Search results for: top load washing machine

Authors: Sky Chou, Joseph C. Chen

Abstract:

This paper focuses on using six sigma methodologies to reach the desired shrinkage of a manufactured high-density polyurethane (HDPE) part produced by the injection molding machine. It presents a case study where the correct shrinkage is required to reduce or eliminate defects and to improve the process capability index Cp and Cpk for an injection molding process. To improve this process and keep the product within specifications, the six sigma methodology, design, measure, analyze, improve, and control (DMAIC) approach, was implemented in this study. The six sigma approach was paired with the Taguchi methodology to identify the optimized processing parameters that keep the shrinkage rate within the specifications by our customer. An L9 orthogonal array was applied in the Taguchi experimental design, with four controllable factors and one non-controllable/noise factor. The four controllable factors identified consist of the cooling time, melt temperature, holding time, and metering stroke. The noise factor is the difference between material brand 1 and material brand 2. After the confirmation run was completed, measurements verify that the new parameter settings are optimal. With the new settings, the process capability index has improved dramatically. The purpose of this study is to show that the six sigma and Taguchi methodology can be efficiently used to determine important factors that will improve the process capability index of the injection molding process.

Keywords: injection molding, shrinkage, six sigma, Taguchi parameter design

Procedia PDF Downloads 178

Authors: Colin Smith, Linsey S Passarella

Abstract:

Due to the proliferation and decentralized nature of academic publication, no widely accepted scheme exists for organizing papers by their scientific field of study (FoS) to the author’s best knowledge. While many academic journals require author provided keywords for papers, these keywords range wildly in scope and are not consistent across papers, journals, or field domains, necessitating alternative approaches to paper classification. Past attempts to perform field-of-study (FoS) classification on scientific texts have largely used a-hierarchical FoS schemas or ignored the schema’s inherently hierarchical structure, e.g. by compressing the structure into a single layer for multi-label classification. In this paper, we introduce an application of a Layered Neural Network (LNN) to the problem of performing supervised hierarchical classification of scientific fields of study (FoS) on research papers. In this approach, paper embeddings from a pretrained language model are fed into a top-down LNN. Beginning with a single neural network (NN) for the highest layer of the class hierarchy, each node uses a separate local NN to classify the subsequent subfield child node(s) for an input embedding of concatenated paper titles and abstracts. We compare our LNN-FOS method to other recent machine learning methods using the Microsoft Academic Graph (MAG) FoS hierarchy and find that the LNN-FOS offers increased classification accuracy at each FoS hierarchical level.

Keywords: hierarchical classification, layer neural network, scientific field of study, scientific taxonomy

Procedia PDF Downloads 132

Authors: Robin Molinier

Abstract:

Industrial symbiosis (I.S) is the realization of Industrial Ecology (I.E) principles in production systems in function. I.S consists in the use of waste materials, fatal energy, recirculated utilities and infrastructure/service sharing as resources for production. Environmental benefits can be achieved from resource conservation but economic profitability is required by the participating actors. I.S indeed involves several actors with their own objectives and resources so that each one must be satisfied by ex-ante arrangements to commit toward I.S execution (investments and transactions). Following the Resource-Based View of transactions we build a modular framework to assess global I.S profitability and to specify each actor’s contributions to costs and benefits in line with their resource endowments and performance requirements formulations. I.S projects specificities implied by the need for customization (asset specificity, non-homogeneity) induce the use of long-term contracts for transactions following Transaction costs economics arguments. Thus we propose first a taxonomy of costs and value drivers for I.S and an assignment to each actor of I.S specific risks that we identified as load profiles mismatch, quality problems and value fluctuations. Then appropriate contractual guidelines (pricing, cost sharing and warranties) that support mutual profitability are derived from the detailed identification of contributions by the cost-benefits model. This analytical framework helps identifying what points to focus on when bargaining over contracting for transactions and investments. Our methodology is applied to I.S archetypes raised from a literature survey on eco-industrial parks initiatives and practitioners interviews.

Keywords: contracts, cost-benefit analysis, industrial symbiosis, risks

Procedia PDF Downloads 338

Authors: Farhad Salek, Shahaboddin Resalati

Abstract:

The production of electric vehicles (EVs) featuring lithium-ion battery technology has substantially escalated over the past decade, demonstrating a steady and persistent upward trajectory. The imminent retirement of electric vehicle (EV) batteries after approximately eight years underscores the critical need for their redirection towards recycling, a task complicated by the current inadequacy of recycling infrastructures globally. A potential solution for such concerns involves extending the operational lifespan of electric vehicle (EV) batteries through their utilization in stationary energy storage systems during secondary applications. Such adoptions, however, require addressing the safety concerns associated with batteries’ knee points and thermal runaways. This paper develops an accurate mathematical model representative of the second-life battery packs from a cell-to-pack scale using an equivalent circuit model (ECM) methodology. Neural network algorithms are employed to forecast the degradation parameters based on the EV batteries' aging history to develop a degradation model. The degradation model is integrated with the ECM to reflect the impacts of the cycle aging mechanism on battery parameters during operation. The developed model is tested under real-life load profiles to evaluate the life span of the batteries in various operating conditions. The methodology and the algorithms introduced in this paper can be considered the basis for Battery Management System (BMS) design and techno-economic analysis of such technologies.

Keywords: second life battery, electric vehicles, degradation, neural network

Procedia PDF Downloads 64

Authors: Zahow Muoftah

Abstract:

Traditional manual visual grading of fruits has been one of the agricultural industry’s major challenges due to its laborious nature as well as inconsistency in the inspection and classification process. The main requirements for computer vision and visual processing are some effective techniques for identifying defects and estimating defect areas. Automated defect detection using computer vision and machine learning has emerged as a promising area of research with a high and direct impact on the visual inspection domain. Grading, sorting, and disease detection are important factors in determining the quality of fruits after harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have used computer vision to evaluate the quality level of fruits during post-harvest. Many studies have been conducted to identify diseases and pests that affect the fruits of agricultural crops. However, most previous studies concentrated solely on the diagnosis of a lesion or disease. This study focused on a comprehensive study to identify pests and diseases of apple and banana fruits using detection and classification defects on Banana and Apples by Computer Vision. As a result, the current article includes research from these domains as well. Finally, various pattern recognition techniques for detecting apple and banana defects are discussed.

Keywords: computer vision, banana, apple, detection, classification

Procedia PDF Downloads 104

Authors: David Halley, Tyra Oseng-Rees, Luca Pagano, Juan A Ferriz-Papi

Abstract:

Recycled glass material is made from 100% recycled bottle glass and consumes less energy than re-melt technology. It also uses no additives in the manufacturing process allowing the recycled glass material, in principal, to go back to the recycling stream after end-of-use, contributing to the circular economy with a low ecological impact. The aim of this paper is to investigate the procedure for testing the recycled glass material for impact resistance, so it can be applied to pavements and other surfaces which are at risk of impact during service. A review of different impact test procedures for construction materials was undertaken, comparing methodologies and international standards applied to other materials such as natural stone, ceramics and glass. A drop weight impact testing machine was designed and manufactured in-house to perform these tests. As a case study, samples of the recycled glass material were manufactured with two different thicknesses and tested. The impact energy was calculated theoretically, obtaining results with 5 and 10 J. The results on the material were subsequently discussed. Improvements on the procedure can be made using high speed video technology to calculate velocity just before and immediately after the impact to know the absorbed energy. The initial results obtained in this procedure were positive although repeatability needs to be developed to obtain a correlation of results and finally be able to validate the procedure. The experiment with samples showed the practicality of this procedure and application to the recycled glass material impact testing although further research needs to be developed.

Keywords: construction materials, drop weight impact, impact testing, recycled glass

Procedia PDF Downloads 294

Authors: Srutirekha Giri, Manoranjan Sahoo, Anuradha Das, Pravanjan Mallick, Biswajit Mallick

Abstract:

Ion Beam (IB) technique is a very powerful experimental technique for both material synthesis and material modifications. In this work, 3MeV proton beam was generated using the 3MV Tandem machine of the Institute of Physics, Bhubaneswar and extracted into air for the irradiation-induced modification purpose[1]. The polymeric material can be modeled for a three-phase system viz. crystalline(I), amorphous(II) and mesomorphic(III). So far, our knowledge is concerned. There are only few techniques reported for the synthesis of this third-phase(III) of polymer. The IB induced technique is one of them and has been reported very recently [2-4]. It was observed that by irradiating polyethylene terephthalate (PET) fiber at very low proton fluence, 10¹⁰ - 10¹² p/s, possess 2D mesophase structure. This was confirmed using X-ray diffraction technique. A low-intensity broad peak was observed at small angle of about 2θ =6º, when the fiber axis was mounted parallel to the X-ray direction. Such peak vanished in the diffraction spectrum when the fiber axis was mounted perpendicular to the beam direction. The appearance of this extra peak in a particular orientation confirms that the phase is 2-dimensionally oriented (mesophase). It is well known that the mesophase is a 2-dimensionally ordered structure but 3-dimensionally disordered. Again, the crystallite of the mesophase peak particle was measured about 3nm. The MeV proton-induced 2D mesophase patterning of nanocrystallites (3nm) of PET due to irradiation was observed within the above low fluence range and failed in high proton fluence. This is mainly due to the breaking of crystallites, radiation-induced thermal degradation, etc.

Keywords: Ion irradiation, mesophase, nanocrystallites, polymer

Procedia PDF Downloads 198

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 16

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: stacking, multi-layers, ensemble, multi-class

Procedia PDF Downloads 268

Authors: Shohei Maruyama, Yasuo Matsuyama, Sachiyo Aburatani

Abstract:

The development of the method to annotate unknown gene functions is an important task in bioinformatics. One of the approaches for the annotation is The identification of the metabolic pathway that genes are involved in. Gene expression data have been utilized for the identification, since gene expression data reflect various intracellular phenomena. However, it has been difficult to estimate the gene function with high accuracy. It is considered that the low accuracy of the estimation is caused by the difficulty of accurately measuring a gene expression. Even though they are measured under the same condition, the gene expressions will vary usually. In this study, we proposed a feature extraction method focusing on the variability of gene expressions to estimate the genes' metabolic pathway accurately. First, we estimated the distribution of each gene expression from replicate data. Next, we calculated the similarity between all gene pairs by KL divergence, which is a method for calculating the similarity between distributions. Finally, we utilized the similarity vectors as feature vectors and trained the multiclass SVM for identifying the genes' metabolic pathway. To evaluate our developed method, we applied the method to budding yeast and trained the multiclass SVM for identifying the seven metabolic pathways. As a result, the accuracy that calculated by our developed method was higher than the one that calculated from the raw gene expression data. Thus, our developed method combined with KL divergence is useful for identifying the genes' metabolic pathway.

Keywords: metabolic pathways, gene expression data, microarray, Kullback–Leibler divergence, KL divergence, support vector machines, SVM, machine learning

Procedia PDF Downloads 401

Authors: Yu-Chen Hsu, Kuang C. Lin

Abstract:

The artificial lung called extracorporeal membrane oxygenation (ECMO) is an important medical machine that supports persons whose heart and lungs dysfunction. Previously, investigation of steady deoxygenated blood flows passing through hollow fibers for oxygen transport was carried out experimentally and computationally. The present study computationally analyzes the effect of biological pulsatile flow on the oxygen transport in blood. A 2-D model with a pulsatile flow condition is employed. The power law model is used to describe the non-Newtonian flow and the Hill equation is utilized to simulate the oxygen saturation of hemoglobin. The dimensionless parameters for the physical model include Reynolds numbers (Re), Womersley parameters (α), pulsation amplitudes (A), Sherwood number (Sh) and Schmidt number (Sc). The present model with steady-state flow conditions is well validated against previous experiment and simulations. It is observed that pulsating flow amplitudes significantly influence the velocity profile, pressure of oxygen (PO2), saturation of oxygen (SO2) and the oxygen mass transfer rates (m ̇_O2). In comparison between steady-state and pulsating flows, our findings suggest that the consideration of pulsating flow in the computational model is needed when Re is raised from 2 to 10 in a typical range for flow in artificial lung.

Keywords: artificial lung, oxygen transport, non-Newtonian flows, pulsating flows

Procedia PDF Downloads 311

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

In recent years, there has been a desire to forecast student academic achievement prior to graduation. This is to help them improve their grades, particularly for individuals with poor performance. The goal of this study is to employ supervised learning techniques to construct a predictive model for student academic achievement. Many academics have already constructed models that predict student academic achievement based on factors such as smoking, demography, culture, social media, parent educational background, parent finances, and family background, to name a few. This feature and the model employed may not have correctly classified the students in terms of their academic performance. This model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester as a prerequisite to predict if the student will perform well in future on related courses. The model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost, returning a 96.7% accuracy. This model is available as a desktop application, allowing both instructors and students to benefit from user-friendly interfaces for predicting student academic achievement. As a result, it is recommended that both students and professors use this tool to better forecast outcomes.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 96

Authors: Iram Zahra

Abstract:

Friction and wear properties of multilayer graphene coatings (MLG) on nickel substrate were investigated at the macroscale, and different failure mechanisms working at the interface of nickel-graphene coatings were evaluated. Multilayer graphene coatings were produced on a nickel substrate using the atmospheric chemical vapour deposition (CVD) technique. Wear tests were performed on the pin-on-disk tribometer apparatus under dry air conditions, and using the saltwater solution, distilled water, and mineral oil lubricants and counterparts used in these wear tests were fabricated of stainless steel, chromium, and silicon nitride. The wear test parameters such as rotational speed, wear track diameter, temperature, relative humidity, and load were 60 rpm, 6 mm, 22˚C, 45%, and 2N, respectively. To analyse the friction and wear behaviour, coefficient of friction (COF) vs time curves were plotted, and the sliding surfaces of the samples and counterparts were examined using the optical microscope. Results indicated that graphene-coated nickel in mineral oil lubrication and dry conditions gave the minimum average value of COP (0.05) and wear track width ( ̴151 µm) against the three different types of counterparts. In contrast, uncoated nickel samples indicated a maximum wear track width ( ̴411 µm) and COF (0.5). Thorough investigation and analysis concluded that graphene-coated samples have two times lower COF and three times lower wear than the bare nickel samples. Furthermore, mechanical failures were significantly lower in the case of graphene-coated nickel. The overall findings suggested that multilayer graphene coatings have drastically decreased wear and friction on nickel substrate at the macroscale under various lubricating conditions and against different counterparts.

Keywords: friction, lubricity, multilayer graphene, sliding, wear

Procedia PDF Downloads 138

Authors: Sai Sankalp Vemavarapu

Abstract:

This paper discusses the application of machine learning in the field of transportation engineering for predicting engineering properties of pavement more accurately and efficiently. Predicting the elastic properties aid us in assessing the current road conditions and taking appropriate measures to avoid any inconvenience to commuters. This improves the longevity and sustainability of the pavement layer while reducing its overall life-cycle cost. As an example, we have implemented differential evolution (DE) in the back-calculation of the elastic modulus of multi-layered pavement. The proposed DE global optimization back-calculation approach is integrated with a forward response model. This approach treats back-calculation as a global optimization problem where the cost function to be minimized is defined as the root mean square error in measured and computed deflections. The optimal solution which is elastic modulus, in this case, is searched for in the solution space by the DE algorithm. The best DE parameter combinations and the most optimum value is predicted so that the results are reproducible whenever the need arises. The algorithm’s performance in varied scenarios was analyzed by changing the input parameters. The prediction was well within the permissible error, establishing the supremacy of DE.

Keywords: cost function, differential evolution, falling weight deflectometer, genetic algorithm, global optimization, metaheuristic algorithm, multilayered pavement, pavement condition assessment, pavement layer moduli back calculation

Procedia PDF Downloads 163

Authors: Almutasim Billa A. Alanazi, Hal S. Tharp

Abstract:

Safe performance and efficient energy consumption are essential factors for designing a control system. This paper presents a reinforcement learning (RL) model that can be applied to control applications to improve safety and reduce energy consumption. As hardware constraints and environmental disturbances are imprecise and unpredictable, conventional control methods may not always be effective in optimizing control designs. However, RL has demonstrated its value in several artificial intelligence (AI) applications, especially in the field of control systems. The proposed model intelligently monitors a system's success by observing the rewards from the environment, with positive rewards counting as a success when the controlled reference is within the desired operating zone. Thus, the model can determine whether the system is safe to continue operating based on the designer/user specifications, which can be adjusted as needed. Additionally, the controller keeps track of energy consumption to improve energy efficiency by enabling the idle mode when the controlled reference is within the desired operating zone, thus reducing the system energy consumption during the controlling operation. Water temperature control for a hydroponic system is taken as a case study for the RL model, adjusting the variance of disturbances to show the model’s robustness and efficiency. On average, the model showed safety improvement by up to 15% and energy efficiency improvements by 35%- 40% compared to a traditional RL model.

Keywords: control system, hydroponics, machine learning, reinforcement learning

Procedia PDF Downloads 184

Authors: Gintarė Sauliutė, Gintaras Svecevičius

Abstract:

Landfill leachates contain a number of persistent pollutants, including heavy metals. They have the ability to spread in ecosystems and accumulate in fish which most of them are classified as top-consumers of trophic chains. Fish are freely swimming organisms; but perhaps, due to their species-specific ecological and behavioral properties, they often prefer the most suitable biotopes and therefore, did not avoid harmful substances or environments. That is why it is necessary to evaluate the persistent pollutant dispersion in hydroecosystem using fish tissue metal concentration. In hydroecosystems of hybrid type (e.g. river-pond-river) the distance from the pollution source could be a perfect indicator of such a kind of metal distribution. The studies were carried out in the Kairiai landfill neighboring hybrid-type ecosystem which is located 5 km east of the Šiauliai City. Fish tissue (gills, liver, and muscle) metal concentration measurements were performed on two types of ecologically-different fishes according to their feeding characteristics: benthophagous (Gibel carp, roach) and predatory (Northern pike, perch). A number of mathematical models (linear, non-linear, using log and other transformations) have been applied in order to identify the most satisfactorily description of the interdependence between fish tissue metal concentration and the distance from the pollution source. However, the only one log-multiple regression model revealed the pattern that the distance from the pollution source is closely and positively correlated with metal concentration in all predatory fish tissues studied (gills, liver, and muscle).

Keywords: bioaccumulation in fish, heavy metals, hydroecosystem, landfill leachate, mathematical model

Procedia PDF Downloads 285

Authors: Yong-Sung Kim, Je-Seok Shin, Ho-Jun Jo, Jin-O Kim

Abstract:

Home Energy Management System (HEMS) which makes the residential consumers contribute to the demand response is attracting attention in recent years. An aim of HEMS is to minimize their electricity cost by controlling the use of their appliances according to electricity price. The use of appliances in HEMS may be affected by some conditions such as external temperature and electricity price. Therefore, the user’s usage pattern of appliances should be modeled according to the external conditions, and the resultant usage pattern is related to the user’s comfortability on use of each appliances. This paper proposes a methodology to model the usage pattern based on the historical data with the copula function. Through copula function, the usage range of each appliance can be obtained and is able to satisfy the appropriate user’s comfort according to the external conditions for next day. Within the usage range, an optimal scheduling for appliances would be conducted so as to minimize an electricity cost with considering user’s comfort. Among the home appliance, electric heater (EH) is a representative appliance which is affected by the external temperature. In this paper, an optimal scheduling algorithm for an electric heater (EH) is addressed based on the method of branch and bound. As a result, scenarios for the EH usage are obtained according to user’s comfort levels and then the residential consumer would select the best scenario. The case study shows the effects of the proposed algorithm compared with the traditional operation of the EH, and it also represents impacts of the comfort level on the scheduling result.

Keywords: load scheduling, usage pattern, user’s comfort, copula function, branch and bound, electric heater

Procedia PDF Downloads 582

Authors: Paolo Fantozzi, Luigi Laura, Umberto Nanni

Abstract:

The problem of Entity relation discovery in structured data, a well covered topic in literature, consists in searching within unstructured sources (typically, text) in order to find connections among entities. These can be a whole dictionary, or a specific collection of named items. In many cases machine learning and/or text mining techniques are used for this goal. These approaches might be unfeasible in computationally challenging problems, such as processing massive data streams. A faster approach consists in collecting the cooccurrences of any two words (entities) in order to create a graph of relations - a cooccurrence graph. Indeed each cooccurrence highlights some grade of semantic correlation between the words because it is more common to have related words close each other than having them in the opposite sides of the text. Some authors have used sliding windows for such problem: they count all the occurrences within a sliding windows running over the whole text. In this paper we generalise such technique, coming up to a Weighted-Distance Sliding Window, where each occurrence of two named items within the window is accounted with a weight depending on the distance between items: a closer distance implies a stronger evidence of a relationship. We develop an experiment in order to support this intuition, by applying this technique to a data set consisting in the text of the Bible, split into verses.

Keywords: cooccurrence graph, entity relation graph, unstructured text, weighted distance

Procedia PDF Downloads 149

Authors: Chandra Gupt Porwal

Abstract:

Excessive vibration means increased wear, increased repair efforts, bad product selection & quality and high energy consumption. This may be sometimes experienced by cavitation or suction/discharge re-circulation which could occur only when net positive suction head available NPSHA drops below the net positive suction head required NPSHR. Cavitation can cause axial surging if it is excessive, will damage mechanical seals, bearings, possibly other pump components frequently and shorten the life of the impeller. Efforts have been made to explain Suction Energy (SE), Specific Speed (Ns), Suction Specific Speed (Nss), NPSHA, NPSHR & their significance, possible reasons of cavitation /internal re-circulation, its diagnostics and remedial measures to arrest and prevent cavitation in this paper. A case study is presented by the author highlighting that the root cause of unwanted noise and vibration is due to cavitation, caused by high specific speeds or inadequate net- positive suction head available which results in damages to material surfaces of impeller & suction bells and degradation of machine performance, its capacity and efficiency too. The author strongly recommends revisiting the technical specifications of CW pumps to provide sufficient NPSH margin ratios > 1.5, for future projects and Nss be limited to 8500 -9000 for cavitation free operation.

Keywords: best efficiency point (BEP), net positive suction head NPSHA, NPSHR, specific speed NS, suction specific speed NSS

Procedia PDF Downloads 252

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 117

Authors: T. Costa, D. Narvaez, K. Melo, M. Villalva

Abstract:

Installation of micro-generators based on renewable energy in power distribution system has increased in recent years, with the main renewable sources being solar and wind. Due to the intermittent nature of renewable energy sources, such micro-generators produce time-varying energy which does not correspond at certain times of the day to the peak energy consumption of end users. For this reason, the use of energy storage units next to the grid contributes to the proper leveling of the buses’ voltage level according to Brazilian energy quality standards. In this work, the effect of the addition of a photovoltaic solar generator and a store of energy in the busbar voltages of an electric system is analyzed. The consumption profile is defined as the average hourly use of appliances in a common residence, and the generation profile is defined as a function of the solar irradiation available in a locality. The power summation method is validated with analytical calculation and is used to calculate the modules and angles of the voltages in the buses of an electrical system based on the IEEE standard, at each hour of the day and with defined load and generation profiles. The results show that bus 5 presents the worst voltage level at the power consumption peaks and stabilizes at the appropriate range with the inclusion of the energy storage during the night time period. Solar generator maintains improvement of the voltage level during the period when it receives solar irradiation, having peaks of production during the 12 pm (without exceeding the appropriate maximum levels of tension).

Keywords: energy storage, power distribution system, solar generator, voltage level

Procedia PDF Downloads 140

Authors: Guliz Kolburan

Abstract:

Juvenile delinquency studies has a special place and importance in criminality researches. Young adolescents, have not reached psychological, mental and physical maturity, and they cannot understand their roles and duties in society. In this case, if such an adolescent turns into a crime machine as a gang leader, he has the least responsibility of this result. All institutions, like family, school, community and the state as a whole have duties and responsibilities in this regard. While planning the studies about prevention of juvenile delinquency, all institutions related with the development of the children, should be involved in the center of the study. So that effective goals for prevention studies can be determined only in this way. Most of youth who commit homicide feel no attachment to anybody or society except for themselves. Children who committed homicide generally developed defense mechanisms about their guilt, sadness, fear and anger. For this reason, treatment of these children should be based on the awareness of these feelings and copying with them. In the movie, events making the youth realize his own feelings and responsibilities were studied from a theoretical perspective. In this study, some of the dialogs and the scenes in the movie were analyzed and the factors cause the young gang leader to be drawn to crime were evaluated in terms of the science of psychology. The aim of this study is to analyze the process of the youth to being drawn into criminal behavior in terms of social and emotional developmental phases in a theoretical perspective via the movie produced in 2005 (94. Min.). The method of this study is discourse analysis.

Keywords: crime, child, evaluation (development), psychology

Procedia PDF Downloads 444

Authors: Abhinav Chaturvedi, Joohi Chaturvedi, Renu Chaturvedi

Abstract:

With rapid urbanization and growth of population, more buildings are require to be constructed to meet the increasing demand of the shelter. 80 % of the world population is living in developing countries, but the adequate energy supplied to only 30% of it. In India situation get little more difficult as majority of the villages of India are still deprived of energy. 1/3 of the Indian household does not have energy supply. So there is big gap between energy demand and supply. Moreover India is producing around 65 % of the energy from Non – Renewable sources and 25 % of the Energy is imported in the form of oil and gas and only 10% of the total, is generated from other sources like solar power, wind power etc. Present modern structures are big energy consumers as they are consuming 40 % of the total energy in providing comfort conditions to the users, in from of heating and cooling,5 % in Building Construction, 20 % in transportation and 20 % in industrial process and 10 % in other processes. If we minimize this Heating and Cooling and lighting load of the building we can conserve huge amount of energy for the future. In history, buildings do not have artificial systems of cooling or heating. These buildings, especially in Hadoti Region which have Semi Arid Climatic conditions, are provided with Solar Passive Design Techniques that is the reason of comfort inside the buildings. So if we use some appropriate elements of these heritage structures, in our present age building design we can find some certain solution to energy crises. Present paper describes Various Solar Passive design techniques used in past, and the same could be used in present to reduce the consumption of energy.

Keywords: energy conservation, Hadoti region, solar passive design techniques , semi - arid climatic condition

Procedia PDF Downloads 472

Authors: A. Kampker, K. Kreisköther, C. Reinders

Abstract:

Since additive manufacturing technologies constantly advance, the use of this technology in mold making seems reasonable. Many manufacturers of additive manufacturing machines, however, do not offer any suggestions on how to parameterize the machine to achieve optimal results for mold making. The purpose of this research is to determine the interdependencies of different materials and parameters within the PolyJet process by using design of experiments (DoE), to additively manufacture molds, e.g. for thermoforming and injection molding applications. Therefore, the general requirements of thermoforming molds, such as heat resistance, surface quality and hardness, have been identified. Then, different materials and parameters of the PolyJet process, such as the orientation of the printed part, the layer thickness, the printing mode (matte or glossy), the distance between printed parts and the scaling of parts, have been examined. The multifactorial analysis covers the following properties of the printed samples: Tensile strength, tensile modulus, bending strength, elongation at break, surface quality, heat deflection temperature and surface hardness. The key objective of this research is that by joining the results from the DoE with the requirements of the mold making, optimal and tailored molds can be additively manufactured with the PolyJet process. These additively manufactured molds can then be used in prototyping processes, in process testing and in small to medium batch production.

Keywords: additive manufacturing, design of experiments, mold making, PolyJet, 3D-Printing

Procedia PDF Downloads 254

Authors: A. Driouiche, S. Mohareb, A. Hadfi

Abstract:

In Morocco’s Agadir region, the reuse of treated wastewater for irrigation of green spaces has faced the problem of scaling of the pipes of these waters. This research paper aims at studying the phenomenon of scaling caused by the treated wastewater from the Mzar sewage treatment plant. These waters are used in the irrigation of golf turf for the Ocean Golf Resort. Ocean Golf, located about 10 km from the center of the city of Agadir, is one of the most important recreation centers in Morocco. The course is a Belt Collins design with 27 holes, and is quite open with deep challenging bunkers. The formation of solid deposits in the irrigation systems has led to a decrease in their lifetime and, consequently, a loss of load and performance. Thus, the sprinklers used in golf turf irrigation are plugged in the first weeks of operation. To study this phenomenon, the wastewater used for the irrigation of the golf turf was taken and analyzed at various points, and also samples of scale formed in the circuits of the passage of these waters were characterized. This characterization of the scale was performed by X-ray fluorescence spectrometry, X-ray diffraction (XRD), thermogravimetric analysis (TGA), differential thermal analysis (DTA), and scanning electron microscopy (SEM). The results of the physicochemical analysis of the waters show that they are full of bicarbonates (653 mg/L), chloride (478 mg/L), nitrate (412 mg/L), sodium (425 mg/L) and calcium (199mg/L). Their pH is slightly alkaline. The analysis of the scale reveals that it is rich in calcium and phosphorus. It is formed of calcium carbonate (CaCO₃), silica (SiO₂), calcium silicate (Ca₂SiO₄), hydroxylapatite (Ca₁₀P₆O₂₆), calcium carbonate and phosphate (Ca₁₀(PO₄) 6CO₃) and silicate calcium and magnesium (Ca₅MgSi₃O₁₂).

Keywords: Agadir, irrigation, scaling water, wastewater

Procedia PDF Downloads 118

Authors: Tohid Rahimi, Yahya Naderi, Babak Yousefi, Seyed Hossein Hoseini

Abstract:

Today’s modern interconnected power system is highly complex in nature. In this, one of the most important requirements during the operation of the electric power system is the reliability and security. Power and frequency oscillation damping mechanism improve the reliability. Because of power system stabilizer (PSS) low speed response against of major fault such as three phase short circuit, FACTs devise that can control the network condition in very fast time, are becoming popular. However, FACTs capability can be seen in a major fault present when nonlinear models of FACTs devise and power system equipment are applied. To realize this aim, the model of multi-machine power system with FACTs controller is developed in MATLAB/SIMULINK using Sim Power System (SPS) blockiest. Among the FACTs device, Static synchronous series compensator (SSSC) due to high speed changes its reactance characteristic inductive to capacitive, is effective power flow controller. Tuning process of controller parameter can be performed using different method. However, Genetic Algorithm (GA) ability tends to use it in controller parameter tuning process. In this paper, firstly POD controller is used to power oscillation damping. But in this station, frequency oscillation dos not has proper damping situation. Therefore, FOD controller that is tuned using GA is using that cause to damp out frequency oscillation properly and power oscillation damping has suitable situation.

Keywords: power oscillation damping (POD), frequency oscillation damping (FOD), Static synchronous series compensator (SSSC), Genetic Algorithm (GA)

Procedia PDF Downloads 474

Authors: Calassandra Nwokoro

Abstract:

Introduction: The nursing profession requires a lot of commitment, effort, and time to efficiently manage patients and provide them quality healthcare services, this work load may eventually cause the nurses to become burned out and experience psychological distress. This study assessed the prevalence of burnout, risk factors, and the coping strategies among nurses working in Lagos University Teaching Hospital (LUTH), Lagos state, Nigeria. Methodology: A descriptive cross-sectional study design was conducted among 308 nurses working in LUTH. Simple random sampling was used in selection of study respondents. The questionnaire comprised three parts; the sociodemographic characteristics of the respondents, the extent of burnout syndrome using the Maslach Burnout Inventory, and the coping strategies used among the respondents using the BRIEF-COPE Inventory. Results: This study revealed relatively high levels of burnout among the nurses in LUTH with a prevalence of 16.9%, 31.2% and 20.1% for high emotional exhaustion, high depersonalization and reduced professional accomplishment respectively. It also showed that burnout was significantly associated with long working hours. Religion was found to be the most commonly used coping strategy overall, while emotional support was the most frequently used coping strategy among nurses who had burnout. Conclusion: This study has revealed a relatively high prevalence of burnout among the nurses in Lagos University Teaching Hospital. In order to minimize the negative health impacts of burnout, the government should collaborate with psychologists and psychiatrists to implement regular stress management and stress inoculation programs for nurses and other health professionals in the country.

Keywords: burnout, nurses, coping strategies, healthcare

Procedia PDF Downloads 80

Authors: Himanshu J. Bahirat, Apoorva S. Janawlekar

Abstract:

Plasma actuators are essential for aerodynamic flow separation control due to their lack of mechanical parts, lightweight, and high response frequency, which have numerous applications in hypersonic or supersonic aircraft. The working of these actuators is based on the formation of a low-temperature plasma between a pair of parallel electrodes by the application of a high-voltage AC signal across the electrodes, after which air molecules from the air surrounding the electrodes are ionized and accelerated through the electric field. The high-frequency operation is required in dielectric discharge barriers to ensure plasma stability. To carry out flow separation control in a hypersonic flow, the optimal design and construction of a power supply to generate dielectric barrier discharges is carried out in this paper. In this paper, it is aspired to construct a simplified circuit topology to emulate the dielectric barrier discharge and study its various frequency responses. The power supply can generate high voltage pulses up to 20kV at the repetitive frequency range of 20-50kHz with an input power of 500W. The power supply has been designed to be short circuit proof and can endure variable plasma load conditions. Its general outline is to charge a capacitor through a half-bridge converter and then later discharge it through a step-up transformer at a high frequency in order to generate high voltage pulses. After simulating the circuit, the PCB design and, eventually, lab tests are carried out to study its effectiveness in controlling flow separation.

Keywords: aircraft propulsion, dielectric barrier discharge, flow separation control, power source

Procedia PDF Downloads 124

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 78

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 111