Pai S.,NMAM Institute of Technology |
Rao R.B.K.N.,COMADEM International
Machining Science and Technology | Year: 2012
The monitoring of tool wear is a most difficult task in the case of various metal-cutting processes. Artificial Neural Networks (ANN) has been used to estimate or classify certain wear parameters, using continuous acquisition of signals from multi-sensor systems. Most of the research has been concentrated on the use of supervised neural network types like multi-layer perceptron (MLP), using back-propagation algorithm and Radial Basis Function (RBF) network. In this article, a new constructive learning algorithm proposed by Fritzke, namely Growing Cell Structures (GCS) has been used for tool wear estimation in face milling operations, thereby monitoring the condition of the tool. GCS generates compact network architecture in less training time and performs well on new untrained data. The performance of this network has been compared with that of another constructive learning algorithm-based neural network, namely the Resource Allocation Network (RAN). For the sake of establishing the effectiveness of GCS, results obtained have been compared with those obtained using Multi Layer Perceptron (MLP), which is a standard and widely used neural network. © 2012 Copyright Taylor and Francis Group, LLC.
Udaya,NMAM Institute of Technology |
Fernandes P.,Alvas Institute Of Engineering And Technology
Materials Science Forum | Year: 2015
The paper illustrates Carbon nanotubes reinforced pure Al (CNT/Al) composites and fly ash reinforced pure Al (FA/Al) composites produced by ball-milling and sintering. Microstructures of the fabricated composite were examined and the mechanical properties of the composites were tested and analysed. It was indicated that the CNTs and fly ash were uniformly dispersed into the Al matrix as ball-milling time increased with increase in hardness. © (2015) Trans Tech Publications, Switzerland.
Bekal S.,NMAM Institute of Technology |
Bhat N.R.,Srinivasa Institute of Technology
Energy Sources, Part A: Recovery, Utilization and Environmental Effects | Year: 2012
The substitution of mineral oil with vegetable oil as a lubricant in a CI engine is explored in this study. The experiments have been conducted with neat pongamia oil, blend of pongamia oil and mineral oil (50% V/V), and neat mineral oil as lubricants; and neat pongamia oil, blends of pongamia oil, and diesel in proportions of 20, 40, and 100, neat pongamia ester, and blends of pongamia ester and diesel in proportions of 20, 40, and 100 as fuel. For various combinations of fuel and lubricant, NOx, smoke, CO, HC, BSEC, EGT, and friction power were compared. It was found that there was no difficulty in operating the engine using the lubricants considered in this work. Further, it was found that the best results were recorded for the fuel-lubricant combination of neat pongamia as both fuel and lubricant. © 2012 Copyright Taylor and Francis Group, LLC.
Mallikappa D.N.,NMAM Institute of Technology |
Pratap Reddy R.P.,Reva institute of Technology and Management |
International Journal of Renewable Energy Research | Year: 2012
This work composed with performance and emission studies of three stationary diesel engines operated with 20% cardanol biofuel volumetric blends. A single cylinder diesel engine and VCR engines were used to evaluate theperformance and emission characteristics of cardanol biofuel. An extended experimental study was conducted on a double cylinder CI engine, to evaluate the performance and emission characteristics. The cardanol biofuel volumetric blends between 0-25% and base fuel (Petro diesel) were tested at various loads between 0-full load. From the results, brake thermal efficiency, increased with increase in load. The brake specific energy consumption decreased by 30 to 40% with increase in brake power. The HC emissions were nominal up to B20, and more at B25. The NOx emissions (ppm) increased with increased proportion of blends. The carbon monoxide emissions increased with higher blends and decreased slightly at higher loads. From this investigation, it is observed that up to 20% blends of cardanol biofuels may be used in CI engines without any modifications.
Mallikappa D.N.,NMAM Institute of Technology |
Reddy R.P.,Reva institute of Technology and Management |
Renewable Energy | Year: 2012
India imports more than seventy percent of the oil it uses and is looking for alternative fuel to reduce its dependence on imports. In India, bio fuels derived from non-edible oils is considered as a renewable alternative to the fossil diesel. The cost of the biodiesel is higher than diesel and hence in this work, cardanol was used as an alternative renewable fuel for the diesel engine. The engine tests were conducted on a double cylinder, direct injection, compression ignition engine. From the engine tests, it is observed that the brake power increases (by 70% approximately) as load increases. Brake specific energy conversion decreases (by 25-30% approximately) with increase in brake power. Brake thermal efficiency increases with higher brake power and emission levels (HC, C O, NO X) were nominal up to 20% blends. © 2011 Elsevier Ltd.
Shenoy P.,NMAM Institute of Technology |
Bangera K.V.,National Institute of Technology Karnataka |
Shivakumar G.K.,National Institute of Technology Karnataka
Crystal Research and Technology | Year: 2010
The investigations on the formation of mixed crystals of ammonium dihydrogen orthophosphate (ADP) and potassium dihydrogen orthophosphate (KDP) i.e. potassium ammonium dihydrogen phosphate, K1-x(NH 4)xH2PO4 have been presented in this paper. Pure and mixed crystals of ADP and KDP have been grown by slow evaporation technique from the supersaturated solution at an ambient temperature 26±1 °C for ammonium concentration x in the range 0.0 ≤ × ≤ 1.0 in the case of mixed crystals. Crystal compositions were determined by flame atomic absorption spectroscopy and chemical analysis. The results of the X-ray analysis of the grown crystals are also reported. Thermogravimetric analysis (TGA) and differential thermal analysis (DTA) were used to study the kinetic process of dehydration and the high temperature phase behaviour. DTA showed the distinct thermal events attributed to dehydration of ADP, KDP and K1-x(NH4)xH2PO4. The results of thermal analysis and chemical analysis are consistent with each other. © 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.
Hebbale A.M.,NMAM Institute of Technology |
S S.M.,Malnad College of Engineering
Materials Today: Proceedings | Year: 2015
In the present work microwave cladding technique was progressed for enhancement of surface properties of high speed steel (SS-304). The experiments were conducted in domestic microwave oven with the help of Al2O3 shield. The clad of thickness, approximately 1mm was developed by microwave exposure at frequency 2.45GHz. The entire setup was exposed to microwave environment for about 1080s. The developed clads were characterized using FE-SEM, EDS, XRD and measurement of Vicker's microhardness. Microstructural study reveals that there is a metallurgical bond with SS-304 substrate & partial diffusion of constituent elements. Chromium was observed segregated around the cell boundaries while iron and nickel were identified inside the cells. © 2015 Elsevier Ltd.
Prabhu N.,NMAM Institute of Technology
Power Systems | Year: 2014
Series compensation of long transmission lines is an economic solution to the problem of enhancing power transfer and improving system stability. However, series compensated transmission lines connected to the turbo generator can result in Subsynchronous Resonance (SSR) leading to undamped Subsynchronous Oscillations (SSO). The advent of Flexible AC Transmission System (FACTS) controllers using high power semiconductors has made it possible to apply these controllers in conjunction with fixed series compensation, not only to improve system performance, but also to overcome the problem of SSR. FACTS controllers based on Voltage Source Converter (VSC) are emerging controllers that have several advantages over the conventional ones using thyristors. STATCOM is a shunt FACTS controller suitable for voltage regulation and damping of oscillations. This chapter describes the analysis and simulation of a series compensated system with STATCOM connected at the electrical center of the transmission line. The SSR characteristic of the combined system is discussed. A new technique of SSR damping is presented in which a STATCOM injects subsynchronous current. © 2015 Springer Science+Business Media Singapore.
Kallapur P.V.,Nmam Institute Of Technology |
Chiplunkar N.N.,Nmam Institute Of Technology
ACE 2010 - 2010 International Conference on Advances in Computer Engineering | Year: 2010
Recent research has provided means by which wireless sensor network with dynamic deadlines can take advantage of mobile agents for the purpose of data gathering. Already some work has been done in this direction in case of networks which are 'static' i.e., whose topology remains same once mobile agent starts its tour. This paper proposes a technique which makes mobile agent 'intelligent' enough to learn 'dynamic' changes in network topology as and when they occur, like new node getting added to network or existing node going down while taking care of dynamic deadlines of nodes. Also, we give analysis of results of applying the proposed technique on a simple real time wireless sensor network model with dynamic deadlines. Finally, paper wi l be concluded with mentioning of future directions of research. © 2010 IEEE.
Rajesh Kumar B.,Nmam Institute Of Technology |
Vardhan H.,National Institute of Technology Karnataka |
Govindaraj M.,National Institute of Technology Karnataka |
Vijay G.S.,Manipal University India
International Journal of Rock Mechanics and Mining Sciences | Year: 2013
This study aims to predict rock properties using soft computing techniques such as multiple regression, artificial neural network (MLP and RBF) models, taking drill bit speed, penetration rate, drill bit diameter and equivalent sound level produced during drilling as the input parameters. A database of 448 cases were tested for determination of uniaxial compressive strength (UCS), Schmidt rebound number (SRN), dry density (ρ), P-wave velocity (Vp), tensile strength (TS), modulus of elasticity (E) and percentage porosity (n) and the prediction capabilities of the models were then analyzed. Results from the analysis demonstrate that neural network approach is efficient when compared to statistical analysis in predicting rock properties from the sound level produced during drilling. © 2012 Elsevier Ltd.