International Journal for Innovative Research in Science & Technology #IJIRST August 2017

International Journal for Innovative Research in Science & Technology

#IJIRST Journal: Call for paper
Volume 4 Issue 3 August 2017
Index Copernicus (IC) Value = 62.83
Impact Factor: 4.371
For more details : http://ijirst.org/

International Journal for Innovative Research in Science & Technology

#IJIRST Journal: Call for paper
Index Copernicus (IC) Value = 62.83
IJIRST Journal: Volume 3 Issue 12
Impact Factor: 4.371
http://ijirst.org

Paper Title:- Development of ANN and AFIS Models for Age Predictionof in-Service Transformer Oil Samples

Paper Title:- Development of ANN and AFIS Models for Age Predictionof in-Service Transformer Oil Samples

Author Name:- Mohammad Aslam Ansari 

Department of Electrical Engineering 

Abstract:- Power transformer is one of the most important and expensive equipment in electrical network. The transformer oil is a very important component of power transformers. It has twin functions of cooling as well as insulation. The oil properties like viscosity, specific gravity, flash point, oxidation stability, total acid number, breakdown voltage, dissipation factor, volume resistivity and dielectric constant suffer a change with respect to time. Hence it is necessary that the oil condition be monitored regularly to predict, if possible, the remaining lifetime of the transformer oil, from time to time. Six properties such as moisture content, resistivity, tan delta, interfacial tension and flash point have been considered. The data for the six properties with respect to age, in days, has been taken from literature, whereby samples of ten working power transformers of 16 to 20 MVA installed at different substations in Punjab, India have been considered. This paper aims at developing ANN and ANFIS models for predicting the age of in-service transformer oil samples. Both the the models use the six properties as inputs and age as target. ANN (Artificial Neural Network) model uses a multi-layer feedforward network employing back propagation algorithm, and ANFIS (Adaptive Neuro Fuzzy Inference System) model is based on Sugeno model. The two models have been simulated for estimating the age of unknown transformer oil samples taken from generator transformers of Anpara Thermal Power Project in state of U.P. India. A comparative analysis of the two models has been made whereby ANFIS model has been found to yield better results than ANN model.     

Keywords: ANN, ANFIS, Power Transformer, Regression, Performance, Backpropagation Algorithm   

I.         Introduction

Power transformer is one of the most important constituent of electrical power system. The transformer oil, a very important ingredient of power transformers, acts as a heat transfer fluid and also serves the purpose of electrical insulation. Its insulating property is subjected to the degradation because of the ageing, high temperature, electrical stress and other chemical reactions. Hence it is necessary that the oil condition be monitored regularly. This will help to predict, if possible, the in-service period or remaining lifetime of the transformer oil, from time to time.

       There are several characteristics which can be measured to assess the present condition of the oil. The main oil characteristics are broadly classified as physical, chemical and electrical characteristics; some of these are viscosity, specific gravity, flash point, oxidation stability, total acid number, breakdown voltage, dissipation factor, volume resistivity and dielectric constant. There exists a co-relation among some of the oil properties and suffer a change in their values with respect to time [2]. This variation of oil properties with respect to time has been utilised to develop the two models as said earlier

      The training data for the proposed work have been obtained from literature, whereby ten working transforms of 16 to 20 MVA, 66/11 KV installed at different substations in the state of Punjab, India have been considered. The six properties of transformer oil such as breakdown voltage (BDV), moisture, resistivity, tan delta, interfacial tension and flash point have been considered as inputs and age as target. Test data have been taken from generator transformers of 250 MVA, 15.75kV/400kV from Anpara Thermal Power Project in state of U. P., India.

II.     “Ann” and “Anfis” methods

It is known that classical models need linear data for their processing, therefore models like ANN and ANFIS that are based on soft computing techniques, play an important role for solving these kinds of non-linear problems.

        Neural networks exhibit characteristics such as mapping capabilities or pattern association, generalization, robustness, fault tolerance, parallel and high speed processing. Neural networks can be trained with known examples of a problem to acquire knowledge about it. Once trained successfully, the network can be put to effective use in solving unknown or untrained instances of the problem. ANN model which uses multilayer feed forward network is based on back propagation (BP) learning algorithm of neural network. Backpropagation gives very good answers when presented with inputs never seen before. This property of generalization makes it possible to train a network on giving set of input-target pairs and get good output.

         ANFIS stands for Adaptive Neural Fuzzy Inference System. Using a given input/output data set, the toolbox function ANFIS constructs a fuzzy inference system (FIS) whose membership function parameters are tuned (adjusted) using either a backpropagation algorithm alone, or in combination with a least squares type of method. This allows the fuzzy systems to learn from the data they are modelling. These techniques provide a method for the fuzzy modeling procedure to learn information about a data set, in order to compute the membership function parameters that best allow the associated fuzzy inference system to track the given input/output data. This learning method works similarly to that of neural networks.

III.       Development of ann model

The proposed ANN model uses “Levenburg-Marquardt (trainlm) algorithm which is independent of learning rate, hence by simply changing the number of neurons in hidden layer, training and testing error could be reduced. A total of 700 data sets obtained from literature [2] were arranged in tabular form and used for training the neural network. The model uses a simple two layer network, one hidden layer and one output layer. Input layer comprises of six neurons, one for the each input, while the output layer has a single neuron for a single output, the age of oil sample.

         It has been found that network architecture that uses 20 neurons in hidden layer gave the best performance with a regression of 0.999 and mean square error (MSE) of 83.0 ( data is non –normalized, so error looks large ) . The training continued for 184 iterations with training functions logsig in hidden layer and purelin in output layer respectively.

For More Information Click Here

Know about it : Big Data is Transforming Sports #IJIRST

This article was originally published on The Conversation. The publication contributed this article to Live Science's Expert Voices: Op-Ed & Insights.

In sport we don’t just want to know who won. We now want to know how to replicate success and then improve on it. And to do this, we’re using data – and lots of it. The field of “big data” analytics has come to sport and athletics, with massive implications for sport as we know it.

IJIRST 1.638

The Women’s Tennis Association recently approved real-time data capture, which means that court-side coaches can now advise their players during a match on best shot placement or serve direction using little more than a smartphone or tablet. It could be argued that this detracts from a player using their instincts to make their own decisions. But it means that to tennis fans watching, it’s easier to understand what makes a good player great and why their opponent lost, while players have an even keener competitive edge.

International Journal for Innovative Research in Science and Technology (IJIRST) is a one of the popular international multidisciplinary, open access, peer-reviewed, fully refereed journal. It is an international journal that aims to contribute to the constant innovative research and training, so as to promote research in the field of science and technology.

Impact Factor: 1.638

New Camera Sensor Eliminates Need for Flash #IJIRST

#IJIRST - Impact factor 1.638

No flash? No problem. A new imaging sensor could soon make it possible for photographers to take clear, sharp photos, even in dim lighting.

for more detail click here: #IJIRST

Created by a team of researchers at Nanyang Technological University (NTU) in Singapore, the new sensor is highly sensitive to both visible and infrared light, which means it could be used in everything from the family Nikon to surveillance and satellite cameras.

IJIRST - IMPACT FACTOR 1.638

The sensor, which is 1,000 times more sensitive to light than the imaging sensors of most of today's cameras, gets this high photoresponse from its innovative structure.

main article of this post : click here

to get more information click here: 

IMPACT FACTOR #IJIRST

International Journal for Innovative Research in Science and Technology (IJIRST)

IJIRST is a monthly international journal publishing the finest peer-reviewed research and review articles in all fields of Science and technology. IJIRSTfollows stringent guidelines to select the manuscripts on the basis of its originality, importance, timeliness, accessibility, grace and astonishing conclusions. IJIRST is also popular for rapid publication of accepted manuscripts.

IMPACT FACTOR – 1.638

Innovation Redefined... #ijirst

Thermal Radar

Photograph by Ralph Smith

Michael Dortch was building video surveillance trailers for industrial parks in Colorado when his clients started asking for near-omniscient views of their properties. They wanted to see intruders in the dark from all angles, but such coverage required up to seven thermal infrared cameras and cost more than $100,000. So Dortch and a colleague spent four years developing a cheaper, more capable alternative. Their Thermal Radar system provides 360-degree infrared coverage that can spot people, fires, vehicles, and more.

main article : click here to view 

The heart of the invention is a single, spinning thermal sensor. Onboard processors constantly stitch images together for a refreshing panoramic video feed, and intelligent software finds threats.

A finished unit will cost about $16,000—many times cheaper than any system that comes close—and should be ready for its debut later this year. The first and biggest market will be corporate security. But the forest service, the Utah Department of Transportation, and even the Pentagon, Dortch says, also have his invention on their radar. how it works

Innovation Redefined... #IJIRST

Evolution of extreme parasites explained by scientists

Extreme adaptations of species often cause such significant changes that their evolutionary history is difficult to reconstruct. Zoologists at the University of Basel in Switzerland have now discovered a new parasite species that represents the missing link between fungi and an extreme group of parasites. Researches are now able to understand for the first time the evolution of these parasites, causing disease in humans and animals. The study has been published in the latest issue of the scientific journal Proceedings of the National Academy of Sciences (PNAS).

Parasites use their hosts to simplify their own lives. In order to do so, they evolved features that are so extreme that it is often impossible to compare them to other species. The evolution of these extreme adaptations is often impossible to reconstruct. The research group lead by Prof. Dieter Ebert from the Department of Environmental Science at the University of Basel has now discovered the missing link that explains how this large group of extreme parasites, the microsporidia, has evolved. The team was supported in their efforts by scientists from Sweden and the U.S.

Innovation Redefined. . . @IJIRST

Between fungi and parasite

The team of zoologists lead by Prof. Dieter Ebert has been studying the evolution of microsporidia for years. When they discovered a new parasite in water fleas a couple of years ago, they classified this undescribed species as a microsporidium, mostly because it possessed the unique harpoon-like infection apparatus (the polar-tube), one of the hallmarks of microsporidia. The analysis of the entire genome had several surprises in store for them: The genome resembles more that of a fungi than a microsporidium and, in addition, also has a mitochondrial genome. The new species, now named Mitosporidium daphniae, thus represents the missing link between fungi and microsporidia.

Source:

The above story is based on materials provided by Universität Basel. Note: Materials may be edited for content and length.

For more details click here: IJIRST