Prediction of Single Cylinder Diesel Engine Emission Characteristics Using Pongamia Oil Blends With Artificial Neural Network
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2014, Vol 2, Issue 12
Abstract
In this study, an artificial neural network, an artificial intelligence technique, is developed to predict the exhaust emissions (CO, CO2, HC and NOx) of the four stroke, single cylinder, vertical, air cooled diesel engine. A single cylinder, four-stroke test engine was fuelled with diesel fuel with various percentages of pongamia oil (0, 5, 15 and 20%) to acquire the data’s for training and testing of the proposed ANN. To acquire data’s for training and testing of the proposed ANN, the test engine was operated at different speeds and loads. A standard back-propagation algorithm which is ANN model based for the engine was developed using some of experimental data’s for training and testing for the proposed ANN. The emission parameters of the single cylinder diesel engine were validated by comparing the proposed ANN’s prediction dataset with the experimental results. Results showed that the ANN gives the best accuracy for predicting the emission parameters for the single cylinder diesel engine with the minimum errors with the average range of 0.03998, 0.0002, 0.0002 and 0.0001 for CO, CO2, HC and NOx respectively.
Authors and Affiliations
R. Girimurugan, K. A. Rameshkumar
Keywords
Related Articles
- EP ID EP19247
- DOI -
- Views 225
- Downloads 4
Key Issuing Scheme For Communication In Peer To Peer Networks
Identity based cryptography (IBC) was introduced into peer-to-peer (P2P) networks. In this paper we propose a secure key issuing scheme for P2P networks using IBC. We are present an IBC infrastructure, which consists of...
Compound Normal with Gamma Mixture Models - A Model Characteristic Perspective
In this paper, we discuss convergence performance issues of Compound Normal with Gamma Mixture(CNGM) and Truncated Compound Normal with Gamma Mixture(TCNGM) models that we have proposed in our earlier work in comparison...
A Survey on Frequent Pattern Mining Methods
In this paper, the frequent pattern mining methods have been discussed that play very important role to generate association rules. The aim of frequent pattern mining is to search repeatedly occurring relationships in a...
Auxetic Materials
Auxetic materials are known for their peculiar behavior unlike conventional materials the thickness of these materials increase under the action of axial pull. In this paper we are going to study the properties of Auxet...
Design and Optimization of H-shaped Fractal Microstrip Patch Antenna with Defected Ground Structure for Wireless Applications
Microstrip antennas find applications in aircraft, satellite and missile applications where important characteristics are size, weight and complexity. They are less bulky and capable of resonating at different bands but...