Open AccessThe Combination of Reliability and Predictive Tools to Determine Ship Engine Performance based on Condition Monitoring
Author(s) -
Muhammad Badrus Zaman,
Nurhadi Siswantoro,
Dwi Priyanta,
Trika Pitana,
Hari Prastowo,
Semin Semin,
Wolfgang Busse
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/698/1/012015
Subject(s) - failure mode, effects, and criticality analysis , reliability engineering , predictive maintenance , reliability (semiconductor) , condition monitoring , failure mode and effects analysis , schedule , artificial neural network , fuzzy logic , computer science , semantic reasoner , engineering , machine learning , artificial intelligence , power (physics) , physics , electrical engineering , quantum mechanics , operating system
The evolution of maintenance has experienced developments in the fourth generation since the beginning of 2000 to the present. The fourth generation is the latest generation that focuses on condition based maintenance, condition monitoring and failure eliminations. The maintenance strategy in the fourth generation aims to reduce the failure rate of an equipment by reducing the probability, based on preventive and predictive approaches. In this research, a maintenance approach was carried out by predicting the results of condition monitoring on ship engine to ensure performance. The concept developed is to use a combination of reliability tools for criticality assessment and predictive tools to determine diagnostic assessments. Reliability tool for criticality assessment is the Failure Mode and Effect Criticality Analysis (FMECA) based on the fuzzy logic approach. FMECA’s bottom-up approach is intended to explore failure modes that provide potential failure in the main engine system. The fuzzy logic theory added to FMECA accommodates uncertainty due to obscure information as well as subjective preference elements that are used in the assessment of failure modes. The predictive assessment process uses the Multilayer Perceptron (MLP) approach using the Artificial Neural Network (ANN) method. ANN has advantages for self-learning, adaptivity, fault tolerance, nonlinearity, and advancement in input to an output mapping. The results of the current diagnostic assessment indicate the condition of the main engine is still normal. However, the trending of exhaust gas temperature prediction shows an increase, combustion and compression pressure which shows a decrease need to be prepared for determining the inspection/survey schedule. In this research, predictive assessment using an Artificial Neural Network based on Multilayer Perceptron (MLP) has been validated with an error of less than 5%.