Search results for: power network

Authors: M. R. Al-Rashidi, K. M. El-Naggar, M. F. Al-Hajri

Abstract:

The fuel cost function describes the electric power generation-cost relationship in thermal plants, hence, it sheds light on economical aspects of power industry. Different models have been proposed to describe this relationship with the quadratic function model being the most popular one. Parameters of second order fuel cost function are estimated in this paper using cuckoo search algorithm. It is a new population based meta-heuristic optimization technique that has been used in this study primarily as an accurate estimation tool. Its main features are flexibility, simplicity, and effectiveness when compared to other estimation techniques. The parameter estimation problem is formulated as an optimization one with the goal being minimizing the error associated with the estimated parameters. A case study is considered in this paper to illustrate cuckoo search promising potential as a valuable estimation and optimization technique.

Keywords: cuckoo search, parameters estimation, fuel cost function, economic dispatch

Procedia PDF Downloads 581

Authors: Alireza Mehdizadeh, Ghanbarali Sheikhzadeh

Abstract:

In this paper the pressure loss of drilling fluid flow in the annulus is investigated. On this purpose the domains between two concentric and two eccentric cylinders are considered as computational domains. In this research foam is used as drilling fluid. Firstly simulation results for laminar flow and non Newtonian fluid and different density like 100, 200, 300 kg/m3 and different inner cylinder rotational velocity like 100, 200, 300 RPM is presented. These results are compared and matched with references results. The power law and Herschel Bulkly methods are used for non Newtonian fluid modeling. After that computations are repeated with turbulence flow considering. K- Model is used for turbulence modeling. Results show that in laminar flow Herschel bulkly model has best result in comparison with power law model. And pressure loss in turbulence flow is higher than laminar flow.

Keywords: simulation, concentric cylinders, drilling, non Newtonian

Procedia PDF Downloads 566

Authors: Rafael Martins Manzano Silva, Jean-Francois Tremong

Abstract:

Electrification of railway lines allows to increase speed, power, capacity and energetic efficiency of rolling stocks. However, this process of electrification is complex and costly. An electrification project is not just about design of catenary. It also includes installation of structures around electrification, as substation installation, electrical isolation, signalling, telecommunication and civil engineering structures. France has more than 30,000 km of railways, whose only 53% are electrified. The others 47% of railways use diesel locomotive and represent only 10% of the circulation (tons.km). For this reason, a new type of electrification, less expensive than the usual, is requested to enable the modernization of these railways. One solution could be the use of hybrids trains. This technology opens up new opportunities for less expensive infrastructure development such as the partial electrification of railway lines. In a partially electrified railway, the power supply of theses hybrid trains could be made either by the catenary or by the on-board energy storage system (ESS). Thus, the on-board ESS would feed the energetic needs of the train along the non-electrified zones while in electrified zones, the catenary would feed the train and recharge the on-board ESS. This paper’s objective deals with the technical and economic potential identification of partial electrification of railway lines. This study provides different scenarios of electrification by replacing the most expensive places to electrify using on-board ESS. The target is to reduce the cost of new electrification projects, i.e. reduce the cost of electrification infrastructures while not increasing the cost of rolling stocks. In this study, scenarios are constructed in function of the electrification’s cost of each structure. The electrification’s cost varies considerably because of the installation of catenary support in tunnels, bridges and viaducts is much more expensive than in others zones of the railway. These scenarios will be used to describe the power supply system and to choose between the catenary and the on-board energy storage depending on the position of the train on the railway. To identify the influence of each partial electrification scenario in the sizing of the on-board ESS, a model of the railway line and of the rolling stock is developed for a real case. This real case concerns a railway line located in the south of France. The energy consumption and the power demanded at each point of the line for each power supply (catenary or on-board ESS) are provided at the end of the simulation. Finally, the cost of a partial electrification is obtained by adding the civil engineering costs of the zones to be electrified plus the cost of the on-board ESS. The study of the technical and economic potential ends with the identification of the most economically interesting scenario of electrification.

Keywords: electrification, hybrid, railway, storage

Procedia PDF Downloads 431

Authors: Borhan Marzougui

Abstract:

Road and Transport Authority (RTA) is moving ahead with the implementation of the leader’s vision in exploring all avenues that may bring better security and safety services to the community. Smart transport means using smart technologies such as IoT (Internet of Things). This technology continues to affirm its important role in the context of Information and Transportation Systems. In fact, IoT is a network of Internet-connected objects able to collect and exchange different data using embedded sensors. With the growth of IoT, Distributed Denial of Service (DDoS) attacks is also growing exponentially. DDoS attacks are the major and a real threat to various transportation services. Currently, the defense mechanisms are mainly passive in nature, and there is a need to develop a smart technique to handle them. In fact, new IoT devices are being used into a botnet for DDoS attackers to accumulate for attacker purposes. The aim of this paper is to provide a relevant understanding of dangerous types of DDoS attack related to IoT and to provide valuable guidance for the future IoT security method. Our methodology is based on development of the distributed algorithm. This algorithm manipulates dedicated intelligent and cooperative agents to prevent and to mitigate DDOS attacks. The proposed technique ensure a preventive action when a malicious packets start to be distributed through the connected node (Network of IoT devices). In addition, the devices such as camera and radio frequency identification (RFID) are connected within the secured network, and the data generated by it are analyzed in real time by intelligent and cooperative agents. The proposed security system is based on a multi-agent system. The obtained result has shown a significant reduction of a number of infected devices and enhanced the capabilities of different security dispositives.

Keywords: IoT, DDoS, attacks, botnet, security, agents

Procedia PDF Downloads 143

Authors: Mathew Wakefield, Matthew Mitchell, Lisa Wise, Christopher McCarthy

Abstract:

The properties of memory representations in artificial neural networks have cognitive implications. Distributed representations that encode instances as a pattern of activity across layers of nodes afford memory compression and enforce the selection of a single point in instance space. These encoding schemes also appear to distort the representational space, as well as trading off the ability to validate that input information is within the bounds of past experience. In contrast, a localist representation which encodes some meaningful information into individual nodes in a network layer affords less memory compression while retaining the integrity of the representational space. This allows the validity of an input to be determined. The validity (or familiarity) of input along with the capacity of localist representation for multiple instance selections affords a memory sampling approach that dynamically balances the bias-variance trade-off. When the input is familiar, bias may be high by referring only to the most similar instances in memory. When the input is less familiar, variance can be increased by referring to more instances that capture a broader range of features. Using this approach in a localist instance memory network, an experiment demonstrates a relationship between representational conflict, generalization performance, and memorization demand. Relatively small sampling ranges produce the best performance on a classic machine learning dataset of visual objects. Combining memory validity with conflict detection produces a reliable confidence judgement that can separate responses with high and low error rates. Confidence can also be used to signal the need for supervisory input. Using this judgement, the need for supervised learning as well as memory encoding can be substantially reduced with only a trivial detriment to classification performance.

Keywords: artificial neural networks, representation, memory, conflict monitoring, confidence

Procedia PDF Downloads 127

Authors: Aiza Dalman

Abstract:

Words are powerful when these are used wisely and strategically. In this study, twelve (12) campaign speeches of President Donald J. Trump were analyzed as to frequently used words and ethos, pathos and logos being employed. The speeches were read thoroughly, analyzed and interpreted. With the use of Word Counter Tool and Text Analyzer software accessible online, it was found out that the word ‘will’ has the highest frequency of 121, followed by Hillary (58), American (38), going (35), plan and Clinton (32), illegal (30), government (28), corruption (26) and criminal (24). When the speeches were analyzed as to ethos, pathos and logos, on the other hand, it revealed that these were all employed in his speeches. The statements under these pointed out against Hillary or in his favor. The unique strategy of President Donald J. Trump as to frequently used words and ethos, pathos and logos in persuading people perhaps lead the way to his victory.

Keywords: campaign speeches, corpus analysis, ethos, logos and pathos, power of words

Procedia PDF Downloads 280

Authors: John Onyima, Ikechukwu Ezepue

Abstract:

Virtualization and cloud computing are among the fast-growing computing innovations in recent times. Organisations all over the world are moving their computing services towards the cloud this is because of its rapid transformation of the organization’s infrastructure and improvement of efficient resource utilization and cost reduction. However, this technology brings new security threats and challenges about safety, reliability and data confidentiality. Evidently, no single security technique can guarantee security or protection against malicious attacks on a cloud computing network hence an integrated model of intrusion detection and prevention system has been proposed. Anomaly-based and signature-based detection techniques will be integrated to enable the network and its host defend themselves with some level of intelligence. The anomaly-base detection was implemented using the local deviation factor graph-based (LDFGB) algorithm while the signature-based detection was implemented using the snort algorithm. Results from this collaborative intrusion detection and prevention techniques show robust and efficient security architecture for cloud computing networks.

Keywords: anomaly-based detection, cloud computing, intrusion detection, intrusion prevention, signature-based detection

Procedia PDF Downloads 307

Authors: Heming Yao

Abstract:

Graphene-based percolative strain gauges could find applications in many places such as touch panels, artificial skins or human motion detection because of its advantages over conventional strain gauges such as flexibility and transparency. These strain gauges rely on a novel sensing mechanism that depends on strain-induced morphology changes. Once a compression or tension strain is applied to Graphene-based percolative strain gauges, the overlap area between neighboring flakes becomes smaller or larger, which is reflected by the considerable change of resistance. Tiny strain change on graphene-based percolative strain sensor can act as an important leverage to tremendously increase resistance of strain sensor, which equipped graphene-based percolative strain gauges with higher gauge factor. Despite ongoing research in the underlying sensing mechanism and the limits of sensitivity, neither suitable understanding has been obtained of what intrinsic factors play the key role in adjust gauge factor, nor explanation on how the strain gauge sensitivity can be enhanced, which is undoubtedly considerably meaningful and provides guideline to design novel and easy-produced strain sensor with high gauge factor. We here simulated the strain process by modeling graphene flakes and its percolative networks. We constructed the 3D resistance network by simulating overlapping process of graphene flakes and interconnecting tremendous number of resistance elements which were obtained by fractionizing each piece of graphene. With strain increasing, the overlapping graphenes was dislocated on new stretched simulation graphene flake simulation film and a new simulation resistance network was formed with smaller flake number density. By solving the resistance network, we can get the resistance of simulation film under different strain. Furthermore, by simulation on possible variable parameters, such as out-of-plane resistance, in-plane resistance, flake size, we obtained the changing tendency of gauge factor with all these variable parameters. Compared with the experimental data, we verified the feasibility of our model and analysis. The increase of out-of-plane resistance of graphene flake and the initial resistance of sensor, based on flake network, both improved gauge factor of sensor, while the smaller graphene flake size gave greater gauge factor. This work can not only serve as a guideline to improve the sensitivity and applicability of graphene-based strain sensors in the future, but also provides method to find the limitation of gauge factor for strain sensor based on graphene flake. Besides, our method can be easily transferred to predict gauge factor of strain sensor based on other nano-structured transparent optical conductors, such as nanowire and carbon nanotube, or of their hybrid with graphene flakes.

Keywords: graphene, gauge factor, percolative transport, strain sensor

Procedia PDF Downloads 416

Authors: Amit Verma, Simranjeet Kaur, Sandeep Kaur

Abstract:

Test Case Prioritization (TCP) has gained wide spread acceptance as it often results in good quality software free from defects. Due to the increase in rate of faults in software traditional techniques for prioritization results in increased cost and time. Main challenge in TCP is difficulty in manually validate the priorities of different test cases due to large size of test suites and no more emphasis are made to make the TCP process automate. The objective of this paper is to detect the priorities of different test cases using an artificial neural network which helps to predict the correct priorities with the help of back propagation algorithm. In our proposed work one such method is implemented in which priorities are assigned to different test cases based on their frequency. After assigning the priorities ANN predicts whether correct priority is assigned to every test case or not otherwise it generates the interrupt when wrong priority is assigned. In order to classify the different priority test cases classifiers are used. Proposed algorithm is very effective as it reduces the complexity with robust efficiency and makes the process automated to prioritize the test cases.

Keywords: test case prioritization, classification, artificial neural networks, TF-IDF

Procedia PDF Downloads 397

Authors: Martabolette Stecher

Abstract:

Introductory: How is knowledge and ability to act on employable opportunities constructed among students and graduates at higher educations? This question have been drawn much attention by researchers, governments and universities in Denmark, since there has been an increases in the rate of unemployment among graduates from higher education. The fact that more than ten thousand graduates from higher education without the opportunity to get a job in these years has a tremendous impact upon the social economy in Denmark. Every time a student graduate from higher education and become unemployed, it is possible to trace upon the person´s chances to get a job many years ahead. This means that the tremendous rate of graduate unemployment implies a decrease in employment and lost prosperity in Denmark within a billion Danish Kroner scale. Basic methodologies: The present study investigates the construction of knowledge and ability to act upon employable opportunities among students and graduates at higher educations in Denmark in a literature review as well as a preliminary study of students from Aarhus University. 15 students from the candidate of drama have been engaging in an introductory program at the beginning of their candidate study, which included three workshops focusing upon the more personal matters of their studies and life. They have reflected upon this process during the intervention and afterwards in a semi-structured interview. Concurrently a thorough literature review has delivered key concepts for the exploration of the research question. Major findings of the study: It is difficult to find one definition of what employability encompasses, hence the overall picture of how to incorporate the concept is difficult. The present theory of employability has been focusing upon the competencies, which students and graduates are going to develop in order to become employable. In recent years there has been an emphasis upon the mechanism which supports graduates to trust themselves and to develop their self-efficacy in terms of getting a sustainable job. However, there has been little or no focus in the literature upon the idea of how students and graduates from higher education construct knowledge about and ability to act upon employable opportunities involving network of actors both material and immaterial network and meaningful relations for students and graduates in developing their enterprising behavior to achieve employment. The Act-network-theory combined with theory of entrepreneurship education suggests an alternative strategy to focus upon when explaining sustainable ways of creating employability among graduates. The preliminary study also supports this theory suggesting that it is difficult to emphasize a single or several factors of importance rather highlighting the effect of a multitude network. Concluding statement: This study is the first step of a ph.d.-study investigating this problem in Denmark and the USA in the period 2015 – 2019.

Keywords: employablity, graduates, action, opportunities

Procedia PDF Downloads 198

Authors: Taus Muganda

Abstract:

This research explores the intricate relationship between e-procurement adoption and effective service delivery in the Uganda Coffee Industry, focusing on the processes involved, key actors, and the impact of digital transformation. The study is guided by three prominent theories, Actor-Network Theory, Resource-Based View Theory, and Institutional Theory to comprehensively explore the dynamics of e-procurement in the context of the coffee sector. The primary aim of this project is to examine the e-procurement adoption process and its role in enhancing service delivery within the Uganda Coffee Industry. The research questions guiding this inquiry are: firstly, whether e-procurement adoption and implementation contribute to achieving quality service delivery; and secondly, how e-procurement adoption can be effectively realized within the Uganda Coffee Industry. To address these questions, the study has laid out specific objectives. Firstly, it seeks to investigate the impact of e-procurement on effective service delivery, analysing how the integration of digital processes influences the overall quality of services provided in the coffee industry. Secondly, it aims to critically analyse the measures required to achieve effective delivery outcomes through the adoption and implementation of e-procurement, assessing the strategies that can maximize the benefits of digital transformation. Furthermore, the research endeavours to identify and examine the key actor’s instrumental in achieving effective service delivery within the Uganda Coffee Industry. By utilizing Actor-Network Theory, the study will elucidate the network of relationships and collaborations among actors involved in the e-procurement process. The research contributes to addressing a critical gap in the sector. Despite coffee being the leading export crop in Uganda, constituting 16% of total exports, there is a recognized need for digital transformation, specifically in the realm of e-procurement, to enhance the productivity of producers and contribute to the economic growth of the country. The study aims to provide insights into transforming the Uganda Coffee Industry by focusing on improving the e-procurement services delivered to actors in the coffee sector. The three forms of e-procurement investigated in this research—E-Sourcing, E-Payment, and E-Invoicing—serve as focal points in understanding the multifaceted dimensions of digital integration within the Uganda Coffee Industry. This research endeavours to offer practical recommendations for policymakers, industry stakeholders, and the UCDA to strategically leverage e-procurement for the benefit of the entire coffee value chain.

Keywords: e-procurement, effective service delivery, actors, actor-network theory, resource-based view theory, institutional theory, e-invocing, e-payment, e-sourcing

Procedia PDF Downloads 71

Authors: Belloui Bouzid

Abstract:

In this paper, broadband design of erbium doped fiber amplifier (EDFA) is demonstrated and proved experimentally. High and broad gain is covered in C and L bands. The used technique combines, in one configuration, two double passes with split band structure for the amplification of two traveled signals one for the C band and the other for L band. This new topology is to investigate the trends of high gain and wide amplification at different status of pumping power, input wavelength, and input signal power. The presented paper is to explore the performance of EDFA gain using what it can be called double pass double branch wide band amplification configuration. The obtained results show high gain and wide broadening range of 44.24 dB and 80 nm amplification respectively.

Keywords: erbium doped fiber amplifier, erbium doped fiber laser, optical amplification, fiber laser

Procedia PDF Downloads 254

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 68

Authors: Zhou Mo, Dennis Chow

Abstract:

In the dynamic positioning system (DPS) for vessels, the reliable information transmission between each note basically relies on the wireless protocols. From the perspective of cluster-based routing protocols for wireless sensor networks, the data fusion technology based on the sleep scheduling mechanism and remaining energy in network layer is proposed, which applies the sleep scheduling mechanism to the routing protocols, considering the remaining energy of node and location information when selecting cluster-head. The problem of uneven distribution of nodes in each cluster is solved by the Equilibrium. At the same time, Classified Forwarding Mechanism as well as Redelivery Policy strategy is adopted to avoid congestion in the transmission of huge amount of data, reduce the delay in data delivery and enhance the real-time response. In this paper, a simulation test is conducted to improve the routing protocols, which turn out to reduce the energy consumption of nodes and increase the efficiency of data delivery.

Keywords: DPS for vessel, wireless sensor network, data fusion, routing protocols

Procedia PDF Downloads 524

Authors: Hui Zhang, Sherif Beskhyroun

Abstract:

In this study, a highly flexible LoRa-Based wireless sensing system was used to assess the strain state performance of building structures. The system was developed to address the local damage limitation of structural health monitoring (SHM) systems. The system is part of an intelligent SHM system designed to monitor, collect and transmit strain changes in key structural components. The main purpose of the wireless sensor system is to reduce the development and installation costs, and reduce the power consumption of the system, so as to achieve long-time monitoring. The highly stretchable flexible strain gauge is mounted on the surface of the structure and is waterproof, heat resistant, and low temperature resistant, greatly reducing the installation and maintenance costs of the sensor. The system was also developed with the aim of using LoRa wireless communication technology to achieve both low power consumption and long-distance transmission, therefore solving the problem of large-scale deployment of sensors to cover more areas in large structures. In the long-term monitoring of the building structure, the system shows very high performance, very low actual power consumption, and wireless transmission stability. The results show that the developed system has a high resolution, sensitivity, and high possibility of long-term monitoring.

Keywords: LoRa, SHM system, strain measurement, civil structures, flexible sensing system

Procedia PDF Downloads 103

Authors: Wararit Panichkitkosolkul

Abstract:

The unit root tests based on the robust estimator for the first-order autoregressive process are proposed and compared with the unit root tests based on the ordinary least squares (OLS) estimator. The percentiles of the null distributions of the unit root test are also reported. The empirical probabilities of Type I error and powers of the unit root tests are estimated via Monte Carlo simulation. Simulation results show that all unit root tests can control the probability of Type I error for all situations. The empirical power of the unit root tests based on the robust estimator are higher than the unit root tests based on the OLS estimator.

Keywords: autoregressive, ordinary least squares, type i error, power of the test, Monte Carlo simulation

Procedia PDF Downloads 289

Authors: Keigo Ide, Toru Maruyama, Michihiro Ito, Hiroyuki Fujimura, Yoshikatu Nakano, Shoichiro Suda, Sachiyo Aburatani, Haruko Takeyama

Abstract:

Understanding environmental system is one of the important tasks. In recent years, conservation of coral environments has been focused for biodiversity issues. The damage of coral reef under environmental impacts has been observed worldwide. However, the casual relationship between damage of coral and environmental impacts has not been clearly understood. On the other hand, structure/diversity of marine bacterial community may be relatively robust under the certain strength of environmental impact. To evaluate the coral environment conditions, it is necessary to investigate relationship between marine bacterial composition in coral reef and environmental factors. In this study, the Time Scale Network Analysis was developed and applied to analyze the marine environmental data for investigating the relationship among coral, bacterial community compositions and environmental factors. Seawater samples were collected fifteen times from November 2014 to May 2016 at two locations, Ishikawabaru and South of Sesoko in Sesoko Island, Okinawa. The physicochemical factors such as temperature, photosynthetic active radiation, dissolved oxygen, turbidity, pH, salinity, chlorophyll, dissolved organic matter and depth were measured at the coral reef area. Metagenome and metatranscriptome in seawater of coral reef were analyzed as the biological factors. Metagenome data was used to clarify marine bacterial community composition. In addition, functional gene composition was estimated from metatranscriptome. For speculating the relationships between physicochemical and biological factors, cross-correlation analysis was applied to time scale data. Even though cross-correlation coefficients usually include the time precedence information, it also included indirect interactions between the variables. To elucidate the direct regulations between both factors, partial correlation coefficients were combined with cross correlation. This analysis was performed against all parameters such as the bacterial composition, the functional gene composition and the physicochemical factors. As the results, time scale network analysis revealed the direct regulation of seawater temperature by photosynthetic active radiation. In addition, concentration of dissolved oxygen regulated the value of chlorophyll. Some reasonable regulatory relationships between environmental factors indicate some part of mechanisms in coral reef area.

Keywords: coral environment, marine microbiology, network analysis, omics data analysis

Procedia PDF Downloads 254

Authors: Shadi Fathi, Moura Mehravar, Mujib Rahman

Abstract:

The railwaytransportation network in the UK is over 100 years old and is known as one of the oldest mass transit systems in the world. This aged track network requires frequent closure for maintenance. One of the main reasons for closure is inadequate drainage due to the leakage in the buried drainage pipes. The leaking water can cause localised subgrade weakness, which subsequently can lead to major ground/substructure failure.Different condition assessment methods are available to assess the railway substructure. However, the existing condition assessment methods are not able to detect any local ground weakness/damageand provide details of the damage (e.g. size and location). To tackle this issue, a hybrid back-analysis technique based on artificial neural network (ANN) and genetic algorithm (GA) has been developed to predict the substructurelayers’ moduli and identify any soil weaknesses. At first, afinite element (FE) model of a railway track section under Falling Weight Deflection (FWD) testing was developed and validated against field trial. Then a drainage pipe and various scenarios of the local defect/ soil weakness around the buried pipe with various geometriesand physical properties were modelled. The impact of the soil local weaknesson the track surface deflection wasalso studied. The FE simulations results were used to generate a database for ANN training, and then a GA wasemployed as an optimisation tool to optimise and back-calculate layers’ moduli and soil weakness moduli (ANN’s input). The hybrid ANN-GA back-analysis technique is a computationally efficient method with no dependency on seed modulus values. The modelcan estimate substructures’ layer moduli and the presence of any localised foundation weakness.

Keywords: finite element (FE) model, drainage defect, falling weight deflectometer (FWD), hybrid ANN-GA

Procedia PDF Downloads 152

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150

Authors: Zachary Pan

Abstract:

Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.

Keywords: body part, healthcare, machine learning, neural networks

Procedia PDF Downloads 103

Authors: Jyh-Cherng Gu, Ming-Ta Yang, Dai-Ling Tsai

Abstract:

Both sparse lashing and dense lashing are applied to secure overhead XLPE (cross-linked polyethylene) covered power lines on ceramic insulators or HDPE polymer insulators. The distribution of electric field in and among the lashing wires, the XLPE power lines and insulators in normal clean condition and when conducting materials such as salt, metal particles, dust, smoke or acidic smog are present is studied in this paper. The ANSYS Maxwell commercial software is used in this study for electric field analysis. Although the simulation analysis is performed assuming ideal conditions due to the constraints of the simulation software, the result may not be the same as in real situation but still be of sufficient practical values.

Keywords: electric field intensity, insulator, XLPE covered aerial line, empty

Procedia PDF Downloads 264

Authors: Jung Hyun Kim, Gyo Woo Lee

Abstract:

In this study, heat release performances of the three extruded-type heat sinks can be used in the inverter for solar power generation were evaluated. Numbers of fins in the heat sinks (namely E-38, E-47 and E-76) were 38, 47 and 76, respectively. Heat transfer areas of them were 1.8, 1.9 and 2.8 m2. The heat release performances of E-38, E-47, and E-76 heat sinks were measured as 79.6, 81.6, and 83.2%, respectively. The results of heat release performance show that the larger amount of heat transfer area the higher heat release rate. While on the other, in this experiment, variations of the mass flow rates caused by different cross-sectional areas of the three heat sinks may not be the major parameter of the heat release. Despite the 47.4% increment of heat transfer area of E-76 heat sink than that of E-47 one, its heat release rate was higher by only 2.0%; this suggests that its heat transfer area need to be optimized.

Keywords: solar Inverter, heat sink, forced convection, heat transfer, performance evaluation

Procedia PDF Downloads 467

Authors: Maibigue Nanglet, Arafat Ousman Béchir, Mahamat Hassan Béchir

Abstract:

The economy of Central African countries is growing very fast, and the demand for energy is increasing every day. As a result, insufficient power generation is one of the major problems slowing down development. This paper explores the factors of degradation of the I-V curve of the PV Generator (GPV) in harsh environments, taking the case of two locals: Mongo and Abeche. Its objective is to quantify the voltage leaks due to the different GPV installation areas; after using the Newton-Raphson numerical method of the solar cell, a survey of several experimental measurement points was made. The results of the simulation in MATLAB/Simulink show a relative power loss factor of 11.8765% on the GPVs installed in Mongo and 8.5463% on those installed in Abeche; these results allow us to say that the supports on which the modules are installed have an average impact of 10.2114% on their efficiency.

Keywords: calculation, degradation, site, GPV, severe environment

Procedia PDF Downloads 36

Authors: Yannick Verbelen, Tim Dekegel, Ann Peeters, Klara Stinders, Niek Blondeel, Sam De Winne, An Braeken, Abdellah Touhafi

Abstract:

Matching an embedded electronic application with a cantilever vibration energy harvester remains a difficult endeavour due to the large number of factors influencing the output power. In the presented work, complementary balanced energy harvester parametrization is used as a methodology for simplification of harvester integration in electronic applications. This is achieved by a dual approach consisting of an adaptation of the general parametrization methodology in conjunction with a straight forward harvester benchmarking strategy. For this purpose, the design and implementation of a suitable user friendly cantilever energy harvester benchmarking platform is discussed. Its effectiveness is demonstrated by applying the methodology to a commercially available Mide V21BL vibration energy harvester, with excitation amplitude and frequency as variables.

Keywords: vibration energy harvesting, piezoelectrics, harvester parametrization, complementary balanced energy harvesting

Procedia PDF Downloads 357

Authors: Han Xue, Zhang Lanyue

Abstract:

In order to seek more effective feature extraction technology, feature extraction method based on MFCC combined with vector hydrophone is exposed in the paper. The sound pressure signal and particle velocity signal of two kinds of ships are extracted by using MFCC and its evolution form, and the extracted features are fused by using fisher-ratio and correlated distance criterion. The features are then identified by BP neural network. The results showed that MFCC, First-Order Differential MFCC and Second-Order Differential MFCC features can be used as effective features for recognition of underwater targets, and the fusion feature can improve the recognition rate. Moreover, the results also showed that the recognition rate of the particle velocity signal is higher than that of the sound pressure signal, and it reflects the superiority of vector signal processing.

Keywords: vector information, MFCC, differential MFCC, fusion feature, BP neural network

Procedia PDF Downloads 529

Authors: Kouzi Katia

Abstract:

This paper proposes a Direct Torque Control (DTC) algorithm of dual Stator Induction Motor (DSIM) drive using two approach intelligent techniques: Artificial Neural Network (ANN) approach replaces the switching table selector block of conventional DTC and Mamdani Fuzzy Logic controller (FLC) is used for stator resistance estimation. The fuzzy estimation method is based on an online stator resistance correction through the variations of stator current estimation error and its variation. The fuzzy logic controller gives the future stator resistance increment at the output. The main advantage of suggested algorithm control is to reduce the hardware complexity of conventional selectors, to avoid the drive instability that may occur in certain situation and ensure the tracking of the actual of the stator resistance. The effectiveness of the technique and the improvement of the whole system performance are proved by results.

Keywords: artificial neural network, direct torque control, dual stator induction motor, fuzzy logic estimator, switching table

Procedia PDF Downloads 345

Authors: Nelson Ponce Jr., Jonas R. Gazoli, Alessandro Sete, Roberto M. G. Velásquez, Valério L. Borges, Moacir A. S. de Andrade

Abstract:

The search for increased efficiency in generation systems has been of great importance in recent years to reduce the impact of greenhouse gas emissions and global warming. For clean energy sources, such as the generation systems that use concentrated solar power technology, this efficiency improvement impacts a lower investment per kW, improving the project’s viability. For the specific case of parabolic trough solar concentrators, their performance is strongly linked to their geometric precision of assembly and the individual efficiencies of their main components, such as parabolic mirrors and receiver tubes. Thus, for accurate efficiency analysis, it should be conducted empirically, looking for mounting and operating conditions like those observed in the field. The Brazilian power generation and distribution company Eletrobras Furnas, through the R&D program of the National Agency of Electrical Energy, has developed a plant for testing parabolic trough concentrators located in Aparecida de Goiânia, in the state of Goiás, Brazil. The main objective of this test plant is the characterization of the prototype concentrator that is being developed by the company itself in partnership with Eudora Energia, seeking to optimize it to obtain the same or better efficiency than the concentrators of this type already known commercially. This test plant is a closed pipe system where a pump circulates a heat transfer fluid, also calledHTF, in the concentrator that is being characterized. A flow meter and two temperature transmitters, installed at the inlet and outlet of the concentrator, record the parameters necessary to know the power absorbed by the system and then calculate its efficiency based on the direct solar irradiation available during the test period. After the HTF gains heat in the concentrator, it flows through heat exchangers that allow the acquired energy to be dissipated into the ambient. The goal is to keep the concentrator inlet temperature constant throughout the desired test period. The developed plant performs the tests in an autonomous way, where the operator must enter the HTF flow rate in the control system, the desired concentrator inlet temperature, and the test time. This paper presents the methodology employed for design and operation, as well as the instrumentation needed for the development of a parabolic trough test plant, being a guideline for standardization facilities.

Keywords: parabolic trough, concentrated solar power, CSP, solar power, test plant, energy efficiency, performance characterization, renewable energy

Procedia PDF Downloads 118

Authors: Balgaisha Mukanova, Natalya Glazyrina, Sergey Glazyrin

Abstract:

The formulated problem of optimization of the technological process of water treatment for thermal power plants is considered in this article. The problem is of multiparametric nature. To optimize the process, namely, reduce the amount of waste water, a new technology was developed to reuse such water. A mathematical model of the technology of wastewater reuse was developed. Optimization parameters were determined. The model consists of a material balance equation, an equation describing the kinetics of ion exchange for the non-equilibrium case and an equation for the ion exchange isotherm. The material balance equation includes a nonlinear term that depends on the kinetics of ion exchange. A direct problem of calculating the impurity concentration at the outlet of the water treatment plant was numerically solved. The direct problem was approximated by an implicit point-to-point computation difference scheme. The inverse problem was formulated as relates to determination of the parameters of the mathematical model of the water treatment plant operating in non-equilibrium conditions. The formulated inverse problem was solved. Following the results of calculation the time of start of the filter regeneration process was determined, as well as the period of regeneration process and the amount of regeneration and wash water. Multi-parameter optimization of water treatment process for thermal power plants allowed decreasing the amount of wastewater by 15%.

Keywords: direct problem, multiparametric optimization, optimization parameters, water treatment

Procedia PDF Downloads 387

Authors: Zsolt János Viharos, Krisztián Balázs Kis, Imre Paniti, Gábor Belső, Péter Németh, János Farkas

Abstract:

The paper presents the results and industrial applications in the production setup period estimation based on industrial data inherited from the field of polymer cutting. The literature of polymer cutting is very limited considering the number of publications. The first polymer cutting machine is known since the second half of the 20th century; however, the production of polymer parts with this kind of technology is still a challenging research topic. The products of the applying industrial partner must met high technical requirements, as they are used in medical, measurement instrumentation and painting industry branches. Typically, 20% of these parts are new work, which means every five years almost the entire product portfolio is replaced in their low series manufacturing environment. Consequently, it requires a flexible production system, where the estimation of the frequent setup periods' lengths is one of the key success factors. In the investigation, several (input) parameters have been studied and grouped to create an adequate training information set for an artificial neural network as a base for the estimation of the individual setup periods. In the first group, product information is collected such as the product name and number of items. The second group contains material data like material type and colour. In the third group, surface quality and tolerance information are collected including the finest surface and tightest (or narrowest) tolerance. The fourth group contains the setup data like machine type and work shift. One source of these parameters is the Manufacturing Execution System (MES) but some data were also collected from Computer Aided Design (CAD) drawings. The number of the applied tools is one of the key factors on which the industrial partners’ estimations were based previously. The artificial neural network model was trained on several thousands of real industrial data. The mean estimation accuracy of the setup periods' lengths was improved by 30%, and in the same time the deviation of the prognosis was also improved by 50%. Furthermore, an investigation on the mentioned parameter groups considering the manufacturing order was also researched. The paper also highlights the manufacturing introduction experiences and further improvements of the proposed methods, both on the shop floor and on the quotation preparation fields. Every week more than 100 real industrial setup events are given and the related data are collected.

Keywords: artificial neural network, low series manufacturing, polymer cutting, setup period estimation

Procedia PDF Downloads 245

Authors: Justin Reverdi, Sixin Zhang, Saïd Aoues, Fabrice Gamboa, Serge Gratton, Thomas Pellegrini

Abstract:

In vapor cycle systems, the mass flow sensor plays a key role for different monitoring and control purposes. However, physical sensors can be inaccurate, heavy, cumbersome, expensive, or highly sensitive to vibrations, which is especially problematic when embedded into an aircraft. The conception of a virtual sensor, based on other standard sensors, is a good alternative. This paper has two main objectives. Firstly, a data-driven model using a convolutional neural network is proposed to estimate the mass flow of the compressor. We show that it significantly outperforms the standard polynomial regression model (thermodynamic maps) in terms of the standard MSE metric and engineer performance metrics. Secondly, a semi-automatic segmentation method is proposed to compute the engineer performance metrics for real datasets, as the standard MSE metric may pose risks in analyzing the dynamic behavior of vapor cycle systems.

Keywords: deep learning, convolutional neural network, vapor cycle system, virtual sensor

Procedia PDF Downloads 61