Time filter

Source Type


Shukla A.K.,JBIET | Raghu T.,Near Net Shape Group | Rajesham S.,CRV Institute of Technology and science | Balasundar I.,Near Net Shape Group
Transactions of the Indian Institute of Metals | Year: 2014

In this study indigenously developed Titan 31, has been hot rolled under alpha-beta process at elevated temperatures with heavy reduction and heat treated at different temperatures with different heat treatment processes to obtain microstructure which is conducive for formability. The uniformly distributed, globular and very fine micro structure has been obtained at finally rolled, and annealed at 800 °C. ANOVA analysis has been carried out to analyze parameters influencing formability on the basis of results obtained from tensile tests in plane strain at different elevated temperatures, at different cross head speeds and different angles to rolling as per Taguchi design of experiment, for anisotropy value, exponent of hardening and percentage elongation. A new matrix model has been developed to optimize formability parameters. The results obtained from new matrix model have been analyzed with results of Taguchi overall evaluation criteria considering combined effect of anisotropy value, exponent of hardening and percentage elongation. The optimized value from new matrix model are temperature 718 °C, crosshead speed 1.0 mm per min (0.00066 per second), angle to rolling to which specimen tested is 44.9° and that of Taguchi overall evaluation criteria temperature 725 °C, crosshead speed (0.0005 per second), angle to rolling to which specimen tested is 45° among all factors selected in the study. © 2014 Indian Institute of Metals. Source

Sagar K.,Chitanya Bharathi Institute of Technology | Vathsal S.,JBIET
Advances in Intelligent Systems and Computing | Year: 2013

We introduce a method, based on genetic algorithm to automate and optimize the design of combinational circuits. Usually, logic circuits are designed by human beings who have a specific repertoire of conventional design techniques. These techniques limit the solutions that may be considered during the design process in both form and quality. The application of genetic algorithms has allowed the creation of circuits which are substantially superior to the best known human designs. We describe the important issues to consider when solving this circuit design problem : the representation scheme, the encoding scheme, the fitness function. We compare the solutions by our approach against those generated by a human designer. We also show that our approach produces better performances both in terms of quality of solution and in terms of speed of convergence. © 2013 Springer-Verlag. Source

Dhanalaxmi B.,Institute of Aeronautical Engineering | Apparao Naidu G.,JBIET
Procedia Computer Science | Year: 2015

The proposed system categorizes various defects by using association rule mining dependent problem classification approach, which is applied to collect the actual defects using recognition. Association rule mining algorithm at times results in useless policies. To avoid this kind of concerns, the principles prior to classification determined by assistance as well as confidence value has to be optimized. In this exploration, Adaptive Particle Swarm (APSO) optimization algorithm is used. This can discover the best assistance and confidence value to have the best policies. And finally Artificial Neural Network (ANN) can be used to classify the actual defects determined. © 2015 Published by Elsevier B.V. Source

Rajeswara Rao D.,niversity | Sahitya S.,niversity | Murthy J.V.R.,Jawaharlal Nehru Technological University Kakinada | Apparao Naidu G.,JBIET
International Journal of Applied Engineering Research | Year: 2014

Sensitive information such as customer data and business secrets constitute the main assets of any organization. Assigning a Misusability weight to a given dataset is strongly related to the way the data is presented (e.g., tabular data, structured or free text) and is domain specific. We define misusability assessment data events in real time data records present in domain expert with publishing data with other users. Records Ranking [LR] handles unknown values well with an assumption is made that the relationships between the attributes and the dependent variable are linear. In this paper, we propose to use Angular Metric for Shape Similarity (AMSS) for calculating the individual misusability score in reliable data record with different users. Here we also use some data assessment techniques for handling misuseability. By using AMSS we also calculate execution times of each assessment individually. © Research India Publications. Source

Rajeswara Rao D.,Koneru Lakshmaiah College of Engineering | Raghuveer A.,Koneru Lakshmaiah College of Engineering | Murthy J.V.R.,Jawaharlal Nehru Technological University Kakinada | Apparao Naidu G.,JBIET
International Journal of Applied Engineering Research | Year: 2014

Social network like Face book, Twitter, Flicker, and You Tube present opportunities and challenges to study collective behavior on a large scale. The scale of these networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we already have an edge-centric clustering scheme to extract sparse social dimensions. In this article, we propose to use a Link Based Clustering Ensemble (LCE) approach for identifying common user activities and grouping similar users using clusters means that the users of same activity can group into one cluster. Finally we draw graph between different clusters. In LCE method the performance is well and execution time is very less than other methods. © Research India Publications. Source

Discover hidden collaborations