Estimation of boiler's tubes life, Artificial Neural Networks approach / Murtadha F. Muhsen

F. Muhsen, Murtadha (2011) Estimation of boiler's tubes life, Artificial Neural Networks approach / Murtadha F. Muhsen. Journal of Mechanical Engineering, 8 (2). pp. 59-69. ISSN 1823-5514


The analysis of creep-damage processes is becoming more and more important in engineering practice due to the fact that the exploitation condition like temperature and pressure are increasing while the weight of the structure should decrease. In the same time the safety standards are increasing too. The accuracy of the mechanical state estimation (stresses, strains and displacements) mainly depends on the introduced constitutive equations and on the chosen structural analysis model. This paper is devoted to the prediction of boiler s tube life using of Artificial Neural Network (ANN) technique. Training data used were obtained from Kapar power station technical reports. Predicted values of the remnant tube life were compared to the experimentally collected data to verify the success of the algorithm; average absolute error obtained was 1.667%. Results obtained show that the designed network is capable of predicting the remnant life of the boilers tube successfully. Predicting boilers tube life successfully presented using this method will help maintenance engineers to schedule preventive maintenance procedure in order to minimize maintenance cost and to prevent any consequences of disasters which may happen if the necessary precautions were not taken.


Item Type: Article
CreatorsID Num. / Email
F. Muhsen, MurtadhaUNSPECIFIED
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Mechanical Engineering
Journal or Publication Title: Journal of Mechanical Engineering
ISSN: 1823-5514
Volume: 8
Number: 2
Page Range: pp. 59-69
Item ID: 17584
Uncontrolled Keywords: Boiler tube Remnant life estimation; Artificial Neural Network; water-tube boiler.


[img] Text

Download (20MB)

Actions (login required)

View Item View Item


Downloads per month over past year