On-condition maintenance of diesel engines modelled by a hidden Markov model

  • Authors:

  • António Simões;José Torres Farinha;Inácio Fonseca;Viriato Marques

  • Affiliations:

  • Department of Mechanical Engineering, Instituto Superior de Engenharia de Coimbra, Coimbra, Portugal;Department of Mechanical Engineering, Instituto Superior de Engenharia de Coimbra, Coimbra, Portugal;Departmernt of Electrical Engineering, Instituto Superior de Engenharia de Coimbra, Coimbra, Portugal;Departmernt of Computer Science and Systems Engineering, Instituto Superior de Engenharia de Coimbra, Coimbra, Portugal

  • Venue:
  • AIC'10/BEBI'10 Proceedings of the 10th WSEAS international conference on applied informatics and communications, and 3rd WSEAS international conference on Biomedical electronics and biomedical informatics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The maintenance of Diesel Engines is usually scheduled according to the maintenance procedures accurately defined by the manufacturers. However, state-of-the-art shows that on-condition maintenance usually improves its management, not just by increasing the intervals between inspections but also by helping to maintain the reliability levels. There are many types of variables that can be used to measure equipment condition, as is the case of several types of pollutant emissions such as NOx, COx, HC, PM and noise. The problem is to construct a prediction model that conjugates all these variables and follow their evolution along time, accurately predicting the actual end of next states. This type of problems can be solved through a Hidden Markov Model (HMM) that has shown to have the adequate characteristics to manage the complexity associated with these different variables, taking into account the specificity of this equipment type. The results demonstrate the adequacy of the model and also its ability to be used in other fields where on-condition maintenance is relevant, such as medical and healthcare equipment.