Search results for: neural tube defect

Authors: Venkatesh Pulletikurthi, Karthik B. Ariyur, Luciano Castillo

Abstract:

The system identification from the turbulence wakes will lead to the tactical advantage to prepare and also, to predict the trajectory of the opponents’ movements. A low-order modeling technique, POD, is used to predict the object based on the wake pattern and compared with pre-trained image recognition neural network (NN) to classify the wake patterns into objects. It is demonstrated that low-order modeling, POD, is able to predict the objects better compared to pretrained NN by ~30%.

Keywords: the bluff body wakes, low-order modeling, neural network, system identification

Procedia PDF Downloads 184

Authors: Debajyoti Mukherjee, Arathy B. S., Arpita Sahu, Saranga P. Pogula

Abstract:

A Functional Model to mimic the functional correctness of a Neural Network Compute Accelerator IP is very crucial for design validation. Neural network workloads are based on a Brain Floating Point (BF-16) data type. The major challenge we were facing was the incompatibility of gcc compilers to BF-16 datatype, which we addressed with a native BF-16 generator integrated to our functional model. Moreover, working with big GEMM (General Matrix Multiplication) or SpMM (Sparse Matrix Multiplication) Work Loads (Dense or Sparse) and debugging the failures related to data integrity is highly painstaking. In this paper, we are addressing the quality challenge of such a complex Neural Network Accelerator design by proposing a Functional Model-based scoreboard or Software model using SystemC. The proposed Functional Model executes the assembly code based on the ISA of the processor IP, decodes all instructions, and executes as expected to be done by the DUT. The said model would give a lot of visibility and debug capability in the DUT bringing up micro-steps of execution.

Keywords: ISA (instruction set architecture), NN (neural network), TLM (transaction-level modeling), GEMM (general matrix multiplication)

Procedia PDF Downloads 87

Authors: Sabri Arik

Abstract:

In this paper, we study the global asymptotic robust stability of delayed neural networks with norm-bounded uncertainties. By employing the Lyapunov stability theory and Homeomorphic mapping theorem, we derive some new types of sufficient conditions ensuring the existence, uniqueness and global asymptotic stability of the equilibrium point for the class of neural networks with discrete time delays under parameter uncertainties and with respect to continuous and slopebounded activation functions. An important aspect of our results is their low computational complexity as the reported results can be verified by checking some properties symmetric matrices associated with the uncertainty sets of network parameters. The obtained results are shown to be generalization of some of the previously published corresponding results. Some comparative numerical examples are also constructed to compare our results with some closely related existing literature results.

Keywords: neural networks, delayed systems, lyapunov functionals, stability analysis

Procedia PDF Downloads 529

Authors: Hassan M. H. Mustafa

Abstract:

This piece of research addresses an interesting comparative analytical study. Which considers two concepts of diverse algorithmic computational intelligence approaches related tightly with Neural and Non-Neural Systems. The first algorithmic intelligent approach concerned with observed obtained practical results after three neural animal systems’ activities. Namely, they are Pavlov’s, and Thorndike’s experimental work. Besides a mouse’s trial during its movement inside figure of eight (8) maze, to reach an optimal solution for reconstruction problem. Conversely, second algorithmic intelligent approach originated from observed activities’ results for Non-Neural Ant Colony System (ACS). These results obtained after reaching an optimal solution while solving Traveling Sales-man Problem (TSP). Interestingly, the effect of increasing number of agents (either neurons or ants) on learning performance shown to be similar for both introduced systems. Finally, performance of both intelligent learning paradigms shown to be in agreement with learning convergence process searching for least mean square error LMS algorithm. While its application for training some Artificial Neural Network (ANN) models. Accordingly, adopted ANN modeling is a relevant and realistic tool to investigate observations and analyze performance for both selected computational intelligence (biological behavioral learning) systems.

Keywords: artificial neural network modeling, animal learning, ant colony system, traveling salesman problem, computational biology

Procedia PDF Downloads 471

Authors: Tugce Talay, Kadir Erkan

Abstract:

In this study, the necessary steps for the design of axial flow permanent magnet motors are shown. The design and analysis of the engine were carried out based on ANSYS Maxwell program. The design parameters of the ANSYS Maxwell program and the artificial neural network system were established in MATLAB and the most efficient design parameters were found with the trained neural network. The results of the Maxwell program and the results of the artificial neural networks are compared and optimal working design parameters are found. The most efficient design parameters were submitted to the ANSYS Maxwell 3D design and the cogging torque was examined and design studies were carried out to reduce the cogging torque.

Keywords: AFPM, ANSYS Maxwell, cogging torque, design optimisation, efficiency, NNTOOL

Procedia PDF Downloads 221

Authors: Mohamed El Morsy, Gabriela Achtenová

Abstract:

Research on damage of gears and gear pairs using vibration signals remains very attractive, because vibration signals from a gear pair are complex in nature and not easy to interpret. Predicting gear pair defects by analyzing changes in vibration signal of gears pairs in operation is a very reliable method. Therefore, a suitable vibration signal processing technique is necessary to extract defect information generally obscured by the noise from dynamic factors of other gear pairs. This article presents the value of cepstrum analysis in vehicle gearbox fault diagnosis. Cepstrum represents the overall power content of a whole family of harmonics and sidebands when more than one family of sidebands is present at the same time. The concept for the measurement and analysis involved in using the technique are briefly outlined. Cepstrum analysis is used for detection of an artificial pitting defect in a vehicle gearbox loaded with different speeds and torques. The test stand is equipped with three dynamometers; the input dynamometer serves as the internal combustion engine, the output dynamometers introduce the load on the flanges of the output joint shafts. The pitting defect is manufactured on the tooth side of a gear of the fifth speed on the secondary shaft. Also, a method for fault diagnosis of gear faults is presented based on order cepstrum. The procedure is illustrated with the experimental vibration data of the vehicle gearbox. The results show the effectiveness of cepstrum analysis in detection and diagnosis of the gear condition.

Keywords: cepstrum analysis, fault diagnosis, gearbox, vibration signals

Procedia PDF Downloads 380

Authors: Mohammed Y. Elsherbeny, Mohamed Salama, Ahmed Lotfy, Hossam Fareed, Nora Mohammed

Abstract:

Background: Developmental neurotoxicity (DNT) entails the toxic effects imparted by various chemicals on brain during the early childhood when human brains are vulnerable during this period. DNT study in vivo cannot determine the effect of the neurotoxins, as it is not applicable, so using the neurosphere cells of lab animals as an alternative is applicable and time saving. Methods: Cell culture: Rat neural progenitor cells were isolated from rat embryos’ brain. The cortices were aseptically dissected out and the tissues were triturated. The dispersed tissues were allowed to settle. The supernatant was then transferred to a fresh tube and centrifuged. The pellet was placed in Hank’s balanced salt solution and cultured as free-floating neurospheres in proliferation medium. Differentiation was initiated by growth factor withdrawal in differentiation medium and plating onto a poly-d-lysine/ laminin matrix. Chemical Exposure: Neurospheres were treated for 2 weeks with papaverine in proliferation medium. Proliferation analyses: Spheres were cultured. After 0, 4, 5, 11 and 14 days, sphere size was determined by software analyses (CellProfiler, version 2.1; Broad Institute). Diameter of each neurosphere was measured and exported to excel file further to statistical analysis. Viability test: Trypsin-EDTA solution was added to neurospheres to dissociate neurospheres into single cells suspension, then viability evaluated by the Trypan Blue exclusion test. Result: As regards proliferation analysis and percentage of viable cells of papaverin treated groups: There was no significant change in cells proliferation compared to control at 0, 4, 5, 11 and 14 days with concentrations 1, 5 and 10 µM of papaverine, but there is a significant change in cell viability compared to control after 1 week and 2 weeks with the same concentrations of papaverine. Conclusion: Papaverine has toxic effect on viability of neural cell, not on their proliferation, so it may produce focal neural lesions not growth morphological changes.

Keywords: developmental neurotoxicity, neurotoxin, papaverine, neuroshperes

Procedia PDF Downloads 386

Authors: Kishore K. Pochampally

Abstract:

The success of a supply chain heavily relies on the efficiency of the suppliers involved. In this paper, we propose a neural network approach to evaluate the efficiency of a supplier, which is being considered for inclusion in a supply chain, using the available linguistic (fuzzy) data of suppliers that already exist in the supply chain. The approach is carried out in three phases, as follows: In phase one, we identify criteria for evaluation of the supplier of interest. Then, in phase two, we use performance measures of already existing suppliers to construct a neural network that gives weights (importance values) of criteria identified in phase one. Finally, in phase three, we calculate the overall rating of the supplier of interest. The following are the major findings of the research conducted for this paper: (i) linguistic (fuzzy) ratings of suppliers such as 'good', 'bad', etc., can be converted (defuzzified) to numerical ratings (1 – 10 scale) using fuzzy logic so that those ratings can be used for further quantitative analysis; (ii) it is possible to construct and train a multi-level neural network in order to determine the weights of the criteria that are used to evaluate a supplier; and (iii) Borda’s rule can be used to group the weighted ratings and calculate the overall efficiency of the supplier.

Keywords: fuzzy data, neural network, supplier, supply chain

Procedia PDF Downloads 114

Authors: Ebenezer Obaloluwa Olaniyi

Abstract:

In this paper, an intelligent system has been designed to grade apple based on either its defective or healthy for production in food processing. This paper is segmented into two different phase. In the first phase, the image processing techniques were employed to extract the necessary features required in the apple. These techniques include grayscale conversion, segmentation where a threshold value is chosen to separate the foreground of the images from the background. Then edge detection was also employed to bring out the features in the images. These extracted features were then fed into the neural network in the second phase of the paper. The second phase is a classification phase where neural network employed to classify the defective apple from the healthy apple. In this phase, the network was trained with back propagation and tested with feed forward network. The recognition rate obtained from our system shows that our system is more accurate and faster as compared with previous work.

Keywords: image processing, neural network, apple, intelligent system

Procedia PDF Downloads 399

Authors: Xuewen Yu, Danhui Dan

Abstract:

The identification of impact load and some hard-to-obtain system parameters is crucial for the activities of analysis, validation, and evaluation in the engineering field. This paper proposes a method that utilizes neural networks based on 1D-CNN to identify the impact load and partial system parameters from measured responses. To this end, forward computations are conducted to provide datasets consisting of the triples (parameter θ, input u, output y). Then neural networks are trained to learn the mapping from input to output, fu|{θ} : y → u, as well as from input and output to parameter, fθ : (u, y) → θ. Afterward, feeding the trained neural networks the measured output response, the input impact load and system parameter can be calculated, respectively. The method is tested on two simulated examples and shows sound accuracy in estimating the impact load (waveform and location) and system parameters.

Keywords: convolutional neural network, impact load identification, system parameter identification, inverse problem

Procedia PDF Downloads 128

Authors: A. Yönetken, A. Erol, A. Yakar, G. Peşmen

Abstract:

The microstructure, mechanical properties and metalgraphic characteristics of Ni plated AlN-Astaloy Cr-M powders were investigated using specimens produced by tube furnace sintering at 1000-1400 °C temperature. A uniform nickel layer on AlN powders was deposited prior to sintering using electroless plating technique. A composite consisting of ternary additions, metallic phase, Ni and ceramic phase AlN within a matrix of Astaloy Cr-M had been prepared under Ar shroud and then tube furnace sintered. The experimental results carried out by using XRD (X-Ray Diffraction) and SEM (Scanning Electron Microscope) for composition (10% AlN-Astaloy Cr-M) 10% Ni at 1400 °C suggest that the best properties as 132.45HB and permittivity were obtained at 1400 °C.

Keywords: composite, electroless nickel plating, powder metallurgy, sintering

Procedia PDF Downloads 277

Authors: Widyani Fatwa Dewi, Subroto Athor

Abstract:

In a telecommunication service provider, quantity and interval of customer demand often difficult to predict due to high dependency on customer expansion strategy and technological development. Demand arrives when a customer needs to add capacity to an existing site or build a network in a new site. Because demand is uncertain for each period, and sometimes there is a null demand for several equipments, it is categorized as intermittent. This research aims to improve demand forecast quality in Indonesia's telecommunication service providers by using Artificial Neural Network. In Artificial Neural Network, the pattern or relationship within data will be analyzed using the training process, followed by the learning process as validation stage. Historical demand data for 36 periods is used to support this research. It is found that demand forecast by using Artificial Neural Network outperforms the existing method if it is reviewed on two criteria: the forecast accuracy, using Mean Absolute Deviation (MAD), Mean of the sum of the Squares of the Forecasting Error (MSE), Mean Error (ME) and service level which is shown through inventory cost. This research is expected to increase the reference for a telecommunication demand forecast, which is currently still limited.

Keywords: artificial neural network, demand forecast, forecast accuracy, intermittent, service level, telecommunication

Procedia PDF Downloads 165

Authors: F. Hekmatipour, M. A. Akhavan-Behabadi, B. Sajadi

Abstract:

In this paper, the combined free and forced convection heat transfer of the Copper Oxide-Heat Transfer Oil (CuO-HTO) nanofluid flow in horizontal and inclined microfin tubes is studied experimentally. The flow regime is laminar, and pipe surface temperature is constant. The effect of nanoparticle and microfin tube on the heat transfer rate is investigated with the Richardson number which is between 0.1 and 0.7. The results show an increasing nanoparticle concentration between 0% and 1.5% leads to enhance the combined free and forced convection heat transfer rate. According to the results, five correlations are proposed to provide estimating the free and forced heat transfer rate as the increasing Richardson number from 0.1 to 0.7. The maximum deviation of both correlations is less than 16%. Moreover, four correlations are suggested to assess the Nusselt number based on the Rayleigh number in inclined tubes from 1800000 to 7000000. The maximum deviation of the correlation is almost 16%. The Darcy friction factor of the nanofluid flow has been investigated. Furthermore, CuO-HTO nanofluid flows in inclined microfin tubes.

Keywords: nanofluid, heat transfer oil, mixed convection, inclined tube, laminar flow

Procedia PDF Downloads 256

Authors: Thomas E. Portegys

Abstract:

An animal behavior problem is presented in the form of a nest-building task that involves two cooperating virtual birds, a male and female. The female builds a nest into which she lays an egg. The male's job is to forage in a forest for food for both himself and the female. In addition, the male must fetch stones from a nearby desert for the female to use as nesting material. The task is completed when the nest is built, and an egg is laid in it. A goal-seeking neural network and a recurrent neural network were trained and tested with little success. The goal-seeking network was then enhanced with “place cells”, allowing the birds to spatially navigate the world, building the nest while keeping themselves fed. Place cells are neurons in the hippocampus that map space.

Keywords: artificial animal intelligence, artificial life, goal-seeking neural network, nest-building, place cells, spatial navigation

Procedia PDF Downloads 59

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: earnings management, generalized linear regression, neural networks multi-layer perceptron, Tehran stock exchange

Procedia PDF Downloads 424

Authors: Saeid Seddegh, Xiaolin Wang, Alan D. Henderson, Dong Chen, Oliver Oims

Abstract:

The main objective of this research is to study the heat transfer processes and phase change behaviour of a phase change material (PCM) in shell and tube latent heat thermal energy storage (LHTES) systems. The thermal behaviour in a vertical and horizontal shell-and-tube heat energy storage system using a pure thermal conduction model and a combined conduction-convection heat transfer model is compared in this paper. The model is first validated using published experimental data available in literature and then used to study the temperature variation, solid-liquid interface, phase distribution, total melting and solidification time during melting and solidification processes of PCMs. The simulated results show that the combined convection and conduction model can better describe the energy transfer in PCMs during melting process. In contrast, heat transfer by conduction is more significant during the solidification process since the two models show little difference. Also, it was concluded that during the charging process for the horizontal orientation, convective heat transfer has a strong effect on melting of the upper part of the solid PCM and is less significant during melting of the lower half of the solid PCM. However, in the vertical orientation, convective heat transfer is the same active during the entire charging process. In the solidification process, the thermal behavior does not show any difference between horizontal and vertical systems.

Keywords: latent heat thermal energy storage, phase change material, natural convection, melting, shell and tube heat exchanger, melting, solidification

Procedia PDF Downloads 555

Authors: Mohammad Heidari

Abstract:

In this paper a method for high strength steel is proposed of residual stresses in autofrettaged tubes by combination of artificial neural networks is presented. Many different thick walled cylinders that were subjected to different conditions were studied. At first, the residual stress is calculated by analytical solution. Then by changing of the parameters that influenced in residual stresses such as percentage of autofrettage, internal pressure, wall ratio of cylinder, material property of cylinder, bauschinger and hardening effect factor, a neural network is created. These parameters are the input of network. The output of network is residual stress. Numerical data, employed for training the network and capabilities of the model in predicting the residual stress has been verified. The output obtained from neural network model is compared with numerical results, and the amount of relative error has been calculated. Based on this verification error, it is shown that the radial basis function of neural network has the average error of 2.75% in predicting residual stress of thick wall cylinder. Further analysis of residual stress of thick wall cylinder under different input conditions has been investigated and comparison results of modeling with numerical considerations shows a good agreement, which also proves the feasibility and effectiveness of the adopted approach.

Keywords: thick walled cylinder, residual stress, radial basis, artificial neural network

Procedia PDF Downloads 417

Authors: Vishal Shetty, Pranjal Khasnis, Saptarshi Mandal

Abstract:

This work explores the design and fabrication of a fundamental pulse detonation engine (PDE) prototype on the basis of pressure and temperature pulse obtained from numerical simulation of the same. PDE is an advanced propulsion system that utilizes detonation waves for thrust generation. PDEs use a fuel-air mixture ignited to create a supersonic detonation wave, resulting in rapid energy release, high pressures, and high temperatures. The operational cycle includes fuel injection, ignition, detonation, exhaust of combustion products, and purging of the chamber for the next cycle. This work presents details of the core operating principles of a PDE, highlighting its potential advantages over traditional jet engines that rely on continuous combustion. The design focuses on a straightforward, valve-controlled system for fuel and oxidizer injection into a detonation tube. The detonation was initiated using an electronically controlled spark plug or similar high-energy ignition source. Following the detonation, a purge valve was employed to expel the combusted gases and prepare the tube for the next cycle. Key considerations for the design include material selection for the detonation tube to withstand the high temperatures and pressures generated during detonation. Fabrication techniques prioritized readily available machining methods to create a functional prototype. This work detailed the testing procedures for verifying the functionality of the PDE prototype. Emphasis was given to the measurement of thrust generation and capturing of pressure data within the detonation tube. The numerical analysis presents performance evaluation and potential areas for future design optimization.

Keywords: pulse detonation engine, ignition, detonation, combustion

Procedia PDF Downloads 24

Authors: Saleh Abu Dabous, Khaled Hamad, Rami Al-Ruzouq

Abstract:

Bridge condition assessment and rating provide essential information needed for bridge management. This paper reviews bridge inspection and condition rating practices and introduces a defect-based urgency index. The index is estimated at the element-level based on the extent and severity of the different defects typical to the bridge element. The urgency index approach has the following advantages: (1) It facilitates judgment submission, i.e. instead of rating the bridge element with a specific linguistic overall expression (which can be subjective and used differently by different people), the approach is based on assessing the defects; (2) It captures multiple defects that can be present within a deteriorated element; and (3) It reflects how critical the element is through quantifying critical defects and their severity. The approach can be further developed and validated. It is expected to be useful for practical purposes as an early-warning system for critical bridge elements.

Keywords: condition rating, deterioration, inspection, maintenance

Procedia PDF Downloads 453

Authors: Hooshmand Kalayeh

Abstract:

The human brain consists of reptilian, mammalian, and thinking brain. And mind consists of conscious, subconscious, and unconscious parallel neural-net programs. The primary objective of this paper is to propose a methodology for quantitative analysis of neural-nets associated with these mental activities in the neocortex. The secondary objective of this paper is to suggest a methodology for quantitative analysis of presence; the proposed methodologies can be used as a first-step to measure, monitor, and understand consciousness and presence. This methodology is based on Neural-Networks (NN), number of neuron in each NN associated with consciousness, subconsciouness, and unconsciousness, and number of neurons in neocortex. It is assumed that the number of neurons in each NN is correlated with the associated area and volume. Therefore, online and offline visualization techniques can be used to identify these neural-networks, and online and offline measurement methods can be used to measure areas and volumes associated with these NNs. So, instead of the number of neurons in each NN, the associated area or volume also can be used in the proposed methodology. This quantitative analysis and associated online and offline measurements and visualizations of different Neural-Networks enable us to rewire the connections in our brain for a more balanced living.

Keywords: brain, mind, consciousness, presence, sub-consciousness, unconsciousness, skills, concentrations, attention

Procedia PDF Downloads 315

Authors: Santhosh Nallapu, G. Radhakrishnamacharya

Abstract:

A two-fluid model of Herschel-Bulkley fluid flow through tubes of small diameters is studied. It is assumed that the core region consists of Herschel-Bulkley fluid and Newtonian fluid in the peripheral region. The analytical solutions for velocity, flow flux, effective viscosity, core hematocrit and mean hematocrit have been derived and the effects of various relevant parameters on these flow variables have been studied. It has been observed that the effective viscosity and mean hematocrit increase with yield stress, power-law index, hematocrit and tube radius. Further, the core hematocrit decreases with hematocrit and tube radius.

Keywords: two-layered model, non-Newtonian fluid, hematocrit, Fahraeus-Lindqvist effect, plug flow

Procedia PDF Downloads 472

Authors: Devineni Vijay Bhaskar, Yendluri Raja

Abstract:

We recommend a model for traffic sign detection stranded on Convolutional Neural Networks (CNN). We first renovate the unique image into the gray scale image through with support vector machines, then use convolutional neural networks with fixed and learnable layers for revealing and understanding. The permanent layer can reduction the amount of attention areas to notice and crop the limits very close to the boundaries of traffic signs. The learnable coverings can rise the accuracy of detection significantly. Besides, we use bootstrap procedures to progress the accuracy and avoid overfitting problem. In the German Traffic Sign Detection Benchmark, we obtained modest results, with an area under the precision-recall curve (AUC) of 99.49% in the group “Risk”, and an AUC of 96.62% in the group “Obligatory”.

Keywords: convolutional neural network, support vector machine, detection, traffic signs, bootstrap procedures, precision-recall curve

Procedia PDF Downloads 123

Authors: Muluken Biadgelegn Wollele, Mebratu Assaye Mengistu

Abstract:

Nanotechnology has created new opportunities for improving industrial efficiency and performance. One of the proposed approaches to improving the effectiveness of temperature exchangers is the use of nanofluids to improve heat transfer performance. The thermal conductivity of nanoparticles, as well as their size, diameter, and volume concentration, all played a role in influencing the rate of heat transfer. Nanofluids are commonly used in automobiles, energy storage, electronic component cooling, solar absorbers, and nuclear reactors. Convective heat transfer must be improved when designing thermal systems in order to reduce heat exchanger size, weight, and cost. Using roughened surfaces to promote heat transfer has been tried several times. Thus, both active and passive heat transfer methods show potential in terms of heat transfer improvement. There will be an added advantage of enhanced heat transfer due to the two methods adopted; however, pressure drop must be considered during flow. Thus, the current research aims to increase heat transfer by adding a twisted tap insert in a plain tube using a working fluid hybrid nanofluid (Al₂O₃-Cu) with a base fluid of water. A circular duct with inserts, a tube length of 3 meters, a hydraulic diameter of 0.01 meters, and tube walls with a constant heat flux of 20 kW/m² and a twist ratio of 125 was used to investigate Al₂O₃-Cu/H₂O hybrid nanofluid with inserts. The temperature distribution is better than with conventional tube designs due to stronger tangential contact and swirls in the twisted tape. The Nusselt number values of plain twisted tape tubes are 1.5–2.0 percent higher than those of plain tubes. When twisted tape is used instead of plain tube, performance evaluation criteria improve by 1.01 times. A heat exchanger that is useful for a number of heat exchanger applications can be built utilizing a mixed flow of analysis that incorporates passive and active methodologies.

Keywords: nanofluids, active method, passive method, Nusselt number, performance evaluation criteria

Procedia PDF Downloads 75

Authors: Deepika Bhalla, Raj Kumar Bansal, Hari Om Gupta

Abstract:

Dissolved Gas Analysis (DGA) has been widely used for fault diagnosis in a transformer. Artificial neural networks (ANN) have high accuracy but are regarded as black boxes that are difficult to interpret. For many problems it is desired to extract knowledge from trained neural networks (NN) so that the user can gain a better understanding of the solution arrived by the NN. This paper applies a pedagogical approach for rule extraction from function approximating neural networks (REFANN) with application to incipient fault diagnosis using the concentrations of the dissolved gases within the transformer oil, as the input to the NN. The input space is split into subregions and for each subregion there is a linear equation that is used to predict the type of fault developing within a transformer. The experiments on real data indicate that the approach used can extract simple and useful rules and give fault predictions that match the actual fault and are at times also better than those predicted by the IEC method.

Keywords: artificial neural networks, dissolved gas analysis, rules extraction, transformer

Procedia PDF Downloads 537

Authors: M. Moody, R. Mahmoodi, A. R. Zolfaghari, A. Aminottojari

Abstract:

In this study, flow inside the shell side of a shell-and-tube heat exchanger is simulated numerically for laminar and turbulent flows in both steady state and transient mode. Governing equations of fluid flow are discrete using finite volume method and central difference scheme and solved with simple algorithm which is staggered grid by using MATLAB programming language. The heat transfer coefficient is obtained using velocity field from equation Dittus-Bolter. In comparison with, heat exchanger is simulated with ANSYS CFX software and experimental data measured in the THTL test loop. Numerical results obtained from the study show good agreement with experimental data and ANSYS CFX results. In addition, by deliberation the effect of the baffle spacing and the baffle cut on the heat transfer rate for turbulent flow, it is illustrated that the heat transfer rate depends on the baffle spacing and the baffle cut directly. In other word in spied of large turbulence, if these two parameters are not selected properly in the heat exchanger, the heat transfer rate can reduce.

Keywords: shell-and-tube heat exchanger, flow and heat transfer, laminar and turbulence flow, turbulence model, baffle spacing, baffle cut

Procedia PDF Downloads 538

Authors: Baladitya Swaika, Rahul Khatry

Abstract:

Computer Adaptive Tests (CATs) is one of the most efficient ways for testing the cognitive abilities of students. CATs are based on Item Response Theory (IRT) which is based on item selection and ability estimation using statistical methods of maximum information selection/selection from posterior and maximum-likelihood (ML)/maximum a posteriori (MAP) estimators respectively. This study aims at combining both classical and Bayesian approaches to IRT to create a dataset which is then fed to a neural network which automates the process of ability estimation and then comparing it to traditional CAT models designed using IRT. This study uses python as the base coding language, pymc for statistical modelling of the IRT and scikit-learn for neural network implementations. On creation of the model and on comparison, it is found that the Neural Network based model performs 7-10% worse than the IRT model for score estimations. Although performing poorly, compared to the IRT model, the neural network model can be beneficially used in back-ends for reducing time complexity as the IRT model would have to re-calculate the ability every-time it gets a request whereas the prediction from a neural network could be done in a single step for an existing trained Regressor. This study also proposes a new kind of framework whereby the neural network model could be used to incorporate feature sets, other than the normal IRT feature set and use a neural network’s capacity of learning unknown functions to give rise to better CAT models. Categorical features like test type, etc. could be learnt and incorporated in IRT functions with the help of techniques like logistic regression and can be used to learn functions and expressed as models which may not be trivial to be expressed via equations. This kind of a framework, when implemented would be highly advantageous in psychometrics and cognitive assessments. This study gives a brief overview as to how neural networks can be used in adaptive testing, not only by reducing time-complexity but also by being able to incorporate newer and better datasets which would eventually lead to higher quality testing.

Keywords: computer adaptive tests, item response theory, machine learning, neural networks

Procedia PDF Downloads 176

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is one of the deep reinforcement learning families that combines deep neural networks (DNN) with reinforcement learning RL to discover the optimum of the control problem through experience gained from the interaction between the robot and its surroundings. In contrast to earlier policy gradient algorithms, which were unable to handle these two types of error because of over-or under-estimation introduced by the deep neural network model, this article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: deep neural networks, deep reinforcement learning, proximal policy optimization, state-of-the-art, trust region policy optimization

Procedia PDF Downloads 170

Authors: Christopher Lama, Alix Rieser, Aleksandra Molchanova, Charles Thangaraj

Abstract:

New technologies like Tesla’s Dojo have made high-performance embedded computing more available. Although automobile computing has developed and benefited enormously from these more recent technologies, the costs are still high, prohibitively high in some cases for broader adaptation, particularly for the after-market and enthusiast markets. This project aims to implement a Raspberry Pi-based low-power (under one hundred Watts) highly mobile computing cluster for a neural network. The computing cluster built from off-the-shelf components is more affordable and, therefore, makes wider adoption possible. The paper describes the design of the neural network, Raspberry Pi-based cluster, and applications the cluster will run. The neural network will use input data from sensors and cameras to project a live view of the road state as the user drives. The neural network will be trained to predict traffic behavior and generate warnings when potentially dangerous situations are predicted. The significant outcomes of this study will be two folds, firstly, to implement and test the low-cost cluster, and secondly, to ascertain the effectiveness of the predictive AI implemented on the cluster.

Keywords: CS pedagogy, student research, cluster computing, machine learning

Procedia PDF Downloads 103

Authors: Jooyoung Park, Junkyeong Kim, Aoqi Zhang, Seunghee Park

Abstract:

Non-destructive testing on cable is in great demand due to safety accidents at sites where many equipments using cables are installed. In this paper, the quantitative change of the obtained signal was analyzed using a magnetic flux leakage (MFL) method. A two-dimensional simulation was conducted with a FEM model replicating real elevator cables. The simulation data were compared for three parameters (depth of defect, width of defect and inspection velocity). Then, an experiment on same conditions was carried out to verify the results of the simulation. Signals obtained from both the simulation and the experiment were transformed to characterize the properties of the damage. Throughout the results, a cable damage detection based on an MFL method was confirmed to be feasible. In further study, it is expected that the MFL signals of an entire specimen will be gained and visualized as well.

Keywords: magnetic flux leakage (mfl), cable damage detection, non-destructive testing, numerical simulation

Procedia PDF Downloads 383

Authors: Slim Chokri

Abstract:

Load forecasting is one of the central functions in power systems operations. Electricity cannot be stored, which means that for electric utility, the estimate of the future demand is necessary in managing the production and purchasing in an economically reasonable way. A majority of the recently reported approaches are based on neural network. The attraction of the methods lies in the assumption that neural networks are able to learn properties of the load. However, the development of the methods is not finished, and the lack of comparative results on different model variations is a problem. This paper presents a new approach in order to predict the Tunisia daily peak load. The proposed method employs a computational intelligence scheme based on the Fuzzy neural network (FNN) and support vector regression (SVR). Experimental results obtained indicate that our proposed FNN-SVR technique gives significantly good prediction accuracy compared to some classical techniques.

Keywords: neural network, load forecasting, fuzzy inference, machine learning, fuzzy modeling and rule extraction, support vector regression

Procedia PDF Downloads 436