, naphthalimide dye, quenching

Procedia PDF Downloads 591

Authors: H. C. Woo, F. Bouanis, C. S. Cojocaur

Abstract:

Graphene, which consists of a single layer of carbon atoms in a honeycomb lattice, is an interesting potential optoelectronic material because of graphene’s high carrier mobility, zero bandgap, and electron–hole symmetry. Graphene can absorb light and convert it into a photocurrent over a wide range of the electromagnetic spectrum, from the ultraviolet to visible and infrared regimes. Over the last several years, a variety of graphene-based photodetectors have been reported, such as graphene transistors, graphene-semiconductor heterojunction photodetectors, graphene based bolometers. It is also reported that there are several physical mechanisms enabling photodetection: photovoltaic effect, photo-thermoelectric effect, bolometric effect, photogating effect, and so on. In this work, we report a simple approach for the realization of graphene based resistive photo-detection devices and the measurements of their photoelectrical response. The graphene were synthesized directly on the glass substrate by novel growth method patented in our lab. Then, the metal electrodes were deposited by thermal evaporation on it, with an electrode length and width of 1.5 mm and 300 μm respectively, using Co to fabricate simple graphene based resistive photosensor. The measurements show that the graphene resistive devices exhibit a photoresponse to the illumination of visible light. The observed re-sistance response was reproducible and similar after many cycles of on and off operations. This photoelectrical response may be attributed not only to the direct photocurrent process but also to the desorption of oxygen. Our work shows that the simple graphene resistive devices have potential in photodetection applications.

Keywords: graphene, resistive sensor, optoelectronics, photoresponse

Procedia PDF Downloads 286

Authors: Ife Elegbeleye, Nnditshedzeni Eric, Regina Maphanga, Femi Elegbeleye, Femi Agunbiade

Abstract:

The global potential of other renewable energy sources such as wind, hydroelectric, bio-mass, and geothermal is estimated to be approximately 13 %, with hydroelectricity constituting a larger percentage. Sunlight provides by far the largest of all carbon-neutral energy sources. More energy from the sunlight strikes the Earth in one hour (4.3 × 1020 J) than all the energy consumed on the planet in a year (4.1 × 1020 J), hence, solar energy remains the most abundant clean, renewable energy resources for mankind. Photovoltaic (PV) devices such as silicon solar cells, dye sensitized solar cells are utilized for harnessing solar energy. Polyene-diphenylaniline organic molecules are important sets of molecules that has stirred many research interest as photosensitizers in TiO₂ semiconductor-based dye sensitized solar cells (DSSCs). The advantages of organic dye molecule over metal-based complexes are higher extinction coefficient, moderate cost, good environmental compatibility, and electrochemical properties. The polyene-diphenylaniline organic dyes with basic configuration of donor-π-acceptor are affordable, easy to synthesize and possess chemical structures that can easily be modified to optimize their photocatalytic and spectral properties. The enormous interest in polyene-diphenylaniline dyes as photosensitizers is due to their fascinating spectral properties which include visible light to near infra-red-light absorption. In this work, density functional theory approach via GPAW software, Avogadro and ASE were employed to study the effect of methoxy functionalized group on the spectral properties of polyene-diphenylaniline dyes and their photons absorbing characteristics in the visible region to near infrared region of the solar spectrum. Our results showed that the two-phenyl based complexes D5 and D7 exhibits maximum absorption peaks at 750 nm and 850 nm, while D9 and D11 with methoxy group shows maximum absorption peak at 800 nm and 900 nm respectively. The highest absorption wavelength is notable for D9 and D11 containing additional polyene and methoxy groups. Also, D9 and D11 chromophores with the methoxy group shows lower energy gap of 0.98 and 0.85 respectively than the corresponding D5 and D7 dyes complexes with energy gap of 1.32 and 1.08. The analysis of their electron injection kinetics ∆Ginject into the band gap of TiO₂ shows that D9 and D11 with the methoxy group has higher electron injection kinetics of -2.070 and -2.030 than the corresponding polyene-diphenylaniline complexes without the addition of polyene group with ∆Ginject values of -2.820 and -2.130 respectively. Our findings suggest that the addition of functionalized group as an extension of the organic complexes results in higher light harvesting efficiencies and bathochromic shift of the absorption spectra to higher wavelength which suggest higher current densities and open circuit voltage in DSSCs. The study suggests that the photocatalytic properties of organic chromophores/complexes with donor-π-acceptor configuration can be enhanced by the addition of functionalized groups.

Keywords: renewable energy resource, solar energy, dye sensitized solar cells, polyene-diphenylaniline organic chromophores

Procedia PDF Downloads 111

Authors: Tatiana G. Smirnova, Stan G. Benjamin

Abstract:

Rapid Update Cycle (RUC) land surface model (LSM) was a land-surface component in several generations of operational weather prediction models at the National Center for Environment Prediction (NCEP) at the National Oceanic and Atmospheric Administration (NOAA). It was designed for short-range weather predictions with an emphasis on severe weather and originally was intentionally simple to avoid uncertainties from poorly known parameters. Nevertheless, the RUC LSM, when coupled with the hourly-assimilating atmospheric model, can produce a realistic evolution of time-varying soil moisture and temperature, as well as the evolution of snow cover on the ground surface. This result is possible only if the soil/vegetation/snow component of the coupled weather prediction model has sufficient skill to avoid long-term drift. RUC LSM was first implemented in the operational NCEP Rapid Update Cycle (RUC) weather model in 1998 and later in the Weather Research Forecasting Model (WRF)-based Rapid Refresh (RAP) and High-resolution Rapid Refresh (HRRR). Being available to the international WRF community, it was implemented in operational weather models in Austria, New Zealand, and Switzerland. Based on the feedback from the US weather service offices and the international WRF community and also based on our own validation, RUC LSM has matured over the years. Also, a sea-ice module was added to RUC LSM for surface predictions over the Arctic sea-ice. Other modifications include refinements to the snow model and a more accurate specification of albedo, roughness length, and other surface properties. At present, RUC LSM is being tested in the regional application of the Unified Forecast System (UFS). The next generation UFS-based regional Rapid Refresh FV3 Standalone (RRFS) model will replace operational RAP and HRRR at NCEP. Over time, RUC LSM participated in several international model intercomparison projects to verify its skill using observed atmospheric forcing. The ESM-SnowMIP was the last of these experiments focused on the verification of snow models for open and forested regions. The simulations were performed for ten sites located in different climatic zones of the world forced with observed atmospheric conditions. While most of the 26 participating models have more sophisticated snow parameterizations than in RUC, RUC LSM got a high ranking in simulations of both snow water equivalent and surface temperature. However, ESM-SnowMIP experiment also revealed some issues in the RUC snow model, which will be addressed in this paper. One of them is the treatment of grid cells partially covered with snow. RUC snow module computes energy and moisture budgets of snow-covered and snow-free areas separately by aggregating the solutions at the end of each time step. Such treatment elevates the importance of computing in the model snow cover fraction. Improvements to the original simplistic threshold-based approach have been implemented and tested both offline and in the coupled weather model. The detailed description of changes to the snow cover fraction and other modifications to RUC soil and snow parameterizations will be described in this paper.

Keywords: land-surface models, weather prediction, hydrology, boundary-layer processes

Procedia PDF Downloads 88

Authors: Iyad M. Muslih, Yehya Abdellatif, Sara Qutishat

Abstract:

Renewable energy and in particular solar photovoltaic energy is emerging as a reasonable power generation source. The intermittent and unpredictable nature of solar energy can represent a serious challenge to the utility grids, specifically at relatively high penetration. To minimize the impact of PV power systems on the grid, self-consumption is encouraged. Self-consumption can be improved by matching the PV power generation with the electrical load consumption profile. This study will focus in studying different load profiles and comparing them to typical solar PV power generation at the selected sites with the purpose of analyzing the mismatch in consumption load profile for different users; residential, commercial, and industrial versus the solar photovoltaic output generation. The PV array orientation can be adjusted to reduce the mismatch effects. The orientation shift produces a corresponding shift in the energy production curve. This shift has a little effect on the mismatch for residential loads due to the fact the peak load occurs at night due to lighting loads. This minor gain does not justify the power production loss associated with the orientation shift. The orientation shift for both commercial and industrial cases lead to valuable decrease in the mismatch effects. Such a design is worth considering for reducing grid penetration. Furthermore, the proposed orientation shift yielded better results during the summer time due to the extended daylight hours.

Keywords: grid impact, HOMER, power mismatch, solar PV energy

Procedia PDF Downloads 604

Authors: Abidi Sourour, Ben Salem Hichem, Zoghlemi Aziza, Mezni Mejid, Nasri Saida

Abstract:

In Tunisia, there is an urgent need to maintain food security by reversing soil degradation and improving crop and livestock productivity. Conservation Agriculture (CA) can be helpful in enhancing crop productivity and soil health. However, the demand for crop residues as animal feed are among the major constraints for the adoption of CA. Thus, the objective of this trial is to test the nutritional value of new forage mixture hays as alternative to cereal residues. Two tri-specific cereal-legume mixture were studied and compared to the classic Vetch-Oat one. They were implemented at farm level in four regions characterized by sub-humi climatic: V70-A15-T15 (Vetch70% - Oat15% -Triticale15%) installed in two sites (Zhir and safasaf), V60-A7-T33 (Vetch60% - Oat7% -Triticale33%) and V70-A30 (Vetch70%-Oat30%). Results revealed a significant variation between mixtures V70-A15-T15 installed at Safsafa, recorded the highest forage yield with 12t DM ha-1 than V60A7T33 and V70A30 installed, respectively in ksar cheikh and Fernana with 11.6 and 11.2.tMSha-1. The same mixture installed in Safsafa gave 22% less yields than the one installed in Safsafa. In fact, the month of March was dry in Z'hir. Moreover, these yields in DM can be comparable to those observed by Yucel and Avci (2009). The CP contents of the samples studied vary significantly between the mixtures (P<0.0003). V70-A15-T15 installed in Safsaf and V70A30 present higher contents of CP (respectively 14.4 and 13.7% DM) compared to the other mixtures. These contents are explained by the high proportion of vetch in the fourth mixture and by the low proportion of weeds in the second. In all cases, the hay produced from these mixtures is significantly richer in protein than that of oats in pure culture (Abdelraheem et al., 2019). The positive correlation between the CP content and the proportion of vetch explains this superior quality. The NDF and ADF contents were similar for all mixtures. These values were similar to those reported in the literature (Abidi and Benyoussef, 2019; Haj-Ayed and al., 2000). In general, the Land Equivalent Ratio (LER) was significantly greater than 1 for the vetch-oat-triticale mixture at Zhiir and Safsafa and also for the vetch-oat a at Fernana, proving that they are more productive in intercropping than in pure culture. For the Ksar Cheikh site, the LER value of the vetch-oat-triticale mixture is maintained at around 1. Proving the absence of the advantage of mixture culture compared to pure culture. This proves the massive presence of weeds interferes with the two partners of the mixture increases. The LER for the vetch-oat mixture reached its maximum in March 13 and decreases in April but remained above 1. This proves that the tutoring power of oats showed itself in a constant way until an advanced stage since the variety used is characterized by very thick stems, protecting it from the risk of lodging. These forages mixture present a promising option, a high nutritional quality that could reduce the use of concentrate and, therefore, the cost of feed. With such feed value, these mixtures allow good animal performance.

Keywords: soybean, lupine, vetch, lamb-ADG, meat

Procedia PDF Downloads 89

Authors: Maryam Shahbazi, Amy B. Cerato

Abstract:

The importance of a systems’ natural frequency (fn) emerges when the vibration force frequency is equivalent to foundation's fn which causes response amplitude (resonance) that may cause irreversible damage to the structure. Several factors such as pile geometry (e.g., length and diameter), soil density, load magnitude, pile condition, and physical structure affect the fn of a soil-pile system; some of these parameters are evaluated in this study. Although experimental and analytical studies have assessed the fn of a soil-pile system, few have included individual and grouped helical piles. Thus, the current study aims to provide quantitative data on dynamic characteristics of helical pile-soil systems from full-scale shake table tests that will allow engineers to predict more realistic dynamic response under motions with variable frequency ranges. To evaluate the fn of single and grouped helical piles in dry dense sand, full-scale shake table tests were conducted in a laminar box (6.7 m x 3.0 m with 4.6 m high). Two different diameters (8.8 cm and 14 cm) helical piles were embedded in the soil box with corresponding lengths of 3.66m (excluding one pile with length of 3.96) and 4.27m. Different configurations were implemented to evaluate conditions such as fixed and pinned connections. In the group configuration, all four piles with similar geometry were tied together. Simulated real earthquake motions, in addition to white noise, were applied to evaluate the wide range of soil-pile system behavior. The Fast Fourier Transform (FFT) of measured time history responses using installed strain gages and accelerometers were used to evaluate fn. Both time-history records using accelerometer or strain gages were found to be acceptable for calculating fn. In this study, the existence of a pile reduced the fn of the soil slightly. Greater fn occurred on single piles with larger l/d ratios (higher slenderness ratio). Also, regardless of the connection type, the more slender pile group which is obviously surrounded by more soil, yielded higher natural frequencies under white noise, which may be due to exhibiting more passive soil resistance around it. Relatively speaking, within both pile groups, a pinned connection led to a lower fn than a fixed connection (e.g., for the same pile group the fn’s are 5.23Hz and 4.65Hz for fixed and pinned connections, respectively). Generally speaking, a stronger motion causes nonlinear behavior and degrades stiffness which reduces a pile’s fn; even more, reduction occurs in soil with a lower density. Moreover, fn of dense sand under white noise signal was obtained 5.03 which is reduced by 44% when an earthquake with the acceleration of 0.5g was applied. By knowing the factors affecting fn, the designer can effectively match the properties of the soil to a type of pile and structure to attempt to avoid resonance. The quantitative results in this study assist engineers in predicting a probable range of fn for helical pile foundations under potential future earthquake, and machine loading applied forces.

Keywords: helical pile, natural frequency, pile group, shake table, stiffness

Procedia PDF Downloads 133

Authors: George Zhou, Yunchan Chen, Candace Chien

Abstract:

Kidney replacement therapy is the current standard of care for end-stage renal diseases. In-center or home hemodialysis remains an integral component of the therapeutic regimen. Arteriovenous fistulas (AVF) make up the vascular circuit through which blood is filtered and returned. Naturally, AVF patency determines whether adequate clearance and filtration can be achieved and directly influences clinical outcomes. Our aim was to build a deep learning model for automated AVF stenosis screening based on the sound of blood flow through the AVF. A total of 311 patients with AVF were enrolled in this study. Blood flow sounds were collected using a digital stethoscope. For each patient, blood flow sounds were collected at 6 different locations along the patient’s AVF. The 6 locations are artery, anastomosis, distal vein, middle vein, proximal vein, and venous arch. A total of 1866 sounds were collected. The blood flow sounds are labeled as “patent” (normal) or “stenotic” (abnormal). The labels are validated from concurrent ultrasound. Our dataset included 1527 “patent” and 339 “stenotic” sounds. We show that blood flow sounds vary significantly along the AVF. For example, the blood flow sound is loudest at the anastomosis site and softest at the cephalic arch. Contextualizing the sound with location metadata significantly improves classification performance. How to encode and incorporate categorical metadata is an active area of research1. Herein, we study ordinal (i.e., integer) encoding schemes. The numerical representation is concatenated to the flattened feature vector. We train a vision transformer (ViT) on spectrogram image representations of the sound and demonstrate that using scalar multiples of our integer encodings improves classification performance. Models are evaluated using a 10-fold cross-validation procedure. The baseline performance of our ViT without any location metadata achieves an AuROC and AuPRC of 0.68 ± 0.05 and 0.28 ± 0.09, respectively. Using the following encodings of Artery:0; Arch: 1; Proximal: 2; Middle: 3; Distal 4: Anastomosis: 5, the ViT achieves an AuROC and AuPRC of 0.69 ± 0.06 and 0.30 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 10; Proximal: 20; Middle: 30; Distal 40: Anastomosis: 50, the ViT achieves an AuROC and AuPRC of 0.74 ± 0.06 and 0.38 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 100; Proximal: 200; Middle: 300; Distal 400: Anastomosis: 500, the ViT achieves an AuROC and AuPRC of 0.78 ± 0.06 and 0.43 ± 0.11. respectively. Interestingly, we see that using increasing scalar multiples of our integer encoding scheme (i.e., encoding “venous arch” as 1,10,100) results in progressively improved performance. In theory, the integer values do not matter since we are optimizing the same loss function; the model can learn to increase or decrease the weights associated with location encodings and converge on the same solution. However, in the setting of limited data and computation resources, increasing the importance at initialization either leads to faster convergence or helps the model escape a local minimum.

Keywords: arteriovenous fistula, blood flow sounds, metadata encoding, deep learning

Procedia PDF Downloads 87