Optimization of Induction Brazing Parameters for Stellite Strip of Steam Turbine Blade Using Taguchi-Neural Network

Abstract

To repair the damaged of steam turbine blades, the method of increasing wear resistance of the blade leading edge with brazing of stellite plates by induction heating has been addressed in this work. Induction brazing of a Cobalt-based alloy to SUS410Cb steam turbine blades in an electrical power plant has been carried out. Ag-Cu-Zn based material was chosen to be the filler metal sandwiched between the stellite strip and the turbine blade. In order to cope with the large size of blades, an automatic brazing process which used moving induction coils has been developed. In the proposed brazing process, there are three parameters that significantly affect the quality of the brazing joints including coil distance, moving coil speed, and power of induction heating. In this work, the optimum choice of brazing parameters is obtained by using a Taguchi-neural network technique. According to the results of our previous work, it is recommended to attain the temperature distribution at around 750°C for maximum strength and good quality brazing in the brazed components. The objective for the evaluation of brazing quality is therefore a function of this temperature and defined as the temperature deviation from the best brazing temperature. The design is verified and confirmed by the manufacturing of brazed joint applying suggested parameters. The experimental results showed that the Taguchi-Neural network method resulted in a better brazed quality than when using only the Taguchi method.

Optimization of vacuum brazing process parameters in AA6061 using Taguchi method

“…While many factors affect the mechanical properties of aluminum alloy, the Taguchi method can optimize the process parameters of vacuum brazing, explaining its widespread use among industrial engineers. The welding and brazing parameters are optimized by Taguchi method in many literatures, such as brazing (Muangsong et al, 2013), friction stir welding (Koilraj et al, 2012;Shojaeefard et al, 2013), tungsten inert gas welding (Juang and Tarng, 2002), laser hybrid welding (Song et al, 2008), and pulsed plasma arc welding (Shih et al, 2012).…”