Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Cluster analysis. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

Experimental Study on Diesel Engine Using Hybrid Fuel Blends

Abstract: In this study, ethyl ester of pungamia oil is added as an additive to prevent separation of bioethanol from diesel. Stability, fuel properties, performance, and emission characteristics of the blended fuels were investigated and compared with base diesel. The result of the tests shows that brake thermal efficiency of the engine was almost equal to that of base diesel. It was observed that the exhaust gas temperature and Carbon dioxide (CO2) emissions of the blends were lower than those of base diesel. The oxides of nitrogen (NOx) and smoke emissions were decreased upto 15% and 12% respectively with an increase of bioethanol upto 25% in the blends as compared with the base diesel. However, a slight increase in hydrocarbon (HC) and carbon monoxide (CO) emissions were observed. It can be concluded from the analysis of experimental results that the blend mixture E20P10D70 could be effectively used as a hybrid fuel in the existing compression ignition engine without any hardware modification.

Effect of diethyl ether and ethanol as an oxygenated additive on Calophyllum inophyllum biodiesel in CI engine.

Abstract: The present experimental investigation is conducted to examine the working characteristics of compression ignition (CI) engine using oxygenated additives such as diethyl ether and ethanol to the blends of Calophyllum inophyllum biodiesel. Experiments are conducted on a water-cooled single-cylinder constant speed DI (direct injection) diesel engine under same operating circumstances. The results indicates that an enhancement of brake thermal efficiency is up to 3.7% and 6.2% with an addition of ethanol and DEE additive in biodiesel blended fuels respectively at maximum load condition. This is attributable to the existence of higher oxygen value and volatile nature of the additives. The combustion characteristics like in-cylinder pressure and net heat release rate of DEE blended fuels are 1.1-5.2% and 0.4-2.7% higher than other blends respectively. This is mainly due to higher cetane number and high volatile nature of DEE. This also results in higher NOX emissions. But 2-9% drop in nitrous oxide emission is noticed for biodiesel with ethanol blends compared to all other blends. This is as a result of superior latent heat of vaporization and lesser cetane number of ethanol which results in lower cylinder pressure about 0.4-2.6% and this end up with more unburned HC and CO emissions. Energy and exergy studies help to analyze the result of ethanol and DEE additive along with blends of biodiesel. The exergy efficiencies of DEE blended fuels enhance up to 2.3-6% compared to other blends at all load conditions. This is attributable to the superior combustion characteristics of DEE.

Multi-Disease Classification Model Using Strassen’s Half of Threshold (SHoT) Training Algorithm in Healthcare Sector

Abstract: In healthcare industry, Neural Network has attained a milestone in solving many real-life classification problems varies from very simple to complex and from linear to non-linear. To improve the training process by reducing the training time, Adaptive Skipping Training algorithm named as Half of Threshold (HOT) has been proposed. To perform the fast classification and also to improve the computational efficiency such as accuracy, error rate, etc., the highlighted characteristics of proposed HOT algorithm has been integrated with Strassen’s matrix multiplication algorithm and derived a novel, hybrid and computationally efficient algorithm for training and validating the neural network named as Strassen’s Half of Threshold (SHoT) Training Algorithm. The experimental outcome based on the simulation demonstrated that the proposed SHOT algorithm outperforms both BPN and HOT algorithm in terms of training time which is reduced with the range of 7% to 54% and its efficiency which is improved with the range of 3% to 15% on various dataset such as Hepatitis, SPeCT, Heart, Liver Disorders, Breast Cancer Wisconsin (Diagnostic), Drug Consumption, Cardiotocography, Splice-junction Gene Sequences and Thyroid Disease dataset that are extracted from Machine Learning Dataset Repository of UCI. It can be integrated with any type of supervised training algorithm.

An improved genetic algorithm-based optimal sizing of solar photovoltaic/wind turbine generator/diesel generator/battery connected hybrid energy systems for standalone applications

Abstract: This paper proposes an improved GA-based new approach for the optimal design of hybrid energy systems comprises of solar PV, wind, diesel generator and battery connected systems for supplying the e...