Design the prediction model of low-sulfur-content fuel oil consumption for M/V NORD VENUS 80,000 DWT sailing on emission control areas by artificial neural networks

The international shipping transportation has an important position in the field of economical development in each nation. It has been presented by increasing the number of ships with sufficiency of sizes and kinds. This development always associates with the environmental pollution. The main reason for this that International Maritime Organization required all ships conform to the International Convention for the Prevention of Pollution from Ships (MARPOL 73/78) and that they want their ships operate in the international routes. Especially, MARPOL 73/78, Annex VI—Prevention of Air Pollution from Ships, gradually impacts the limited value of low-sulfur-content fuel oil on ships no more than 0.50% m/m (mass by mass) from 1 January 2020, against the limit of 1.00% in effect up until 31 December 2014. Following the actual conditions, a lot of countries in the world have given the solutions in response to these above regulations. In Vietnam, VINIC shipping transportation company also has the solution in changing-over procedures from heavy fuel oil into light heavy fuel oil with low-sulfur content for bulk carriers. Based on the development of science and technology nowadays, especially machine learning method, the author has designed prediction model of low-sulfur-content fuel oil consumption by applying artificial neural networks model. The object of this study is a bulk carrier of VINIC shipping transportation company in Vietnam with ship name M/V NORD VENUS 80,000 DWT. The mass of low-sulfur-content fuel oil consumption has been recorded and compared with the results collected in this research when ship sailed on emission control areas. The simulation results of prediction model have been represented on artificial neural networks tool of MATLAB program. The advantage of this model will be represented through comparing with traditional statistical regression methods. The artificial neural networks prediction model of low-sulfur-content fuel oil consumption is more reliable than other traditional methods. The traditional statistical regression methods have been supported in this case by Minitab software. The superior model will save the low-sulfur-content fuel oil on bulk carriers and reduce the sea environmental pollution. This article will be an initial basis for applying the different types of ships when sailing on emission control areas in the future.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01700521
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Feb 7 2019 8:39AM