ANN based evaluation of the NOx concentration in the exhaust gas of a marine two-stroke diesel engine

Jerzy Kowalski

doi:10.2478/v10012-008-0023-7

Abstract

ANN based evaluation of the NOx concentration in the exhaust gas of a marine two-stroke diesel engineThe article presents results of a study on the possible application of artificial neural networks (ANNs) to the evaluation of NOx concentration in the exhaust gas of a marine two-stroke Diesel engine. A concept is presented how to use the ANN as an alternative to direct measurements carried out on a ship at sea. Methods of proper ANN selection, configuration and training are presented. Also included are the results of laboratory tests, performed to obtain data for ANN training and tests, and the results obtained from modelling certain processes with the aid of selected ANNs. As a result of the performed investigations, an ANN was constructed and trained to calculate NOx concentration in the Diesel engine exhaust gas based on the engine operation parameters measured with an average error of 1.83%, and the fuel consumption measured with an average error of 1.12%.

Highlights

Chemical compounds of oxygen and nitrogen (NOx) emitted to the atmosphere with the exhaust gas from a ship engine are a source of pollution of the marine environment
In order to prevent negative effects on the environment, the International Marine Organisation adopted Annex VI to the MARPOL 73/78 Convention. This Annex forces the ship owners to reduce the emission of NOx down to the agreed limits defined in the NOx Technical Code [1]
One best trained artificial neural networks (ANNs) was selected from each tested ANN configuration using the following criteria: the error must not exceed 10% for a possibly large number of data sets, the mean square error calculated for all collected data sets is the smallest

Summary

Introduction

Chemical compounds of oxygen and nitrogen (NOx) emitted to the atmosphere with the exhaust gas from a ship engine are a source of pollution of the marine environment. The article presents the application of the ANN to modelling the combustion process in a two-stroke piston engine in order to assess the level of NOx emission in the exhaust gas.

Results

Conclusion