The use of artificial neural network (ANN) for modeling the useful life of the failure assessment in blades of steam turbines

Abstract Steam turbines have many applications in various industrial sectors and by common experience blade failures are the main origin of operational breakdowns in these machines, causing great economic loss in turbo machinery industry. The turbines are designed to work in stable conditions of operation. Nevertheless, failure in blades has been present after a short time period of work. These failures commonly attributed to resonance stress of the blades at different stages to certain excitation frequencies. Artificial neural network (ANN) approach was developed to predict the useful life (UL) of the blades. The configuration 6–3–1 (6 inputs, 3 hidden and 1 output neurons) presented an excellent agreement (R2 = 0.9912 and RMSE = 0.00022) between experimental and simulated useful life value considering the hyperbolic tangent sigmoid and linear transfer function in the hidden layer and output layer. In the following study, the sensitivity analysis was carried out, and showed, also that all studied input variables (resonance stress, frequency ratio, dynamic stress, damping, fatigue strength, mean stress) have strong effect on blades steam turbines in terms of useful life. However, the resonance stress is the most influential parameter with relative importance of 35.5%, followed by frequency ratio. The results showed that neural network modeling could effectively predict and simulate the behavior of life cycles assessment in blades of steam turbines.

[1]  David R.H. Jones,et al.  Buckling failures of pressurised vessels—Two case studies , 1994 .

[2]  Giovanni P. Terrasi,et al.  Structural failures of rope-based systems , 2009 .

[3]  Amilton Sinatora,et al.  Erosion-fatigue of steam turbine blades , 2009 .

[4]  R Marloth,et al.  On-line monitoring of damage to a sintering press , 1999 .

[5]  J. S. Rao,et al.  Fatigue Life Estimation Procedure for a Turbine Blade Under Transient Loads , 1992 .

[6]  Omar S. Es-Said,et al.  Low-cycle fatigue of titanium 6A1-4V surgical tools , 1998 .

[7]  C.R.F. Azevedo,et al.  Failure analysis of a crude oil pipeline , 2007 .

[8]  J. S. Rao Turbomachine Blade Vibration , 1991 .

[9]  Colin Gagg,et al.  Wear as a product failure mechanism – Overview and case studies , 2007 .

[10]  Omar S. Es-Said,et al.  Corrosion of 15-5PH H1025 stainless steel due to environmental conditions , 2010 .

[11]  Omar S. Es-Said,et al.  Corrosion of flexible waveguides , 1998 .

[12]  Omar S. Es-Said,et al.  Failure analysis of K-monel 500 (Ni–Cu–Al alloy) bolts , 2000 .

[13]  Zhi-wei Yu,et al.  Failure analysis of a diesel engine cylinder head , 2006 .

[14]  Omar S. Es-Said,et al.  Corrosion of a stainless steel chemical hood , 1998 .

[15]  S. Silva-Martínez,et al.  Optimal performance of COD removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network , 2011 .

[16]  Zhi-wei Yu,et al.  Failure analysis of an idler gear of diesel engine gearbox , 2006 .

[17]  Earl Logan,et al.  Handbook of Turbomachinery , 1994 .

[18]  David R.H. Jones Analysis of a fatal bungee-jumping accident , 2004 .

[19]  Lorrie Molent,et al.  Life assessment and repair of fatigue damaged high strength aluminium alloy structure using a peening rework method , 2008 .

[20]  J. C. García,et al.  Failure analysis of the 350 MW steam turbine blade root , 2009 .

[21]  Zdzislaw Mazur,et al.  Steam turbine blade failure analysis , 2008 .

[22]  Panayiotis Papadopoulos,et al.  Constitutive modelling and numerical simulation of multivariant phase transformation in superelastic shape‐memory alloys , 2004 .

[23]  Jorge Andaverde,et al.  Application of the error propagation theory in estimates of static formation temperatures in geothermal and petroleum boreholes , 2006 .

[24]  Omar S. Es-Said,et al.  The attachment of thin alumina ceramic plates to Kovar® using gold germanium solder , 1998 .

[25]  R. B. Tait,et al.  An experimental study of the residual stresses, and their alleviation, in tube to tube-sheet welds of industrial boilers , 2001 .

[26]  Gustavo Urquiza,et al.  Failure analysis of the 150 MW gas turbine blades , 2009 .

[27]  David Taylor Crack modelling: A technique for the fatigue design of components , 1996 .

[28]  Y. Abu Hasan Predicting Biochemical Oxygen Demand As Indicator Of River Pollution Using Artificial Neural Networks , 2009 .

[29]  Jose Luis Otegui,et al.  Two competing crack growth mechanisms in very high pressures tubes , 2011 .

[30]  R. Clegg,et al.  Liquid Metal Embrittlement of Tensile Specimens of En19 Steel by Tin , 2003 .

[31]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[32]  Mirko Gojić,et al.  Embrittlement damage of low alloy Mn–V steel , 2003 .

[33]  P Hopkins,et al.  Assessing mechanical damage in offshore pipelines – Two case studies , 2007 .

[34]  Omar S. Es-Said,et al.  Formation of a crater in the workpiece on an electrical discharge machine , 2002 .

[35]  G. H. Babcock,et al.  Steam / its generation and use , 1972 .

[36]  Nenad Gubeljak,et al.  Application of the european SINTAP procedure to the failure analysis of a broken forklift , 2004 .